whiterose

linux unikernel
Log | Files | Refs | README | LICENSE | git clone https://git.ne02ptzero.me/git/whiterose

commit 636deed6c0bc137a7c4f4a97ae1fcf0ad75323da
parent aa2e3ac64ace127f403be85aa4d6015b859385f2
Author: Linus Torvalds <torvalds@linux-foundation.org>
Date:   Fri, 15 Mar 2019 15:00:28 -0700

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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - some cleanups
   - direct physical timer assignment
   - cache sanitization for 32-bit guests

  s390:
   - interrupt cleanup
   - introduction of the Guest Information Block
   - preparation for processor subfunctions in cpu models

  PPC:
   - bug fixes and improvements, especially related to machine checks
     and protection keys

  x86:
   - many, many cleanups, including removing a bunch of MMU code for
     unnecessary optimizations
   - AVIC fixes

  Generic:
   - memcg accounting"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (147 commits)
  kvm: vmx: fix formatting of a comment
  KVM: doc: Document the life cycle of a VM and its resources
  MAINTAINERS: Add KVM selftests to existing KVM entry
  Revert "KVM/MMU: Flush tlb directly in the kvm_zap_gfn_range()"
  KVM: PPC: Book3S: Add count cache flush parameters to kvmppc_get_cpu_char()
  KVM: PPC: Fix compilation when KVM is not enabled
  KVM: Minor cleanups for kvm_main.c
  KVM: s390: add debug logging for cpu model subfunctions
  KVM: s390: implement subfunction processor calls
  arm64: KVM: Fix architecturally invalid reset value for FPEXC32_EL2
  KVM: arm/arm64: Remove unused timer variable
  KVM: PPC: Book3S: Improve KVM reference counting
  KVM: PPC: Book3S HV: Fix build failure without IOMMU support
  Revert "KVM: Eliminate extra function calls in kvm_get_dirty_log_protect()"
  x86: kvmguest: use TSC clocksource if invariant TSC is exposed
  KVM: Never start grow vCPU halt_poll_ns from value below halt_poll_ns_grow_start
  KVM: Expose the initial start value in grow_halt_poll_ns() as a module parameter
  KVM: grow_halt_poll_ns() should never shrink vCPU halt_poll_ns
  KVM: x86/mmu: Consolidate kvm_mmu_zap_all() and kvm_mmu_zap_mmio_sptes()
  KVM: x86/mmu: WARN if zapping a MMIO spte results in zapping children
  ...

Diffstat:
MDocumentation/virtual/kvm/api.txt | 17+++++++++++++++++
MDocumentation/virtual/kvm/halt-polling.txt | 37+++++++++++++++++++++++--------------
MDocumentation/virtual/kvm/mmu.txt | 41+++++++++--------------------------------
MMAINTAINERS | 19++++++++-----------
March/arm/include/asm/arch_gicv3.h | 4++--
March/arm/include/asm/kvm_emulate.h | 8++++++++
March/arm/include/asm/kvm_host.h | 53++++++++++++++++++++++++++++++++++++++++++++++-------
March/arm/include/asm/kvm_hyp.h | 4++++
March/arm/include/asm/kvm_mmu.h | 9+++++++--
March/arm/kvm/Makefile | 5++---
March/arm/kvm/coproc.c | 23++++++++++++++---------
March/arm/kvm/hyp/cp15-sr.c | 1-
March/arm/kvm/hyp/hyp-entry.S | 2+-
March/arm/kvm/hyp/switch.c | 2+-
March/arm/kvm/hyp/tlb.c | 4++--
March/arm/kvm/interrupts.S | 4++--
March/arm64/include/asm/kvm_emulate.h | 12++++++++++++
March/arm64/include/asm/kvm_host.h | 48++++++++++++++++++++++++++++++++++++++++++++----
March/arm64/include/asm/kvm_hyp.h | 3++-
March/arm64/include/asm/kvm_mmu.h | 13++++++++++---
March/arm64/include/asm/sysreg.h | 7++++++-
March/arm64/kvm/Makefile | 4+---
March/arm64/kvm/debug.c | 2+-
March/arm64/kvm/hyp.S | 3---
March/arm64/kvm/hyp/hyp-entry.S | 12------------
March/arm64/kvm/hyp/sysreg-sr.c | 1-
March/arm64/kvm/sys_regs.c | 168+++++++++++++++++++++++++++++++++++++++++++++++++++++---------------------------
March/mips/include/asm/kvm_host.h | 2+-
March/powerpc/include/asm/kvm_host.h | 5++++-
March/powerpc/include/asm/kvm_ppc.h | 14++++++++++++++
March/powerpc/include/uapi/asm/kvm.h | 2++
March/powerpc/kvm/book3s.c | 13++++++++-----
March/powerpc/kvm/book3s_32_mmu.c | 1+
March/powerpc/kvm/book3s_64_mmu.c | 14++++++++++++++
March/powerpc/kvm/book3s_64_mmu_hv.c | 18++++++++++++++++++
March/powerpc/kvm/book3s_64_mmu_radix.c | 15++++++++++++++-
March/powerpc/kvm/book3s_64_vio.c | 8++++----
March/powerpc/kvm/book3s_emulate.c | 18++++++++++++++++++
March/powerpc/kvm/book3s_hv.c | 33+++++++++++++++++----------------
March/powerpc/kvm/book3s_hv_builtin.c | 14+++++++-------
March/powerpc/kvm/book3s_hv_rm_xics.c | 7+++++++
March/powerpc/kvm/book3s_hv_rmhandlers.S | 10++++++++++
March/powerpc/kvm/book3s_rtas.c | 8++++----
March/powerpc/kvm/powerpc.c | 22++++++++++++++++------
March/s390/include/asm/cio.h | 1+
March/s390/include/asm/irq.h | 1+
March/s390/include/asm/isc.h | 1+
March/s390/include/asm/kvm_host.h | 39+++++++++++++++++++++++++++++++++++----
March/s390/kernel/irq.c | 1+
March/s390/kvm/interrupt.c | 431+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++--------
March/s390/kvm/kvm-s390.c | 190++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-------
March/s390/kvm/kvm-s390.h | 4+++-
March/x86/include/asm/kvm_host.h | 42+++++++++++++++++++-----------------------
Aarch/x86/include/asm/kvm_vcpu_regs.h | 25+++++++++++++++++++++++++
March/x86/kernel/kvmclock.c | 20+++++++++++++++-----
March/x86/kvm/cpuid.c | 2+-
March/x86/kvm/hyperv.c | 2+-
March/x86/kvm/i8254.c | 2+-
March/x86/kvm/i8259.c | 2+-
March/x86/kvm/ioapic.c | 2+-
March/x86/kvm/lapic.c | 7++++---
March/x86/kvm/mmu.c | 466+++++++++++++++++++++++++++++++++++++------------------------------------------
March/x86/kvm/mmu.h | 1-
March/x86/kvm/mmutrace.h | 42+++++++++---------------------------------
March/x86/kvm/page_track.c | 2+-
March/x86/kvm/svm.c | 120++++++++++++++++++++++++++++++++++++++++----------------------------------------
March/x86/kvm/vmx/nested.c | 129++++++++++++++++++++++++++++++++++++++++++++++++-------------------------------
March/x86/kvm/vmx/vmcs.h | 1+
March/x86/kvm/vmx/vmenter.S | 167+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
March/x86/kvm/vmx/vmx.c | 188+++++++++++++++----------------------------------------------------------------
March/x86/kvm/vmx/vmx.h | 20+++++++++++---------
March/x86/kvm/x86.c | 32++++++++++++++++++++------------
March/x86/kvm/x86.h | 7++++++-
Mdrivers/clocksource/arm_arch_timer.c | 11+++++++++--
Mdrivers/s390/cio/chsc.c | 37+++++++++++++++++++++++++++++++++++++
Mdrivers/s390/cio/chsc.h | 1+
Minclude/clocksource/arm_arch_timer.h | 1+
Minclude/kvm/arm_arch_timer.h | 68+++++++++++++++++++++++++++++++++++++++++++++++++-------------------
Minclude/linux/kvm_host.h | 24+++++++++++++++++++++++-
Mtools/testing/selftests/kvm/.gitignore | 1+
Mtools/testing/selftests/kvm/Makefile | 1+
Atools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c | 95+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Mvirt/kvm/arm/arch_timer.c | 608+++++++++++++++++++++++++++++++++++++++++++++++++++++++------------------------
Mvirt/kvm/arm/arm.c | 64+++++++++++++++++++++++-----------------------------------------
Mvirt/kvm/arm/hyp/vgic-v3-sr.c | 2+-
Mvirt/kvm/arm/mmu.c | 20+++++++++-----------
Mvirt/kvm/arm/trace.h | 107++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
Mvirt/kvm/arm/vgic/vgic-v3.c | 4++--
Mvirt/kvm/coalesced_mmio.c | 3++-
Mvirt/kvm/eventfd.c | 7++++---
Mvirt/kvm/irqchip.c | 4++--
Mvirt/kvm/kvm_main.c | 103+++++++++++++++++++++++++++++++++++++++++--------------------------------------
Mvirt/kvm/vfio.c | 4++--
93 files changed, 2623 insertions(+), 1199 deletions(-)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt @@ -45,6 +45,23 @@ the API. The only supported use is one virtual machine per process, and one vcpu per thread. +It is important to note that althought VM ioctls may only be issued from +the process that created the VM, a VM's lifecycle is associated with its +file descriptor, not its creator (process). In other words, the VM and +its resources, *including the associated address space*, are not freed +until the last reference to the VM's file descriptor has been released. +For example, if fork() is issued after ioctl(KVM_CREATE_VM), the VM will +not be freed until both the parent (original) process and its child have +put their references to the VM's file descriptor. + +Because a VM's resources are not freed until the last reference to its +file descriptor is released, creating additional references to a VM via +via fork(), dup(), etc... without careful consideration is strongly +discouraged and may have unwanted side effects, e.g. memory allocated +by and on behalf of the VM's process may not be freed/unaccounted when +the VM is shut down. + + 3. Extensions ------------- diff --git a/Documentation/virtual/kvm/halt-polling.txt b/Documentation/virtual/kvm/halt-polling.txt @@ -53,7 +53,8 @@ the global max polling interval then the polling interval can be increased in the hope that next time during the longer polling interval the wake up source will be received while the host is polling and the latency benefits will be received. The polling interval is grown in the function grow_halt_poll_ns() and -is multiplied by the module parameter halt_poll_ns_grow. +is multiplied by the module parameters halt_poll_ns_grow and +halt_poll_ns_grow_start. In the event that the total block time was greater than the global max polling interval then the host will never poll for long enough (limited by the global @@ -80,22 +81,30 @@ shrunk. These variables are defined in include/linux/kvm_host.h and as module parameters in virt/kvm/kvm_main.c, or arch/powerpc/kvm/book3s_hv.c in the powerpc kvm-hv case. -Module Parameter | Description | Default Value +Module Parameter | Description | Default Value -------------------------------------------------------------------------------- -halt_poll_ns | The global max polling interval | KVM_HALT_POLL_NS_DEFAULT - | which defines the ceiling value | - | of the polling interval for | (per arch value) - | each vcpu. | +halt_poll_ns | The global max polling | KVM_HALT_POLL_NS_DEFAULT + | interval which defines | + | the ceiling value of the | + | polling interval for | (per arch value) + | each vcpu. | -------------------------------------------------------------------------------- -halt_poll_ns_grow | The value by which the halt | 2 - | polling interval is multiplied | - | in the grow_halt_poll_ns() | - | function. | +halt_poll_ns_grow | The value by which the | 2 + | halt polling interval is | + | multiplied in the | + | grow_halt_poll_ns() | + | function. | -------------------------------------------------------------------------------- -halt_poll_ns_shrink | The value by which the halt | 0 - | polling interval is divided in | - | the shrink_halt_poll_ns() | - | function. | +halt_poll_ns_grow_start | The initial value to grow | 10000 + | to from zero in the | + | grow_halt_poll_ns() | + | function. | +-------------------------------------------------------------------------------- +halt_poll_ns_shrink | The value by which the | 0 + | halt polling interval is | + | divided in the | + | shrink_halt_poll_ns() | + | function. | -------------------------------------------------------------------------------- These module parameters can be set from the debugfs files in: diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt @@ -224,10 +224,6 @@ Shadow pages contain the following information: A bitmap indicating which sptes in spt point (directly or indirectly) at pages that may be unsynchronized. Used to quickly locate all unsychronized pages reachable from a given page. - mmu_valid_gen: - Generation number of the page. It is compared with kvm->arch.mmu_valid_gen - during hash table lookup, and used to skip invalidated shadow pages (see - "Zapping all pages" below.) clear_spte_count: Only present on 32-bit hosts, where a 64-bit spte cannot be written atomically. The reader uses this while running out of the MMU lock @@ -402,27 +398,6 @@ causes its disallow_lpage to be incremented, thus preventing instantiation of a large spte. The frames at the end of an unaligned memory slot have artificially inflated ->disallow_lpages so they can never be instantiated. -Zapping all pages (page generation count) -========================================= - -For the large memory guests, walking and zapping all pages is really slow -(because there are a lot of pages), and also blocks memory accesses of -all VCPUs because it needs to hold the MMU lock. - -To make it be more scalable, kvm maintains a global generation number -which is stored in kvm->arch.mmu_valid_gen. Every shadow page stores -the current global generation-number into sp->mmu_valid_gen when it -is created. Pages with a mismatching generation number are "obsolete". - -When KVM need zap all shadow pages sptes, it just simply increases the global -generation-number then reload root shadow pages on all vcpus. As the VCPUs -create new shadow page tables, the old pages are not used because of the -mismatching generation number. - -KVM then walks through all pages and zaps obsolete pages. While the zap -operation needs to take the MMU lock, the lock can be released periodically -so that the VCPUs can make progress. - Fast invalidation of MMIO sptes =============================== @@ -435,8 +410,7 @@ shadow pages, and is made more scalable with a similar technique. MMIO sptes have a few spare bits, which are used to store a generation number. The global generation number is stored in kvm_memslots(kvm)->generation, and increased whenever guest memory info -changes. This generation number is distinct from the one described in -the previous section. +changes. When KVM finds an MMIO spte, it checks the generation number of the spte. If the generation number of the spte does not equal the global generation @@ -452,13 +426,16 @@ stored into the MMIO spte. Thus, the MMIO spte might be created based on out-of-date information, but with an up-to-date generation number. To avoid this, the generation number is incremented again after synchronize_srcu -returns; thus, the low bit of kvm_memslots(kvm)->generation is only 1 during a +returns; thus, bit 63 of kvm_memslots(kvm)->generation set to 1 only during a memslot update, while some SRCU readers might be using the old copy. We do not want to use an MMIO sptes created with an odd generation number, and we can do -this without losing a bit in the MMIO spte. The low bit of the generation -is not stored in MMIO spte, and presumed zero when it is extracted out of the -spte. If KVM is unlucky and creates an MMIO spte while the low bit is 1, -the next access to the spte will always be a cache miss. +this without losing a bit in the MMIO spte. The "update in-progress" bit of the +generation is not stored in MMIO spte, and is so is implicitly zero when the +generation is extracted out of the spte. If KVM is unlucky and creates an MMIO +spte while an update is in-progress, the next access to the spte will always be +a cache miss. For example, a subsequent access during the update window will +miss due to the in-progress flag diverging, while an access after the update +window closes will have a higher generation number (as compared to the spte). Further reading diff --git a/MAINTAINERS b/MAINTAINERS @@ -8461,6 +8461,7 @@ F: include/linux/kvm* F: include/kvm/iodev.h F: virt/kvm/* F: tools/kvm/ +F: tools/testing/selftests/kvm/ KERNEL VIRTUAL MACHINE FOR AMD-V (KVM/amd) M: Joerg Roedel <joro@8bytes.org> @@ -8470,29 +8471,25 @@ S: Maintained F: arch/x86/include/asm/svm.h F: arch/x86/kvm/svm.c -KERNEL VIRTUAL MACHINE FOR ARM (KVM/arm) +KERNEL VIRTUAL MACHINE FOR ARM/ARM64 (KVM/arm, KVM/arm64) M: Christoffer Dall <christoffer.dall@arm.com> M: Marc Zyngier <marc.zyngier@arm.com> +R: James Morse <james.morse@arm.com> +R: Julien Thierry <julien.thierry@arm.com> +R: Suzuki K Pouloze <suzuki.poulose@arm.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: kvmarm@lists.cs.columbia.edu W: http://systems.cs.columbia.edu/projects/kvm-arm T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm.git -S: Supported +S: Maintained F: arch/arm/include/uapi/asm/kvm* F: arch/arm/include/asm/kvm* F: arch/arm/kvm/ -F: virt/kvm/arm/ -F: include/kvm/arm_* - -KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64) -M: Christoffer Dall <christoffer.dall@arm.com> -M: Marc Zyngier <marc.zyngier@arm.com> -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -L: kvmarm@lists.cs.columbia.edu -S: Maintained F: arch/arm64/include/uapi/asm/kvm* F: arch/arm64/include/asm/kvm* F: arch/arm64/kvm/ +F: virt/kvm/arm/ +F: include/kvm/arm_* KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips) M: James Hogan <jhogan@kernel.org> diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h @@ -55,7 +55,7 @@ #define ICH_VTR __ACCESS_CP15(c12, 4, c11, 1) #define ICH_MISR __ACCESS_CP15(c12, 4, c11, 2) #define ICH_EISR __ACCESS_CP15(c12, 4, c11, 3) -#define ICH_ELSR __ACCESS_CP15(c12, 4, c11, 5) +#define ICH_ELRSR __ACCESS_CP15(c12, 4, c11, 5) #define ICH_VMCR __ACCESS_CP15(c12, 4, c11, 7) #define __LR0(x) __ACCESS_CP15(c12, 4, c12, x) @@ -152,7 +152,7 @@ CPUIF_MAP(ICH_HCR, ICH_HCR_EL2) CPUIF_MAP(ICH_VTR, ICH_VTR_EL2) CPUIF_MAP(ICH_MISR, ICH_MISR_EL2) CPUIF_MAP(ICH_EISR, ICH_EISR_EL2) -CPUIF_MAP(ICH_ELSR, ICH_ELSR_EL2) +CPUIF_MAP(ICH_ELRSR, ICH_ELRSR_EL2) CPUIF_MAP(ICH_VMCR, ICH_VMCR_EL2) CPUIF_MAP(ICH_AP0R3, ICH_AP0R3_EL2) CPUIF_MAP(ICH_AP0R2, ICH_AP0R2_EL2) diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h @@ -265,6 +265,14 @@ static inline bool kvm_vcpu_dabt_isextabt(struct kvm_vcpu *vcpu) } } +static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu) +{ + if (kvm_vcpu_trap_is_iabt(vcpu)) + return false; + + return kvm_vcpu_dabt_iswrite(vcpu); +} + static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h @@ -26,6 +26,7 @@ #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> #include <asm/fpstate.h> +#include <asm/smp_plat.h> #include <kvm/arm_arch_timer.h> #define __KVM_HAVE_ARCH_INTC_INITIALIZED @@ -57,10 +58,13 @@ int __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); void kvm_reset_coprocs(struct kvm_vcpu *vcpu); -struct kvm_arch { - /* VTTBR value associated with below pgd and vmid */ - u64 vttbr; +struct kvm_vmid { + /* The VMID generation used for the virt. memory system */ + u64 vmid_gen; + u32 vmid; +}; +struct kvm_arch { /* The last vcpu id that ran on each physical CPU */ int __percpu *last_vcpu_ran; @@ -70,11 +74,11 @@ struct kvm_arch { */ /* The VMID generation used for the virt. memory system */ - u64 vmid_gen; - u32 vmid; + struct kvm_vmid vmid; /* Stage-2 page table */ pgd_t *pgd; + phys_addr_t pgd_phys; /* Interrupt controller */ struct vgic_dist vgic; @@ -148,6 +152,13 @@ struct kvm_cpu_context { typedef struct kvm_cpu_context kvm_cpu_context_t; +static inline void kvm_init_host_cpu_context(kvm_cpu_context_t *cpu_ctxt, + int cpu) +{ + /* The host's MPIDR is immutable, so let's set it up at boot time */ + cpu_ctxt->cp15[c0_MPIDR] = cpu_logical_map(cpu); +} + struct vcpu_reset_state { unsigned long pc; unsigned long r0; @@ -224,7 +235,35 @@ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); -unsigned long kvm_call_hyp(void *hypfn, ...); + +unsigned long __kvm_call_hyp(void *hypfn, ...); + +/* + * The has_vhe() part doesn't get emitted, but is used for type-checking. + */ +#define kvm_call_hyp(f, ...) \ + do { \ + if (has_vhe()) { \ + f(__VA_ARGS__); \ + } else { \ + __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__); \ + } \ + } while(0) + +#define kvm_call_hyp_ret(f, ...) \ + ({ \ + typeof(f(__VA_ARGS__)) ret; \ + \ + if (has_vhe()) { \ + ret = f(__VA_ARGS__); \ + } else { \ + ret = __kvm_call_hyp(kvm_ksym_ref(f), \ + ##__VA_ARGS__); \ + } \ + \ + ret; \ + }) + void force_vm_exit(const cpumask_t *mask); int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); @@ -275,7 +314,7 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, * compliant with the PCS!). */ - kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr); + __kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr); } static inline void __cpu_init_stage2(void) diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h @@ -40,6 +40,7 @@ #define TTBR1 __ACCESS_CP15_64(1, c2) #define VTTBR __ACCESS_CP15_64(6, c2) #define PAR __ACCESS_CP15_64(0, c7) +#define CNTP_CVAL __ACCESS_CP15_64(2, c14) #define CNTV_CVAL __ACCESS_CP15_64(3, c14) #define CNTVOFF __ACCESS_CP15_64(4, c14) @@ -85,6 +86,7 @@ #define TID_PRIV __ACCESS_CP15(c13, 0, c0, 4) #define HTPIDR __ACCESS_CP15(c13, 4, c0, 2) #define CNTKCTL __ACCESS_CP15(c14, 0, c1, 0) +#define CNTP_CTL __ACCESS_CP15(c14, 0, c2, 1) #define CNTV_CTL __ACCESS_CP15(c14, 0, c3, 1) #define CNTHCTL __ACCESS_CP15(c14, 4, c1, 0) @@ -94,6 +96,8 @@ #define read_sysreg_el0(r) read_sysreg(r##_el0) #define write_sysreg_el0(v, r) write_sysreg(v, r##_el0) +#define cntp_ctl_el0 CNTP_CTL +#define cntp_cval_el0 CNTP_CVAL #define cntv_ctl_el0 CNTV_CTL #define cntv_cval_el0 CNTV_CVAL #define cntvoff_el2 CNTVOFF diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h @@ -421,9 +421,14 @@ static inline int hyp_map_aux_data(void) static inline void kvm_set_ipa_limit(void) {} -static inline bool kvm_cpu_has_cnp(void) +static __always_inline u64 kvm_get_vttbr(struct kvm *kvm) { - return false; + struct kvm_vmid *vmid = &kvm->arch.vmid; + u64 vmid_field, baddr; + + baddr = kvm->arch.pgd_phys; + vmid_field = (u64)vmid->vmid << VTTBR_VMID_SHIFT; + return kvm_phys_to_vttbr(baddr) | vmid_field; } #endif /* !__ASSEMBLY__ */ diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile @@ -8,9 +8,8 @@ ifeq ($(plus_virt),+virt) plus_virt_def := -DREQUIRES_VIRT=1 endif -ccflags-y += -Iarch/arm/kvm -Ivirt/kvm/arm/vgic -CFLAGS_arm.o := -I. $(plus_virt_def) -CFLAGS_mmu.o := -I. +ccflags-y += -I $(srctree)/$(src) -I $(srctree)/virt/kvm/arm/vgic +CFLAGS_arm.o := $(plus_virt_def) AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt) AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c @@ -293,15 +293,16 @@ static bool access_cntp_tval(struct kvm_vcpu *vcpu, const struct coproc_params *p, const struct coproc_reg *r) { - u64 now = kvm_phys_timer_read(); - u64 val; + u32 val; if (p->is_write) { val = *vcpu_reg(vcpu, p->Rt1); - kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL, val + now); + kvm_arm_timer_write_sysreg(vcpu, + TIMER_PTIMER, TIMER_REG_TVAL, val); } else { - val = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL); - *vcpu_reg(vcpu, p->Rt1) = val - now; + val = kvm_arm_timer_read_sysreg(vcpu, + TIMER_PTIMER, TIMER_REG_TVAL); + *vcpu_reg(vcpu, p->Rt1) = val; } return true; @@ -315,9 +316,11 @@ static bool access_cntp_ctl(struct kvm_vcpu *vcpu, if (p->is_write) { val = *vcpu_reg(vcpu, p->Rt1); - kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CTL, val); + kvm_arm_timer_write_sysreg(vcpu, + TIMER_PTIMER, TIMER_REG_CTL, val); } else { - val = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CTL); + val = kvm_arm_timer_read_sysreg(vcpu, + TIMER_PTIMER, TIMER_REG_CTL); *vcpu_reg(vcpu, p->Rt1) = val; } @@ -333,9 +336,11 @@ static bool access_cntp_cval(struct kvm_vcpu *vcpu, if (p->is_write) { val = (u64)*vcpu_reg(vcpu, p->Rt2) << 32; val |= *vcpu_reg(vcpu, p->Rt1); - kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL, val); + kvm_arm_timer_write_sysreg(vcpu, + TIMER_PTIMER, TIMER_REG_CVAL, val); } else { - val = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL); + val = kvm_arm_timer_read_sysreg(vcpu, + TIMER_PTIMER, TIMER_REG_CVAL); *vcpu_reg(vcpu, p->Rt1) = val; *vcpu_reg(vcpu, p->Rt2) = val >> 32; } diff --git a/arch/arm/kvm/hyp/cp15-sr.c b/arch/arm/kvm/hyp/cp15-sr.c @@ -27,7 +27,6 @@ static u64 *cp15_64(struct kvm_cpu_context *ctxt, int idx) void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt) { - ctxt->cp15[c0_MPIDR] = read_sysreg(VMPIDR); ctxt->cp15[c0_CSSELR] = read_sysreg(CSSELR); ctxt->cp15[c1_SCTLR] = read_sysreg(SCTLR); ctxt->cp15[c1_CPACR] = read_sysreg(CPACR); diff --git a/arch/arm/kvm/hyp/hyp-entry.S b/arch/arm/kvm/hyp/hyp-entry.S @@ -176,7 +176,7 @@ THUMB( orr lr, lr, #PSR_T_BIT ) msr spsr_cxsf, lr ldr lr, =panic msr ELR_hyp, lr - ldr lr, =kvm_call_hyp + ldr lr, =__kvm_call_hyp clrex eret ENDPROC(__hyp_do_panic) diff --git a/arch/arm/kvm/hyp/switch.c b/arch/arm/kvm/hyp/switch.c @@ -77,7 +77,7 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu) static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu) { struct kvm *kvm = kern_hyp_va(vcpu->kvm); - write_sysreg(kvm->arch.vttbr, VTTBR); + write_sysreg(kvm_get_vttbr(kvm), VTTBR); write_sysreg(vcpu->arch.midr, VPIDR); } diff --git a/arch/arm/kvm/hyp/tlb.c b/arch/arm/kvm/hyp/tlb.c @@ -41,7 +41,7 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) /* Switch to requested VMID */ kvm = kern_hyp_va(kvm); - write_sysreg(kvm->arch.vttbr, VTTBR); + write_sysreg(kvm_get_vttbr(kvm), VTTBR); isb(); write_sysreg(0, TLBIALLIS); @@ -61,7 +61,7 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm); /* Switch to requested VMID */ - write_sysreg(kvm->arch.vttbr, VTTBR); + write_sysreg(kvm_get_vttbr(kvm), VTTBR); isb(); write_sysreg(0, TLBIALL); diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S @@ -42,7 +42,7 @@ * r12: caller save * rest: callee save */ -ENTRY(kvm_call_hyp) +ENTRY(__kvm_call_hyp) hvc #0 bx lr -ENDPROC(kvm_call_hyp) +ENDPROC(__kvm_call_hyp) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h @@ -77,6 +77,10 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) */ if (!vcpu_el1_is_32bit(vcpu)) vcpu->arch.hcr_el2 |= HCR_TID3; + + if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) || + vcpu_el1_is_32bit(vcpu)) + vcpu->arch.hcr_el2 |= HCR_TID2; } static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu) @@ -331,6 +335,14 @@ static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) return ESR_ELx_SYS64_ISS_RT(esr); } +static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu) +{ + if (kvm_vcpu_trap_is_iabt(vcpu)) + return false; + + return kvm_vcpu_dabt_iswrite(vcpu); +} + static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu) { return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h @@ -31,6 +31,7 @@ #include <asm/kvm.h> #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> +#include <asm/smp_plat.h> #include <asm/thread_info.h> #define __KVM_HAVE_ARCH_INTC_INITIALIZED @@ -58,16 +59,19 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu); int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext); void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start); -struct kvm_arch { +struct kvm_vmid { /* The VMID generation used for the virt. memory system */ u64 vmid_gen; u32 vmid; +}; + +struct kvm_arch { + struct kvm_vmid vmid; /* stage2 entry level table */ pgd_t *pgd; + phys_addr_t pgd_phys; - /* VTTBR value associated with above pgd and vmid */ - u64 vttbr; /* VTCR_EL2 value for this VM */ u64 vtcr; @@ -382,7 +386,36 @@ void kvm_arm_halt_guest(struct kvm *kvm); void kvm_arm_resume_guest(struct kvm *kvm); u64 __kvm_call_hyp(void *hypfn, ...); -#define kvm_call_hyp(f, ...) __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__) + +/* + * The couple of isb() below are there to guarantee the same behaviour + * on VHE as on !VHE, where the eret to EL1 acts as a context + * synchronization event. + */ +#define kvm_call_hyp(f, ...) \ + do { \ + if (has_vhe()) { \ + f(__VA_ARGS__); \ + isb(); \ + } else { \ + __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__); \ + } \ + } while(0) + +#define kvm_call_hyp_ret(f, ...) \ + ({ \ + typeof(f(__VA_ARGS__)) ret; \ + \ + if (has_vhe()) { \ + ret = f(__VA_ARGS__); \ + isb(); \ + } else { \ + ret = __kvm_call_hyp(kvm_ksym_ref(f), \ + ##__VA_ARGS__); \ + } \ + \ + ret; \ + }) void force_vm_exit(const cpumask_t *mask); void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot); @@ -401,6 +434,13 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); DECLARE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state); +static inline void kvm_init_host_cpu_context(kvm_cpu_context_t *cpu_ctxt, + int cpu) +{ + /* The host's MPIDR is immutable, so let's set it up at boot time */ + cpu_ctxt->sys_regs[MPIDR_EL1] = cpu_logical_map(cpu); +} + void __kvm_enable_ssbs(void); static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h @@ -21,6 +21,7 @@ #include <linux/compiler.h> #include <linux/kvm_host.h> #include <asm/alternative.h> +#include <asm/kvm_mmu.h> #include <asm/sysreg.h> #define __hyp_text __section(.hyp.text) notrace @@ -163,7 +164,7 @@ void __noreturn __hyp_do_panic(unsigned long, ...); static __always_inline void __hyp_text __load_guest_stage2(struct kvm *kvm) { write_sysreg(kvm->arch.vtcr, vtcr_el2); - write_sysreg(kvm->arch.vttbr, vttbr_el2); + write_sysreg(kvm_get_vttbr(kvm), vttbr_el2); /* * ARM erratum 1165522 requires the actual execution of the above diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h @@ -138,7 +138,8 @@ static inline unsigned long __kern_hyp_va(unsigned long v) }) /* - * We currently only support a 40bit IPA. + * We currently support using a VM-specified IPA size. For backward + * compatibility, the default IPA size is fixed to 40bits. */ #define KVM_PHYS_SHIFT (40) @@ -591,9 +592,15 @@ static inline u64 kvm_vttbr_baddr_mask(struct kvm *kvm) return vttbr_baddr_mask(kvm_phys_shift(kvm), kvm_stage2_levels(kvm)); } -static inline bool kvm_cpu_has_cnp(void) +static __always_inline u64 kvm_get_vttbr(struct kvm *kvm) { - return system_supports_cnp(); + struct kvm_vmid *vmid = &kvm->arch.vmid; + u64 vmid_field, baddr; + u64 cnp = system_supports_cnp() ? VTTBR_CNP_BIT : 0; + + baddr = kvm->arch.pgd_phys; + vmid_field = (u64)vmid->vmid << VTTBR_VMID_SHIFT; + return kvm_phys_to_vttbr(baddr) | vmid_field | cnp; } #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h @@ -361,6 +361,7 @@ #define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0) +#define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0) #define SYS_CLIDR_EL1 sys_reg(3, 1, 0, 0, 1) #define SYS_AIDR_EL1 sys_reg(3, 1, 0, 0, 7) @@ -392,6 +393,10 @@ #define SYS_CNTP_CTL_EL0 sys_reg(3, 3, 14, 2, 1) #define SYS_CNTP_CVAL_EL0 sys_reg(3, 3, 14, 2, 2) +#define SYS_AARCH32_CNTP_TVAL sys_reg(0, 0, 14, 2, 0) +#define SYS_AARCH32_CNTP_CTL sys_reg(0, 0, 14, 2, 1) +#define SYS_AARCH32_CNTP_CVAL sys_reg(0, 2, 0, 14, 0) + #define __PMEV_op2(n) ((n) & 0x7) #define __CNTR_CRm(n) (0x8 | (((n) >> 3) & 0x3)) #define SYS_PMEVCNTRn_EL0(n) sys_reg(3, 3, 14, __CNTR_CRm(n), __PMEV_op2(n)) @@ -426,7 +431,7 @@ #define SYS_ICH_VTR_EL2 sys_reg(3, 4, 12, 11, 1) #define SYS_ICH_MISR_EL2 sys_reg(3, 4, 12, 11, 2) #define SYS_ICH_EISR_EL2 sys_reg(3, 4, 12, 11, 3) -#define SYS_ICH_ELSR_EL2 sys_reg(3, 4, 12, 11, 5) +#define SYS_ICH_ELRSR_EL2 sys_reg(3, 4, 12, 11, 5) #define SYS_ICH_VMCR_EL2 sys_reg(3, 4, 12, 11, 7) #define __SYS__LR0_EL2(x) sys_reg(3, 4, 12, 12, x) diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile @@ -3,9 +3,7 @@ # Makefile for Kernel-based Virtual Machine module # -ccflags-y += -Iarch/arm64/kvm -Ivirt/kvm/arm/vgic -CFLAGS_arm.o := -I. -CFLAGS_mmu.o := -I. +ccflags-y += -I $(srctree)/$(src) -I $(srctree)/virt/kvm/arm/vgic KVM=../../../virt/kvm diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c @@ -76,7 +76,7 @@ static void restore_guest_debug_regs(struct kvm_vcpu *vcpu) void kvm_arm_init_debug(void) { - __this_cpu_write(mdcr_el2, kvm_call_hyp(__kvm_get_mdcr_el2)); + __this_cpu_write(mdcr_el2, kvm_call_hyp_ret(__kvm_get_mdcr_el2)); } /** diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S @@ -40,9 +40,6 @@ * arch/arm64/kernel/hyp_stub.S. */ ENTRY(__kvm_call_hyp) -alternative_if_not ARM64_HAS_VIRT_HOST_EXTN hvc #0 ret -alternative_else_nop_endif - b __vhe_hyp_call ENDPROC(__kvm_call_hyp) diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S @@ -43,18 +43,6 @@ ldr lr, [sp], #16 .endm -ENTRY(__vhe_hyp_call) - do_el2_call - /* - * We used to rely on having an exception return to get - * an implicit isb. In the E2H case, we don't have it anymore. - * rather than changing all the leaf functions, just do it here - * before returning to the rest of the kernel. - */ - isb - ret -ENDPROC(__vhe_hyp_call) - el1_sync: // Guest trapped into EL2 mrs x0, esr_el2 diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -53,7 +53,6 @@ static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt) static void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) { - ctxt->sys_regs[MPIDR_EL1] = read_sysreg(vmpidr_el2); ctxt->sys_regs[CSSELR_EL1] = read_sysreg(csselr_el1); ctxt->sys_regs[SCTLR_EL1] = read_sysreg_el1(sctlr); ctxt->sys_regs[ACTLR_EL1] = read_sysreg(actlr_el1); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c @@ -982,6 +982,10 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return true; } +#define reg_to_encoding(x) \ + sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \ + (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2); + /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */ #define DBG_BCR_BVR_WCR_WVR_EL1(n) \ { SYS_DESC(SYS_DBGBVRn_EL1(n)), \ @@ -1003,44 +1007,38 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { SYS_DESC(SYS_PMEVTYPERn_EL0(n)), \ access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), } -static bool access_cntp_tval(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *r) +static bool access_arch_timer(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) { - u64 now = kvm_phys_timer_read(); - u64 cval; + enum kvm_arch_timers tmr; + enum kvm_arch_timer_regs treg; + u64 reg = reg_to_encoding(r); - if (p->is_write) { - kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL, - p->regval + now); - } else { - cval = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL); - p->regval = cval - now; + switch (reg) { + case SYS_CNTP_TVAL_EL0: + case SYS_AARCH32_CNTP_TVAL: + tmr = TIMER_PTIMER; + treg = TIMER_REG_TVAL; + break; + case SYS_CNTP_CTL_EL0: + case SYS_AARCH32_CNTP_CTL: + tmr = TIMER_PTIMER; + treg = TIMER_REG_CTL; + break; + case SYS_CNTP_CVAL_EL0: + case SYS_AARCH32_CNTP_CVAL: + tmr = TIMER_PTIMER; + treg = TIMER_REG_CVAL; + break; + default: + BUG(); } - return true; -} - -static bool access_cntp_ctl(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *r) -{ - if (p->is_write) - kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CTL, p->regval); - else - p->regval = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CTL); - - return true; -} - -static bool access_cntp_cval(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *r) -{ if (p->is_write) - kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL, p->regval); + kvm_arm_timer_write_sysreg(vcpu, tmr, treg, p->regval); else - p->regval = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL); + p->regval = kvm_arm_timer_read_sysreg(vcpu, tmr, treg); return true; } @@ -1160,6 +1158,64 @@ static int set_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, return __set_id_reg(rd, uaddr, true); } +static bool access_ctr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + return write_to_read_only(vcpu, p, r); + + p->regval = read_sanitised_ftr_reg(SYS_CTR_EL0); + return true; +} + +static bool access_clidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + return write_to_read_only(vcpu, p, r); + + p->regval = read_sysreg(clidr_el1); + return true; +} + +static bool access_csselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + vcpu_write_sys_reg(vcpu, p->regval, r->reg); + else + p->regval = vcpu_read_sys_reg(vcpu, r->reg); + return true; +} + +static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + u32 csselr; + + if (p->is_write) + return write_to_read_only(vcpu, p, r); + + csselr = vcpu_read_sys_reg(vcpu, CSSELR_EL1); + p->regval = get_ccsidr(csselr); + + /* + * Guests should not be doing cache operations by set/way at all, and + * for this reason, we trap them and attempt to infer the intent, so + * that we can flush the entire guest's address space at the appropriate + * time. + * To prevent this trapping from causing performance problems, let's + * expose the geometry of all data and unified caches (which are + * guaranteed to be PIPT and thus non-aliasing) as 1 set and 1 way. + * [If guests should attempt to infer aliasing properties from the + * geometry (which is not permitted by the architecture), they would + * only do so for virtually indexed caches.] + */ + if (!(csselr & 1)) // data or unified cache + p->regval &= ~GENMASK(27, 3); + return true; +} + /* sys_reg_desc initialiser for known cpufeature ID registers */ #define ID_SANITISED(name) { \ SYS_DESC(SYS_##name), \ @@ -1377,7 +1433,10 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0}, - { SYS_DESC(SYS_CSSELR_EL1), NULL, reset_unknown, CSSELR_EL1 }, + { SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr }, + { SYS_DESC(SYS_CLIDR_EL1), access_clidr }, + { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, + { SYS_DESC(SYS_CTR_EL0), access_ctr }, { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, }, { SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 }, @@ -1400,9 +1459,9 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, - { SYS_DESC(SYS_CNTP_TVAL_EL0), access_cntp_tval }, - { SYS_DESC(SYS_CNTP_CTL_EL0), access_cntp_ctl }, - { SYS_DESC(SYS_CNTP_CVAL_EL0), access_cntp_cval }, + { SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer }, + { SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer }, + { SYS_DESC(SYS_CNTP_CVAL_EL0), access_arch_timer }, /* PMEVCNTRn_EL0 */ PMU_PMEVCNTR_EL0(0), @@ -1476,7 +1535,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 }, { SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 }, - { SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x70 }, + { SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x700 }, }; static bool trap_dbgidr(struct kvm_vcpu *vcpu, @@ -1677,6 +1736,7 @@ static const struct sys_reg_desc cp14_64_regs[] = { * register). */ static const struct sys_reg_desc cp15_regs[] = { + { Op1( 0), CRn( 0), CRm( 0), Op2( 1), access_ctr }, { Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR }, { Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 }, { Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 }, @@ -1723,10 +1783,9 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID }, - /* CNTP_TVAL */ - { Op1( 0), CRn(14), CRm( 2), Op2( 0), access_cntp_tval }, - /* CNTP_CTL */ - { Op1( 0), CRn(14), CRm( 2), Op2( 1), access_cntp_ctl }, + /* Arch Tmers */ + { SYS_DESC(SYS_AARCH32_CNTP_TVAL), access_arch_timer }, + { SYS_DESC(SYS_AARCH32_CNTP_CTL), access_arch_timer }, /* PMEVCNTRn */ PMU_PMEVCNTR(0), @@ -1794,6 +1853,10 @@ static const struct sys_reg_desc cp15_regs[] = { PMU_PMEVTYPER(30), /* PMCCFILTR */ { Op1(0), CRn(14), CRm(15), Op2(7), access_pmu_evtyper }, + + { Op1(1), CRn( 0), CRm( 0), Op2(0), access_ccsidr }, + { Op1(1), CRn( 0), CRm( 0), Op2(1), access_clidr }, + { Op1(2), CRn( 0), CRm( 0), Op2(0), access_csselr, NULL, c0_CSSELR }, }; static const struct sys_reg_desc cp15_64_regs[] = { @@ -1803,7 +1866,7 @@ static const struct sys_reg_desc cp15_64_regs[] = { { Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 }, { Op1( 1), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_ASGI1R */ { Op1( 2), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI0R */ - { Op1( 2), CRn( 0), CRm(14), Op2( 0), access_cntp_cval }, + { SYS_DESC(SYS_AARCH32_CNTP_CVAL), access_arch_timer }, }; /* Target specific emulation tables */ @@ -1832,30 +1895,19 @@ static const struct sys_reg_desc *get_target_table(unsigned target, } } -#define reg_to_match_value(x) \ - ({ \ - unsigned long val; \ - val = (x)->Op0 << 14; \ - val |= (x)->Op1 << 11; \ - val |= (x)->CRn << 7; \ - val |= (x)->CRm << 3; \ - val |= (x)->Op2; \ - val; \ - }) - static int match_sys_reg(const void *key, const void *elt) { const unsigned long pval = (unsigned long)key; const struct sys_reg_desc *r = elt; - return pval - reg_to_match_value(r); + return pval - reg_to_encoding(r); } static const struct sys_reg_desc *find_reg(const struct sys_reg_params *params, const struct sys_reg_desc table[], unsigned int num) { - unsigned long pval = reg_to_match_value(params); + unsigned long pval = reg_to_encoding(params); return bsearch((void *)pval, table, num, sizeof(table[0]), match_sys_reg); } @@ -2218,11 +2270,15 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu, } FUNCTION_INVARIANT(midr_el1) -FUNCTION_INVARIANT(ctr_el0) FUNCTION_INVARIANT(revidr_el1) FUNCTION_INVARIANT(clidr_el1) FUNCTION_INVARIANT(aidr_el1) +static void get_ctr_el0(struct kvm_vcpu *v, const struct sys_reg_desc *r) +{ + ((struct sys_reg_desc *)r)->val = read_sanitised_ftr_reg(SYS_CTR_EL0); +} + /* ->val is filled in by kvm_sys_reg_table_init() */ static struct sys_reg_desc invariant_sys_regs[] = { { SYS_DESC(SYS_MIDR_EL1), NULL, get_midr_el1 }, diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h @@ -1134,7 +1134,7 @@ static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {} -static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {} +static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h @@ -99,6 +99,8 @@ struct kvm_nested_guest; struct kvm_vm_stat { ulong remote_tlb_flush; + ulong num_2M_pages; + ulong num_1G_pages; }; struct kvm_vcpu_stat { @@ -377,6 +379,7 @@ struct kvmppc_mmu { void (*slbmte)(struct kvm_vcpu *vcpu, u64 rb, u64 rs); u64 (*slbmfee)(struct kvm_vcpu *vcpu, u64 slb_nr); u64 (*slbmfev)(struct kvm_vcpu *vcpu, u64 slb_nr); + int (*slbfee)(struct kvm_vcpu *vcpu, gva_t eaddr, ulong *ret_slb); void (*slbie)(struct kvm_vcpu *vcpu, u64 slb_nr); void (*slbia)(struct kvm_vcpu *vcpu); /* book3s */ @@ -837,7 +840,7 @@ struct kvm_vcpu_arch { static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} -static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {} +static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_exit(void) {} diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h @@ -36,6 +36,8 @@ #endif #ifdef CONFIG_KVM_BOOK3S_64_HANDLER #include <asm/paca.h> +#include <asm/xive.h> +#include <asm/cpu_has_feature.h> #endif /* @@ -617,6 +619,18 @@ static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 ir static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { } #endif /* CONFIG_KVM_XIVE */ +#if defined(CONFIG_PPC_POWERNV) && defined(CONFIG_KVM_BOOK3S_64_HANDLER) +static inline bool xics_on_xive(void) +{ + return xive_enabled() && cpu_has_feature(CPU_FTR_HVMODE); +} +#else +static inline bool xics_on_xive(void) +{ + return false; +} +#endif + /* * Prototypes for functions called only from assembler code. * Having prototypes reduces sparse errors. diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h @@ -463,10 +463,12 @@ struct kvm_ppc_cpu_char { #define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED (1ULL << 58) #define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF (1ULL << 57) #define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS (1ULL << 56) +#define KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54) #define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY (1ULL << 63) #define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR (1ULL << 62) #define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ULL << 61) +#define KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58) /* Per-vcpu XICS interrupt controller state */ #define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c) diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c @@ -39,6 +39,7 @@ #include "book3s.h" #include "trace.h" +#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU /* #define EXIT_DEBUG */ @@ -71,6 +72,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "pthru_all", VCPU_STAT(pthru_all) }, { "pthru_host", VCPU_STAT(pthru_host) }, { "pthru_bad_aff", VCPU_STAT(pthru_bad_aff) }, + { "largepages_2M", VM_STAT(num_2M_pages) }, + { "largepages_1G", VM_STAT(num_1G_pages) }, { NULL } }; @@ -642,7 +645,7 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, r = -ENXIO; break; } - if (xive_enabled()) + if (xics_on_xive()) *val = get_reg_val(id, kvmppc_xive_get_icp(vcpu)); else *val = get_reg_val(id, kvmppc_xics_get_icp(vcpu)); @@ -715,7 +718,7 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, r = -ENXIO; break; } - if (xive_enabled()) + if (xics_on_xive()) r = kvmppc_xive_set_icp(vcpu, set_reg_val(id, *val)); else r = kvmppc_xics_set_icp(vcpu, set_reg_val(id, *val)); @@ -991,7 +994,7 @@ int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hcall) int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status) { - if (xive_enabled()) + if (xics_on_xive()) return kvmppc_xive_set_irq(kvm, irq_source_id, irq, level, line_status); else @@ -1044,7 +1047,7 @@ static int kvmppc_book3s_init(void) #ifdef CONFIG_KVM_XICS #ifdef CONFIG_KVM_XIVE - if (xive_enabled()) { + if (xics_on_xive()) { kvmppc_xive_init_module(); kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS); } else @@ -1057,7 +1060,7 @@ static int kvmppc_book3s_init(void) static void kvmppc_book3s_exit(void) { #ifdef CONFIG_KVM_XICS - if (xive_enabled()) + if (xics_on_xive()) kvmppc_xive_exit_module(); #endif #ifdef CONFIG_KVM_BOOK3S_32_HANDLER diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c @@ -425,6 +425,7 @@ void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu) mmu->slbmte = NULL; mmu->slbmfee = NULL; mmu->slbmfev = NULL; + mmu->slbfee = NULL; mmu->slbie = NULL; mmu->slbia = NULL; } diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c @@ -435,6 +435,19 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb) kvmppc_mmu_map_segment(vcpu, esid << SID_SHIFT); } +static int kvmppc_mmu_book3s_64_slbfee(struct kvm_vcpu *vcpu, gva_t eaddr, + ulong *ret_slb) +{ + struct kvmppc_slb *slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu, eaddr); + + if (slbe) { + *ret_slb = slbe->origv; + return 0; + } + *ret_slb = 0; + return -ENOENT; +} + static u64 kvmppc_mmu_book3s_64_slbmfee(struct kvm_vcpu *vcpu, u64 slb_nr) { struct kvmppc_slb *slbe; @@ -670,6 +683,7 @@ void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu) mmu->slbmte = kvmppc_mmu_book3s_64_slbmte; mmu->slbmfee = kvmppc_mmu_book3s_64_slbmfee; mmu->slbmfev = kvmppc_mmu_book3s_64_slbmfev; + mmu->slbfee = kvmppc_mmu_book3s_64_slbfee; mmu->slbie = kvmppc_mmu_book3s_64_slbie; mmu->slbia = kvmppc_mmu_book3s_64_slbia; mmu->xlate = kvmppc_mmu_book3s_64_xlate; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -442,6 +442,24 @@ int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu, u32 last_inst; /* + * Fast path - check if the guest physical address corresponds to a + * device on the FAST_MMIO_BUS, if so we can avoid loading the + * instruction all together, then we can just handle it and return. + */ + if (is_store) { + int idx, ret; + + idx = srcu_read_lock(&vcpu->kvm->srcu); + ret = kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, (gpa_t) gpa, 0, + NULL); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + if (!ret) { + kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4); + return RESUME_GUEST; + } + } + + /* * If we fail, we just return to the guest and try executing it again. */ if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst) != diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -403,8 +403,13 @@ void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa, if (!memslot) return; } - if (shift) + if (shift) { /* 1GB or 2MB page */ page_size = 1ul << shift; + if (shift == PMD_SHIFT) + kvm->stat.num_2M_pages--; + else if (shift == PUD_SHIFT) + kvm->stat.num_1G_pages--; + } gpa &= ~(page_size - 1); hpa = old & PTE_RPN_MASK; @@ -878,6 +883,14 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu, put_page(page); } + /* Increment number of large pages if we (successfully) inserted one */ + if (!ret) { + if (level == 1) + kvm->stat.num_2M_pages++; + else if (level == 2) + kvm->stat.num_1G_pages++; + } + return ret; } diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c @@ -133,7 +133,6 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm, continue; kref_put(&stit->kref, kvm_spapr_tce_liobn_put); - return; } } } @@ -338,14 +337,15 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, } } + kvm_get_kvm(kvm); if (!ret) ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops, stt, O_RDWR | O_CLOEXEC); - if (ret >= 0) { + if (ret >= 0) list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables); - kvm_get_kvm(kvm); - } + else + kvm_put_kvm(kvm); mutex_unlock(&kvm->lock); diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c @@ -47,6 +47,7 @@ #define OP_31_XOP_SLBMFEV 851 #define OP_31_XOP_EIOIO 854 #define OP_31_XOP_SLBMFEE 915 +#define OP_31_XOP_SLBFEE 979 #define OP_31_XOP_TBEGIN 654 #define OP_31_XOP_TABORT 910 @@ -416,6 +417,23 @@ int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->arch.mmu.slbia(vcpu); break; + case OP_31_XOP_SLBFEE: + if (!(inst & 1) || !vcpu->arch.mmu.slbfee) { + return EMULATE_FAIL; + } else { + ulong b, t; + ulong cr = kvmppc_get_cr(vcpu) & ~CR0_MASK; + + b = kvmppc_get_gpr(vcpu, rb); + if (!vcpu->arch.mmu.slbfee(vcpu, b, &t)) + cr |= 2 << CR0_SHIFT; + kvmppc_set_gpr(vcpu, rt, t); + /* copy XER[SO] bit to CR0[SO] */ + cr |= (vcpu->arch.regs.xer & 0x80000000) >> + (31 - CR0_SHIFT); + kvmppc_set_cr(vcpu, cr); + } + break; case OP_31_XOP_SLBMFEE: if (!vcpu->arch.mmu.slbmfee) { emulated = EMULATE_FAIL; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c @@ -922,7 +922,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) case H_IPOLL: case H_XIRR_X: if (kvmppc_xics_enabled(vcpu)) { - if (xive_enabled()) { + if (xics_on_xive()) { ret = H_NOT_AVAILABLE; return RESUME_GUEST; } @@ -937,6 +937,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) ret = kvmppc_h_set_xdabr(vcpu, kvmppc_get_gpr(vcpu, 4), kvmppc_get_gpr(vcpu, 5)); break; +#ifdef CONFIG_SPAPR_TCE_IOMMU case H_GET_TCE: ret = kvmppc_h_get_tce(vcpu, kvmppc_get_gpr(vcpu, 4), kvmppc_get_gpr(vcpu, 5)); @@ -966,6 +967,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) if (ret == H_TOO_HARD) return RESUME_HOST; break; +#endif case H_RANDOM: if (!powernv_get_random_long(&vcpu->arch.regs.gpr[4])) ret = H_HARDWARE; @@ -1445,7 +1447,7 @@ static int kvmppc_handle_nested_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) case BOOK3S_INTERRUPT_HV_RM_HARD: vcpu->arch.trap = 0; r = RESUME_GUEST; - if (!xive_enabled()) + if (!xics_on_xive()) kvmppc_xics_rm_complete(vcpu, 0); break; default: @@ -3648,11 +3650,12 @@ static void kvmppc_wait_for_exec(struct kvmppc_vcore *vc, static void grow_halt_poll_ns(struct kvmppc_vcore *vc) { - /* 10us base */ - if (vc->halt_poll_ns == 0 && halt_poll_ns_grow) - vc->halt_poll_ns = 10000; - else - vc->halt_poll_ns *= halt_poll_ns_grow; + if (!halt_poll_ns_grow) + return; + + vc->halt_poll_ns *= halt_poll_ns_grow; + if (vc->halt_poll_ns < halt_poll_ns_grow_start) + vc->halt_poll_ns = halt_poll_ns_grow_start; } static void shrink_halt_poll_ns(struct kvmppc_vcore *vc) @@ -3666,7 +3669,7 @@ static void shrink_halt_poll_ns(struct kvmppc_vcore *vc) #ifdef CONFIG_KVM_XICS static inline bool xive_interrupt_pending(struct kvm_vcpu *vcpu) { - if (!xive_enabled()) + if (!xics_on_xive()) return false; return vcpu->arch.irq_pending || vcpu->arch.xive_saved_state.pipr < vcpu->arch.xive_saved_state.cppr; @@ -4226,7 +4229,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) vcpu->arch.fault_dar, vcpu->arch.fault_dsisr); srcu_read_unlock(&kvm->srcu, srcu_idx); } else if (r == RESUME_PASSTHROUGH) { - if (WARN_ON(xive_enabled())) + if (WARN_ON(xics_on_xive())) r = H_SUCCESS; else r = kvmppc_xics_rm_complete(vcpu, 0); @@ -4750,7 +4753,7 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) * If xive is enabled, we route 0x500 interrupts directly * to the guest. */ - if (xive_enabled()) + if (xics_on_xive()) lpcr |= LPCR_LPES; } @@ -4986,7 +4989,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) if (i == pimap->n_mapped) pimap->n_mapped++; - if (xive_enabled()) + if (xics_on_xive()) rc = kvmppc_xive_set_mapped(kvm, guest_gsi, desc); else kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq); @@ -5027,7 +5030,7 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) return -ENODEV; } - if (xive_enabled()) + if (xics_on_xive()) rc = kvmppc_xive_clr_mapped(kvm, guest_gsi, pimap->mapped[i].desc); else kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq); @@ -5359,13 +5362,11 @@ static int kvm_init_subcore_bitmap(void) continue; sibling_subcore_state = - kmalloc_node(sizeof(struct sibling_subcore_state), + kzalloc_node(sizeof(struct sibling_subcore_state), GFP_KERNEL, node); if (!sibling_subcore_state) return -ENOMEM; - memset(sibling_subcore_state, 0, - sizeof(struct sibling_subcore_state)); for (j = 0; j < threads_per_core; j++) { int cpu = first_cpu + j; @@ -5406,7 +5407,7 @@ static int kvmppc_book3s_init_hv(void) * indirectly, via OPAL. */ #ifdef CONFIG_SMP - if (!xive_enabled() && !kvmhv_on_pseries() && + if (!xics_on_xive() && !kvmhv_on_pseries() && !local_paca->kvm_hstate.xics_phys) { struct device_node *np; diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -257,7 +257,7 @@ void kvmhv_rm_send_ipi(int cpu) } /* We should never reach this */ - if (WARN_ON_ONCE(xive_enabled())) + if (WARN_ON_ONCE(xics_on_xive())) return; /* Else poke the target with an IPI */ @@ -577,7 +577,7 @@ unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu) { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xive_enabled()) { + if (xics_on_xive()) { if (is_rm()) return xive_rm_h_xirr(vcpu); if (unlikely(!__xive_vm_h_xirr)) @@ -592,7 +592,7 @@ unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu) if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; vcpu->arch.regs.gpr[5] = get_tb(); - if (xive_enabled()) { + if (xics_on_xive()) { if (is_rm()) return xive_rm_h_xirr(vcpu); if (unlikely(!__xive_vm_h_xirr)) @@ -606,7 +606,7 @@ unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server) { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xive_enabled()) { + if (xics_on_xive()) { if (is_rm()) return xive_rm_h_ipoll(vcpu, server); if (unlikely(!__xive_vm_h_ipoll)) @@ -621,7 +621,7 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xive_enabled()) { + if (xics_on_xive()) { if (is_rm()) return xive_rm_h_ipi(vcpu, server, mfrr); if (unlikely(!__xive_vm_h_ipi)) @@ -635,7 +635,7 @@ int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr) { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xive_enabled()) { + if (xics_on_xive()) { if (is_rm()) return xive_rm_h_cppr(vcpu, cppr); if (unlikely(!__xive_vm_h_cppr)) @@ -649,7 +649,7 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) { if (!kvmppc_xics_enabled(vcpu)) return H_TOO_HARD; - if (xive_enabled()) { + if (xics_on_xive()) { if (is_rm()) return xive_rm_h_eoi(vcpu, xirr); if (unlikely(!__xive_vm_h_eoi)) diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -144,6 +144,13 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu, return; } + if (xive_enabled() && kvmhv_on_pseries()) { + /* No XICS access or hypercalls available, too hard */ + this_icp->rm_action |= XICS_RM_KICK_VCPU; + this_icp->rm_kick_target = vcpu; + return; + } + /* * Check if the core is loaded, * if not, find an available host core to post to wake the VCPU, diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2272,8 +2272,13 @@ hcall_real_table: .long DOTSYM(kvmppc_h_clear_mod) - hcall_real_table .long DOTSYM(kvmppc_h_clear_ref) - hcall_real_table .long DOTSYM(kvmppc_h_protect) - hcall_real_table +#ifdef CONFIG_SPAPR_TCE_IOMMU .long DOTSYM(kvmppc_h_get_tce) - hcall_real_table .long DOTSYM(kvmppc_rm_h_put_tce) - hcall_real_table +#else + .long 0 /* 0x1c */ + .long 0 /* 0x20 */ +#endif .long 0 /* 0x24 - H_SET_SPRG0 */ .long DOTSYM(kvmppc_h_set_dabr) - hcall_real_table .long 0 /* 0x2c */ @@ -2351,8 +2356,13 @@ hcall_real_table: .long 0 /* 0x12c */ .long 0 /* 0x130 */ .long DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table +#ifdef CONFIG_SPAPR_TCE_IOMMU .long DOTSYM(kvmppc_rm_h_stuff_tce) - hcall_real_table .long DOTSYM(kvmppc_rm_h_put_tce_indirect) - hcall_real_table +#else + .long 0 /* 0x138 */ + .long 0 /* 0x13c */ +#endif .long 0 /* 0x140 */ .long 0 /* 0x144 */ .long 0 /* 0x148 */ diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c @@ -33,7 +33,7 @@ static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args) server = be32_to_cpu(args->args[1]); priority = be32_to_cpu(args->args[2]); - if (xive_enabled()) + if (xics_on_xive()) rc = kvmppc_xive_set_xive(vcpu->kvm, irq, server, priority); else rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority); @@ -56,7 +56,7 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args) irq = be32_to_cpu(args->args[0]); server = priority = 0; - if (xive_enabled()) + if (xics_on_xive()) rc = kvmppc_xive_get_xive(vcpu->kvm, irq, &server, &priority); else rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority); @@ -83,7 +83,7 @@ static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args) irq = be32_to_cpu(args->args[0]); - if (xive_enabled()) + if (xics_on_xive()) rc = kvmppc_xive_int_off(vcpu->kvm, irq); else rc = kvmppc_xics_int_off(vcpu->kvm, irq); @@ -105,7 +105,7 @@ static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args) irq = be32_to_cpu(args->args[0]); - if (xive_enabled()) + if (xics_on_xive()) rc = kvmppc_xive_int_on(vcpu->kvm, irq); else rc = kvmppc_xics_int_on(vcpu->kvm, irq); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c @@ -748,7 +748,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) kvmppc_mpic_disconnect_vcpu(vcpu->arch.mpic, vcpu); break; case KVMPPC_IRQ_XICS: - if (xive_enabled()) + if (xics_on_xive()) kvmppc_xive_cleanup_vcpu(vcpu); else kvmppc_xics_free_icp(vcpu); @@ -1931,7 +1931,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, r = -EPERM; dev = kvm_device_from_filp(f.file); if (dev) { - if (xive_enabled()) + if (xics_on_xive()) r = kvmppc_xive_connect_vcpu(dev, vcpu, cap->args[1]); else r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]); @@ -2189,10 +2189,12 @@ static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp) KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV | KVM_PPC_CPU_CHAR_BR_HINT_HONOURED | KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF | - KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS; + KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS | + KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST; cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY | KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR | - KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR; + KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR | + KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE; } return 0; } @@ -2251,12 +2253,16 @@ static int kvmppc_get_cpu_char(struct kvm_ppc_cpu_char *cp) if (have_fw_feat(fw_features, "enabled", "fw-count-cache-disabled")) cp->character |= KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS; + if (have_fw_feat(fw_features, "enabled", + "fw-count-cache-flush-bcctr2,0,0")) + cp->character |= KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST; cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 | KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED | KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 | KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 | KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV | - KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS; + KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS | + KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST; if (have_fw_feat(fw_features, "enabled", "speculation-policy-favor-security")) @@ -2267,9 +2273,13 @@ static int kvmppc_get_cpu_char(struct kvm_ppc_cpu_char *cp) if (!have_fw_feat(fw_features, "disabled", "needs-spec-barrier-for-bound-checks")) cp->behaviour |= KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR; + if (have_fw_feat(fw_features, "enabled", + "needs-count-cache-flush-on-context-switch")) + cp->behaviour |= KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE; cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY | KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR | - KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR; + KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR | + KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE; of_node_put(fw_features); } diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h @@ -331,5 +331,6 @@ extern void css_schedule_reprobe(void); /* Function from drivers/s390/cio/chsc.c */ int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta); int chsc_sstpi(void *page, void *result, size_t size); +int chsc_sgib(u32 origin); #endif diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h @@ -62,6 +62,7 @@ enum interruption_class { IRQIO_MSI, IRQIO_VIR, IRQIO_VAI, + IRQIO_GAL, NMI_NMI, CPU_RST, NR_ARCH_IRQS diff --git a/arch/s390/include/asm/isc.h b/arch/s390/include/asm/isc.h @@ -21,6 +21,7 @@ /* Adapter interrupts. */ #define QDIO_AIRQ_ISC IO_SCH_ISC /* I/O subchannel in qdio mode */ #define PCI_ISC 2 /* PCI I/O subchannels */ +#define GAL_ISC 5 /* GIB alert */ #define AP_ISC 6 /* adjunct processor (crypto) devices */ /* Functions for registration of I/O interruption subclasses */ diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h @@ -591,7 +591,6 @@ struct kvm_s390_float_interrupt { struct kvm_s390_mchk_info mchk; struct kvm_s390_ext_info srv_signal; int next_rr_cpu; - unsigned long idle_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)]; struct mutex ais_lock; u8 simm; u8 nimm; @@ -712,6 +711,7 @@ struct s390_io_adapter { struct kvm_s390_cpu_model { /* facility mask supported by kvm & hosting machine */ __u64 fac_mask[S390_ARCH_FAC_LIST_SIZE_U64]; + struct kvm_s390_vm_cpu_subfunc subfuncs; /* facility list requested by guest (in dma page) */ __u64 *fac_list; u64 cpuid; @@ -782,9 +782,21 @@ struct kvm_s390_gisa { u8 reserved03[11]; u32 airq_count; } g1; + struct { + u64 word[4]; + } u64; }; }; +struct kvm_s390_gib { + u32 alert_list_origin; + u32 reserved01; + u8:5; + u8 nisc:3; + u8 reserved03[3]; + u32 reserved04[5]; +}; + /* * sie_page2 has to be allocated as DMA because fac_list, crycb and * gisa need 31bit addresses in the sie control block. @@ -793,7 +805,8 @@ struct sie_page2 { __u64 fac_list[S390_ARCH_FAC_LIST_SIZE_U64]; /* 0x0000 */ struct kvm_s390_crypto_cb crycb; /* 0x0800 */ struct kvm_s390_gisa gisa; /* 0x0900 */ - u8 reserved920[0x1000 - 0x920]; /* 0x0920 */ + struct kvm *kvm; /* 0x0920 */ + u8 reserved928[0x1000 - 0x928]; /* 0x0928 */ }; struct kvm_s390_vsie { @@ -804,6 +817,20 @@ struct kvm_s390_vsie { struct page *pages[KVM_MAX_VCPUS]; }; +struct kvm_s390_gisa_iam { + u8 mask; + spinlock_t ref_lock; + u32 ref_count[MAX_ISC + 1]; +}; + +struct kvm_s390_gisa_interrupt { + struct kvm_s390_gisa *origin; + struct kvm_s390_gisa_iam alert; + struct hrtimer timer; + u64 expires; + DECLARE_BITMAP(kicked_mask, KVM_MAX_VCPUS); +}; + struct kvm_arch{ void *sca; int use_esca; @@ -837,7 +864,8 @@ struct kvm_arch{ atomic64_t cmma_dirty_pages; /* subset of available cpu features enabled by user space */ DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS); - struct kvm_s390_gisa *gisa; + DECLARE_BITMAP(idle_mask, KVM_MAX_VCPUS); + struct kvm_s390_gisa_interrupt gisa_int; }; #define KVM_HVA_ERR_BAD (-1UL) @@ -871,6 +899,9 @@ void kvm_arch_crypto_set_masks(struct kvm *kvm, unsigned long *apm, extern int sie64a(struct kvm_s390_sie_block *, u64 *); extern char sie_exit; +extern int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc); +extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc); + static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_check_processor_compat(void *rtn) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} @@ -878,7 +909,7 @@ static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {} -static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {} +static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) {} diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c @@ -88,6 +88,7 @@ static const struct irq_class irqclass_sub_desc[] = { {.irq = IRQIO_MSI, .name = "MSI", .desc = "[I/O] MSI Interrupt" }, {.irq = IRQIO_VIR, .name = "VIR", .desc = "[I/O] Virtual I/O Devices"}, {.irq = IRQIO_VAI, .name = "VAI", .desc = "[I/O] Virtual I/O Devices AI"}, + {.irq = IRQIO_GAL, .name = "GAL", .desc = "[I/O] GIB Alert"}, {.irq = NMI_NMI, .name = "NMI", .desc = "[NMI] Machine Check"}, {.irq = CPU_RST, .name = "RST", .desc = "[CPU] CPU Restart"}, }; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c @@ -7,6 +7,9 @@ * Author(s): Carsten Otte <cotte@de.ibm.com> */ +#define KMSG_COMPONENT "kvm-s390" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/interrupt.h> #include <linux/kvm_host.h> #include <linux/hrtimer.h> @@ -23,6 +26,7 @@ #include <asm/gmap.h> #include <asm/switch_to.h> #include <asm/nmi.h> +#include <asm/airq.h> #include "kvm-s390.h" #include "gaccess.h" #include "trace-s390.h" @@ -31,6 +35,8 @@ #define PFAULT_DONE 0x0680 #define VIRTIO_PARAM 0x0d00 +static struct kvm_s390_gib *gib; + /* handle external calls via sigp interpretation facility */ static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id) { @@ -217,22 +223,100 @@ static inline u8 int_word_to_isc(u32 int_word) */ #define IPM_BIT_OFFSET (offsetof(struct kvm_s390_gisa, ipm) * BITS_PER_BYTE) -static inline void kvm_s390_gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) +/** + * gisa_set_iam - change the GISA interruption alert mask + * + * @gisa: gisa to operate on + * @iam: new IAM value to use + * + * Change the IAM atomically with the next alert address and the IPM + * of the GISA if the GISA is not part of the GIB alert list. All three + * fields are located in the first long word of the GISA. + * + * Returns: 0 on success + * -EBUSY in case the gisa is part of the alert list + */ +static inline int gisa_set_iam(struct kvm_s390_gisa *gisa, u8 iam) +{ + u64 word, _word; + + do { + word = READ_ONCE(gisa->u64.word[0]); + if ((u64)gisa != word >> 32) + return -EBUSY; + _word = (word & ~0xffUL) | iam; + } while (cmpxchg(&gisa->u64.word[0], word, _word) != word); + + return 0; +} + +/** + * gisa_clear_ipm - clear the GISA interruption pending mask + * + * @gisa: gisa to operate on + * + * Clear the IPM atomically with the next alert address and the IAM + * of the GISA unconditionally. All three fields are located in the + * first long word of the GISA. + */ +static inline void gisa_clear_ipm(struct kvm_s390_gisa *gisa) +{ + u64 word, _word; + + do { + word = READ_ONCE(gisa->u64.word[0]); + _word = word & ~(0xffUL << 24); + } while (cmpxchg(&gisa->u64.word[0], word, _word) != word); +} + +/** + * gisa_get_ipm_or_restore_iam - return IPM or restore GISA IAM + * + * @gi: gisa interrupt struct to work on + * + * Atomically restores the interruption alert mask if none of the + * relevant ISCs are pending and return the IPM. + * + * Returns: the relevant pending ISCs + */ +static inline u8 gisa_get_ipm_or_restore_iam(struct kvm_s390_gisa_interrupt *gi) +{ + u8 pending_mask, alert_mask; + u64 word, _word; + + do { + word = READ_ONCE(gi->origin->u64.word[0]); + alert_mask = READ_ONCE(gi->alert.mask); + pending_mask = (u8)(word >> 24) & alert_mask; + if (pending_mask) + return pending_mask; + _word = (word & ~0xffUL) | alert_mask; + } while (cmpxchg(&gi->origin->u64.word[0], word, _word) != word); + + return 0; +} + +static inline int gisa_in_alert_list(struct kvm_s390_gisa *gisa) +{ + return READ_ONCE(gisa->next_alert) != (u32)(u64)gisa; +} + +static inline void gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) { set_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa); } -static inline u8 kvm_s390_gisa_get_ipm(struct kvm_s390_gisa *gisa) +static inline u8 gisa_get_ipm(struct kvm_s390_gisa *gisa) { return READ_ONCE(gisa->ipm); } -static inline void kvm_s390_gisa_clear_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) +static inline void gisa_clear_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) { clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa); } -static inline int kvm_s390_gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) +static inline int gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) { return test_and_clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa); } @@ -245,8 +329,13 @@ static inline unsigned long pending_irqs_no_gisa(struct kvm_vcpu *vcpu) static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu) { - return pending_irqs_no_gisa(vcpu) | - kvm_s390_gisa_get_ipm(vcpu->kvm->arch.gisa) << IRQ_PEND_IO_ISC_7; + struct kvm_s390_gisa_interrupt *gi = &vcpu->kvm->arch.gisa_int; + unsigned long pending_mask; + + pending_mask = pending_irqs_no_gisa(vcpu); + if (gi->origin) + pending_mask |= gisa_get_ipm(gi->origin) << IRQ_PEND_IO_ISC_7; + return pending_mask; } static inline int isc_to_irq_type(unsigned long isc) @@ -318,13 +407,13 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) static void __set_cpu_idle(struct kvm_vcpu *vcpu) { kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT); - set_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask); + set_bit(vcpu->vcpu_id, vcpu->kvm->arch.idle_mask); } static void __unset_cpu_idle(struct kvm_vcpu *vcpu) { kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT); - clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask); + clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.idle_mask); } static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) @@ -345,7 +434,7 @@ static void set_intercept_indicators_io(struct kvm_vcpu *vcpu) { if (!(pending_irqs_no_gisa(vcpu) & IRQ_PEND_IO_MASK)) return; - else if (psw_ioint_disabled(vcpu)) + if (psw_ioint_disabled(vcpu)) kvm_s390_set_cpuflags(vcpu, CPUSTAT_IO_INT); else vcpu->arch.sie_block->lctl |= LCTL_CR6; @@ -353,7 +442,7 @@ static void set_intercept_indicators_io(struct kvm_vcpu *vcpu) static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu) { - if (!(pending_irqs(vcpu) & IRQ_PEND_EXT_MASK)) + if (!(pending_irqs_no_gisa(vcpu) & IRQ_PEND_EXT_MASK)) return; if (psw_extint_disabled(vcpu)) kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT); @@ -363,7 +452,7 @@ static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu) static void set_intercept_indicators_mchk(struct kvm_vcpu *vcpu) { - if (!(pending_irqs(vcpu) & IRQ_PEND_MCHK_MASK)) + if (!(pending_irqs_no_gisa(vcpu) & IRQ_PEND_MCHK_MASK)) return; if (psw_mchk_disabled(vcpu)) vcpu->arch.sie_block->ictl |= ICTL_LPSW; @@ -956,6 +1045,7 @@ static int __must_check __deliver_io(struct kvm_vcpu *vcpu, { struct list_head *isc_list; struct kvm_s390_float_interrupt *fi; + struct kvm_s390_gisa_interrupt *gi = &vcpu->kvm->arch.gisa_int; struct kvm_s390_interrupt_info *inti = NULL; struct kvm_s390_io_info io; u32 isc; @@ -998,8 +1088,7 @@ static int __must_check __deliver_io(struct kvm_vcpu *vcpu, goto out; } - if (vcpu->kvm->arch.gisa && - kvm_s390_gisa_tac_ipm_gisc(vcpu->kvm->arch.gisa, isc)) { + if (gi->origin && gisa_tac_ipm_gisc(gi->origin, isc)) { /* * in case an adapter interrupt was not delivered * in SIE context KVM will handle the delivery @@ -1089,6 +1178,7 @@ static u64 __calculate_sltime(struct kvm_vcpu *vcpu) int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) { + struct kvm_s390_gisa_interrupt *gi = &vcpu->kvm->arch.gisa_int; u64 sltime; vcpu->stat.exit_wait_state++; @@ -1102,6 +1192,11 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; /* disabled wait */ } + if (gi->origin && + (gisa_get_ipm_or_restore_iam(gi) & + vcpu->arch.sie_block->gcr[6] >> 24)) + return 0; + if (!ckc_interrupts_enabled(vcpu) && !cpu_timer_interrupts_enabled(vcpu)) { VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer"); @@ -1533,18 +1628,19 @@ static struct kvm_s390_interrupt_info *get_top_io_int(struct kvm *kvm, static int get_top_gisa_isc(struct kvm *kvm, u64 isc_mask, u32 schid) { + struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int; unsigned long active_mask; int isc; if (schid) goto out; - if (!kvm->arch.gisa) + if (!gi->origin) goto out; - active_mask = (isc_mask & kvm_s390_gisa_get_ipm(kvm->arch.gisa) << 24) << 32; + active_mask = (isc_mask & gisa_get_ipm(gi->origin) << 24) << 32; while (active_mask) { isc = __fls(active_mask) ^ (BITS_PER_LONG - 1); - if (kvm_s390_gisa_tac_ipm_gisc(kvm->arch.gisa, isc)) + if (gisa_tac_ipm_gisc(gi->origin, isc)) return isc; clear_bit_inv(isc, &active_mask); } @@ -1567,6 +1663,7 @@ out: struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, u64 isc_mask, u32 schid) { + struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int; struct kvm_s390_interrupt_info *inti, *tmp_inti; int isc; @@ -1584,7 +1681,7 @@ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, /* both types of interrupts present */ if (int_word_to_isc(inti->io.io_int_word) <= isc) { /* classical IO int with higher priority */ - kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc); + gisa_set_ipm_gisc(gi->origin, isc); goto out; } gisa_out: @@ -1596,7 +1693,7 @@ gisa_out: kvm_s390_reinject_io_int(kvm, inti); inti = tmp_inti; } else - kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc); + gisa_set_ipm_gisc(gi->origin, isc); out: return inti; } @@ -1685,6 +1782,7 @@ static int __inject_float_mchk(struct kvm *kvm, static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) { + struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int; struct kvm_s390_float_interrupt *fi; struct list_head *list; int isc; @@ -1692,9 +1790,9 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) kvm->stat.inject_io++; isc = int_word_to_isc(inti->io.io_int_word); - if (kvm->arch.gisa && inti->type & KVM_S390_INT_IO_AI_MASK) { + if (gi->origin && inti->type & KVM_S390_INT_IO_AI_MASK) { VM_EVENT(kvm, 4, "%s isc %1u", "inject: I/O (AI/gisa)", isc); - kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc); + gisa_set_ipm_gisc(gi->origin, isc); kfree(inti); return 0; } @@ -1726,7 +1824,6 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) */ static void __floating_irq_kick(struct kvm *kvm, u64 type) { - struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; struct kvm_vcpu *dst_vcpu; int sigcpu, online_vcpus, nr_tries = 0; @@ -1735,11 +1832,11 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type) return; /* find idle VCPUs first, then round robin */ - sigcpu = find_first_bit(fi->idle_mask, online_vcpus); + sigcpu = find_first_bit(kvm->arch.idle_mask, online_vcpus); if (sigcpu == online_vcpus) { do { - sigcpu = fi->next_rr_cpu; - fi->next_rr_cpu = (fi->next_rr_cpu + 1) % online_vcpus; + sigcpu = kvm->arch.float_int.next_rr_cpu++; + kvm->arch.float_int.next_rr_cpu %= online_vcpus; /* avoid endless loops if all vcpus are stopped */ if (nr_tries++ >= online_vcpus) return; @@ -1753,7 +1850,8 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type) kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_STOP_INT); break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - if (!(type & KVM_S390_INT_IO_AI_MASK && kvm->arch.gisa)) + if (!(type & KVM_S390_INT_IO_AI_MASK && + kvm->arch.gisa_int.origin)) kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT); break; default: @@ -2003,6 +2101,7 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm) static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) { + struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int; struct kvm_s390_interrupt_info *inti; struct kvm_s390_float_interrupt *fi; struct kvm_s390_irq *buf; @@ -2026,15 +2125,14 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) max_irqs = len / sizeof(struct kvm_s390_irq); - if (kvm->arch.gisa && - kvm_s390_gisa_get_ipm(kvm->arch.gisa)) { + if (gi->origin && gisa_get_ipm(gi->origin)) { for (i = 0; i <= MAX_ISC; i++) { if (n == max_irqs) { /* signal userspace to try again */ ret = -ENOMEM; goto out_nolock; } - if (kvm_s390_gisa_tac_ipm_gisc(kvm->arch.gisa, i)) { + if (gisa_tac_ipm_gisc(gi->origin, i)) { irq = (struct kvm_s390_irq *) &buf[n]; irq->type = KVM_S390_INT_IO(1, 0, 0, 0); irq->u.io.io_int_word = isc_to_int_word(i); @@ -2831,7 +2929,7 @@ static void store_local_irq(struct kvm_s390_local_interrupt *li, int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len) { int scn; - unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS); struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; unsigned long pending_irqs; struct kvm_s390_irq irq; @@ -2884,27 +2982,278 @@ int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len) return n; } -void kvm_s390_gisa_clear(struct kvm *kvm) +static void __airqs_kick_single_vcpu(struct kvm *kvm, u8 deliverable_mask) { - if (kvm->arch.gisa) { - memset(kvm->arch.gisa, 0, sizeof(struct kvm_s390_gisa)); - kvm->arch.gisa->next_alert = (u32)(u64)kvm->arch.gisa; - VM_EVENT(kvm, 3, "gisa 0x%pK cleared", kvm->arch.gisa); + int vcpu_id, online_vcpus = atomic_read(&kvm->online_vcpus); + struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int; + struct kvm_vcpu *vcpu; + + for_each_set_bit(vcpu_id, kvm->arch.idle_mask, online_vcpus) { + vcpu = kvm_get_vcpu(kvm, vcpu_id); + if (psw_ioint_disabled(vcpu)) + continue; + deliverable_mask &= (u8)(vcpu->arch.sie_block->gcr[6] >> 24); + if (deliverable_mask) { + /* lately kicked but not yet running */ + if (test_and_set_bit(vcpu_id, gi->kicked_mask)) + return; + kvm_s390_vcpu_wakeup(vcpu); + return; + } } } +static enum hrtimer_restart gisa_vcpu_kicker(struct hrtimer *timer) +{ + struct kvm_s390_gisa_interrupt *gi = + container_of(timer, struct kvm_s390_gisa_interrupt, timer); + struct kvm *kvm = + container_of(gi->origin, struct sie_page2, gisa)->kvm; + u8 pending_mask; + + pending_mask = gisa_get_ipm_or_restore_iam(gi); + if (pending_mask) { + __airqs_kick_single_vcpu(kvm, pending_mask); + hrtimer_forward_now(timer, ns_to_ktime(gi->expires)); + return HRTIMER_RESTART; + }; + + return HRTIMER_NORESTART; +} + +#define NULL_GISA_ADDR 0x00000000UL +#define NONE_GISA_ADDR 0x00000001UL +#define GISA_ADDR_MASK 0xfffff000UL + +static void process_gib_alert_list(void) +{ + struct kvm_s390_gisa_interrupt *gi; + struct kvm_s390_gisa *gisa; + struct kvm *kvm; + u32 final, origin = 0UL; + + do { + /* + * If the NONE_GISA_ADDR is still stored in the alert list + * origin, we will leave the outer loop. No further GISA has + * been added to the alert list by millicode while processing + * the current alert list. + */ + final = (origin & NONE_GISA_ADDR); + /* + * Cut off the alert list and store the NONE_GISA_ADDR in the + * alert list origin to avoid further GAL interruptions. + * A new alert list can be build up by millicode in parallel + * for guests not in the yet cut-off alert list. When in the + * final loop, store the NULL_GISA_ADDR instead. This will re- + * enable GAL interruptions on the host again. + */ + origin = xchg(&gib->alert_list_origin, + (!final) ? NONE_GISA_ADDR : NULL_GISA_ADDR); + /* + * Loop through the just cut-off alert list and start the + * gisa timers to kick idle vcpus to consume the pending + * interruptions asap. + */ + while (origin & GISA_ADDR_MASK) { + gisa = (struct kvm_s390_gisa *)(u64)origin; + origin = gisa->next_alert; + gisa->next_alert = (u32)(u64)gisa; + kvm = container_of(gisa, struct sie_page2, gisa)->kvm; + gi = &kvm->arch.gisa_int; + if (hrtimer_active(&gi->timer)) + hrtimer_cancel(&gi->timer); + hrtimer_start(&gi->timer, 0, HRTIMER_MODE_REL); + } + } while (!final); + +} + +void kvm_s390_gisa_clear(struct kvm *kvm) +{ + struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int; + + if (!gi->origin) + return; + gisa_clear_ipm(gi->origin); + VM_EVENT(kvm, 3, "gisa 0x%pK cleared", gi->origin); +} + void kvm_s390_gisa_init(struct kvm *kvm) { - if (css_general_characteristics.aiv) { - kvm->arch.gisa = &kvm->arch.sie_page2->gisa; - VM_EVENT(kvm, 3, "gisa 0x%pK initialized", kvm->arch.gisa); - kvm_s390_gisa_clear(kvm); - } + struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int; + + if (!css_general_characteristics.aiv) + return; + gi->origin = &kvm->arch.sie_page2->gisa; + gi->alert.mask = 0; + spin_lock_init(&gi->alert.ref_lock); + gi->expires = 50 * 1000; /* 50 usec */ + hrtimer_init(&gi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + gi->timer.function = gisa_vcpu_kicker; + memset(gi->origin, 0, sizeof(struct kvm_s390_gisa)); + gi->origin->next_alert = (u32)(u64)gi->origin; + VM_EVENT(kvm, 3, "gisa 0x%pK initialized", gi->origin); } void kvm_s390_gisa_destroy(struct kvm *kvm) { - if (!kvm->arch.gisa) + struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int; + + if (!gi->origin) + return; + if (gi->alert.mask) + KVM_EVENT(3, "vm 0x%pK has unexpected iam 0x%02x", + kvm, gi->alert.mask); + while (gisa_in_alert_list(gi->origin)) + cpu_relax(); + hrtimer_cancel(&gi->timer); + gi->origin = NULL; +} + +/** + * kvm_s390_gisc_register - register a guest ISC + * + * @kvm: the kernel vm to work with + * @gisc: the guest interruption sub class to register + * + * The function extends the vm specific alert mask to use. + * The effective IAM mask in the GISA is updated as well + * in case the GISA is not part of the GIB alert list. + * It will be updated latest when the IAM gets restored + * by gisa_get_ipm_or_restore_iam(). + * + * Returns: the nonspecific ISC (NISC) the gib alert mechanism + * has registered with the channel subsystem. + * -ENODEV in case the vm uses no GISA + * -ERANGE in case the guest ISC is invalid + */ +int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc) +{ + struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int; + + if (!gi->origin) + return -ENODEV; + if (gisc > MAX_ISC) + return -ERANGE; + + spin_lock(&gi->alert.ref_lock); + gi->alert.ref_count[gisc]++; + if (gi->alert.ref_count[gisc] == 1) { + gi->alert.mask |= 0x80 >> gisc; + gisa_set_iam(gi->origin, gi->alert.mask); + } + spin_unlock(&gi->alert.ref_lock); + + return gib->nisc; +} +EXPORT_SYMBOL_GPL(kvm_s390_gisc_register); + +/** + * kvm_s390_gisc_unregister - unregister a guest ISC + * + * @kvm: the kernel vm to work with + * @gisc: the guest interruption sub class to register + * + * The function reduces the vm specific alert mask to use. + * The effective IAM mask in the GISA is updated as well + * in case the GISA is not part of the GIB alert list. + * It will be updated latest when the IAM gets restored + * by gisa_get_ipm_or_restore_iam(). + * + * Returns: the nonspecific ISC (NISC) the gib alert mechanism + * has registered with the channel subsystem. + * -ENODEV in case the vm uses no GISA + * -ERANGE in case the guest ISC is invalid + * -EINVAL in case the guest ISC is not registered + */ +int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc) +{ + struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int; + int rc = 0; + + if (!gi->origin) + return -ENODEV; + if (gisc > MAX_ISC) + return -ERANGE; + + spin_lock(&gi->alert.ref_lock); + if (gi->alert.ref_count[gisc] == 0) { + rc = -EINVAL; + goto out; + } + gi->alert.ref_count[gisc]--; + if (gi->alert.ref_count[gisc] == 0) { + gi->alert.mask &= ~(0x80 >> gisc); + gisa_set_iam(gi->origin, gi->alert.mask); + } +out: + spin_unlock(&gi->alert.ref_lock); + + return rc; +} +EXPORT_SYMBOL_GPL(kvm_s390_gisc_unregister); + +static void gib_alert_irq_handler(struct airq_struct *airq) +{ + inc_irq_stat(IRQIO_GAL); + process_gib_alert_list(); +} + +static struct airq_struct gib_alert_irq = { + .handler = gib_alert_irq_handler, + .lsi_ptr = &gib_alert_irq.lsi_mask, +}; + +void kvm_s390_gib_destroy(void) +{ + if (!gib) return; - kvm->arch.gisa = NULL; + chsc_sgib(0); + unregister_adapter_interrupt(&gib_alert_irq); + free_page((unsigned long)gib); + gib = NULL; +} + +int kvm_s390_gib_init(u8 nisc) +{ + int rc = 0; + + if (!css_general_characteristics.aiv) { + KVM_EVENT(3, "%s", "gib not initialized, no AIV facility"); + goto out; + } + + gib = (struct kvm_s390_gib *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + if (!gib) { + rc = -ENOMEM; + goto out; + } + + gib_alert_irq.isc = nisc; + if (register_adapter_interrupt(&gib_alert_irq)) { + pr_err("Registering the GIB alert interruption handler failed\n"); + rc = -EIO; + goto out_free_gib; + } + + gib->nisc = nisc; + if (chsc_sgib((u32)(u64)gib)) { + pr_err("Associating the GIB with the AIV facility failed\n"); + free_page((unsigned long)gib); + gib = NULL; + rc = -EIO; + goto out_unreg_gal; + } + + KVM_EVENT(3, "gib 0x%pK (nisc=%d) initialized", gib, gib->nisc); + goto out; + +out_unreg_gal: + unregister_adapter_interrupt(&gib_alert_irq); +out_free_gib: + free_page((unsigned long)gib); + gib = NULL; +out: + return rc; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c @@ -432,11 +432,18 @@ int kvm_arch_init(void *opaque) /* Register floating interrupt controller interface. */ rc = kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC); if (rc) { - pr_err("Failed to register FLIC rc=%d\n", rc); + pr_err("A FLIC registration call failed with rc=%d\n", rc); goto out_debug_unreg; } + + rc = kvm_s390_gib_init(GAL_ISC); + if (rc) + goto out_gib_destroy; + return 0; +out_gib_destroy: + kvm_s390_gib_destroy(); out_debug_unreg: debug_unregister(kvm_s390_dbf); return rc; @@ -444,6 +451,7 @@ out_debug_unreg: void kvm_arch_exit(void) { + kvm_s390_gib_destroy(); debug_unregister(kvm_s390_dbf); } @@ -1258,11 +1266,65 @@ static int kvm_s390_set_processor_feat(struct kvm *kvm, static int kvm_s390_set_processor_subfunc(struct kvm *kvm, struct kvm_device_attr *attr) { - /* - * Once supported by kernel + hw, we have to store the subfunctions - * in kvm->arch and remember that user space configured them. - */ - return -ENXIO; + mutex_lock(&kvm->lock); + if (kvm->created_vcpus) { + mutex_unlock(&kvm->lock); + return -EBUSY; + } + + if (copy_from_user(&kvm->arch.model.subfuncs, (void __user *)attr->addr, + sizeof(struct kvm_s390_vm_cpu_subfunc))) { + mutex_unlock(&kvm->lock); + return -EFAULT; + } + mutex_unlock(&kvm->lock); + + VM_EVENT(kvm, 3, "SET: guest PLO subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.plo)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.plo)[1], + ((unsigned long *) &kvm->arch.model.subfuncs.plo)[2], + ((unsigned long *) &kvm->arch.model.subfuncs.plo)[3]); + VM_EVENT(kvm, 3, "SET: guest PTFF subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.ptff)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.ptff)[1]); + VM_EVENT(kvm, 3, "SET: guest KMAC subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kmac)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kmac)[1]); + VM_EVENT(kvm, 3, "SET: guest KMC subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kmc)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kmc)[1]); + VM_EVENT(kvm, 3, "SET: guest KM subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.km)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.km)[1]); + VM_EVENT(kvm, 3, "SET: guest KIMD subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kimd)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kimd)[1]); + VM_EVENT(kvm, 3, "SET: guest KLMD subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.klmd)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.klmd)[1]); + VM_EVENT(kvm, 3, "SET: guest PCKMO subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.pckmo)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.pckmo)[1]); + VM_EVENT(kvm, 3, "SET: guest KMCTR subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kmctr)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kmctr)[1]); + VM_EVENT(kvm, 3, "SET: guest KMF subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kmf)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kmf)[1]); + VM_EVENT(kvm, 3, "SET: guest KMO subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kmo)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kmo)[1]); + VM_EVENT(kvm, 3, "SET: guest PCC subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.pcc)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.pcc)[1]); + VM_EVENT(kvm, 3, "SET: guest PPNO subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.ppno)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.ppno)[1]); + VM_EVENT(kvm, 3, "SET: guest KMA subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kma)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kma)[1]); + + return 0; } static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr) @@ -1381,12 +1443,56 @@ static int kvm_s390_get_machine_feat(struct kvm *kvm, static int kvm_s390_get_processor_subfunc(struct kvm *kvm, struct kvm_device_attr *attr) { - /* - * Once we can actually configure subfunctions (kernel + hw support), - * we have to check if they were already set by user space, if so copy - * them from kvm->arch. - */ - return -ENXIO; + if (copy_to_user((void __user *)attr->addr, &kvm->arch.model.subfuncs, + sizeof(struct kvm_s390_vm_cpu_subfunc))) + return -EFAULT; + + VM_EVENT(kvm, 3, "GET: guest PLO subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.plo)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.plo)[1], + ((unsigned long *) &kvm->arch.model.subfuncs.plo)[2], + ((unsigned long *) &kvm->arch.model.subfuncs.plo)[3]); + VM_EVENT(kvm, 3, "GET: guest PTFF subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.ptff)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.ptff)[1]); + VM_EVENT(kvm, 3, "GET: guest KMAC subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kmac)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kmac)[1]); + VM_EVENT(kvm, 3, "GET: guest KMC subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kmc)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kmc)[1]); + VM_EVENT(kvm, 3, "GET: guest KM subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.km)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.km)[1]); + VM_EVENT(kvm, 3, "GET: guest KIMD subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kimd)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kimd)[1]); + VM_EVENT(kvm, 3, "GET: guest KLMD subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.klmd)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.klmd)[1]); + VM_EVENT(kvm, 3, "GET: guest PCKMO subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.pckmo)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.pckmo)[1]); + VM_EVENT(kvm, 3, "GET: guest KMCTR subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kmctr)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kmctr)[1]); + VM_EVENT(kvm, 3, "GET: guest KMF subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kmf)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kmf)[1]); + VM_EVENT(kvm, 3, "GET: guest KMO subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kmo)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kmo)[1]); + VM_EVENT(kvm, 3, "GET: guest PCC subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.pcc)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.pcc)[1]); + VM_EVENT(kvm, 3, "GET: guest PPNO subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.ppno)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.ppno)[1]); + VM_EVENT(kvm, 3, "GET: guest KMA subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm->arch.model.subfuncs.kma)[0], + ((unsigned long *) &kvm->arch.model.subfuncs.kma)[1]); + + return 0; } static int kvm_s390_get_machine_subfunc(struct kvm *kvm, @@ -1395,8 +1501,55 @@ static int kvm_s390_get_machine_subfunc(struct kvm *kvm, if (copy_to_user((void __user *)attr->addr, &kvm_s390_available_subfunc, sizeof(struct kvm_s390_vm_cpu_subfunc))) return -EFAULT; + + VM_EVENT(kvm, 3, "GET: host PLO subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.plo)[0], + ((unsigned long *) &kvm_s390_available_subfunc.plo)[1], + ((unsigned long *) &kvm_s390_available_subfunc.plo)[2], + ((unsigned long *) &kvm_s390_available_subfunc.plo)[3]); + VM_EVENT(kvm, 3, "GET: host PTFF subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.ptff)[0], + ((unsigned long *) &kvm_s390_available_subfunc.ptff)[1]); + VM_EVENT(kvm, 3, "GET: host KMAC subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.kmac)[0], + ((unsigned long *) &kvm_s390_available_subfunc.kmac)[1]); + VM_EVENT(kvm, 3, "GET: host KMC subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.kmc)[0], + ((unsigned long *) &kvm_s390_available_subfunc.kmc)[1]); + VM_EVENT(kvm, 3, "GET: host KM subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.km)[0], + ((unsigned long *) &kvm_s390_available_subfunc.km)[1]); + VM_EVENT(kvm, 3, "GET: host KIMD subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.kimd)[0], + ((unsigned long *) &kvm_s390_available_subfunc.kimd)[1]); + VM_EVENT(kvm, 3, "GET: host KLMD subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.klmd)[0], + ((unsigned long *) &kvm_s390_available_subfunc.klmd)[1]); + VM_EVENT(kvm, 3, "GET: host PCKMO subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.pckmo)[0], + ((unsigned long *) &kvm_s390_available_subfunc.pckmo)[1]); + VM_EVENT(kvm, 3, "GET: host KMCTR subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.kmctr)[0], + ((unsigned long *) &kvm_s390_available_subfunc.kmctr)[1]); + VM_EVENT(kvm, 3, "GET: host KMF subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.kmf)[0], + ((unsigned long *) &kvm_s390_available_subfunc.kmf)[1]); + VM_EVENT(kvm, 3, "GET: host KMO subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.kmo)[0], + ((unsigned long *) &kvm_s390_available_subfunc.kmo)[1]); + VM_EVENT(kvm, 3, "GET: host PCC subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.pcc)[0], + ((unsigned long *) &kvm_s390_available_subfunc.pcc)[1]); + VM_EVENT(kvm, 3, "GET: host PPNO subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.ppno)[0], + ((unsigned long *) &kvm_s390_available_subfunc.ppno)[1]); + VM_EVENT(kvm, 3, "GET: host KMA subfunc 0x%16.16lx.%16.16lx", + ((unsigned long *) &kvm_s390_available_subfunc.kma)[0], + ((unsigned long *) &kvm_s390_available_subfunc.kma)[1]); + return 0; } + static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr) { int ret = -ENXIO; @@ -1514,10 +1667,9 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_CPU_PROCESSOR_FEAT: case KVM_S390_VM_CPU_MACHINE_FEAT: case KVM_S390_VM_CPU_MACHINE_SUBFUNC: + case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC: ret = 0; break; - /* configuring subfunctions is not supported yet */ - case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC: default: ret = -ENXIO; break; @@ -2209,6 +2361,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (!kvm->arch.sie_page2) goto out_err; + kvm->arch.sie_page2->kvm = kvm; kvm->arch.model.fac_list = kvm->arch.sie_page2->fac_list; for (i = 0; i < kvm_s390_fac_size(); i++) { @@ -2218,6 +2371,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.model.fac_list[i] = S390_lowcore.stfle_fac_list[i] & kvm_s390_fac_base[i]; } + kvm->arch.model.subfuncs = kvm_s390_available_subfunc; /* we are always in czam mode - even on pre z14 machines */ set_kvm_facility(kvm->arch.model.fac_mask, 138); @@ -2812,7 +2966,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.sie_block->icpua = id; spin_lock_init(&vcpu->arch.local_int.lock); - vcpu->arch.sie_block->gd = (u32)(u64)kvm->arch.gisa; + vcpu->arch.sie_block->gd = (u32)(u64)kvm->arch.gisa_int.origin; if (vcpu->arch.sie_block->gd && sclp.has_gisaf) vcpu->arch.sie_block->gd |= GISA_FORMAT1; seqcount_init(&vcpu->arch.cputm_seqcount); @@ -3458,6 +3612,8 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) kvm_s390_patch_guest_per_regs(vcpu); } + clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.gisa_int.kicked_mask); + vcpu->arch.sie_block->icptcode = 0; cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags); VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags); @@ -4293,12 +4449,12 @@ static int __init kvm_s390_init(void) int i; if (!sclp.has_sief2) { - pr_info("SIE not available\n"); + pr_info("SIE is not available\n"); return -ENODEV; } if (nested && hpage) { - pr_info("nested (vSIE) and hpage (huge page backing) can currently not be activated concurrently"); + pr_info("A KVM host that supports nesting cannot back its KVM guests with huge pages\n"); return -EINVAL; } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h @@ -67,7 +67,7 @@ static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu) static inline int is_vcpu_idle(struct kvm_vcpu *vcpu) { - return test_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask); + return test_bit(vcpu->vcpu_id, vcpu->kvm->arch.idle_mask); } static inline int kvm_is_ucontrol(struct kvm *kvm) @@ -381,6 +381,8 @@ int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, void kvm_s390_gisa_init(struct kvm *kvm); void kvm_s390_gisa_clear(struct kvm *kvm); void kvm_s390_gisa_destroy(struct kvm *kvm); +int kvm_s390_gib_init(u8 nisc); +void kvm_s390_gib_destroy(void); /* implemented in guestdbg.c */ void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h @@ -35,6 +35,7 @@ #include <asm/msr-index.h> #include <asm/asm.h> #include <asm/kvm_page_track.h> +#include <asm/kvm_vcpu_regs.h> #include <asm/hyperv-tlfs.h> #define KVM_MAX_VCPUS 288 @@ -137,23 +138,23 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) #define ASYNC_PF_PER_VCPU 64 enum kvm_reg { - VCPU_REGS_RAX = 0, - VCPU_REGS_RCX = 1, - VCPU_REGS_RDX = 2, - VCPU_REGS_RBX = 3, - VCPU_REGS_RSP = 4, - VCPU_REGS_RBP = 5, - VCPU_REGS_RSI = 6, - VCPU_REGS_RDI = 7, + VCPU_REGS_RAX = __VCPU_REGS_RAX, + VCPU_REGS_RCX = __VCPU_REGS_RCX, + VCPU_REGS_RDX = __VCPU_REGS_RDX, + VCPU_REGS_RBX = __VCPU_REGS_RBX, + VCPU_REGS_RSP = __VCPU_REGS_RSP, + VCPU_REGS_RBP = __VCPU_REGS_RBP, + VCPU_REGS_RSI = __VCPU_REGS_RSI, + VCPU_REGS_RDI = __VCPU_REGS_RDI, #ifdef CONFIG_X86_64 - VCPU_REGS_R8 = 8, - VCPU_REGS_R9 = 9, - VCPU_REGS_R10 = 10, - VCPU_REGS_R11 = 11, - VCPU_REGS_R12 = 12, - VCPU_REGS_R13 = 13, - VCPU_REGS_R14 = 14, - VCPU_REGS_R15 = 15, + VCPU_REGS_R8 = __VCPU_REGS_R8, + VCPU_REGS_R9 = __VCPU_REGS_R9, + VCPU_REGS_R10 = __VCPU_REGS_R10, + VCPU_REGS_R11 = __VCPU_REGS_R11, + VCPU_REGS_R12 = __VCPU_REGS_R12, + VCPU_REGS_R13 = __VCPU_REGS_R13, + VCPU_REGS_R14 = __VCPU_REGS_R14, + VCPU_REGS_R15 = __VCPU_REGS_R15, #endif VCPU_REGS_RIP, NR_VCPU_REGS @@ -319,6 +320,7 @@ struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; bool unsync; + bool mmio_cached; /* * The following two entries are used to key the shadow page in the @@ -333,10 +335,6 @@ struct kvm_mmu_page { int root_count; /* Currently serving as active root */ unsigned int unsync_children; struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ - - /* The page is obsolete if mmu_valid_gen != kvm->arch.mmu_valid_gen. */ - unsigned long mmu_valid_gen; - DECLARE_BITMAP(unsync_child_bitmap, 512); #ifdef CONFIG_X86_32 @@ -848,13 +846,11 @@ struct kvm_arch { unsigned int n_requested_mmu_pages; unsigned int n_max_mmu_pages; unsigned int indirect_shadow_pages; - unsigned long mmu_valid_gen; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; /* * Hash table of struct kvm_mmu_page. */ struct list_head active_mmu_pages; - struct list_head zapped_obsolete_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; @@ -1255,7 +1251,7 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); void kvm_mmu_zap_all(struct kvm *kvm); -void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots); +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); diff --git a/arch/x86/include/asm/kvm_vcpu_regs.h b/arch/x86/include/asm/kvm_vcpu_regs.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_KVM_VCPU_REGS_H +#define _ASM_X86_KVM_VCPU_REGS_H + +#define __VCPU_REGS_RAX 0 +#define __VCPU_REGS_RCX 1 +#define __VCPU_REGS_RDX 2 +#define __VCPU_REGS_RBX 3 +#define __VCPU_REGS_RSP 4 +#define __VCPU_REGS_RBP 5 +#define __VCPU_REGS_RSI 6 +#define __VCPU_REGS_RDI 7 + +#ifdef CONFIG_X86_64 +#define __VCPU_REGS_R8 8 +#define __VCPU_REGS_R9 9 +#define __VCPU_REGS_R10 10 +#define __VCPU_REGS_R11 11 +#define __VCPU_REGS_R12 12 +#define __VCPU_REGS_R13 13 +#define __VCPU_REGS_R14 14 +#define __VCPU_REGS_R15 15 +#endif + +#endif /* _ASM_X86_KVM_VCPU_REGS_H */ diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c @@ -104,12 +104,8 @@ static u64 kvm_sched_clock_read(void) static inline void kvm_sched_clock_init(bool stable) { - if (!stable) { - pv_ops.time.sched_clock = kvm_clock_read; + if (!stable) clear_sched_clock_stable(); - return; - } - kvm_sched_clock_offset = kvm_clock_read(); pv_ops.time.sched_clock = kvm_sched_clock_read; @@ -355,6 +351,20 @@ void __init kvmclock_init(void) machine_ops.crash_shutdown = kvm_crash_shutdown; #endif kvm_get_preset_lpj(); + + /* + * X86_FEATURE_NONSTOP_TSC is TSC runs at constant rate + * with P/T states and does not stop in deep C-states. + * + * Invariant TSC exposed by host means kvmclock is not necessary: + * can use TSC as clocksource. + * + */ + if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && + boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && + !check_tsc_unstable()) + kvm_clock.rating = 299; + clocksource_register_hz(&kvm_clock, NSEC_PER_SEC); pv_info.name = "KVM"; } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c @@ -405,7 +405,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | - F(CLDEMOTE); + F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B); /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c @@ -1729,7 +1729,7 @@ static int kvm_hv_eventfd_assign(struct kvm *kvm, u32 conn_id, int fd) mutex_lock(&hv->hv_lock); ret = idr_alloc(&hv->conn_to_evt, eventfd, conn_id, conn_id + 1, - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); mutex_unlock(&hv->hv_lock); if (ret >= 0) diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c @@ -653,7 +653,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) pid_t pid_nr; int ret; - pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL); + pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL_ACCOUNT); if (!pit) return NULL; diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c @@ -583,7 +583,7 @@ int kvm_pic_init(struct kvm *kvm) struct kvm_pic *s; int ret; - s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL); + s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL_ACCOUNT); if (!s) return -ENOMEM; spin_lock_init(&s->lock); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c @@ -622,7 +622,7 @@ int kvm_ioapic_init(struct kvm *kvm) struct kvm_ioapic *ioapic; int ret; - ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL); + ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL_ACCOUNT); if (!ioapic) return -ENOMEM; spin_lock_init(&ioapic->lock); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c @@ -181,7 +181,8 @@ static void recalculate_apic_map(struct kvm *kvm) max_id = max(max_id, kvm_x2apic_id(vcpu->arch.apic)); new = kvzalloc(sizeof(struct kvm_apic_map) + - sizeof(struct kvm_lapic *) * ((u64)max_id + 1), GFP_KERNEL); + sizeof(struct kvm_lapic *) * ((u64)max_id + 1), + GFP_KERNEL_ACCOUNT); if (!new) goto out; @@ -2259,13 +2260,13 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) ASSERT(vcpu != NULL); apic_debug("apic_init %d\n", vcpu->vcpu_id); - apic = kzalloc(sizeof(*apic), GFP_KERNEL); + apic = kzalloc(sizeof(*apic), GFP_KERNEL_ACCOUNT); if (!apic) goto nomem; vcpu->arch.apic = apic; - apic->regs = (void *)get_zeroed_page(GFP_KERNEL); + apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!apic->regs) { printk(KERN_ERR "malloc apic regs error for vcpu %x\n", vcpu->vcpu_id); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c @@ -109,9 +109,11 @@ module_param(dbg, bool, 0644); (((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1)) -#define PT64_BASE_ADDR_MASK __sme_clr((((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))) -#define PT64_DIR_BASE_ADDR_MASK \ - (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1)) +#ifdef CONFIG_DYNAMIC_PHYSICAL_MASK +#define PT64_BASE_ADDR_MASK (physical_mask & ~(u64)(PAGE_SIZE-1)) +#else +#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) +#endif #define PT64_LVL_ADDR_MASK(level) \ (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \ * PT64_LEVEL_BITS))) - 1)) @@ -330,53 +332,56 @@ static inline bool is_access_track_spte(u64 spte) } /* - * the low bit of the generation number is always presumed to be zero. - * This disables mmio caching during memslot updates. The concept is - * similar to a seqcount but instead of retrying the access we just punt - * and ignore the cache. + * Due to limited space in PTEs, the MMIO generation is a 19 bit subset of + * the memslots generation and is derived as follows: * - * spte bits 3-11 are used as bits 1-9 of the generation number, - * the bits 52-61 are used as bits 10-19 of the generation number. + * Bits 0-8 of the MMIO generation are propagated to spte bits 3-11 + * Bits 9-18 of the MMIO generation are propagated to spte bits 52-61 + * + * The KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS flag is intentionally not included in + * the MMIO generation number, as doing so would require stealing a bit from + * the "real" generation number and thus effectively halve the maximum number + * of MMIO generations that can be handled before encountering a wrap (which + * requires a full MMU zap). The flag is instead explicitly queried when + * checking for MMIO spte cache hits. */ -#define MMIO_SPTE_GEN_LOW_SHIFT 2 -#define MMIO_SPTE_GEN_HIGH_SHIFT 52 +#define MMIO_SPTE_GEN_MASK GENMASK_ULL(18, 0) -#define MMIO_GEN_SHIFT 20 -#define MMIO_GEN_LOW_SHIFT 10 -#define MMIO_GEN_LOW_MASK ((1 << MMIO_GEN_LOW_SHIFT) - 2) -#define MMIO_GEN_MASK ((1 << MMIO_GEN_SHIFT) - 1) +#define MMIO_SPTE_GEN_LOW_START 3 +#define MMIO_SPTE_GEN_LOW_END 11 +#define MMIO_SPTE_GEN_LOW_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \ + MMIO_SPTE_GEN_LOW_START) -static u64 generation_mmio_spte_mask(unsigned int gen) +#define MMIO_SPTE_GEN_HIGH_START 52 +#define MMIO_SPTE_GEN_HIGH_END 61 +#define MMIO_SPTE_GEN_HIGH_MASK GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \ + MMIO_SPTE_GEN_HIGH_START) +static u64 generation_mmio_spte_mask(u64 gen) { u64 mask; - WARN_ON(gen & ~MMIO_GEN_MASK); + WARN_ON(gen & ~MMIO_SPTE_GEN_MASK); - mask = (gen & MMIO_GEN_LOW_MASK) << MMIO_SPTE_GEN_LOW_SHIFT; - mask |= ((u64)gen >> MMIO_GEN_LOW_SHIFT) << MMIO_SPTE_GEN_HIGH_SHIFT; + mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK; + mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK; return mask; } -static unsigned int get_mmio_spte_generation(u64 spte) +static u64 get_mmio_spte_generation(u64 spte) { - unsigned int gen; + u64 gen; spte &= ~shadow_mmio_mask; - gen = (spte >> MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_GEN_LOW_MASK; - gen |= (spte >> MMIO_SPTE_GEN_HIGH_SHIFT) << MMIO_GEN_LOW_SHIFT; + gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START; + gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START; return gen; } -static unsigned int kvm_current_mmio_generation(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_memslots(vcpu)->generation & MMIO_GEN_MASK; -} - static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, unsigned access) { - unsigned int gen = kvm_current_mmio_generation(vcpu); + u64 gen = kvm_vcpu_memslots(vcpu)->generation & MMIO_SPTE_GEN_MASK; u64 mask = generation_mmio_spte_mask(gen); u64 gpa = gfn << PAGE_SHIFT; @@ -386,6 +391,8 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, mask |= (gpa & shadow_nonpresent_or_rsvd_mask) << shadow_nonpresent_or_rsvd_mask_len; + page_header(__pa(sptep))->mmio_cached = true; + trace_mark_mmio_spte(sptep, gfn, access, gen); mmu_spte_set(sptep, mask); } @@ -407,7 +414,7 @@ static gfn_t get_mmio_spte_gfn(u64 spte) static unsigned get_mmio_spte_access(u64 spte) { - u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask; + u64 mask = generation_mmio_spte_mask(MMIO_SPTE_GEN_MASK) | shadow_mmio_mask; return (spte & ~mask) & ~PAGE_MASK; } @@ -424,9 +431,13 @@ static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) { - unsigned int kvm_gen, spte_gen; + u64 kvm_gen, spte_gen, gen; - kvm_gen = kvm_current_mmio_generation(vcpu); + gen = kvm_vcpu_memslots(vcpu)->generation; + if (unlikely(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS)) + return false; + + kvm_gen = gen & MMIO_SPTE_GEN_MASK; spte_gen = get_mmio_spte_generation(spte); trace_check_mmio_spte(spte, kvm_gen, spte_gen); @@ -959,7 +970,7 @@ static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, if (cache->nobjs >= min) return 0; while (cache->nobjs < ARRAY_SIZE(cache->objects)) { - obj = kmem_cache_zalloc(base_cache, GFP_KERNEL); + obj = kmem_cache_zalloc(base_cache, GFP_KERNEL_ACCOUNT); if (!obj) return cache->nobjs >= min ? 0 : -ENOMEM; cache->objects[cache->nobjs++] = obj; @@ -2049,12 +2060,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct if (!direct) sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); - - /* - * The active_mmu_pages list is the FIFO list, do not move the - * page until it is zapped. kvm_zap_obsolete_pages depends on - * this feature. See the comments in kvm_zap_obsolete_pages(). - */ list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); kvm_mod_used_mmu_pages(vcpu->kvm, +1); return sp; @@ -2195,23 +2200,15 @@ static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) --kvm->stat.mmu_unsync; } -static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, - struct list_head *invalid_list); +static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, + struct list_head *invalid_list); static void kvm_mmu_commit_zap_page(struct kvm *kvm, struct list_head *invalid_list); -/* - * NOTE: we should pay more attention on the zapped-obsolete page - * (is_obsolete_sp(sp) && sp->role.invalid) when you do hash list walk - * since it has been deleted from active_mmu_pages but still can be found - * at hast list. - * - * for_each_valid_sp() has skipped that kind of pages. - */ #define for_each_valid_sp(_kvm, _sp, _gfn) \ hlist_for_each_entry(_sp, \ &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \ - if (is_obsolete_sp((_kvm), (_sp)) || (_sp)->role.invalid) { \ + if ((_sp)->role.invalid) { \ } else #define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn) \ @@ -2231,18 +2228,28 @@ static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, return true; } +static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm, + struct list_head *invalid_list, + bool remote_flush) +{ + if (!remote_flush && !list_empty(invalid_list)) + return false; + + if (!list_empty(invalid_list)) + kvm_mmu_commit_zap_page(kvm, invalid_list); + else + kvm_flush_remote_tlbs(kvm); + return true; +} + static void kvm_mmu_flush_or_zap(struct kvm_vcpu *vcpu, struct list_head *invalid_list, bool remote_flush, bool local_flush) { - if (!list_empty(invalid_list)) { - kvm_mmu_commit_zap_page(vcpu->kvm, invalid_list); + if (kvm_mmu_remote_flush_or_zap(vcpu->kvm, invalid_list, remote_flush)) return; - } - if (remote_flush) - kvm_flush_remote_tlbs(vcpu->kvm); - else if (local_flush) + if (local_flush) kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } @@ -2253,11 +2260,6 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { } static void mmu_audit_disable(void) { } #endif -static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) -{ - return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); -} - static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { @@ -2482,7 +2484,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, if (level > PT_PAGE_TABLE_LEVEL && need_sync) flush |= kvm_sync_pages(vcpu, gfn, &invalid_list); } - sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; clear_page(sp->spt); trace_kvm_mmu_get_page(sp, true); @@ -2668,17 +2669,22 @@ static int mmu_zap_unsync_children(struct kvm *kvm, return zapped; } -static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, - struct list_head *invalid_list) +static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, + struct kvm_mmu_page *sp, + struct list_head *invalid_list, + int *nr_zapped) { - int ret; + bool list_unstable; trace_kvm_mmu_prepare_zap_page(sp); ++kvm->stat.mmu_shadow_zapped; - ret = mmu_zap_unsync_children(kvm, sp, invalid_list); + *nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list); kvm_mmu_page_unlink_children(kvm, sp); kvm_mmu_unlink_parents(kvm, sp); + /* Zapping children means active_mmu_pages has become unstable. */ + list_unstable = *nr_zapped; + if (!sp->role.invalid && !sp->role.direct) unaccount_shadowed(kvm, sp); @@ -2686,22 +2692,27 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, kvm_unlink_unsync_page(kvm, sp); if (!sp->root_count) { /* Count self */ - ret++; + (*nr_zapped)++; list_move(&sp->link, invalid_list); kvm_mod_used_mmu_pages(kvm, -1); } else { list_move(&sp->link, &kvm->arch.active_mmu_pages); - /* - * The obsolete pages can not be used on any vcpus. - * See the comments in kvm_mmu_invalidate_zap_all_pages(). - */ - if (!sp->role.invalid && !is_obsolete_sp(kvm, sp)) + if (!sp->role.invalid) kvm_reload_remote_mmus(kvm); } sp->role.invalid = 1; - return ret; + return list_unstable; +} + +static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, + struct list_head *invalid_list) +{ + int nr_zapped; + + __kvm_mmu_prepare_zap_page(kvm, sp, invalid_list, &nr_zapped); + return nr_zapped; } static void kvm_mmu_commit_zap_page(struct kvm *kvm, @@ -3703,7 +3714,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) u64 *lm_root; - lm_root = (void*)get_zeroed_page(GFP_KERNEL); + lm_root = (void*)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (lm_root == NULL) return 1; @@ -4204,14 +4215,6 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3, return false; if (cached_root_available(vcpu, new_cr3, new_role)) { - /* - * It is possible that the cached previous root page is - * obsolete because of a change in the MMU - * generation number. However, that is accompanied by - * KVM_REQ_MMU_RELOAD, which will free the root that we - * have set here and allocate a new one. - */ - kvm_make_request(KVM_REQ_LOAD_CR3, vcpu); if (!skip_tlb_flush) { kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); @@ -5486,6 +5489,76 @@ void kvm_disable_tdp(void) } EXPORT_SYMBOL_GPL(kvm_disable_tdp); + +/* The return value indicates if tlb flush on all vcpus is needed. */ +typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); + +/* The caller should hold mmu-lock before calling this function. */ +static __always_inline bool +slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, int start_level, int end_level, + gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) +{ + struct slot_rmap_walk_iterator iterator; + bool flush = false; + + for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn, + end_gfn, &iterator) { + if (iterator.rmap) + flush |= fn(kvm, iterator.rmap); + + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + if (flush && lock_flush_tlb) { + kvm_flush_remote_tlbs(kvm); + flush = false; + } + cond_resched_lock(&kvm->mmu_lock); + } + } + + if (flush && lock_flush_tlb) { + kvm_flush_remote_tlbs(kvm); + flush = false; + } + + return flush; +} + +static __always_inline bool +slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, int start_level, int end_level, + bool lock_flush_tlb) +{ + return slot_handle_level_range(kvm, memslot, fn, start_level, + end_level, memslot->base_gfn, + memslot->base_gfn + memslot->npages - 1, + lock_flush_tlb); +} + +static __always_inline bool +slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, + PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); +} + +static __always_inline bool +slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1, + PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); +} + +static __always_inline bool +slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, + PT_PAGE_TABLE_LEVEL, lock_flush_tlb); +} + static void free_mmu_pages(struct kvm_vcpu *vcpu) { free_page((unsigned long)vcpu->arch.mmu->pae_root); @@ -5505,7 +5578,7 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu) * Therefore we need to allocate shadow page tables in the first * 4GB of memory, which happens to fit the DMA32 zone. */ - page = alloc_page(GFP_KERNEL | __GFP_DMA32); + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_DMA32); if (!page) return -ENOMEM; @@ -5543,105 +5616,62 @@ static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, struct kvm_page_track_notifier_node *node) { - kvm_mmu_invalidate_zap_all_pages(kvm); -} - -void kvm_mmu_init_vm(struct kvm *kvm) -{ - struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; - - node->track_write = kvm_mmu_pte_write; - node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot; - kvm_page_track_register_notifier(kvm, node); -} + struct kvm_mmu_page *sp; + LIST_HEAD(invalid_list); + unsigned long i; + bool flush; + gfn_t gfn; -void kvm_mmu_uninit_vm(struct kvm *kvm) -{ - struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; + spin_lock(&kvm->mmu_lock); - kvm_page_track_unregister_notifier(kvm, node); -} + if (list_empty(&kvm->arch.active_mmu_pages)) + goto out_unlock; -/* The return value indicates if tlb flush on all vcpus is needed. */ -typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); + flush = slot_handle_all_level(kvm, slot, kvm_zap_rmapp, false); -/* The caller should hold mmu-lock before calling this function. */ -static __always_inline bool -slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, int start_level, int end_level, - gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) -{ - struct slot_rmap_walk_iterator iterator; - bool flush = false; + for (i = 0; i < slot->npages; i++) { + gfn = slot->base_gfn + i; - for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn, - end_gfn, &iterator) { - if (iterator.rmap) - flush |= fn(kvm, iterator.rmap); + for_each_valid_sp(kvm, sp, gfn) { + if (sp->gfn != gfn) + continue; + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + } if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { - if (flush && lock_flush_tlb) { - kvm_flush_remote_tlbs(kvm); - flush = false; - } + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); + flush = false; cond_resched_lock(&kvm->mmu_lock); } } + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); - if (flush && lock_flush_tlb) { - kvm_flush_remote_tlbs(kvm); - flush = false; - } - - return flush; +out_unlock: + spin_unlock(&kvm->mmu_lock); } -static __always_inline bool -slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, int start_level, int end_level, - bool lock_flush_tlb) +void kvm_mmu_init_vm(struct kvm *kvm) { - return slot_handle_level_range(kvm, memslot, fn, start_level, - end_level, memslot->base_gfn, - memslot->base_gfn + memslot->npages - 1, - lock_flush_tlb); -} + struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; -static __always_inline bool -slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, bool lock_flush_tlb) -{ - return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, - PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); + node->track_write = kvm_mmu_pte_write; + node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot; + kvm_page_track_register_notifier(kvm, node); } -static __always_inline bool -slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, bool lock_flush_tlb) +void kvm_mmu_uninit_vm(struct kvm *kvm) { - return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1, - PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); -} + struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; -static __always_inline bool -slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, bool lock_flush_tlb) -{ - return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, - PT_PAGE_TABLE_LEVEL, lock_flush_tlb); + kvm_page_track_unregister_notifier(kvm, node); } void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - bool flush_tlb = true; - bool flush = false; int i; - if (kvm_available_flush_tlb_with_range()) - flush_tlb = false; - spin_lock(&kvm->mmu_lock); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); @@ -5653,17 +5683,12 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) if (start >= end) continue; - flush |= slot_handle_level_range(kvm, memslot, - kvm_zap_rmapp, PT_PAGE_TABLE_LEVEL, - PT_MAX_HUGEPAGE_LEVEL, start, - end - 1, flush_tlb); + slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, + PT_PAGE_TABLE_LEVEL, PT_MAX_HUGEPAGE_LEVEL, + start, end - 1, true); } } - if (flush) - kvm_flush_remote_tlbs_with_address(kvm, gfn_start, - gfn_end - gfn_start + 1); - spin_unlock(&kvm->mmu_lock); } @@ -5815,101 +5840,58 @@ void kvm_mmu_slot_set_dirty(struct kvm *kvm, } EXPORT_SYMBOL_GPL(kvm_mmu_slot_set_dirty); -#define BATCH_ZAP_PAGES 10 -static void kvm_zap_obsolete_pages(struct kvm *kvm) +static void __kvm_mmu_zap_all(struct kvm *kvm, bool mmio_only) { struct kvm_mmu_page *sp, *node; - int batch = 0; + LIST_HEAD(invalid_list); + int ign; + spin_lock(&kvm->mmu_lock); restart: - list_for_each_entry_safe_reverse(sp, node, - &kvm->arch.active_mmu_pages, link) { - int ret; - - /* - * No obsolete page exists before new created page since - * active_mmu_pages is the FIFO list. - */ - if (!is_obsolete_sp(kvm, sp)) - break; - - /* - * Since we are reversely walking the list and the invalid - * list will be moved to the head, skip the invalid page - * can help us to avoid the infinity list walking. - */ - if (sp->role.invalid) + list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) { + if (mmio_only && !sp->mmio_cached) continue; - - /* - * Need not flush tlb since we only zap the sp with invalid - * generation number. - */ - if (batch >= BATCH_ZAP_PAGES && - cond_resched_lock(&kvm->mmu_lock)) { - batch = 0; + if (sp->role.invalid && sp->root_count) + continue; + if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign)) { + WARN_ON_ONCE(mmio_only); goto restart; } - - ret = kvm_mmu_prepare_zap_page(kvm, sp, - &kvm->arch.zapped_obsolete_pages); - batch += ret; - - if (ret) + if (cond_resched_lock(&kvm->mmu_lock)) goto restart; } - /* - * Should flush tlb before free page tables since lockless-walking - * may use the pages. - */ - kvm_mmu_commit_zap_page(kvm, &kvm->arch.zapped_obsolete_pages); -} - -/* - * Fast invalidate all shadow pages and use lock-break technique - * to zap obsolete pages. - * - * It's required when memslot is being deleted or VM is being - * destroyed, in these cases, we should ensure that KVM MMU does - * not use any resource of the being-deleted slot or all slots - * after calling the function. - */ -void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm) -{ - spin_lock(&kvm->mmu_lock); - trace_kvm_mmu_invalidate_zap_all_pages(kvm); - kvm->arch.mmu_valid_gen++; - - /* - * Notify all vcpus to reload its shadow page table - * and flush TLB. Then all vcpus will switch to new - * shadow page table with the new mmu_valid_gen. - * - * Note: we should do this under the protection of - * mmu-lock, otherwise, vcpu would purge shadow page - * but miss tlb flush. - */ - kvm_reload_remote_mmus(kvm); - - kvm_zap_obsolete_pages(kvm); + kvm_mmu_commit_zap_page(kvm, &invalid_list); spin_unlock(&kvm->mmu_lock); } -static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) +void kvm_mmu_zap_all(struct kvm *kvm) { - return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); + return __kvm_mmu_zap_all(kvm, false); } -void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots) +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) { + WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); + + gen &= MMIO_SPTE_GEN_MASK; + /* - * The very rare case: if the generation-number is round, + * Generation numbers are incremented in multiples of the number of + * address spaces in order to provide unique generations across all + * address spaces. Strip what is effectively the address space + * modifier prior to checking for a wrap of the MMIO generation so + * that a wrap in any address space is detected. + */ + gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1); + + /* + * The very rare case: if the MMIO generation number has wrapped, * zap all shadow pages. */ - if (unlikely((slots->generation & MMIO_GEN_MASK) == 0)) { + if (unlikely(gen == 0)) { kvm_debug_ratelimited("kvm: zapping shadow pages for mmio generation wraparound\n"); - kvm_mmu_invalidate_zap_all_pages(kvm); + __kvm_mmu_zap_all(kvm, true); } } @@ -5940,24 +5922,16 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) * want to shrink a VM that only started to populate its MMU * anyway. */ - if (!kvm->arch.n_used_mmu_pages && - !kvm_has_zapped_obsolete_pages(kvm)) + if (!kvm->arch.n_used_mmu_pages) continue; idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); - if (kvm_has_zapped_obsolete_pages(kvm)) { - kvm_mmu_commit_zap_page(kvm, - &kvm->arch.zapped_obsolete_pages); - goto unlock; - } - if (prepare_zap_oldest_mmu_page(kvm, &invalid_list)) freed++; kvm_mmu_commit_zap_page(kvm, &invalid_list); -unlock: spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h @@ -203,7 +203,6 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, return -(u32)fault & errcode; } -void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm); void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h @@ -8,18 +8,16 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvmmmu -#define KVM_MMU_PAGE_FIELDS \ - __field(unsigned long, mmu_valid_gen) \ - __field(__u64, gfn) \ - __field(__u32, role) \ - __field(__u32, root_count) \ +#define KVM_MMU_PAGE_FIELDS \ + __field(__u64, gfn) \ + __field(__u32, role) \ + __field(__u32, root_count) \ __field(bool, unsync) -#define KVM_MMU_PAGE_ASSIGN(sp) \ - __entry->mmu_valid_gen = sp->mmu_valid_gen; \ - __entry->gfn = sp->gfn; \ - __entry->role = sp->role.word; \ - __entry->root_count = sp->root_count; \ +#define KVM_MMU_PAGE_ASSIGN(sp) \ + __entry->gfn = sp->gfn; \ + __entry->role = sp->role.word; \ + __entry->root_count = sp->root_count; \ __entry->unsync = sp->unsync; #define KVM_MMU_PAGE_PRINTK() ({ \ @@ -31,9 +29,8 @@ \ role.word = __entry->role; \ \ - trace_seq_printf(p, "sp gen %lx gfn %llx l%u%s q%u%s %s%s" \ + trace_seq_printf(p, "sp gfn %llx l%u%s q%u%s %s%s" \ " %snxe %sad root %u %s%c", \ - __entry->mmu_valid_gen, \ __entry->gfn, role.level, \ role.cr4_pae ? " pae" : "", \ role.quadrant, \ @@ -283,27 +280,6 @@ TRACE_EVENT( ); TRACE_EVENT( - kvm_mmu_invalidate_zap_all_pages, - TP_PROTO(struct kvm *kvm), - TP_ARGS(kvm), - - TP_STRUCT__entry( - __field(unsigned long, mmu_valid_gen) - __field(unsigned int, mmu_used_pages) - ), - - TP_fast_assign( - __entry->mmu_valid_gen = kvm->arch.mmu_valid_gen; - __entry->mmu_used_pages = kvm->arch.n_used_mmu_pages; - ), - - TP_printk("kvm-mmu-valid-gen %lx used_pages %x", - __entry->mmu_valid_gen, __entry->mmu_used_pages - ) -); - - -TRACE_EVENT( check_mmio_spte, TP_PROTO(u64 spte, unsigned int kvm_gen, unsigned int spte_gen), TP_ARGS(spte, kvm_gen, spte_gen), diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c @@ -42,7 +42,7 @@ int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) { slot->arch.gfn_track[i] = kvcalloc(npages, sizeof(*slot->arch.gfn_track[i]), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!slot->arch.gfn_track[i]) goto track_free; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c @@ -145,7 +145,6 @@ struct kvm_svm { /* Struct members for AVIC */ u32 avic_vm_id; - u32 ldr_mode; struct page *avic_logical_id_table_page; struct page *avic_physical_id_table_page; struct hlist_node hnode; @@ -236,6 +235,7 @@ struct vcpu_svm { bool nrips_enabled : 1; u32 ldr_reg; + u32 dfr_reg; struct page *avic_backing_page; u64 *avic_physical_id_cache; bool avic_is_running; @@ -1795,9 +1795,10 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, /* Avoid using vmalloc for smaller buffers. */ size = npages * sizeof(struct page *); if (size > PAGE_SIZE) - pages = vmalloc(size); + pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO, + PAGE_KERNEL); else - pages = kmalloc(size, GFP_KERNEL); + pages = kmalloc(size, GFP_KERNEL_ACCOUNT); if (!pages) return NULL; @@ -1865,7 +1866,9 @@ static void __unregister_enc_region_locked(struct kvm *kvm, static struct kvm *svm_vm_alloc(void) { - struct kvm_svm *kvm_svm = vzalloc(sizeof(struct kvm_svm)); + struct kvm_svm *kvm_svm = __vmalloc(sizeof(struct kvm_svm), + GFP_KERNEL_ACCOUNT | __GFP_ZERO, + PAGE_KERNEL); return &kvm_svm->kvm; } @@ -1940,7 +1943,7 @@ static int avic_vm_init(struct kvm *kvm) return 0; /* Allocating physical APIC ID table (4KB) */ - p_page = alloc_page(GFP_KERNEL); + p_page = alloc_page(GFP_KERNEL_ACCOUNT); if (!p_page) goto free_avic; @@ -1948,7 +1951,7 @@ static int avic_vm_init(struct kvm *kvm) clear_page(page_address(p_page)); /* Allocating logical APIC ID table (4KB) */ - l_page = alloc_page(GFP_KERNEL); + l_page = alloc_page(GFP_KERNEL_ACCOUNT); if (!l_page) goto free_avic; @@ -2106,6 +2109,7 @@ static int avic_init_vcpu(struct vcpu_svm *svm) INIT_LIST_HEAD(&svm->ir_list); spin_lock_init(&svm->ir_list_lock); + svm->dfr_reg = APIC_DFR_FLAT; return ret; } @@ -2119,13 +2123,14 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) struct page *nested_msrpm_pages; int err; - svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); if (!svm) { err = -ENOMEM; goto out; } - svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL); + svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); if (!svm->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; @@ -2137,19 +2142,19 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto free_svm; err = -ENOMEM; - page = alloc_page(GFP_KERNEL); + page = alloc_page(GFP_KERNEL_ACCOUNT); if (!page) goto uninit; - msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); + msrpm_pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER); if (!msrpm_pages) goto free_page1; - nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); + nested_msrpm_pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER); if (!nested_msrpm_pages) goto free_page2; - hsave_page = alloc_page(GFP_KERNEL); + hsave_page = alloc_page(GFP_KERNEL_ACCOUNT); if (!hsave_page) goto free_page3; @@ -4565,8 +4570,7 @@ static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat) return &logical_apic_id_table[index]; } -static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr, - bool valid) +static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) { bool flat; u32 *entry, new_entry; @@ -4579,31 +4583,39 @@ static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr, new_entry = READ_ONCE(*entry); new_entry &= ~AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; new_entry |= (g_physical_id & AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK); - if (valid) - new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK; - else - new_entry &= ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK; + new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK; WRITE_ONCE(*entry, new_entry); return 0; } +static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + bool flat = svm->dfr_reg == APIC_DFR_FLAT; + u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat); + + if (entry) + WRITE_ONCE(*entry, (u32) ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK); +} + static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) { - int ret; + int ret = 0; struct vcpu_svm *svm = to_svm(vcpu); u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR); - if (!ldr) - return 1; + if (ldr == svm->ldr_reg) + return 0; - ret = avic_ldr_write(vcpu, vcpu->vcpu_id, ldr, true); - if (ret && svm->ldr_reg) { - avic_ldr_write(vcpu, 0, svm->ldr_reg, false); - svm->ldr_reg = 0; - } else { + avic_invalidate_logical_id_entry(vcpu); + + if (ldr) + ret = avic_ldr_write(vcpu, vcpu->vcpu_id, ldr); + + if (!ret) svm->ldr_reg = ldr; - } + return ret; } @@ -4637,27 +4649,16 @@ static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu) return 0; } -static int avic_handle_dfr_update(struct kvm_vcpu *vcpu) +static void avic_handle_dfr_update(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); u32 dfr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR); - u32 mod = (dfr >> 28) & 0xf; - /* - * We assume that all local APICs are using the same type. - * If this changes, we need to flush the AVIC logical - * APID id table. - */ - if (kvm_svm->ldr_mode == mod) - return 0; - - clear_page(page_address(kvm_svm->avic_logical_id_table_page)); - kvm_svm->ldr_mode = mod; + if (svm->dfr_reg == dfr) + return; - if (svm->ldr_reg) - avic_handle_ldr_update(vcpu); - return 0; + avic_invalidate_logical_id_entry(vcpu); + svm->dfr_reg = dfr; } static int avic_unaccel_trap_write(struct vcpu_svm *svm) @@ -5125,11 +5126,11 @@ static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - if (!kvm_vcpu_apicv_active(&svm->vcpu)) - return; - - vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; - mark_dirty(vmcb, VMCB_INTR); + if (kvm_vcpu_apicv_active(vcpu)) + vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + else + vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; + mark_dirty(vmcb, VMCB_AVIC); } static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) @@ -5195,7 +5196,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) * Allocating new amd_iommu_pi_data, which will get * add to the per-vcpu ir_list. */ - ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL); + ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT); if (!ir) { ret = -ENOMEM; goto out; @@ -6163,8 +6164,7 @@ static inline void avic_post_state_restore(struct kvm_vcpu *vcpu) { if (avic_handle_apic_id_update(vcpu) != 0) return; - if (avic_handle_dfr_update(vcpu) != 0) - return; + avic_handle_dfr_update(vcpu); avic_handle_ldr_update(vcpu); } @@ -6311,7 +6311,7 @@ static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) if (ret) return ret; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -6361,7 +6361,7 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params))) return -EFAULT; - start = kzalloc(sizeof(*start), GFP_KERNEL); + start = kzalloc(sizeof(*start), GFP_KERNEL_ACCOUNT); if (!start) return -ENOMEM; @@ -6458,7 +6458,7 @@ static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params))) return -EFAULT; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -6535,7 +6535,7 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) if (copy_from_user(&params, measure, sizeof(params))) return -EFAULT; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -6597,7 +6597,7 @@ static int sev_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -6618,7 +6618,7 @@ static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!sev_guest(kvm)) return -ENOTTY; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -6646,7 +6646,7 @@ static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src, struct sev_data_dbg *data; int ret; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) return -ENOMEM; @@ -6901,7 +6901,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) } ret = -ENOMEM; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); if (!data) goto e_unpin_memory; @@ -7007,7 +7007,7 @@ static int svm_register_enc_region(struct kvm *kvm, if (range->addr > ULONG_MAX || range->size > ULONG_MAX) return -EINVAL; - region = kzalloc(sizeof(*region), GFP_KERNEL); + region = kzalloc(sizeof(*region), GFP_KERNEL_ACCOUNT); if (!region) return -ENOMEM; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c @@ -211,7 +211,6 @@ static void free_nested(struct kvm_vcpu *vcpu) if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon) return; - hrtimer_cancel(&vmx->nested.preemption_timer); vmx->nested.vmxon = false; vmx->nested.smm.vmxon = false; free_vpid(vmx->nested.vpid02); @@ -274,6 +273,7 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu) { vcpu_load(vcpu); + vmx_leave_nested(vcpu); vmx_switch_vmcs(vcpu, &to_vmx(vcpu)->vmcs01); free_nested(vcpu); vcpu_put(vcpu); @@ -1980,17 +1980,6 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) prepare_vmcs02_early_full(vmx, vmcs12); /* - * HOST_RSP is normally set correctly in vmx_vcpu_run() just before - * entry, but only if the current (host) sp changed from the value - * we wrote last (vmx->host_rsp). This cache is no longer relevant - * if we switch vmcs, and rather than hold a separate cache per vmcs, - * here we just force the write to happen on entry. host_rsp will - * also be written unconditionally by nested_vmx_check_vmentry_hw() - * if we are doing early consistency checks via hardware. - */ - vmx->host_rsp = 0; - - /* * PIN CONTROLS */ exec_control = vmcs12->pin_based_vm_exec_control; @@ -2289,10 +2278,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } vmx_set_rflags(vcpu, vmcs12->guest_rflags); - vmx->nested.preemption_timer_expired = false; - if (nested_cpu_has_preemption_timer(vmcs12)) - vmx_start_preemption_timer(vcpu); - /* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the * bitwise-or of what L1 wants to trap for L2, and what we want to * trap. Note that CR0.TS also needs updating - we do this later. @@ -2722,6 +2707,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; + bool vm_fail; if (!nested_early_check) return 0; @@ -2755,29 +2741,34 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->host_state.cr4 = cr4; } - vmx->__launched = vmx->loaded_vmcs->launched; - asm( - /* Set HOST_RSP */ "sub $%c[wordsize], %%" _ASM_SP "\n\t" /* temporarily adjust RSP for CALL */ - __ex("vmwrite %%" _ASM_SP ", %%" _ASM_DX) "\n\t" - "mov %%" _ASM_SP ", %c[host_rsp](%1)\n\t" + "cmp %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t" + "je 1f \n\t" + __ex("vmwrite %%" _ASM_SP ", %[HOST_RSP]") "\n\t" + "mov %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t" + "1: \n\t" "add $%c[wordsize], %%" _ASM_SP "\n\t" /* un-adjust RSP */ /* Check if vmlaunch or vmresume is needed */ - "cmpl $0, %c[launched](%% " _ASM_CX")\n\t" + "cmpb $0, %c[launched](%[loaded_vmcs])\n\t" + /* + * VMLAUNCH and VMRESUME clear RFLAGS.{CF,ZF} on VM-Exit, set + * RFLAGS.CF on VM-Fail Invalid and set RFLAGS.ZF on VM-Fail + * Valid. vmx_vmenter() directly "returns" RFLAGS, and so the + * results of VM-Enter is captured via CC_{SET,OUT} to vm_fail. + */ "call vmx_vmenter\n\t" - /* Set vmx->fail accordingly */ - "setbe %c[fail](%% " _ASM_CX")\n\t" - : ASM_CALL_CONSTRAINT - : "c"(vmx), "d"((unsigned long)HOST_RSP), - [launched]"i"(offsetof(struct vcpu_vmx, __launched)), - [fail]"i"(offsetof(struct vcpu_vmx, fail)), - [host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp)), + CC_SET(be) + : ASM_CALL_CONSTRAINT, CC_OUT(be) (vm_fail) + : [HOST_RSP]"r"((unsigned long)HOST_RSP), + [loaded_vmcs]"r"(vmx->loaded_vmcs), + [launched]"i"(offsetof(struct loaded_vmcs, launched)), + [host_state_rsp]"i"(offsetof(struct loaded_vmcs, host_state.rsp)), [wordsize]"i"(sizeof(ulong)) - : "rax", "cc", "memory" + : "cc", "memory" ); preempt_enable(); @@ -2787,10 +2778,9 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) if (vmx->msr_autoload.guest.nr) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); - if (vmx->fail) { + if (vm_fail) { WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) != VMXERR_ENTRY_INVALID_CONTROL_FIELD); - vmx->fail = 0; return 1; } @@ -2813,8 +2803,6 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) return 0; } -STACK_FRAME_NON_STANDARD(nested_vmx_check_vmentry_hw); - static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12); @@ -3031,6 +3019,15 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) kvm_make_request(KVM_REQ_EVENT, vcpu); /* + * Do not start the preemption timer hrtimer until after we know + * we are successful, so that only nested_vmx_vmexit needs to cancel + * the timer. + */ + vmx->nested.preemption_timer_expired = false; + if (nested_cpu_has_preemption_timer(vmcs12)) + vmx_start_preemption_timer(vcpu); + + /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet * returned as far as L1 is concerned. It will only return (and set @@ -3450,13 +3447,10 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) else vmcs12->guest_activity_state = GUEST_ACTIVITY_ACTIVE; - if (nested_cpu_has_preemption_timer(vmcs12)) { - if (vmcs12->vm_exit_controls & - VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) + if (nested_cpu_has_preemption_timer(vmcs12) && + vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) vmcs12->vmx_preemption_timer_value = vmx_get_preemption_timer_value(vcpu); - hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer); - } /* * In some cases (usually, nested EPT), L2 is allowed to change its @@ -3864,6 +3858,9 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, leave_guest_mode(vcpu); + if (nested_cpu_has_preemption_timer(vmcs12)) + hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer); + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) vcpu->arch.tsc_offset -= vmcs12->tsc_offset; @@ -3915,9 +3912,6 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmx_flush_tlb(vcpu, true); } - /* This is needed for same reason as it was needed in prepare_vmcs02 */ - vmx->host_rsp = 0; - /* Unpin physical memory we referred to in vmcs02 */ if (vmx->nested.apic_access_page) { kvm_release_page_dirty(vmx->nested.apic_access_page); @@ -4035,25 +4029,50 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, /* Addr = segment_base + offset */ /* offset = base + [index * scale] + displacement */ off = exit_qualification; /* holds the displacement */ + if (addr_size == 1) + off = (gva_t)sign_extend64(off, 31); + else if (addr_size == 0) + off = (gva_t)sign_extend64(off, 15); if (base_is_valid) off += kvm_register_read(vcpu, base_reg); if (index_is_valid) off += kvm_register_read(vcpu, index_reg)<<scaling; vmx_get_segment(vcpu, &s, seg_reg); - *ret = s.base + off; + /* + * The effective address, i.e. @off, of a memory operand is truncated + * based on the address size of the instruction. Note that this is + * the *effective address*, i.e. the address prior to accounting for + * the segment's base. + */ if (addr_size == 1) /* 32 bit */ - *ret &= 0xffffffff; + off &= 0xffffffff; + else if (addr_size == 0) /* 16 bit */ + off &= 0xffff; /* Checks for #GP/#SS exceptions. */ exn = false; if (is_long_mode(vcpu)) { + /* + * The virtual/linear address is never truncated in 64-bit + * mode, e.g. a 32-bit address size can yield a 64-bit virtual + * address when using FS/GS with a non-zero base. + */ + *ret = s.base + off; + /* Long mode: #GP(0)/#SS(0) if the memory address is in a * non-canonical form. This is the only check on the memory * destination for long mode! */ exn = is_noncanonical_address(*ret, vcpu); - } else if (is_protmode(vcpu)) { + } else { + /* + * When not in long mode, the virtual/linear address is + * unconditionally truncated to 32 bits regardless of the + * address size. + */ + *ret = (s.base + off) & 0xffffffff; + /* Protected mode: apply checks for segment validity in the * following order: * - segment type check (#GP(0) may be thrown) @@ -4077,10 +4096,16 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. */ exn = (s.unusable != 0); - /* Protected mode: #GP(0)/#SS(0) if the memory - * operand is outside the segment limit. + + /* + * Protected mode: #GP(0)/#SS(0) if the memory operand is + * outside the segment limit. All CPUs that support VMX ignore + * limit checks for flat segments, i.e. segments with base==0, + * limit==0xffffffff and of type expand-up data or code. */ - exn = exn || (off + sizeof(u64) > s.limit); + if (!(s.base == 0 && s.limit == 0xffffffff && + ((s.type & 8) || !(s.type & 4)))) + exn = exn || (off + sizeof(u64) > s.limit); } if (exn) { kvm_queue_exception_e(vcpu, @@ -4145,11 +4170,11 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) if (r < 0) goto out_vmcs02; - vmx->nested.cached_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL); + vmx->nested.cached_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT); if (!vmx->nested.cached_vmcs12) goto out_cached_vmcs12; - vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL); + vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT); if (!vmx->nested.cached_shadow_vmcs12) goto out_cached_shadow_vmcs12; @@ -5696,6 +5721,10 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) enable_shadow_vmcs = 0; if (enable_shadow_vmcs) { for (i = 0; i < VMX_BITMAP_NR; i++) { + /* + * The vmx_bitmap is not tied to a VM and so should + * not be charged to a memcg. + */ vmx_bitmap[i] = (unsigned long *) __get_free_page(GFP_KERNEL); if (!vmx_bitmap[i]) { diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h @@ -34,6 +34,7 @@ struct vmcs_host_state { unsigned long cr4; /* May not match real cr4 */ unsigned long gs_base; unsigned long fs_base; + unsigned long rsp; u16 fs_sel, gs_sel, ldt_sel; #ifdef CONFIG_X86_64 diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S @@ -1,6 +1,30 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> #include <asm/asm.h> +#include <asm/bitsperlong.h> +#include <asm/kvm_vcpu_regs.h> + +#define WORD_SIZE (BITS_PER_LONG / 8) + +#define VCPU_RAX __VCPU_REGS_RAX * WORD_SIZE +#define VCPU_RCX __VCPU_REGS_RCX * WORD_SIZE +#define VCPU_RDX __VCPU_REGS_RDX * WORD_SIZE +#define VCPU_RBX __VCPU_REGS_RBX * WORD_SIZE +/* Intentionally omit RSP as it's context switched by hardware */ +#define VCPU_RBP __VCPU_REGS_RBP * WORD_SIZE +#define VCPU_RSI __VCPU_REGS_RSI * WORD_SIZE +#define VCPU_RDI __VCPU_REGS_RDI * WORD_SIZE + +#ifdef CONFIG_X86_64 +#define VCPU_R8 __VCPU_REGS_R8 * WORD_SIZE +#define VCPU_R9 __VCPU_REGS_R9 * WORD_SIZE +#define VCPU_R10 __VCPU_REGS_R10 * WORD_SIZE +#define VCPU_R11 __VCPU_REGS_R11 * WORD_SIZE +#define VCPU_R12 __VCPU_REGS_R12 * WORD_SIZE +#define VCPU_R13 __VCPU_REGS_R13 * WORD_SIZE +#define VCPU_R14 __VCPU_REGS_R14 * WORD_SIZE +#define VCPU_R15 __VCPU_REGS_R15 * WORD_SIZE +#endif .text @@ -55,3 +79,146 @@ ENDPROC(vmx_vmenter) ENTRY(vmx_vmexit) ret ENDPROC(vmx_vmexit) + +/** + * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode + * @vmx: struct vcpu_vmx * + * @regs: unsigned long * (to guest registers) + * @launched: %true if the VMCS has been launched + * + * Returns: + * 0 on VM-Exit, 1 on VM-Fail + */ +ENTRY(__vmx_vcpu_run) + push %_ASM_BP + mov %_ASM_SP, %_ASM_BP +#ifdef CONFIG_X86_64 + push %r15 + push %r14 + push %r13 + push %r12 +#else + push %edi + push %esi +#endif + push %_ASM_BX + + /* + * Save @regs, _ASM_ARG2 may be modified by vmx_update_host_rsp() and + * @regs is needed after VM-Exit to save the guest's register values. + */ + push %_ASM_ARG2 + + /* Copy @launched to BL, _ASM_ARG3 is volatile. */ + mov %_ASM_ARG3B, %bl + + /* Adjust RSP to account for the CALL to vmx_vmenter(). */ + lea -WORD_SIZE(%_ASM_SP), %_ASM_ARG2 + call vmx_update_host_rsp + + /* Load @regs to RAX. */ + mov (%_ASM_SP), %_ASM_AX + + /* Check if vmlaunch or vmresume is needed */ + cmpb $0, %bl + + /* Load guest registers. Don't clobber flags. */ + mov VCPU_RBX(%_ASM_AX), %_ASM_BX + mov VCPU_RCX(%_ASM_AX), %_ASM_CX + mov VCPU_RDX(%_ASM_AX), %_ASM_DX + mov VCPU_RSI(%_ASM_AX), %_ASM_SI + mov VCPU_RDI(%_ASM_AX), %_ASM_DI + mov VCPU_RBP(%_ASM_AX), %_ASM_BP +#ifdef CONFIG_X86_64 + mov VCPU_R8 (%_ASM_AX), %r8 + mov VCPU_R9 (%_ASM_AX), %r9 + mov VCPU_R10(%_ASM_AX), %r10 + mov VCPU_R11(%_ASM_AX), %r11 + mov VCPU_R12(%_ASM_AX), %r12 + mov VCPU_R13(%_ASM_AX), %r13 + mov VCPU_R14(%_ASM_AX), %r14 + mov VCPU_R15(%_ASM_AX), %r15 +#endif + /* Load guest RAX. This kills the vmx_vcpu pointer! */ + mov VCPU_RAX(%_ASM_AX), %_ASM_AX + + /* Enter guest mode */ + call vmx_vmenter + + /* Jump on VM-Fail. */ + jbe 2f + + /* Temporarily save guest's RAX. */ + push %_ASM_AX + + /* Reload @regs to RAX. */ + mov WORD_SIZE(%_ASM_SP), %_ASM_AX + + /* Save all guest registers, including RAX from the stack */ + __ASM_SIZE(pop) VCPU_RAX(%_ASM_AX) + mov %_ASM_BX, VCPU_RBX(%_ASM_AX) + mov %_ASM_CX, VCPU_RCX(%_ASM_AX) + mov %_ASM_DX, VCPU_RDX(%_ASM_AX) + mov %_ASM_SI, VCPU_RSI(%_ASM_AX) + mov %_ASM_DI, VCPU_RDI(%_ASM_AX) + mov %_ASM_BP, VCPU_RBP(%_ASM_AX) +#ifdef CONFIG_X86_64 + mov %r8, VCPU_R8 (%_ASM_AX) + mov %r9, VCPU_R9 (%_ASM_AX) + mov %r10, VCPU_R10(%_ASM_AX) + mov %r11, VCPU_R11(%_ASM_AX) + mov %r12, VCPU_R12(%_ASM_AX) + mov %r13, VCPU_R13(%_ASM_AX) + mov %r14, VCPU_R14(%_ASM_AX) + mov %r15, VCPU_R15(%_ASM_AX) +#endif + + /* Clear RAX to indicate VM-Exit (as opposed to VM-Fail). */ + xor %eax, %eax + + /* + * Clear all general purpose registers except RSP and RAX to prevent + * speculative use of the guest's values, even those that are reloaded + * via the stack. In theory, an L1 cache miss when restoring registers + * could lead to speculative execution with the guest's values. + * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially + * free. RSP and RAX are exempt as RSP is restored by hardware during + * VM-Exit and RAX is explicitly loaded with 0 or 1 to return VM-Fail. + */ +1: xor %ebx, %ebx + xor %ecx, %ecx + xor %edx, %edx + xor %esi, %esi + xor %edi, %edi + xor %ebp, %ebp +#ifdef CONFIG_X86_64 + xor %r8d, %r8d + xor %r9d, %r9d + xor %r10d, %r10d + xor %r11d, %r11d + xor %r12d, %r12d + xor %r13d, %r13d + xor %r14d, %r14d + xor %r15d, %r15d +#endif + + /* "POP" @regs. */ + add $WORD_SIZE, %_ASM_SP + pop %_ASM_BX + +#ifdef CONFIG_X86_64 + pop %r12 + pop %r13 + pop %r14 + pop %r15 +#else + pop %esi + pop %edi +#endif + pop %_ASM_BP + ret + + /* VM-Fail. Out-of-line to avoid a taken Jcc after VM-Exit. */ +2: mov $1, %eax + jmp 1b +ENDPROC(__vmx_vcpu_run) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c @@ -246,6 +246,10 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages && !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) { + /* + * This allocation for vmx_l1d_flush_pages is not tied to a VM + * lifetime and so should not be charged to a memcg. + */ page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER); if (!page) return -ENOMEM; @@ -2387,13 +2391,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, return 0; } -struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu) +struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) { int node = cpu_to_node(cpu); struct page *pages; struct vmcs *vmcs; - pages = __alloc_pages_node(node, GFP_KERNEL, vmcs_config.order); + pages = __alloc_pages_node(node, flags, vmcs_config.order); if (!pages) return NULL; vmcs = page_address(pages); @@ -2440,7 +2444,8 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) loaded_vmcs_init(loaded_vmcs); if (cpu_has_vmx_msr_bitmap()) { - loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); + loaded_vmcs->msr_bitmap = (unsigned long *) + __get_free_page(GFP_KERNEL_ACCOUNT); if (!loaded_vmcs->msr_bitmap) goto out_vmcs; memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); @@ -2481,7 +2486,7 @@ static __init int alloc_kvm_area(void) for_each_possible_cpu(cpu) { struct vmcs *vmcs; - vmcs = alloc_vmcs_cpu(false, cpu); + vmcs = alloc_vmcs_cpu(false, cpu, GFP_KERNEL); if (!vmcs) { free_kvm_area(); return -ENOMEM; @@ -6360,150 +6365,15 @@ static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->hv_timer_armed = false; } -static void __vmx_vcpu_run(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) +void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) { - unsigned long evmcs_rsp; - - vmx->__launched = vmx->loaded_vmcs->launched; - - evmcs_rsp = static_branch_unlikely(&enable_evmcs) ? - (unsigned long)&current_evmcs->host_rsp : 0; - - if (static_branch_unlikely(&vmx_l1d_should_flush)) - vmx_l1d_flush(vcpu); - - asm( - /* Store host registers */ - "push %%" _ASM_DX "; push %%" _ASM_BP ";" - "push %%" _ASM_CX " \n\t" /* placeholder for guest rcx */ - "push %%" _ASM_CX " \n\t" - "sub $%c[wordsize], %%" _ASM_SP "\n\t" /* temporarily adjust RSP for CALL */ - "cmp %%" _ASM_SP ", %c[host_rsp](%%" _ASM_CX ") \n\t" - "je 1f \n\t" - "mov %%" _ASM_SP ", %c[host_rsp](%%" _ASM_CX ") \n\t" - /* Avoid VMWRITE when Enlightened VMCS is in use */ - "test %%" _ASM_SI ", %%" _ASM_SI " \n\t" - "jz 2f \n\t" - "mov %%" _ASM_SP ", (%%" _ASM_SI ") \n\t" - "jmp 1f \n\t" - "2: \n\t" - __ex("vmwrite %%" _ASM_SP ", %%" _ASM_DX) "\n\t" - "1: \n\t" - "add $%c[wordsize], %%" _ASM_SP "\n\t" /* un-adjust RSP */ - - /* Reload cr2 if changed */ - "mov %c[cr2](%%" _ASM_CX "), %%" _ASM_AX " \n\t" - "mov %%cr2, %%" _ASM_DX " \n\t" - "cmp %%" _ASM_AX ", %%" _ASM_DX " \n\t" - "je 3f \n\t" - "mov %%" _ASM_AX", %%cr2 \n\t" - "3: \n\t" - /* Check if vmlaunch or vmresume is needed */ - "cmpl $0, %c[launched](%%" _ASM_CX ") \n\t" - /* Load guest registers. Don't clobber flags. */ - "mov %c[rax](%%" _ASM_CX "), %%" _ASM_AX " \n\t" - "mov %c[rbx](%%" _ASM_CX "), %%" _ASM_BX " \n\t" - "mov %c[rdx](%%" _ASM_CX "), %%" _ASM_DX " \n\t" - "mov %c[rsi](%%" _ASM_CX "), %%" _ASM_SI " \n\t" - "mov %c[rdi](%%" _ASM_CX "), %%" _ASM_DI " \n\t" - "mov %c[rbp](%%" _ASM_CX "), %%" _ASM_BP " \n\t" -#ifdef CONFIG_X86_64 - "mov %c[r8](%%" _ASM_CX "), %%r8 \n\t" - "mov %c[r9](%%" _ASM_CX "), %%r9 \n\t" - "mov %c[r10](%%" _ASM_CX "), %%r10 \n\t" - "mov %c[r11](%%" _ASM_CX "), %%r11 \n\t" - "mov %c[r12](%%" _ASM_CX "), %%r12 \n\t" - "mov %c[r13](%%" _ASM_CX "), %%r13 \n\t" - "mov %c[r14](%%" _ASM_CX "), %%r14 \n\t" - "mov %c[r15](%%" _ASM_CX "), %%r15 \n\t" -#endif - /* Load guest RCX. This kills the vmx_vcpu pointer! */ - "mov %c[rcx](%%" _ASM_CX "), %%" _ASM_CX " \n\t" - - /* Enter guest mode */ - "call vmx_vmenter\n\t" - - /* Save guest's RCX to the stack placeholder (see above) */ - "mov %%" _ASM_CX ", %c[wordsize](%%" _ASM_SP ") \n\t" - - /* Load host's RCX, i.e. the vmx_vcpu pointer */ - "pop %%" _ASM_CX " \n\t" - - /* Set vmx->fail based on EFLAGS.{CF,ZF} */ - "setbe %c[fail](%%" _ASM_CX ")\n\t" - - /* Save all guest registers, including RCX from the stack */ - "mov %%" _ASM_AX ", %c[rax](%%" _ASM_CX ") \n\t" - "mov %%" _ASM_BX ", %c[rbx](%%" _ASM_CX ") \n\t" - __ASM_SIZE(pop) " %c[rcx](%%" _ASM_CX ") \n\t" - "mov %%" _ASM_DX ", %c[rdx](%%" _ASM_CX ") \n\t" - "mov %%" _ASM_SI ", %c[rsi](%%" _ASM_CX ") \n\t" - "mov %%" _ASM_DI ", %c[rdi](%%" _ASM_CX ") \n\t" - "mov %%" _ASM_BP ", %c[rbp](%%" _ASM_CX ") \n\t" -#ifdef CONFIG_X86_64 - "mov %%r8, %c[r8](%%" _ASM_CX ") \n\t" - "mov %%r9, %c[r9](%%" _ASM_CX ") \n\t" - "mov %%r10, %c[r10](%%" _ASM_CX ") \n\t" - "mov %%r11, %c[r11](%%" _ASM_CX ") \n\t" - "mov %%r12, %c[r12](%%" _ASM_CX ") \n\t" - "mov %%r13, %c[r13](%%" _ASM_CX ") \n\t" - "mov %%r14, %c[r14](%%" _ASM_CX ") \n\t" - "mov %%r15, %c[r15](%%" _ASM_CX ") \n\t" - /* - * Clear host registers marked as clobbered to prevent - * speculative use. - */ - "xor %%r8d, %%r8d \n\t" - "xor %%r9d, %%r9d \n\t" - "xor %%r10d, %%r10d \n\t" - "xor %%r11d, %%r11d \n\t" - "xor %%r12d, %%r12d \n\t" - "xor %%r13d, %%r13d \n\t" - "xor %%r14d, %%r14d \n\t" - "xor %%r15d, %%r15d \n\t" -#endif - "mov %%cr2, %%" _ASM_AX " \n\t" - "mov %%" _ASM_AX ", %c[cr2](%%" _ASM_CX ") \n\t" - - "xor %%eax, %%eax \n\t" - "xor %%ebx, %%ebx \n\t" - "xor %%esi, %%esi \n\t" - "xor %%edi, %%edi \n\t" - "pop %%" _ASM_BP "; pop %%" _ASM_DX " \n\t" - : ASM_CALL_CONSTRAINT - : "c"(vmx), "d"((unsigned long)HOST_RSP), "S"(evmcs_rsp), - [launched]"i"(offsetof(struct vcpu_vmx, __launched)), - [fail]"i"(offsetof(struct vcpu_vmx, fail)), - [host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp)), - [rax]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RAX])), - [rbx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBX])), - [rcx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RCX])), - [rdx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDX])), - [rsi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RSI])), - [rdi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDI])), - [rbp]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBP])), -#ifdef CONFIG_X86_64 - [r8]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R8])), - [r9]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R9])), - [r10]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R10])), - [r11]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R11])), - [r12]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R12])), - [r13]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R13])), - [r14]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R14])), - [r15]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R15])), -#endif - [cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)), - [wordsize]"i"(sizeof(ulong)) - : "cc", "memory" -#ifdef CONFIG_X86_64 - , "rax", "rbx", "rdi" - , "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15" -#else - , "eax", "ebx", "edi" -#endif - ); + if (unlikely(host_rsp != vmx->loaded_vmcs->host_state.rsp)) { + vmx->loaded_vmcs->host_state.rsp = host_rsp; + vmcs_writel(HOST_RSP, host_rsp); + } } -STACK_FRAME_NON_STANDARD(__vmx_vcpu_run); + +bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched); static void vmx_vcpu_run(struct kvm_vcpu *vcpu) { @@ -6572,7 +6442,16 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) */ x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0); - __vmx_vcpu_run(vcpu, vmx); + if (static_branch_unlikely(&vmx_l1d_should_flush)) + vmx_l1d_flush(vcpu); + + if (vcpu->arch.cr2 != read_cr2()) + write_cr2(vcpu->arch.cr2); + + vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, + vmx->loaded_vmcs->launched); + + vcpu->arch.cr2 = read_cr2(); /* * We do not use IBRS in the kernel. If this vCPU has used the @@ -6657,7 +6536,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) static struct kvm *vmx_vm_alloc(void) { - struct kvm_vmx *kvm_vmx = vzalloc(sizeof(struct kvm_vmx)); + struct kvm_vmx *kvm_vmx = __vmalloc(sizeof(struct kvm_vmx), + GFP_KERNEL_ACCOUNT | __GFP_ZERO, + PAGE_KERNEL); return &kvm_vmx->kvm; } @@ -6673,7 +6554,6 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) if (enable_pml) vmx_destroy_pml_buffer(vmx); free_vpid(vmx->vpid); - leave_guest_mode(vcpu); nested_vmx_free_vcpu(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); kfree(vmx->guest_msrs); @@ -6685,14 +6565,16 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) { int err; - struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + struct vcpu_vmx *vmx; unsigned long *msr_bitmap; int cpu; + vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); if (!vmx) return ERR_PTR(-ENOMEM); - vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL); + vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); if (!vmx->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; @@ -6714,12 +6596,12 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) * for the guest, etc. */ if (enable_pml) { - vmx->pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO); + vmx->pml_pg = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!vmx->pml_pg) goto uninit_vcpu; } - vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); + vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT); BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0]) > PAGE_SIZE); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h @@ -175,7 +175,6 @@ struct nested_vmx { struct vcpu_vmx { struct kvm_vcpu vcpu; - unsigned long host_rsp; u8 fail; u8 msr_bitmap_mode; u32 exit_intr_info; @@ -209,7 +208,7 @@ struct vcpu_vmx { struct loaded_vmcs vmcs01; struct loaded_vmcs *loaded_vmcs; struct loaded_vmcs *loaded_cpu_state; - bool __launched; /* temporary, used in vmx_vcpu_run */ + struct msr_autoload { struct vmx_msrs guest; struct vmx_msrs host; @@ -339,8 +338,8 @@ static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) static inline void pi_set_sn(struct pi_desc *pi_desc) { - return set_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); + set_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); } static inline void pi_set_on(struct pi_desc *pi_desc) @@ -445,7 +444,8 @@ static inline u32 vmx_vmentry_ctrl(void) { u32 vmentry_ctrl = vmcs_config.vmentry_ctrl; if (pt_mode == PT_MODE_SYSTEM) - vmentry_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | VM_EXIT_CLEAR_IA32_RTIT_CTL); + vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | + VM_ENTRY_LOAD_IA32_RTIT_CTL); /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ return vmentry_ctrl & ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER); @@ -455,9 +455,10 @@ static inline u32 vmx_vmexit_ctrl(void) { u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; if (pt_mode == PT_MODE_SYSTEM) - vmexit_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | VM_ENTRY_LOAD_IA32_RTIT_CTL); + vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | + VM_EXIT_CLEAR_IA32_RTIT_CTL); /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ - return vmcs_config.vmexit_ctrl & + return vmexit_ctrl & ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER); } @@ -478,7 +479,7 @@ static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) return &(to_vmx(vcpu)->pi_desc); } -struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu); +struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags); void free_vmcs(struct vmcs *vmcs); int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs); void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs); @@ -487,7 +488,8 @@ void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs); static inline struct vmcs *alloc_vmcs(bool shadow) { - return alloc_vmcs_cpu(shadow, raw_smp_processor_id()); + return alloc_vmcs_cpu(shadow, raw_smp_processor_id(), + GFP_KERNEL_ACCOUNT); } u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c @@ -3879,7 +3879,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; if (!lapic_in_kernel(vcpu)) goto out; - u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); + u.lapic = kzalloc(sizeof(struct kvm_lapic_state), + GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!u.lapic) @@ -4066,7 +4067,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_GET_XSAVE: { - u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL); + u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!u.xsave) break; @@ -4090,7 +4091,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_GET_XCRS: { - u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL); + u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!u.xcrs) break; @@ -7055,6 +7056,13 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu) { + if (!lapic_in_kernel(vcpu)) { + WARN_ON_ONCE(vcpu->arch.apicv_active); + return; + } + if (!vcpu->arch.apicv_active) + return; + vcpu->arch.apicv_active = false; kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu); } @@ -9005,7 +9013,6 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) struct page *page; int r; - vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu); vcpu->arch.emulate_ctxt.ops = &emulate_ops; if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -9026,6 +9033,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_free_pio_data; if (irqchip_in_kernel(vcpu->kvm)) { + vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu); r = kvm_create_lapic(vcpu); if (r < 0) goto fail_mmu_destroy; @@ -9033,14 +9041,15 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) static_key_slow_inc(&kvm_no_apic_vcpu); vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4, - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!vcpu->arch.mce_banks) { r = -ENOMEM; goto fail_free_lapic; } vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; - if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL)) { + if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, + GFP_KERNEL_ACCOUNT)) { r = -ENOMEM; goto fail_free_mce_banks; } @@ -9104,7 +9113,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); - INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -9299,13 +9307,13 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, slot->arch.rmap[i] = kvcalloc(lpages, sizeof(*slot->arch.rmap[i]), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!slot->arch.rmap[i]) goto out_free; if (i == 0) continue; - linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL); + linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT); if (!linfo) goto out_free; @@ -9348,13 +9356,13 @@ out_free: return -ENOMEM; } -void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) +void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { /* * memslots->generation has been incremented. * mmio generation may have reached its maximum value. */ - kvm_mmu_invalidate_mmio_sptes(kvm, slots); + kvm_mmu_invalidate_mmio_sptes(kvm, gen); } int kvm_arch_prepare_memory_region(struct kvm *kvm, @@ -9462,7 +9470,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, void kvm_arch_flush_shadow_all(struct kvm *kvm) { - kvm_mmu_invalidate_zap_all_pages(kvm); + kvm_mmu_zap_all(kvm); } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h @@ -181,6 +181,11 @@ static inline bool emul_is_noncanonical_address(u64 la, static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, unsigned access) { + u64 gen = kvm_memslots(vcpu->kvm)->generation; + + if (unlikely(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS)) + return; + /* * If this is a shadow nested page table, the "GVA" is * actually a nGPA. @@ -188,7 +193,7 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, vcpu->arch.mmio_gva = mmu_is_nested(vcpu) ? 0 : gva & PAGE_MASK; vcpu->arch.access = access; vcpu->arch.mmio_gfn = gfn; - vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation; + vcpu->arch.mmio_gen = gen; } static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu) diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c @@ -1261,6 +1261,13 @@ static enum arch_timer_ppi_nr __init arch_timer_select_ppi(void) return ARCH_TIMER_PHYS_SECURE_PPI; } +static void __init arch_timer_populate_kvm_info(void) +{ + arch_timer_kvm_info.virtual_irq = arch_timer_ppi[ARCH_TIMER_VIRT_PPI]; + if (is_kernel_in_hyp_mode()) + arch_timer_kvm_info.physical_irq = arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]; +} + static int __init arch_timer_of_init(struct device_node *np) { int i, ret; @@ -1275,7 +1282,7 @@ static int __init arch_timer_of_init(struct device_node *np) for (i = ARCH_TIMER_PHYS_SECURE_PPI; i < ARCH_TIMER_MAX_TIMER_PPI; i++) arch_timer_ppi[i] = irq_of_parse_and_map(np, i); - arch_timer_kvm_info.virtual_irq = arch_timer_ppi[ARCH_TIMER_VIRT_PPI]; + arch_timer_populate_kvm_info(); rate = arch_timer_get_cntfrq(); arch_timer_of_configure_rate(rate, np); @@ -1605,7 +1612,7 @@ static int __init arch_timer_acpi_init(struct acpi_table_header *table) arch_timer_ppi[ARCH_TIMER_HYP_PPI] = acpi_gtdt_map_ppi(ARCH_TIMER_HYP_PPI); - arch_timer_kvm_info.virtual_irq = arch_timer_ppi[ARCH_TIMER_VIRT_PPI]; + arch_timer_populate_kvm_info(); /* * When probing via ACPI, we have no mechanism to override the sysreg diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c @@ -1382,3 +1382,40 @@ int chsc_pnso_brinfo(struct subchannel_id schid, return chsc_error_from_response(brinfo_area->response.code); } EXPORT_SYMBOL_GPL(chsc_pnso_brinfo); + +int chsc_sgib(u32 origin) +{ + struct { + struct chsc_header request; + u16 op; + u8 reserved01[2]; + u8 reserved02:4; + u8 fmt:4; + u8 reserved03[7]; + /* operation data area begin */ + u8 reserved04[4]; + u32 gib_origin; + u8 reserved05[10]; + u8 aix; + u8 reserved06[4029]; + struct chsc_header response; + u8 reserved07[4]; + } *sgib_area; + int ret; + + spin_lock_irq(&chsc_page_lock); + memset(chsc_page, 0, PAGE_SIZE); + sgib_area = chsc_page; + sgib_area->request.length = 0x0fe0; + sgib_area->request.code = 0x0021; + sgib_area->op = 0x1; + sgib_area->gib_origin = origin; + + ret = chsc(sgib_area); + if (ret == 0) + ret = chsc_error_from_response(sgib_area->response.code); + spin_unlock_irq(&chsc_page_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(chsc_sgib); diff --git a/drivers/s390/cio/chsc.h b/drivers/s390/cio/chsc.h @@ -164,6 +164,7 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp); int chsc_ssqd(struct subchannel_id schid, struct chsc_ssqd_area *ssqd); int chsc_sadc(struct subchannel_id schid, struct chsc_scssc_area *scssc, u64 summary_indicator_addr, u64 subchannel_indicator_addr); +int chsc_sgib(u32 origin); int chsc_error_from_response(int response); int chsc_siosl(struct subchannel_id schid); diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h @@ -74,6 +74,7 @@ enum arch_timer_spi_nr { struct arch_timer_kvm_info { struct timecounter timecounter; int virtual_irq; + int physical_irq; }; struct arch_timer_mem_frame { diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h @@ -22,7 +22,22 @@ #include <linux/clocksource.h> #include <linux/hrtimer.h> +enum kvm_arch_timers { + TIMER_PTIMER, + TIMER_VTIMER, + NR_KVM_TIMERS +}; + +enum kvm_arch_timer_regs { + TIMER_REG_CNT, + TIMER_REG_CVAL, + TIMER_REG_TVAL, + TIMER_REG_CTL, +}; + struct arch_timer_context { + struct kvm_vcpu *vcpu; + /* Registers: control register, timer value */ u32 cnt_ctl; u64 cnt_cval; @@ -30,30 +45,36 @@ struct arch_timer_context { /* Timer IRQ */ struct kvm_irq_level irq; + /* Virtual offset */ + u64 cntvoff; + + /* Emulated Timer (may be unused) */ + struct hrtimer hrtimer; + /* - * We have multiple paths which can save/restore the timer state - * onto the hardware, so we need some way of keeping track of - * where the latest state is. - * - * loaded == true: State is loaded on the hardware registers. - * loaded == false: State is stored in memory. + * We have multiple paths which can save/restore the timer state onto + * the hardware, so we need some way of keeping track of where the + * latest state is. */ - bool loaded; + bool loaded; - /* Virtual offset */ - u64 cntvoff; + /* Duplicated state from arch_timer.c for convenience */ + u32 host_timer_irq; + u32 host_timer_irq_flags; +}; + +struct timer_map { + struct arch_timer_context *direct_vtimer; + struct arch_timer_context *direct_ptimer; + struct arch_timer_context *emul_ptimer; }; struct arch_timer_cpu { - struct arch_timer_context vtimer; - struct arch_timer_context ptimer; + struct arch_timer_context timers[NR_KVM_TIMERS]; /* Background timer used when the guest is not running */ struct hrtimer bg_timer; - /* Physical timer emulation */ - struct hrtimer phys_timer; - /* Is the timer enabled */ bool enabled; }; @@ -76,9 +97,6 @@ int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); bool kvm_timer_is_pending(struct kvm_vcpu *vcpu); -void kvm_timer_schedule(struct kvm_vcpu *vcpu); -void kvm_timer_unschedule(struct kvm_vcpu *vcpu); - u64 kvm_phys_timer_read(void); void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu); @@ -88,7 +106,19 @@ void kvm_timer_init_vhe(void); bool kvm_arch_timer_get_input_level(int vintid); -#define vcpu_vtimer(v) (&(v)->arch.timer_cpu.vtimer) -#define vcpu_ptimer(v) (&(v)->arch.timer_cpu.ptimer) +#define vcpu_timer(v) (&(v)->arch.timer_cpu) +#define vcpu_get_timer(v,t) (&vcpu_timer(v)->timers[(t)]) +#define vcpu_vtimer(v) (&(v)->arch.timer_cpu.timers[TIMER_VTIMER]) +#define vcpu_ptimer(v) (&(v)->arch.timer_cpu.timers[TIMER_PTIMER]) + +#define arch_timer_ctx_index(ctx) ((ctx) - vcpu_timer((ctx)->vcpu)->timers) + +u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, + enum kvm_arch_timers tmr, + enum kvm_arch_timer_regs treg); +void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, + enum kvm_arch_timers tmr, + enum kvm_arch_timer_regs treg, + u64 val); #endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h @@ -48,6 +48,27 @@ */ #define KVM_MEMSLOT_INVALID (1UL << 16) +/* + * Bit 63 of the memslot generation number is an "update in-progress flag", + * e.g. is temporarily set for the duration of install_new_memslots(). + * This flag effectively creates a unique generation number that is used to + * mark cached memslot data, e.g. MMIO accesses, as potentially being stale, + * i.e. may (or may not) have come from the previous memslots generation. + * + * This is necessary because the actual memslots update is not atomic with + * respect to the generation number update. Updating the generation number + * first would allow a vCPU to cache a spte from the old memslots using the + * new generation number, and updating the generation number after switching + * to the new memslots would allow cache hits using the old generation number + * to reference the defunct memslots. + * + * This mechanism is used to prevent getting hits in KVM's caches while a + * memslot update is in-progress, and to prevent cache hits *after* updating + * the actual generation number against accesses that were inserted into the + * cache *before* the memslots were updated. + */ +#define KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS BIT_ULL(63) + /* Two fragments for cross MMIO pages. */ #define KVM_MAX_MMIO_FRAGMENTS 2 @@ -634,7 +655,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont); int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned long npages); -void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots); +void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, const struct kvm_userspace_memory_region *mem, @@ -1182,6 +1203,7 @@ extern bool kvm_rebooting; extern unsigned int halt_poll_ns; extern unsigned int halt_poll_ns_grow; +extern unsigned int halt_poll_ns_grow_start; extern unsigned int halt_poll_ns_shrink; struct kvm_device { diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore @@ -3,6 +3,7 @@ /x86_64/platform_info_test /x86_64/set_sregs_test /x86_64/sync_regs_test +/x86_64/vmx_close_while_nested_test /x86_64/vmx_tsc_adjust_test /x86_64/state_test /dirty_log_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile @@ -16,6 +16,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid +TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += clear_dirty_log_test diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c @@ -0,0 +1,95 @@ +/* + * vmx_close_while_nested + * + * Copyright (C) 2019, Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Verify that nothing bad happens if a KVM user exits with open + * file descriptors while executing a nested guest. + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "vmx.h" + +#include <string.h> +#include <sys/ioctl.h> + +#include "kselftest.h" + +#define VCPU_ID 5 + +enum { + PORT_L0_EXIT = 0x2000, +}; + +/* The virtual machine object. */ +static struct kvm_vm *vm; + +static void l2_guest_code(void) +{ + /* Exit to L0 */ + asm volatile("inb %%dx, %%al" + : : [port] "d" (PORT_L0_EXIT) : "rax"); +} + +static void l1_guest_code(struct vmx_pages *vmx_pages) +{ +#define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + uint32_t control; + uintptr_t save_cr3; + + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + GUEST_ASSERT(load_vmcs(vmx_pages)); + + /* Prepare the VMCS for L2 execution. */ + prepare_vmcs(vmx_pages, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + GUEST_ASSERT(!vmlaunch()); + GUEST_ASSERT(0); +} + +int main(int argc, char *argv[]) +{ + struct vmx_pages *vmx_pages; + vm_vaddr_t vmx_pages_gva; + struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); + + if (!(entry->ecx & CPUID_VMX)) { + fprintf(stderr, "nested VMX not enabled, skipping test\n"); + exit(KSFT_SKIP); + } + + vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + /* Allocate VMX pages and shared descriptors (vmx_pages). */ + vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + + for (;;) { + volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + if (run->io.port == PORT_L0_EXIT) + break; + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_ASSERT(false, "%s", (const char *)uc.args[0]); + /* NOT REACHED */ + default: + TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); + } + } +} diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c @@ -25,6 +25,7 @@ #include <clocksource/arm_arch_timer.h> #include <asm/arch_timer.h> +#include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <kvm/arm_vgic.h> @@ -34,7 +35,9 @@ static struct timecounter *timecounter; static unsigned int host_vtimer_irq; +static unsigned int host_ptimer_irq; static u32 host_vtimer_irq_flags; +static u32 host_ptimer_irq_flags; static DEFINE_STATIC_KEY_FALSE(has_gic_active_state); @@ -52,12 +55,34 @@ static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx); static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, struct arch_timer_context *timer_ctx); static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx); +static void kvm_arm_timer_write(struct kvm_vcpu *vcpu, + struct arch_timer_context *timer, + enum kvm_arch_timer_regs treg, + u64 val); +static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, + struct arch_timer_context *timer, + enum kvm_arch_timer_regs treg); u64 kvm_phys_timer_read(void) { return timecounter->cc->read(timecounter->cc); } +static void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map) +{ + if (has_vhe()) { + map->direct_vtimer = vcpu_vtimer(vcpu); + map->direct_ptimer = vcpu_ptimer(vcpu); + map->emul_ptimer = NULL; + } else { + map->direct_vtimer = vcpu_vtimer(vcpu); + map->direct_ptimer = NULL; + map->emul_ptimer = vcpu_ptimer(vcpu); + } + + trace_kvm_get_timer_map(vcpu->vcpu_id, map); +} + static inline bool userspace_irqchip(struct kvm *kvm) { return static_branch_unlikely(&userspace_irqchip_in_use) && @@ -78,20 +103,27 @@ static void soft_timer_cancel(struct hrtimer *hrt) static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) { struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id; - struct arch_timer_context *vtimer; + struct arch_timer_context *ctx; + struct timer_map map; /* * We may see a timer interrupt after vcpu_put() has been called which * sets the CPU's vcpu pointer to NULL, because even though the timer - * has been disabled in vtimer_save_state(), the hardware interrupt + * has been disabled in timer_save_state(), the hardware interrupt * signal may not have been retired from the interrupt controller yet. */ if (!vcpu) return IRQ_HANDLED; - vtimer = vcpu_vtimer(vcpu); - if (kvm_timer_should_fire(vtimer)) - kvm_timer_update_irq(vcpu, true, vtimer); + get_timer_map(vcpu, &map); + + if (irq == host_vtimer_irq) + ctx = map.direct_vtimer; + else + ctx = map.direct_ptimer; + + if (kvm_timer_should_fire(ctx)) + kvm_timer_update_irq(vcpu, true, ctx); if (userspace_irqchip(vcpu->kvm) && !static_branch_unlikely(&has_gic_active_state)) @@ -122,7 +154,9 @@ static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx) static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx) { - return !(timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_IT_MASK) && + WARN_ON(timer_ctx && timer_ctx->loaded); + return timer_ctx && + !(timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_IT_MASK) && (timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_ENABLE); } @@ -132,21 +166,22 @@ static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx) */ static u64 kvm_timer_earliest_exp(struct kvm_vcpu *vcpu) { - u64 min_virt = ULLONG_MAX, min_phys = ULLONG_MAX; - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + u64 min_delta = ULLONG_MAX; + int i; - if (kvm_timer_irq_can_fire(vtimer)) - min_virt = kvm_timer_compute_delta(vtimer); + for (i = 0; i < NR_KVM_TIMERS; i++) { + struct arch_timer_context *ctx = &vcpu->arch.timer_cpu.timers[i]; - if (kvm_timer_irq_can_fire(ptimer)) - min_phys = kvm_timer_compute_delta(ptimer); + WARN(ctx->loaded, "timer %d loaded\n", i); + if (kvm_timer_irq_can_fire(ctx)) + min_delta = min(min_delta, kvm_timer_compute_delta(ctx)); + } /* If none of timers can fire, then return 0 */ - if ((min_virt == ULLONG_MAX) && (min_phys == ULLONG_MAX)) + if (min_delta == ULLONG_MAX) return 0; - return min(min_virt, min_phys); + return min_delta; } static enum hrtimer_restart kvm_bg_timer_expire(struct hrtimer *hrt) @@ -173,41 +208,58 @@ static enum hrtimer_restart kvm_bg_timer_expire(struct hrtimer *hrt) return HRTIMER_NORESTART; } -static enum hrtimer_restart kvm_phys_timer_expire(struct hrtimer *hrt) +static enum hrtimer_restart kvm_hrtimer_expire(struct hrtimer *hrt) { - struct arch_timer_context *ptimer; - struct arch_timer_cpu *timer; + struct arch_timer_context *ctx; struct kvm_vcpu *vcpu; u64 ns; - timer = container_of(hrt, struct arch_timer_cpu, phys_timer); - vcpu = container_of(timer, struct kvm_vcpu, arch.timer_cpu); - ptimer = vcpu_ptimer(vcpu); + ctx = container_of(hrt, struct arch_timer_context, hrtimer); + vcpu = ctx->vcpu; + + trace_kvm_timer_hrtimer_expire(ctx); /* * Check that the timer has really expired from the guest's * PoV (NTP on the host may have forced it to expire * early). If not ready, schedule for a later time. */ - ns = kvm_timer_compute_delta(ptimer); + ns = kvm_timer_compute_delta(ctx); if (unlikely(ns)) { hrtimer_forward_now(hrt, ns_to_ktime(ns)); return HRTIMER_RESTART; } - kvm_timer_update_irq(vcpu, true, ptimer); + kvm_timer_update_irq(vcpu, true, ctx); return HRTIMER_NORESTART; } static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx) { + enum kvm_arch_timers index; u64 cval, now; + if (!timer_ctx) + return false; + + index = arch_timer_ctx_index(timer_ctx); + if (timer_ctx->loaded) { - u32 cnt_ctl; + u32 cnt_ctl = 0; + + switch (index) { + case TIMER_VTIMER: + cnt_ctl = read_sysreg_el0(cntv_ctl); + break; + case TIMER_PTIMER: + cnt_ctl = read_sysreg_el0(cntp_ctl); + break; + case NR_KVM_TIMERS: + /* GCC is braindead */ + cnt_ctl = 0; + break; + } - /* Only the virtual timer can be loaded so far */ - cnt_ctl = read_sysreg_el0(cntv_ctl); return (cnt_ctl & ARCH_TIMER_CTRL_ENABLE) && (cnt_ctl & ARCH_TIMER_CTRL_IT_STAT) && !(cnt_ctl & ARCH_TIMER_CTRL_IT_MASK); @@ -224,13 +276,13 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx) bool kvm_timer_is_pending(struct kvm_vcpu *vcpu) { - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + struct timer_map map; - if (kvm_timer_should_fire(vtimer)) - return true; + get_timer_map(vcpu, &map); - return kvm_timer_should_fire(ptimer); + return kvm_timer_should_fire(map.direct_vtimer) || + kvm_timer_should_fire(map.direct_ptimer) || + kvm_timer_should_fire(map.emul_ptimer); } /* @@ -269,77 +321,70 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, } } -/* Schedule the background timer for the emulated timer. */ -static void phys_timer_emulate(struct kvm_vcpu *vcpu) +static void timer_emulate(struct arch_timer_context *ctx) { - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + bool should_fire = kvm_timer_should_fire(ctx); + + trace_kvm_timer_emulate(ctx, should_fire); + + if (should_fire) { + kvm_timer_update_irq(ctx->vcpu, true, ctx); + return; + } /* * If the timer can fire now, we don't need to have a soft timer * scheduled for the future. If the timer cannot fire at all, * then we also don't need a soft timer. */ - if (kvm_timer_should_fire(ptimer) || !kvm_timer_irq_can_fire(ptimer)) { - soft_timer_cancel(&timer->phys_timer); + if (!kvm_timer_irq_can_fire(ctx)) { + soft_timer_cancel(&ctx->hrtimer); return; } - soft_timer_start(&timer->phys_timer, kvm_timer_compute_delta(ptimer)); + soft_timer_start(&ctx->hrtimer, kvm_timer_compute_delta(ctx)); } -/* - * Check if there was a change in the timer state, so that we should either - * raise or lower the line level to the GIC or schedule a background timer to - * emulate the physical timer. - */ -static void kvm_timer_update_state(struct kvm_vcpu *vcpu) +static void timer_save_state(struct arch_timer_context *ctx) { - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); - bool level; + struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu); + enum kvm_arch_timers index = arch_timer_ctx_index(ctx); + unsigned long flags; - if (unlikely(!timer->enabled)) + if (!timer->enabled) return; - /* - * The vtimer virtual interrupt is a 'mapped' interrupt, meaning part - * of its lifecycle is offloaded to the hardware, and we therefore may - * not have lowered the irq.level value before having to signal a new - * interrupt, but have to signal an interrupt every time the level is - * asserted. - */ - level = kvm_timer_should_fire(vtimer); - kvm_timer_update_irq(vcpu, level, vtimer); + local_irq_save(flags); - phys_timer_emulate(vcpu); + if (!ctx->loaded) + goto out; - if (kvm_timer_should_fire(ptimer) != ptimer->irq.level) - kvm_timer_update_irq(vcpu, !ptimer->irq.level, ptimer); -} + switch (index) { + case TIMER_VTIMER: + ctx->cnt_ctl = read_sysreg_el0(cntv_ctl); + ctx->cnt_cval = read_sysreg_el0(cntv_cval); -static void vtimer_save_state(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - unsigned long flags; + /* Disable the timer */ + write_sysreg_el0(0, cntv_ctl); + isb(); - local_irq_save(flags); + break; + case TIMER_PTIMER: + ctx->cnt_ctl = read_sysreg_el0(cntp_ctl); + ctx->cnt_cval = read_sysreg_el0(cntp_cval); - if (!vtimer->loaded) - goto out; + /* Disable the timer */ + write_sysreg_el0(0, cntp_ctl); + isb(); - if (timer->enabled) { - vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl); - vtimer->cnt_cval = read_sysreg_el0(cntv_cval); + break; + case NR_KVM_TIMERS: + BUG(); } - /* Disable the virtual timer */ - write_sysreg_el0(0, cntv_ctl); - isb(); + trace_kvm_timer_save_state(ctx); - vtimer->loaded = false; + ctx->loaded = false; out: local_irq_restore(flags); } @@ -349,67 +394,72 @@ out: * thread is removed from its waitqueue and made runnable when there's a timer * interrupt to handle. */ -void kvm_timer_schedule(struct kvm_vcpu *vcpu) +static void kvm_timer_blocking(struct kvm_vcpu *vcpu) { - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); - - vtimer_save_state(vcpu); + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + struct timer_map map; - /* - * No need to schedule a background timer if any guest timer has - * already expired, because kvm_vcpu_block will return before putting - * the thread to sleep. - */ - if (kvm_timer_should_fire(vtimer) || kvm_timer_should_fire(ptimer)) - return; + get_timer_map(vcpu, &map); /* - * If both timers are not capable of raising interrupts (disabled or + * If no timers are capable of raising interrupts (disabled or * masked), then there's no more work for us to do. */ - if (!kvm_timer_irq_can_fire(vtimer) && !kvm_timer_irq_can_fire(ptimer)) + if (!kvm_timer_irq_can_fire(map.direct_vtimer) && + !kvm_timer_irq_can_fire(map.direct_ptimer) && + !kvm_timer_irq_can_fire(map.emul_ptimer)) return; /* - * The guest timers have not yet expired, schedule a background timer. + * At least one guest time will expire. Schedule a background timer. * Set the earliest expiration time among the guest timers. */ soft_timer_start(&timer->bg_timer, kvm_timer_earliest_exp(vcpu)); } -static void vtimer_restore_state(struct kvm_vcpu *vcpu) +static void kvm_timer_unblocking(struct kvm_vcpu *vcpu) { - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + + soft_timer_cancel(&timer->bg_timer); +} + +static void timer_restore_state(struct arch_timer_context *ctx) +{ + struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu); + enum kvm_arch_timers index = arch_timer_ctx_index(ctx); unsigned long flags; + if (!timer->enabled) + return; + local_irq_save(flags); - if (vtimer->loaded) + if (ctx->loaded) goto out; - if (timer->enabled) { - write_sysreg_el0(vtimer->cnt_cval, cntv_cval); + switch (index) { + case TIMER_VTIMER: + write_sysreg_el0(ctx->cnt_cval, cntv_cval); isb(); - write_sysreg_el0(vtimer->cnt_ctl, cntv_ctl); + write_sysreg_el0(ctx->cnt_ctl, cntv_ctl); + break; + case TIMER_PTIMER: + write_sysreg_el0(ctx->cnt_cval, cntp_cval); + isb(); + write_sysreg_el0(ctx->cnt_ctl, cntp_ctl); + break; + case NR_KVM_TIMERS: + BUG(); } - vtimer->loaded = true; + trace_kvm_timer_restore_state(ctx); + + ctx->loaded = true; out: local_irq_restore(flags); } -void kvm_timer_unschedule(struct kvm_vcpu *vcpu) -{ - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - - vtimer_restore_state(vcpu); - - soft_timer_cancel(&timer->bg_timer); -} - static void set_cntvoff(u64 cntvoff) { u32 low = lower_32_bits(cntvoff); @@ -425,23 +475,32 @@ static void set_cntvoff(u64 cntvoff) kvm_call_hyp(__kvm_timer_set_cntvoff, low, high); } -static inline void set_vtimer_irq_phys_active(struct kvm_vcpu *vcpu, bool active) +static inline void set_timer_irq_phys_active(struct arch_timer_context *ctx, bool active) { int r; - r = irq_set_irqchip_state(host_vtimer_irq, IRQCHIP_STATE_ACTIVE, active); + r = irq_set_irqchip_state(ctx->host_timer_irq, IRQCHIP_STATE_ACTIVE, active); WARN_ON(r); } -static void kvm_timer_vcpu_load_gic(struct kvm_vcpu *vcpu) +static void kvm_timer_vcpu_load_gic(struct arch_timer_context *ctx) { - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - bool phys_active; + struct kvm_vcpu *vcpu = ctx->vcpu; + bool phys_active = false; + + /* + * Update the timer output so that it is likely to match the + * state we're about to restore. If the timer expires between + * this point and the register restoration, we'll take the + * interrupt anyway. + */ + kvm_timer_update_irq(ctx->vcpu, kvm_timer_should_fire(ctx), ctx); if (irqchip_in_kernel(vcpu->kvm)) - phys_active = kvm_vgic_map_is_active(vcpu, vtimer->irq.irq); - else - phys_active = vtimer->irq.level; - set_vtimer_irq_phys_active(vcpu, phys_active); + phys_active = kvm_vgic_map_is_active(vcpu, ctx->irq.irq); + + phys_active |= ctx->irq.level; + + set_timer_irq_phys_active(ctx, phys_active); } static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu) @@ -466,28 +525,32 @@ static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu) void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) { - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + struct timer_map map; if (unlikely(!timer->enabled)) return; - if (static_branch_likely(&has_gic_active_state)) - kvm_timer_vcpu_load_gic(vcpu); - else + get_timer_map(vcpu, &map); + + if (static_branch_likely(&has_gic_active_state)) { + kvm_timer_vcpu_load_gic(map.direct_vtimer); + if (map.direct_ptimer) + kvm_timer_vcpu_load_gic(map.direct_ptimer); + } else { kvm_timer_vcpu_load_nogic(vcpu); + } - set_cntvoff(vtimer->cntvoff); + set_cntvoff(map.direct_vtimer->cntvoff); - vtimer_restore_state(vcpu); + kvm_timer_unblocking(vcpu); - /* Set the background timer for the physical timer emulation. */ - phys_timer_emulate(vcpu); + timer_restore_state(map.direct_vtimer); + if (map.direct_ptimer) + timer_restore_state(map.direct_ptimer); - /* If the timer fired while we weren't running, inject it now */ - if (kvm_timer_should_fire(ptimer) != ptimer->irq.level) - kvm_timer_update_irq(vcpu, !ptimer->irq.level, ptimer); + if (map.emul_ptimer) + timer_emulate(map.emul_ptimer); } bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu) @@ -509,15 +572,20 @@ bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu) void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) { - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + struct timer_map map; if (unlikely(!timer->enabled)) return; - vtimer_save_state(vcpu); + get_timer_map(vcpu, &map); + + timer_save_state(map.direct_vtimer); + if (map.direct_ptimer) + timer_save_state(map.direct_ptimer); /* - * Cancel the physical timer emulation, because the only case where we + * Cancel soft timer emulation, because the only case where we * need it after a vcpu_put is in the context of a sleeping VCPU, and * in that case we already factor in the deadline for the physical * timer when scheduling the bg_timer. @@ -525,7 +593,11 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) * In any case, we re-schedule the hrtimer for the physical timer when * coming back to the VCPU thread in kvm_timer_vcpu_load(). */ - soft_timer_cancel(&timer->phys_timer); + if (map.emul_ptimer) + soft_timer_cancel(&map.emul_ptimer->hrtimer); + + if (swait_active(kvm_arch_vcpu_wq(vcpu))) + kvm_timer_blocking(vcpu); /* * The kernel may decide to run userspace after calling vcpu_put, so @@ -534,8 +606,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) * counter of non-VHE case. For VHE, the virtual counter uses a fixed * virtual offset of zero, so no need to zero CNTVOFF_EL2 register. */ - if (!has_vhe()) - set_cntvoff(0); + set_cntvoff(0); } /* @@ -550,7 +621,7 @@ static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu) if (!kvm_timer_should_fire(vtimer)) { kvm_timer_update_irq(vcpu, false, vtimer); if (static_branch_likely(&has_gic_active_state)) - set_vtimer_irq_phys_active(vcpu, false); + set_timer_irq_phys_active(vtimer, false); else enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); } @@ -558,7 +629,7 @@ static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu) void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) { - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + struct arch_timer_cpu *timer = vcpu_timer(vcpu); if (unlikely(!timer->enabled)) return; @@ -569,9 +640,10 @@ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) { - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + struct timer_map map; + + get_timer_map(vcpu, &map); /* * The bits in CNTV_CTL are architecturally reset to UNKNOWN for ARMv8 @@ -579,12 +651,22 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) * resets the timer to be disabled and unmasked and is compliant with * the ARMv7 architecture. */ - vtimer->cnt_ctl = 0; - ptimer->cnt_ctl = 0; - kvm_timer_update_state(vcpu); + vcpu_vtimer(vcpu)->cnt_ctl = 0; + vcpu_ptimer(vcpu)->cnt_ctl = 0; - if (timer->enabled && irqchip_in_kernel(vcpu->kvm)) - kvm_vgic_reset_mapped_irq(vcpu, vtimer->irq.irq); + if (timer->enabled) { + kvm_timer_update_irq(vcpu, false, vcpu_vtimer(vcpu)); + kvm_timer_update_irq(vcpu, false, vcpu_ptimer(vcpu)); + + if (irqchip_in_kernel(vcpu->kvm)) { + kvm_vgic_reset_mapped_irq(vcpu, map.direct_vtimer->irq.irq); + if (map.direct_ptimer) + kvm_vgic_reset_mapped_irq(vcpu, map.direct_ptimer->irq.irq); + } + } + + if (map.emul_ptimer) + soft_timer_cancel(&map.emul_ptimer->hrtimer); return 0; } @@ -610,56 +692,76 @@ static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff) void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) { - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + struct arch_timer_cpu *timer = vcpu_timer(vcpu); struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); /* Synchronize cntvoff across all vtimers of a VM. */ update_vtimer_cntvoff(vcpu, kvm_phys_timer_read()); - vcpu_ptimer(vcpu)->cntvoff = 0; + ptimer->cntvoff = 0; hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); timer->bg_timer.function = kvm_bg_timer_expire; - hrtimer_init(&timer->phys_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - timer->phys_timer.function = kvm_phys_timer_expire; + hrtimer_init(&vtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init(&ptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + vtimer->hrtimer.function = kvm_hrtimer_expire; + ptimer->hrtimer.function = kvm_hrtimer_expire; vtimer->irq.irq = default_vtimer_irq.irq; ptimer->irq.irq = default_ptimer_irq.irq; + + vtimer->host_timer_irq = host_vtimer_irq; + ptimer->host_timer_irq = host_ptimer_irq; + + vtimer->host_timer_irq_flags = host_vtimer_irq_flags; + ptimer->host_timer_irq_flags = host_ptimer_irq_flags; + + vtimer->vcpu = vcpu; + ptimer->vcpu = vcpu; } static void kvm_timer_init_interrupt(void *info) { enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); + enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags); } int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) { - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + struct arch_timer_context *timer; + bool level; switch (regid) { case KVM_REG_ARM_TIMER_CTL: - vtimer->cnt_ctl = value & ~ARCH_TIMER_CTRL_IT_STAT; + timer = vcpu_vtimer(vcpu); + kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value); break; case KVM_REG_ARM_TIMER_CNT: + timer = vcpu_vtimer(vcpu); update_vtimer_cntvoff(vcpu, kvm_phys_timer_read() - value); break; case KVM_REG_ARM_TIMER_CVAL: - vtimer->cnt_cval = value; + timer = vcpu_vtimer(vcpu); + kvm_arm_timer_write(vcpu, timer, TIMER_REG_CVAL, value); break; case KVM_REG_ARM_PTIMER_CTL: - ptimer->cnt_ctl = value & ~ARCH_TIMER_CTRL_IT_STAT; + timer = vcpu_ptimer(vcpu); + kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value); break; case KVM_REG_ARM_PTIMER_CVAL: - ptimer->cnt_cval = value; + timer = vcpu_ptimer(vcpu); + kvm_arm_timer_write(vcpu, timer, TIMER_REG_CVAL, value); break; default: return -1; } - kvm_timer_update_state(vcpu); + level = kvm_timer_should_fire(timer); + kvm_timer_update_irq(vcpu, level, timer); + timer_emulate(timer); + return 0; } @@ -679,26 +781,113 @@ static u64 read_timer_ctl(struct arch_timer_context *timer) u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid) { - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - switch (regid) { case KVM_REG_ARM_TIMER_CTL: - return read_timer_ctl(vtimer); + return kvm_arm_timer_read(vcpu, + vcpu_vtimer(vcpu), TIMER_REG_CTL); case KVM_REG_ARM_TIMER_CNT: - return kvm_phys_timer_read() - vtimer->cntvoff; + return kvm_arm_timer_read(vcpu, + vcpu_vtimer(vcpu), TIMER_REG_CNT); case KVM_REG_ARM_TIMER_CVAL: - return vtimer->cnt_cval; + return kvm_arm_timer_read(vcpu, + vcpu_vtimer(vcpu), TIMER_REG_CVAL); case KVM_REG_ARM_PTIMER_CTL: - return read_timer_ctl(ptimer); - case KVM_REG_ARM_PTIMER_CVAL: - return ptimer->cnt_cval; + return kvm_arm_timer_read(vcpu, + vcpu_ptimer(vcpu), TIMER_REG_CTL); case KVM_REG_ARM_PTIMER_CNT: - return kvm_phys_timer_read(); + return kvm_arm_timer_read(vcpu, + vcpu_vtimer(vcpu), TIMER_REG_CNT); + case KVM_REG_ARM_PTIMER_CVAL: + return kvm_arm_timer_read(vcpu, + vcpu_ptimer(vcpu), TIMER_REG_CVAL); } return (u64)-1; } +static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, + struct arch_timer_context *timer, + enum kvm_arch_timer_regs treg) +{ + u64 val; + + switch (treg) { + case TIMER_REG_TVAL: + val = kvm_phys_timer_read() - timer->cntvoff - timer->cnt_cval; + break; + + case TIMER_REG_CTL: + val = read_timer_ctl(timer); + break; + + case TIMER_REG_CVAL: + val = timer->cnt_cval; + break; + + case TIMER_REG_CNT: + val = kvm_phys_timer_read() - timer->cntvoff; + break; + + default: + BUG(); + } + + return val; +} + +u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, + enum kvm_arch_timers tmr, + enum kvm_arch_timer_regs treg) +{ + u64 val; + + preempt_disable(); + kvm_timer_vcpu_put(vcpu); + + val = kvm_arm_timer_read(vcpu, vcpu_get_timer(vcpu, tmr), treg); + + kvm_timer_vcpu_load(vcpu); + preempt_enable(); + + return val; +} + +static void kvm_arm_timer_write(struct kvm_vcpu *vcpu, + struct arch_timer_context *timer, + enum kvm_arch_timer_regs treg, + u64 val) +{ + switch (treg) { + case TIMER_REG_TVAL: + timer->cnt_cval = val - kvm_phys_timer_read() - timer->cntvoff; + break; + + case TIMER_REG_CTL: + timer->cnt_ctl = val & ~ARCH_TIMER_CTRL_IT_STAT; + break; + + case TIMER_REG_CVAL: + timer->cnt_cval = val; + break; + + default: + BUG(); + } +} + +void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, + enum kvm_arch_timers tmr, + enum kvm_arch_timer_regs treg, + u64 val) +{ + preempt_disable(); + kvm_timer_vcpu_put(vcpu); + + kvm_arm_timer_write(vcpu, vcpu_get_timer(vcpu, tmr), treg, val); + + kvm_timer_vcpu_load(vcpu); + preempt_enable(); +} + static int kvm_timer_starting_cpu(unsigned int cpu) { kvm_timer_init_interrupt(NULL); @@ -724,6 +913,8 @@ int kvm_timer_hyp_init(bool has_gic) return -ENODEV; } + /* First, do the virtual EL1 timer irq */ + if (info->virtual_irq <= 0) { kvm_err("kvm_arch_timer: invalid virtual timer IRQ: %d\n", info->virtual_irq); @@ -734,15 +925,15 @@ int kvm_timer_hyp_init(bool has_gic) host_vtimer_irq_flags = irq_get_trigger_type(host_vtimer_irq); if (host_vtimer_irq_flags != IRQF_TRIGGER_HIGH && host_vtimer_irq_flags != IRQF_TRIGGER_LOW) { - kvm_err("Invalid trigger for IRQ%d, assuming level low\n", + kvm_err("Invalid trigger for vtimer IRQ%d, assuming level low\n", host_vtimer_irq); host_vtimer_irq_flags = IRQF_TRIGGER_LOW; } err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler, - "kvm guest timer", kvm_get_running_vcpus()); + "kvm guest vtimer", kvm_get_running_vcpus()); if (err) { - kvm_err("kvm_arch_timer: can't request interrupt %d (%d)\n", + kvm_err("kvm_arch_timer: can't request vtimer interrupt %d (%d)\n", host_vtimer_irq, err); return err; } @@ -760,6 +951,43 @@ int kvm_timer_hyp_init(bool has_gic) kvm_debug("virtual timer IRQ%d\n", host_vtimer_irq); + /* Now let's do the physical EL1 timer irq */ + + if (info->physical_irq > 0) { + host_ptimer_irq = info->physical_irq; + host_ptimer_irq_flags = irq_get_trigger_type(host_ptimer_irq); + if (host_ptimer_irq_flags != IRQF_TRIGGER_HIGH && + host_ptimer_irq_flags != IRQF_TRIGGER_LOW) { + kvm_err("Invalid trigger for ptimer IRQ%d, assuming level low\n", + host_ptimer_irq); + host_ptimer_irq_flags = IRQF_TRIGGER_LOW; + } + + err = request_percpu_irq(host_ptimer_irq, kvm_arch_timer_handler, + "kvm guest ptimer", kvm_get_running_vcpus()); + if (err) { + kvm_err("kvm_arch_timer: can't request ptimer interrupt %d (%d)\n", + host_ptimer_irq, err); + return err; + } + + if (has_gic) { + err = irq_set_vcpu_affinity(host_ptimer_irq, + kvm_get_running_vcpus()); + if (err) { + kvm_err("kvm_arch_timer: error setting vcpu affinity\n"); + goto out_free_irq; + } + } + + kvm_debug("physical timer IRQ%d\n", host_ptimer_irq); + } else if (has_vhe()) { + kvm_err("kvm_arch_timer: invalid physical timer IRQ: %d\n", + info->physical_irq); + err = -ENODEV; + goto out_free_irq; + } + cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING, "kvm/arm/timer:starting", kvm_timer_starting_cpu, kvm_timer_dying_cpu); @@ -771,7 +999,7 @@ out_free_irq: void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) { - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + struct arch_timer_cpu *timer = vcpu_timer(vcpu); soft_timer_cancel(&timer->bg_timer); } @@ -807,16 +1035,18 @@ bool kvm_arch_timer_get_input_level(int vintid) if (vintid == vcpu_vtimer(vcpu)->irq.irq) timer = vcpu_vtimer(vcpu); + else if (vintid == vcpu_ptimer(vcpu)->irq.irq) + timer = vcpu_ptimer(vcpu); else - BUG(); /* We only map the vtimer so far */ + BUG(); return kvm_timer_should_fire(timer); } int kvm_timer_enable(struct kvm_vcpu *vcpu) { - struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + struct timer_map map; int ret; if (timer->enabled) @@ -834,19 +1064,33 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu) return -EINVAL; } - ret = kvm_vgic_map_phys_irq(vcpu, host_vtimer_irq, vtimer->irq.irq, + get_timer_map(vcpu, &map); + + ret = kvm_vgic_map_phys_irq(vcpu, + map.direct_vtimer->host_timer_irq, + map.direct_vtimer->irq.irq, kvm_arch_timer_get_input_level); if (ret) return ret; + if (map.direct_ptimer) { + ret = kvm_vgic_map_phys_irq(vcpu, + map.direct_ptimer->host_timer_irq, + map.direct_ptimer->irq.irq, + kvm_arch_timer_get_input_level); + } + + if (ret) + return ret; + no_vgic: timer->enabled = 1; return 0; } /* - * On VHE system, we only need to configure trap on physical timer and counter - * accesses in EL0 and EL1 once, not for every world switch. + * On VHE system, we only need to configure the EL2 timer trap register once, + * not for every world switch. * The host kernel runs at EL2 with HCR_EL2.TGE == 1, * and this makes those bits have no effect for the host kernel execution. */ @@ -857,11 +1101,11 @@ void kvm_timer_init_vhe(void) u64 val; /* - * Disallow physical timer access for the guest. - * Physical counter access is allowed. + * VHE systems allow the guest direct access to the EL1 physical + * timer/counter. */ val = read_sysreg(cnthctl_el2); - val &= ~(CNTHCTL_EL1PCEN << cnthctl_shift); + val |= (CNTHCTL_EL1PCEN << cnthctl_shift); val |= (CNTHCTL_EL1PCTEN << cnthctl_shift); write_sysreg(val, cnthctl_el2); } diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c @@ -65,7 +65,6 @@ static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu); /* The VMID used in the VTTBR */ static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1); static u32 kvm_next_vmid; -static unsigned int kvm_vmid_bits __read_mostly; static DEFINE_SPINLOCK(kvm_vmid_lock); static bool vgic_present; @@ -142,7 +141,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_vgic_early_init(kvm); /* Mark the initial VMID generation invalid */ - kvm->arch.vmid_gen = 0; + kvm->arch.vmid.vmid_gen = 0; /* The maximum number of VCPUs is limited by the host's GIC model */ kvm->arch.max_vcpus = vgic_present ? @@ -336,13 +335,11 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { - kvm_timer_schedule(vcpu); kvm_vgic_v4_enable_doorbell(vcpu); } void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { - kvm_timer_unschedule(vcpu); kvm_vgic_v4_disable_doorbell(vcpu); } @@ -472,37 +469,31 @@ void force_vm_exit(const cpumask_t *mask) /** * need_new_vmid_gen - check that the VMID is still valid - * @kvm: The VM's VMID to check + * @vmid: The VMID to check * * return true if there is a new generation of VMIDs being used * - * The hardware supports only 256 values with the value zero reserved for the - * host, so we check if an assigned value belongs to a previous generation, - * which which requires us to assign a new value. If we're the first to use a - * VMID for the new generation, we must flush necessary caches and TLBs on all - * CPUs. + * The hardware supports a limited set of values with the value zero reserved + * for the host, so we check if an assigned value belongs to a previous + * generation, which which requires us to assign a new value. If we're the + * first to use a VMID for the new generation, we must flush necessary caches + * and TLBs on all CPUs. */ -static bool need_new_vmid_gen(struct kvm *kvm) +static bool need_new_vmid_gen(struct kvm_vmid *vmid) { u64 current_vmid_gen = atomic64_read(&kvm_vmid_gen); smp_rmb(); /* Orders read of kvm_vmid_gen and kvm->arch.vmid */ - return unlikely(READ_ONCE(kvm->arch.vmid_gen) != current_vmid_gen); + return unlikely(READ_ONCE(vmid->vmid_gen) != current_vmid_gen); } /** - * update_vttbr - Update the VTTBR with a valid VMID before the guest runs - * @kvm The guest that we are about to run - * - * Called from kvm_arch_vcpu_ioctl_run before entering the guest to ensure the - * VM has a valid VMID, otherwise assigns a new one and flushes corresponding - * caches and TLBs. + * update_vmid - Update the vmid with a valid VMID for the current generation + * @kvm: The guest that struct vmid belongs to + * @vmid: The stage-2 VMID information struct */ -static void update_vttbr(struct kvm *kvm) +static void update_vmid(struct kvm_vmid *vmid) { - phys_addr_t pgd_phys; - u64 vmid, cnp = kvm_cpu_has_cnp() ? VTTBR_CNP_BIT : 0; - - if (!need_new_vmid_gen(kvm)) + if (!need_new_vmid_gen(vmid)) return; spin_lock(&kvm_vmid_lock); @@ -512,7 +503,7 @@ static void update_vttbr(struct kvm *kvm) * already allocated a valid vmid for this vm, then this vcpu should * use the same vmid. */ - if (!need_new_vmid_gen(kvm)) { + if (!need_new_vmid_gen(vmid)) { spin_unlock(&kvm_vmid_lock); return; } @@ -536,18 +527,12 @@ static void update_vttbr(struct kvm *kvm) kvm_call_hyp(__kvm_flush_vm_context); } - kvm->arch.vmid = kvm_next_vmid; + vmid->vmid = kvm_next_vmid; kvm_next_vmid++; - kvm_next_vmid &= (1 << kvm_vmid_bits) - 1; - - /* update vttbr to be used with the new vmid */ - pgd_phys = virt_to_phys(kvm->arch.pgd); - BUG_ON(pgd_phys & ~kvm_vttbr_baddr_mask(kvm)); - vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits); - kvm->arch.vttbr = kvm_phys_to_vttbr(pgd_phys) | vmid | cnp; + kvm_next_vmid &= (1 << kvm_get_vmid_bits()) - 1; smp_wmb(); - WRITE_ONCE(kvm->arch.vmid_gen, atomic64_read(&kvm_vmid_gen)); + WRITE_ONCE(vmid->vmid_gen, atomic64_read(&kvm_vmid_gen)); spin_unlock(&kvm_vmid_lock); } @@ -700,7 +685,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) */ cond_resched(); - update_vttbr(vcpu->kvm); + update_vmid(&vcpu->kvm->arch.vmid); check_vcpu_requests(vcpu); @@ -749,7 +734,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) */ smp_store_mb(vcpu->mode, IN_GUEST_MODE); - if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) || + if (ret <= 0 || need_new_vmid_gen(&vcpu->kvm->arch.vmid) || kvm_request_pending(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; isb(); /* Ensure work in x_flush_hwstate is committed */ @@ -775,7 +760,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = kvm_vcpu_run_vhe(vcpu); kvm_arm_vhe_guest_exit(); } else { - ret = kvm_call_hyp(__kvm_vcpu_run_nvhe, vcpu); + ret = kvm_call_hyp_ret(__kvm_vcpu_run_nvhe, vcpu); } vcpu->mode = OUTSIDE_GUEST_MODE; @@ -1427,10 +1412,6 @@ static inline void hyp_cpu_pm_exit(void) static int init_common_resources(void) { - /* set size of VMID supported by CPU */ - kvm_vmid_bits = kvm_get_vmid_bits(); - kvm_info("%d-bit VMID\n", kvm_vmid_bits); - kvm_set_ipa_limit(); return 0; @@ -1571,6 +1552,7 @@ static int init_hyp_mode(void) kvm_cpu_context_t *cpu_ctxt; cpu_ctxt = per_cpu_ptr(&kvm_host_cpu_state, cpu); + kvm_init_host_cpu_context(cpu_ctxt, cpu); err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1, PAGE_HYP); if (err) { @@ -1581,7 +1563,7 @@ static int init_hyp_mode(void) err = hyp_map_aux_data(); if (err) - kvm_err("Cannot map host auxilary data: %d\n", err); + kvm_err("Cannot map host auxiliary data: %d\n", err); return 0; diff --git a/virt/kvm/arm/hyp/vgic-v3-sr.c b/virt/kvm/arm/hyp/vgic-v3-sr.c @@ -226,7 +226,7 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu) int i; u32 elrsr; - elrsr = read_gicreg(ICH_ELSR_EL2); + elrsr = read_gicreg(ICH_ELRSR_EL2); write_gicreg(cpu_if->vgic_hcr & ~ICH_HCR_EN, ICH_HCR_EL2); diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c @@ -908,6 +908,7 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, */ int kvm_alloc_stage2_pgd(struct kvm *kvm) { + phys_addr_t pgd_phys; pgd_t *pgd; if (kvm->arch.pgd != NULL) { @@ -920,7 +921,12 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) if (!pgd) return -ENOMEM; + pgd_phys = virt_to_phys(pgd); + if (WARN_ON(pgd_phys & ~kvm_vttbr_baddr_mask(kvm))) + return -EINVAL; + kvm->arch.pgd = pgd; + kvm->arch.pgd_phys = pgd_phys; return 0; } @@ -1008,6 +1014,7 @@ void kvm_free_stage2_pgd(struct kvm *kvm) unmap_stage2_range(kvm, 0, kvm_phys_size(kvm)); pgd = READ_ONCE(kvm->arch.pgd); kvm->arch.pgd = NULL; + kvm->arch.pgd_phys = 0; } spin_unlock(&kvm->mmu_lock); @@ -1396,14 +1403,6 @@ static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap) return false; } -static bool kvm_is_write_fault(struct kvm_vcpu *vcpu) -{ - if (kvm_vcpu_trap_is_iabt(vcpu)) - return false; - - return kvm_vcpu_dabt_iswrite(vcpu); -} - /** * stage2_wp_ptes - write protect PMD range * @pmd: pointer to pmd entry @@ -1598,14 +1597,13 @@ static void kvm_send_hwpoison_signal(unsigned long address, static bool fault_supports_stage2_pmd_mappings(struct kvm_memory_slot *memslot, unsigned long hva) { - gpa_t gpa_start, gpa_end; + gpa_t gpa_start; hva_t uaddr_start, uaddr_end; size_t size; size = memslot->npages * PAGE_SIZE; gpa_start = memslot->base_gfn << PAGE_SHIFT; - gpa_end = gpa_start + size; uaddr_start = memslot->userspace_addr; uaddr_end = uaddr_start + size; @@ -2353,7 +2351,7 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, return 0; } -void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) +void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { } diff --git a/virt/kvm/arm/trace.h b/virt/kvm/arm/trace.h @@ -2,6 +2,7 @@ #if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KVM_H +#include <kvm/arm_arch_timer.h> #include <linux/tracepoint.h> #undef TRACE_SYSTEM @@ -262,10 +263,114 @@ TRACE_EVENT(kvm_timer_update_irq, __entry->vcpu_id, __entry->irq, __entry->level) ); +TRACE_EVENT(kvm_get_timer_map, + TP_PROTO(unsigned long vcpu_id, struct timer_map *map), + TP_ARGS(vcpu_id, map), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_id ) + __field( int, direct_vtimer ) + __field( int, direct_ptimer ) + __field( int, emul_ptimer ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->direct_vtimer = arch_timer_ctx_index(map->direct_vtimer); + __entry->direct_ptimer = + (map->direct_ptimer) ? arch_timer_ctx_index(map->direct_ptimer) : -1; + __entry->emul_ptimer = + (map->emul_ptimer) ? arch_timer_ctx_index(map->emul_ptimer) : -1; + ), + + TP_printk("VCPU: %ld, dv: %d, dp: %d, ep: %d", + __entry->vcpu_id, + __entry->direct_vtimer, + __entry->direct_ptimer, + __entry->emul_ptimer) +); + +TRACE_EVENT(kvm_timer_save_state, + TP_PROTO(struct arch_timer_context *ctx), + TP_ARGS(ctx), + + TP_STRUCT__entry( + __field( unsigned long, ctl ) + __field( unsigned long long, cval ) + __field( int, timer_idx ) + ), + + TP_fast_assign( + __entry->ctl = ctx->cnt_ctl; + __entry->cval = ctx->cnt_cval; + __entry->timer_idx = arch_timer_ctx_index(ctx); + ), + + TP_printk(" CTL: %#08lx CVAL: %#16llx arch_timer_ctx_index: %d", + __entry->ctl, + __entry->cval, + __entry->timer_idx) +); + +TRACE_EVENT(kvm_timer_restore_state, + TP_PROTO(struct arch_timer_context *ctx), + TP_ARGS(ctx), + + TP_STRUCT__entry( + __field( unsigned long, ctl ) + __field( unsigned long long, cval ) + __field( int, timer_idx ) + ), + + TP_fast_assign( + __entry->ctl = ctx->cnt_ctl; + __entry->cval = ctx->cnt_cval; + __entry->timer_idx = arch_timer_ctx_index(ctx); + ), + + TP_printk("CTL: %#08lx CVAL: %#16llx arch_timer_ctx_index: %d", + __entry->ctl, + __entry->cval, + __entry->timer_idx) +); + +TRACE_EVENT(kvm_timer_hrtimer_expire, + TP_PROTO(struct arch_timer_context *ctx), + TP_ARGS(ctx), + + TP_STRUCT__entry( + __field( int, timer_idx ) + ), + + TP_fast_assign( + __entry->timer_idx = arch_timer_ctx_index(ctx); + ), + + TP_printk("arch_timer_ctx_index: %d", __entry->timer_idx) +); + +TRACE_EVENT(kvm_timer_emulate, + TP_PROTO(struct arch_timer_context *ctx, bool should_fire), + TP_ARGS(ctx, should_fire), + + TP_STRUCT__entry( + __field( int, timer_idx ) + __field( bool, should_fire ) + ), + + TP_fast_assign( + __entry->timer_idx = arch_timer_ctx_index(ctx); + __entry->should_fire = should_fire; + ), + + TP_printk("arch_timer_ctx_index: %d (should_fire: %d)", + __entry->timer_idx, __entry->should_fire) +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH ../../../virt/kvm/arm +#define TRACE_INCLUDE_PATH ../../virt/kvm/arm #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c @@ -589,7 +589,7 @@ early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable); */ int vgic_v3_probe(const struct gic_kvm_info *info) { - u32 ich_vtr_el2 = kvm_call_hyp(__vgic_v3_get_ich_vtr_el2); + u32 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_ich_vtr_el2); int ret; /* @@ -679,7 +679,7 @@ void vgic_v3_put(struct kvm_vcpu *vcpu) struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; if (likely(cpu_if->vgic_sre)) - cpu_if->vgic_vmcr = kvm_call_hyp(__vgic_v3_read_vmcr); + cpu_if->vgic_vmcr = kvm_call_hyp_ret(__vgic_v3_read_vmcr); kvm_call_hyp(__vgic_v3_save_aprs, vcpu); diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c @@ -144,7 +144,8 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, if (zone->pio != 1 && zone->pio != 0) return -EINVAL; - dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL); + dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), + GFP_KERNEL_ACCOUNT); if (!dev) return -ENOMEM; diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c @@ -297,7 +297,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) if (!kvm_arch_intc_initialized(kvm)) return -EAGAIN; - irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL); + irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL_ACCOUNT); if (!irqfd) return -ENOMEM; @@ -345,7 +345,8 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) } if (!irqfd->resampler) { - resampler = kzalloc(sizeof(*resampler), GFP_KERNEL); + resampler = kzalloc(sizeof(*resampler), + GFP_KERNEL_ACCOUNT); if (!resampler) { ret = -ENOMEM; mutex_unlock(&kvm->irqfds.resampler_lock); @@ -797,7 +798,7 @@ static int kvm_assign_ioeventfd_idx(struct kvm *kvm, if (IS_ERR(eventfd)) return PTR_ERR(eventfd); - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kzalloc(sizeof(*p), GFP_KERNEL_ACCOUNT); if (!p) { ret = -ENOMEM; goto fail; diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c @@ -196,7 +196,7 @@ int kvm_set_irq_routing(struct kvm *kvm, nr_rt_entries += 1; new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head)), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!new) return -ENOMEM; @@ -208,7 +208,7 @@ int kvm_set_irq_routing(struct kvm *kvm, for (i = 0; i < nr; ++i) { r = -ENOMEM; - e = kzalloc(sizeof(*e), GFP_KERNEL); + e = kzalloc(sizeof(*e), GFP_KERNEL_ACCOUNT); if (!e) goto out; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c @@ -81,6 +81,11 @@ unsigned int halt_poll_ns_grow = 2; module_param(halt_poll_ns_grow, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns_grow); +/* The start value to grow halt_poll_ns from */ +unsigned int halt_poll_ns_grow_start = 10000; /* 10us */ +module_param(halt_poll_ns_grow_start, uint, 0644); +EXPORT_SYMBOL_GPL(halt_poll_ns_grow_start); + /* Default resets per-vcpu halt_poll_ns . */ unsigned int halt_poll_ns_shrink; module_param(halt_poll_ns_shrink, uint, 0644); @@ -525,7 +530,7 @@ static struct kvm_memslots *kvm_alloc_memslots(void) int i; struct kvm_memslots *slots; - slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT); if (!slots) return NULL; @@ -601,12 +606,12 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries, sizeof(*kvm->debugfs_stat_data), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!kvm->debugfs_stat_data) return -ENOMEM; for (p = debugfs_entries; p->name; p++) { - stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL); + stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT); if (!stat_data) return -ENOMEM; @@ -656,12 +661,8 @@ static struct kvm *kvm_create_vm(unsigned long type) struct kvm_memslots *slots = kvm_alloc_memslots(); if (!slots) goto out_err_no_srcu; - /* - * Generations must be different for each address space. - * Init kvm generation close to the maximum to easily test the - * code of handling generation number wrap-around. - */ - slots->generation = i * 2 - 150; + /* Generations must be different for each address space. */ + slots->generation = i; rcu_assign_pointer(kvm->memslots[i], slots); } @@ -671,7 +672,7 @@ static struct kvm *kvm_create_vm(unsigned long type) goto out_err_no_irq_srcu; for (i = 0; i < KVM_NR_BUSES; i++) { rcu_assign_pointer(kvm->buses[i], - kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL)); + kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT)); if (!kvm->buses[i]) goto out_err; } @@ -789,7 +790,7 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot) { unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot); - memslot->dirty_bitmap = kvzalloc(dirty_bytes, GFP_KERNEL); + memslot->dirty_bitmap = kvzalloc(dirty_bytes, GFP_KERNEL_ACCOUNT); if (!memslot->dirty_bitmap) return -ENOMEM; @@ -874,31 +875,34 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, int as_id, struct kvm_memslots *slots) { struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id); + u64 gen = old_memslots->generation; - /* - * Set the low bit in the generation, which disables SPTE caching - * until the end of synchronize_srcu_expedited. - */ - WARN_ON(old_memslots->generation & 1); - slots->generation = old_memslots->generation + 1; + WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); + slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; rcu_assign_pointer(kvm->memslots[as_id], slots); synchronize_srcu_expedited(&kvm->srcu); /* - * Increment the new memslot generation a second time. This prevents - * vm exits that race with memslot updates from caching a memslot - * generation that will (potentially) be valid forever. - * + * Increment the new memslot generation a second time, dropping the + * update in-progress flag and incrementing then generation based on + * the number of address spaces. This provides a unique and easily + * identifiable generation number while the memslots are in flux. + */ + gen = slots->generation & ~KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; + + /* * Generations must be unique even across address spaces. We do not need * a global counter for that, instead the generation space is evenly split * across address spaces. For example, with two address spaces, address - * space 0 will use generations 0, 4, 8, ... while * address space 1 will - * use generations 2, 6, 10, 14, ... + * space 0 will use generations 0, 2, 4, ... while address space 1 will + * use generations 1, 3, 5, ... */ - slots->generation += KVM_ADDRESS_SPACE_NUM * 2 - 1; + gen += KVM_ADDRESS_SPACE_NUM; + + kvm_arch_memslots_updated(kvm, gen); - kvm_arch_memslots_updated(kvm, slots); + slots->generation = gen; return old_memslots; } @@ -1018,7 +1022,7 @@ int __kvm_set_memory_region(struct kvm *kvm, goto out_free; } - slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT); if (!slots) goto out_free; memcpy(slots, __kvm_memslots(kvm, as_id), sizeof(struct kvm_memslots)); @@ -1201,11 +1205,9 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, mask = xchg(&dirty_bitmap[i], 0); dirty_bitmap_buffer[i] = mask; - if (mask) { - offset = i * BITS_PER_LONG; - kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, - offset, mask); - } + offset = i * BITS_PER_LONG; + kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, + offset, mask); } spin_unlock(&kvm->mmu_lock); } @@ -2185,20 +2187,23 @@ void kvm_sigset_deactivate(struct kvm_vcpu *vcpu) static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) { - unsigned int old, val, grow; + unsigned int old, val, grow, grow_start; old = val = vcpu->halt_poll_ns; + grow_start = READ_ONCE(halt_poll_ns_grow_start); grow = READ_ONCE(halt_poll_ns_grow); - /* 10us base */ - if (val == 0 && grow) - val = 10000; - else - val *= grow; + if (!grow) + goto out; + + val *= grow; + if (val < grow_start) + val = grow_start; if (val > halt_poll_ns) val = halt_poll_ns; vcpu->halt_poll_ns = val; +out: trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old); } @@ -2683,7 +2688,7 @@ static long kvm_vcpu_ioctl(struct file *filp, struct kvm_regs *kvm_regs; r = -ENOMEM; - kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL); + kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL_ACCOUNT); if (!kvm_regs) goto out; r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs); @@ -2711,7 +2716,8 @@ out_free1: break; } case KVM_GET_SREGS: { - kvm_sregs = kzalloc(sizeof(struct kvm_sregs), GFP_KERNEL); + kvm_sregs = kzalloc(sizeof(struct kvm_sregs), + GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!kvm_sregs) goto out; @@ -2803,7 +2809,7 @@ out_free1: break; } case KVM_GET_FPU: { - fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL); + fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL_ACCOUNT); r = -ENOMEM; if (!fpu) goto out; @@ -2980,7 +2986,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm, if (test) return 0; - dev = kzalloc(sizeof(*dev), GFP_KERNEL); + dev = kzalloc(sizeof(*dev), GFP_KERNEL_ACCOUNT); if (!dev) return -ENOMEM; @@ -3625,6 +3631,7 @@ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, r = __kvm_io_bus_write(vcpu, bus, &range, val); return r < 0 ? r : 0; } +EXPORT_SYMBOL_GPL(kvm_io_bus_write); /* kvm_io_bus_write_cookie - called under kvm->slots_lock */ int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, @@ -3675,7 +3682,6 @@ static int __kvm_io_bus_read(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus, return -EOPNOTSUPP; } -EXPORT_SYMBOL_GPL(kvm_io_bus_write); /* kvm_io_bus_read - called under kvm->slots_lock */ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, @@ -3697,7 +3703,6 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, return r < 0 ? r : 0; } - /* Caller must hold slots_lock. */ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev) @@ -3714,8 +3719,8 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1) return -ENOSPC; - new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count + 1) * - sizeof(struct kvm_io_range)), GFP_KERNEL); + new_bus = kmalloc(struct_size(bus, range, bus->dev_count + 1), + GFP_KERNEL_ACCOUNT); if (!new_bus) return -ENOMEM; @@ -3760,8 +3765,8 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, if (i == bus->dev_count) return; - new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count - 1) * - sizeof(struct kvm_io_range)), GFP_KERNEL); + new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1), + GFP_KERNEL_ACCOUNT); if (!new_bus) { pr_err("kvm: failed to shrink bus, removing it completely\n"); goto broken; @@ -4029,7 +4034,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) active = kvm_active_vms; spin_unlock(&kvm_lock); - env = kzalloc(sizeof(*env), GFP_KERNEL); + env = kzalloc(sizeof(*env), GFP_KERNEL_ACCOUNT); if (!env) return; @@ -4045,7 +4050,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) add_uevent_var(env, "PID=%d", kvm->userspace_pid); if (!IS_ERR_OR_NULL(kvm->debugfs_dentry)) { - char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL); + char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT); if (p) { tmp = dentry_path_raw(kvm->debugfs_dentry, p, PATH_MAX); diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c @@ -219,7 +219,7 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg) } } - kvg = kzalloc(sizeof(*kvg), GFP_KERNEL); + kvg = kzalloc(sizeof(*kvg), GFP_KERNEL_ACCOUNT); if (!kvg) { mutex_unlock(&kv->lock); kvm_vfio_group_put_external_user(vfio_group); @@ -405,7 +405,7 @@ static int kvm_vfio_create(struct kvm_device *dev, u32 type) if (tmp->ops == &kvm_vfio_ops) return -EBUSY; - kv = kzalloc(sizeof(*kv), GFP_KERNEL); + kv = kzalloc(sizeof(*kv), GFP_KERNEL_ACCOUNT); if (!kv) return -ENOMEM;