diff options
261 files changed, 3069 insertions, 2654 deletions
diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst index 36890b026e77..1c4e1825d769 100644 --- a/Documentation/dev-tools/kcov.rst +++ b/Documentation/dev-tools/kcov.rst @@ -251,11 +251,11 @@ selectively from different subsystems. .. code-block:: c struct kcov_remote_arg { - unsigned trace_mode; - unsigned area_size; - unsigned num_handles; - uint64_t common_handle; - uint64_t handles[0]; + __u32 trace_mode; + __u32 area_size; + __u32 num_handles; + __aligned_u64 common_handle; + __aligned_u64 handles[0]; }; #define KCOV_INIT_TRACE _IOR('c', 1, unsigned long) diff --git a/Documentation/features/debug/gcov-profile-all/arch-support.txt b/Documentation/features/debug/gcov-profile-all/arch-support.txt index 059d58a549c7..6fb2b0671994 100644 --- a/Documentation/features/debug/gcov-profile-all/arch-support.txt +++ b/Documentation/features/debug/gcov-profile-all/arch-support.txt @@ -23,7 +23,7 @@ | openrisc: | TODO | | parisc: | TODO | | powerpc: | ok | - | riscv: | TODO | + | riscv: | ok | | s390: | ok | | sh: | ok | | sparc: | TODO | diff --git a/Documentation/networking/dsa/sja1105.rst b/Documentation/networking/dsa/sja1105.rst index eef20d0bcf7c..64553d8d91cb 100644 --- a/Documentation/networking/dsa/sja1105.rst +++ b/Documentation/networking/dsa/sja1105.rst @@ -230,12 +230,6 @@ simultaneously on two ports. The driver checks the consistency of the schedules against this restriction and errors out when appropriate. Schedule analysis is needed to avoid this, which is outside the scope of the document. -At the moment, the time-aware scheduler can only be triggered based on a -standalone clock and not based on PTP time. This means the base-time argument -from tc-taprio is ignored and the schedule starts right away. It also means it -is more difficult to phase-align the scheduler with the other devices in the -network. - Device Tree bindings and board design ===================================== diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst index 21aa7d5358e6..6399d92f0b21 100644 --- a/Documentation/process/index.rst +++ b/Documentation/process/index.rst @@ -60,6 +60,7 @@ lack of a better place. volatile-considered-harmful botching-up-ioctls clang-format + ../riscv/patch-acceptance .. only:: subproject and html diff --git a/Documentation/riscv/index.rst b/Documentation/riscv/index.rst index 215fd3c1f2d5..fa33bffd8992 100644 --- a/Documentation/riscv/index.rst +++ b/Documentation/riscv/index.rst @@ -7,6 +7,7 @@ RISC-V architecture boot-image-header pmu + patch-acceptance .. only:: subproject and html diff --git a/Documentation/riscv/patch-acceptance.rst b/Documentation/riscv/patch-acceptance.rst new file mode 100644 index 000000000000..dfe0ac5624fb --- /dev/null +++ b/Documentation/riscv/patch-acceptance.rst @@ -0,0 +1,35 @@ +.. SPDX-License-Identifier: GPL-2.0 + +arch/riscv maintenance guidelines for developers +================================================ + +Overview +-------- +The RISC-V instruction set architecture is developed in the open: +in-progress drafts are available for all to review and to experiment +with implementations. New module or extension drafts can change +during the development process - sometimes in ways that are +incompatible with previous drafts. This flexibility can present a +challenge for RISC-V Linux maintenance. Linux maintainers disapprove +of churn, and the Linux development process prefers well-reviewed and +tested code over experimental code. We wish to extend these same +principles to the RISC-V-related code that will be accepted for +inclusion in the kernel. + +Submit Checklist Addendum +------------------------- +We'll only accept patches for new modules or extensions if the +specifications for those modules or extensions are listed as being +"Frozen" or "Ratified" by the RISC-V Foundation. (Developers may, of +course, maintain their own Linux kernel trees that contain code for +any draft extensions that they wish.) + +Additionally, the RISC-V specification allows implementors to create +their own custom extensions. These custom extensions aren't required +to go through any review or ratification process by the RISC-V +Foundation. To avoid the maintenance complexity and potential +performance impact of adding kernel code for implementor-specific +RISC-V extensions, we'll only to accept patches for extensions that +have been officially frozen or ratified by the RISC-V Foundation. +(Implementors, may, of course, maintain their own Linux kernel trees +containing code for any custom extensions that they wish.) diff --git a/MAINTAINERS b/MAINTAINERS index e09bd92a1e44..8982c6e013b3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -771,6 +771,8 @@ F: drivers/thermal/thermal_mmio.c AMAZON ETHERNET DRIVERS M: Netanel Belgazal <netanel@amazon.com> +M: Arthur Kiyanovski <akiyano@amazon.com> +R: Guy Tzalik <gtzalik@amazon.com> R: Saeed Bishara <saeedb@amazon.com> R: Zorik Machulsky <zorik@amazon.com> L: netdev@vger.kernel.org @@ -14119,6 +14121,7 @@ M: Paul Walmsley <paul.walmsley@sifive.com> M: Palmer Dabbelt <palmer@dabbelt.com> M: Albert Ou <aou@eecs.berkeley.edu> L: linux-riscv@lists.infradead.org +P: Documentation/riscv/patch-acceptance.rst T: git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git S: Supported F: arch/riscv/ @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index bd2233805d99..c3314b286a61 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -280,8 +280,6 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); -struct kvm_vcpu *kvm_arm_get_running_vcpu(void); -struct kvm_vcpu __percpu **kvm_get_running_vcpus(void); void kvm_arm_halt_guest(struct kvm *kvm); void kvm_arm_resume_guest(struct kvm *kvm); @@ -367,9 +365,9 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); static inline bool kvm_arch_requires_vhe(void) { return false; } static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} -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_vcpu_block_finish(struct kvm_vcpu *vcpu) {} +static inline void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) {} static inline void kvm_arm_init_debug(void) {} static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {} diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 0e6f23504c26..9f7ae0d8690f 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -34,11 +34,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) -{ - return 0; -} - static u64 core_reg_offset_from_id(u64 id) { return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f6a77ddab956..524ab67b73e8 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -52,7 +52,7 @@ int kvm_arm_init_sve(void); int __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); -void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu); +void kvm_arm_vcpu_destroy(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); @@ -442,8 +442,6 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); -struct kvm_vcpu *kvm_arm_get_running_vcpu(void); -struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); void kvm_arm_halt_guest(struct kvm *kvm); void kvm_arm_resume_guest(struct kvm *kvm); diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 2fff06114a8f..2bd92301d32f 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -47,11 +47,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) -{ - return 0; -} - static bool core_reg_offset_is_vreg(u64 off) { return off >= KVM_REG_ARM_CORE_REG(fp_regs.vregs) && diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index f4a8ae918827..30b7ea680f66 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -204,7 +204,7 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu) return true; } -void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) +void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) { kfree(vcpu->arch.sve_state); } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 5a3b15a14a7f..40797cbfba2d 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1070,7 +1070,6 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; /* * FIXME: Cleanup page tables (also in arch_add_memory() in case @@ -1079,7 +1078,6 @@ void arch_remove_memory(int nid, u64 start, u64 size, * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be * unlocked yet. */ - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h index 12cd9231c4b8..0231d69c8bf2 100644 --- a/arch/hexagon/include/asm/atomic.h +++ b/arch/hexagon/include/asm/atomic.h @@ -91,7 +91,7 @@ static inline void atomic_##op(int i, atomic_t *v) \ "1: %0 = memw_locked(%1);\n" \ " %0 = "#op "(%0,%2);\n" \ " memw_locked(%1,P3)=%0;\n" \ - " if !P3 jump 1b;\n" \ + " if (!P3) jump 1b;\n" \ : "=&r" (output) \ : "r" (&v->counter), "r" (i) \ : "memory", "p3" \ @@ -107,7 +107,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ "1: %0 = memw_locked(%1);\n" \ " %0 = "#op "(%0,%2);\n" \ " memw_locked(%1,P3)=%0;\n" \ - " if !P3 jump 1b;\n" \ + " if (!P3) jump 1b;\n" \ : "=&r" (output) \ : "r" (&v->counter), "r" (i) \ : "memory", "p3" \ @@ -124,7 +124,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ "1: %0 = memw_locked(%2);\n" \ " %1 = "#op "(%0,%3);\n" \ " memw_locked(%2,P3)=%1;\n" \ - " if !P3 jump 1b;\n" \ + " if (!P3) jump 1b;\n" \ : "=&r" (output), "=&r" (val) \ : "r" (&v->counter), "r" (i) \ : "memory", "p3" \ @@ -173,7 +173,7 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) " }" " memw_locked(%2, p3) = %1;" " {" - " if !p3 jump 1b;" + " if (!p3) jump 1b;" " }" "2:" : "=&r" (__oldval), "=&r" (tmp) diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h index 47384b094b94..71429f756af0 100644 --- a/arch/hexagon/include/asm/bitops.h +++ b/arch/hexagon/include/asm/bitops.h @@ -38,7 +38,7 @@ static inline int test_and_clear_bit(int nr, volatile void *addr) "1: R12 = memw_locked(R10);\n" " { P0 = tstbit(R12,R11); R12 = clrbit(R12,R11); }\n" " memw_locked(R10,P1) = R12;\n" - " {if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n" + " {if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n" : "=&r" (oldval) : "r" (addr), "r" (nr) : "r10", "r11", "r12", "p0", "p1", "memory" @@ -62,7 +62,7 @@ static inline int test_and_set_bit(int nr, volatile void *addr) "1: R12 = memw_locked(R10);\n" " { P0 = tstbit(R12,R11); R12 = setbit(R12,R11); }\n" " memw_locked(R10,P1) = R12;\n" - " {if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n" + " {if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n" : "=&r" (oldval) : "r" (addr), "r" (nr) : "r10", "r11", "r12", "p0", "p1", "memory" @@ -88,7 +88,7 @@ static inline int test_and_change_bit(int nr, volatile void *addr) "1: R12 = memw_locked(R10);\n" " { P0 = tstbit(R12,R11); R12 = togglebit(R12,R11); }\n" " memw_locked(R10,P1) = R12;\n" - " {if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n" + " {if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n" : "=&r" (oldval) : "r" (addr), "r" (nr) : "r10", "r11", "r12", "p0", "p1", "memory" @@ -223,7 +223,7 @@ static inline int ffs(int x) int r; asm("{ P0 = cmp.eq(%1,#0); %0 = ct0(%1);}\n" - "{ if P0 %0 = #0; if !P0 %0 = add(%0,#1);}\n" + "{ if (P0) %0 = #0; if (!P0) %0 = add(%0,#1);}\n" : "=&r" (r) : "r" (x) : "p0"); diff --git a/arch/hexagon/include/asm/cmpxchg.h b/arch/hexagon/include/asm/cmpxchg.h index 6091322c3af9..92b8a02e588a 100644 --- a/arch/hexagon/include/asm/cmpxchg.h +++ b/arch/hexagon/include/asm/cmpxchg.h @@ -30,7 +30,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, __asm__ __volatile__ ( "1: %0 = memw_locked(%1);\n" /* load into retval */ " memw_locked(%1,P0) = %2;\n" /* store into memory */ - " if !P0 jump 1b;\n" + " if (!P0) jump 1b;\n" : "=&r" (retval) : "r" (ptr), "r" (x) : "memory", "p0" diff --git a/arch/hexagon/include/asm/futex.h b/arch/hexagon/include/asm/futex.h index cb635216a732..0191f7c7193e 100644 --- a/arch/hexagon/include/asm/futex.h +++ b/arch/hexagon/include/asm/futex.h @@ -16,7 +16,7 @@ /* For example: %1 = %4 */ \ insn \ "2: memw_locked(%3,p2) = %1;\n" \ - " if !p2 jump 1b;\n" \ + " if (!p2) jump 1b;\n" \ " %1 = #0;\n" \ "3:\n" \ ".section .fixup,\"ax\"\n" \ @@ -84,10 +84,10 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, "1: %1 = memw_locked(%3)\n" " {\n" " p2 = cmp.eq(%1,%4)\n" - " if !p2.new jump:NT 3f\n" + " if (!p2.new) jump:NT 3f\n" " }\n" "2: memw_locked(%3,p2) = %5\n" - " if !p2 jump 1b\n" + " if (!p2) jump 1b\n" "3:\n" ".section .fixup,\"ax\"\n" "4: %0 = #%6\n" diff --git a/arch/hexagon/include/asm/io.h b/arch/hexagon/include/asm/io.h index 539e3efcf39c..b0dbc3473172 100644 --- a/arch/hexagon/include/asm/io.h +++ b/arch/hexagon/include/asm/io.h @@ -173,6 +173,7 @@ static inline void writel(u32 data, volatile void __iomem *addr) void __iomem *ioremap(unsigned long phys_addr, unsigned long size); #define ioremap_nocache ioremap +#define ioremap_uc(X, Y) ioremap((X), (Y)) #define __raw_writel writel diff --git a/arch/hexagon/include/asm/spinlock.h b/arch/hexagon/include/asm/spinlock.h index bfe07d842ff3..ef103b73bec8 100644 --- a/arch/hexagon/include/asm/spinlock.h +++ b/arch/hexagon/include/asm/spinlock.h @@ -30,9 +30,9 @@ static inline void arch_read_lock(arch_rwlock_t *lock) __asm__ __volatile__( "1: R6 = memw_locked(%0);\n" " { P3 = cmp.ge(R6,#0); R6 = add(R6,#1);}\n" - " { if !P3 jump 1b; }\n" + " { if (!P3) jump 1b; }\n" " memw_locked(%0,P3) = R6;\n" - " { if !P3 jump 1b; }\n" + " { if (!P3) jump 1b; }\n" : : "r" (&lock->lock) : "memory", "r6", "p3" @@ -46,7 +46,7 @@ static inline void arch_read_unlock(arch_rwlock_t *lock) "1: R6 = memw_locked(%0);\n" " R6 = add(R6,#-1);\n" " memw_locked(%0,P3) = R6\n" - " if !P3 jump 1b;\n" + " if (!P3) jump 1b;\n" : : "r" (&lock->lock) : "memory", "r6", "p3" @@ -61,7 +61,7 @@ static inline int arch_read_trylock(arch_rwlock_t *lock) __asm__ __volatile__( " R6 = memw_locked(%1);\n" " { %0 = #0; P3 = cmp.ge(R6,#0); R6 = add(R6,#1);}\n" - " { if !P3 jump 1f; }\n" + " { if (!P3) jump 1f; }\n" " memw_locked(%1,P3) = R6;\n" " { %0 = P3 }\n" "1:\n" @@ -78,9 +78,9 @@ static inline void arch_write_lock(arch_rwlock_t *lock) __asm__ __volatile__( "1: R6 = memw_locked(%0)\n" " { P3 = cmp.eq(R6,#0); R6 = #-1;}\n" - " { if !P3 jump 1b; }\n" + " { if (!P3) jump 1b; }\n" " memw_locked(%0,P3) = R6;\n" - " { if !P3 jump 1b; }\n" + " { if (!P3) jump 1b; }\n" : : "r" (&lock->lock) : "memory", "r6", "p3" @@ -94,7 +94,7 @@ static inline int arch_write_trylock(arch_rwlock_t *lock) __asm__ __volatile__( " R6 = memw_locked(%1)\n" " { %0 = #0; P3 = cmp.eq(R6,#0); R6 = #-1;}\n" - " { if !P3 jump 1f; }\n" + " { if (!P3) jump 1f; }\n" " memw_locked(%1,P3) = R6;\n" " %0 = P3;\n" "1:\n" @@ -117,9 +117,9 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) __asm__ __volatile__( "1: R6 = memw_locked(%0);\n" " P3 = cmp.eq(R6,#0);\n" - " { if !P3 jump 1b; R6 = #1; }\n" + " { if (!P3) jump 1b; R6 = #1; }\n" " memw_locked(%0,P3) = R6;\n" - " { if !P3 jump 1b; }\n" + " { if (!P3) jump 1b; }\n" : : "r" (&lock->lock) : "memory", "r6", "p3" @@ -139,7 +139,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock) __asm__ __volatile__( " R6 = memw_locked(%1);\n" " P3 = cmp.eq(R6,#0);\n" - " { if !P3 jump 1f; R6 = #1; %0 = #0; }\n" + " { if (!P3) jump 1f; R6 = #1; %0 = #0; }\n" " memw_locked(%1,P3) = R6;\n" " %0 = P3;\n" "1:\n" diff --git a/arch/hexagon/kernel/stacktrace.c b/arch/hexagon/kernel/stacktrace.c index 35f29423fda8..5ed02f699479 100644 --- a/arch/hexagon/kernel/stacktrace.c +++ b/arch/hexagon/kernel/stacktrace.c @@ -11,8 +11,6 @@ #include <linux/thread_info.h> #include <linux/module.h> -register unsigned long current_frame_pointer asm("r30"); - struct stackframe { unsigned long fp; unsigned long rets; @@ -30,7 +28,7 @@ void save_stack_trace(struct stack_trace *trace) low = (unsigned long)task_stack_page(current); high = low + THREAD_SIZE; - fp = current_frame_pointer; + fp = (unsigned long)__builtin_frame_address(0); while (fp >= low && fp <= (high - sizeof(*frame))) { frame = (struct stackframe *)fp; diff --git a/arch/hexagon/kernel/vm_entry.S b/arch/hexagon/kernel/vm_entry.S index 12242c27e2df..4023fdbea490 100644 --- a/arch/hexagon/kernel/vm_entry.S +++ b/arch/hexagon/kernel/vm_entry.S @@ -369,7 +369,7 @@ ret_from_fork: R26.L = #LO(do_work_pending); R0 = #VM_INT_DISABLE; } - if P0 jump check_work_pending + if (P0) jump check_work_pending { R0 = R25; callr R24 diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 58fd67068bac..b01d68a2d5d9 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -689,9 +689,7 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index add388236f4e..ed8e28b0fb3e 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -47,7 +47,7 @@ config MIPS select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES select HAVE_ASM_MODVERSIONS - select HAVE_EBPF_JIT if (!CPU_MICROMIPS) + select HAVE_EBPF_JIT if 64BIT && !CPU_MICROMIPS && TARGET_ISA_REV >= 2 select HAVE_CONTEXT_TRACKING select HAVE_COPY_THREAD_TLS select HAVE_C_RECORDMCOUNT diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index 172801ed35b8..d859f079b771 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -29,6 +29,9 @@ KBUILD_AFLAGS := $(KBUILD_AFLAGS) -D__ASSEMBLY__ \ -DBOOT_HEAP_SIZE=$(BOOT_HEAP_SIZE) \ -DKERNEL_ENTRY=$(VMLINUX_ENTRY_ADDRESS) +# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. +KCOV_INSTRUMENT := n + # decompressor objects (linked with vmlinuz) vmlinuzobjs-y := $(obj)/head.o $(obj)/decompress.o $(obj)/string.o diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h index c46c59b0f1b4..49f0061a6051 100644 --- a/arch/mips/include/asm/cpu-type.h +++ b/arch/mips/include/asm/cpu-type.h @@ -15,7 +15,8 @@ static inline int __pure __get_cpu_type(const int cpu_type) { switch (cpu_type) { -#if defined(CONFIG_SYS_HAS_CPU_LOONGSON2EF) +#if defined(CONFIG_SYS_HAS_CPU_LOONGSON2E) || \ + defined(CONFIG_SYS_HAS_CPU_LOONGSON2F) case CPU_LOONGSON2EF: #endif diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index 4993db40482c..ee26f9a4575d 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -49,8 +49,26 @@ struct thread_info { .addr_limit = KERNEL_DS, \ } -/* How to get the thread information struct from C. */ +/* + * A pointer to the struct thread_info for the currently executing thread is + * held in register $28/$gp. + * + * We declare __current_thread_info as a global register variable rather than a + * local register variable within current_thread_info() because clang doesn't + * support explicit local register variables. + * + * When building the VDSO we take care not to declare the global register + * variable because this causes GCC to not preserve the value of $28/$gp in + * functions that change its value (which is common in the PIC VDSO when + * accessing the GOT). Since the VDSO shouldn't be accessing + * __current_thread_info anyway we declare it extern in order to cause a link + * failure if it's referenced. + */ +#ifdef __VDSO__ +extern struct thread_info *__current_thread_info; +#else register struct thread_info *__current_thread_info __asm__("$28"); +#endif static inline struct thread_info *current_thread_info(void) { diff --git a/arch/mips/include/asm/vdso/gettimeofday.h b/arch/mips/include/asm/vdso/gettimeofday.h index b08825531e9f..0ae9b4cbc153 100644 --- a/arch/mips/include/asm/vdso/gettimeofday.h +++ b/arch/mips/include/asm/vdso/gettimeofday.h @@ -26,8 +26,6 @@ #define __VDSO_USE_SYSCALL ULLONG_MAX -#ifdef CONFIG_MIPS_CLOCK_VSYSCALL - static __always_inline long gettimeofday_fallback( struct __kernel_old_timeval *_tv, struct timezone *_tz) @@ -48,17 +46,6 @@ static __always_inline long gettimeofday_fallback( return error ? -ret : ret; } -#else - -static __always_inline long gettimeofday_fallback( - struct __kernel_old_timeval *_tv, - struct timezone *_tz) -{ - return -1; -} - -#endif - static __always_inline long clock_gettime_fallback( clockid_t _clkid, struct __kernel_timespec *_ts) diff --git a/arch/mips/kernel/cacheinfo.c b/arch/mips/kernel/cacheinfo.c index f777e44653d5..47312c529410 100644 --- a/arch/mips/kernel/cacheinfo.c +++ b/arch/mips/kernel/cacheinfo.c @@ -50,6 +50,25 @@ static int __init_cache_level(unsigned int cpu) return 0; } +static void fill_cpumask_siblings(int cpu, cpumask_t *cpu_map) +{ + int cpu1; + + for_each_possible_cpu(cpu1) + if (cpus_are_siblings(cpu, cpu1)) + cpumask_set_cpu(cpu1, cpu_map); +} + +static void fill_cpumask_cluster(int cpu, cpumask_t *cpu_map) +{ + int cpu1; + int cluster = cpu_cluster(&cpu_data[cpu]); + + for_each_possible_cpu(cpu1) + if (cpu_cluster(&cpu_data[cpu1]) == cluster) + cpumask_set_cpu(cpu1, cpu_map); +} + static int __populate_cache_leaves(unsigned int cpu) { struct cpuinfo_mips *c = ¤t_cpu_data; @@ -57,14 +76,20 @@ static int __populate_cache_leaves(unsigned int cpu) struct cacheinfo *this_leaf = this_cpu_ci->info_list; if (c->icache.waysize) { + /* L1 caches are per core */ + fill_cpumask_siblings(cpu, &this_leaf->shared_cpu_map); populate_cache(dcache, this_leaf, 1, CACHE_TYPE_DATA); + fill_cpumask_siblings(cpu, &this_leaf->shared_cpu_map); populate_cache(icache, this_leaf, 1, CACHE_TYPE_INST); } else { populate_cache(dcache, this_leaf, 1, CACHE_TYPE_UNIFIED); } - if (c->scache.waysize) + if (c->scache.waysize) { + /* L2 cache is per cluster */ + fill_cpumask_cluster(cpu, &this_leaf->shared_cpu_map); populate_cache(scache, this_leaf, 2, CACHE_TYPE_UNIFIED); + } if (c->tcache.waysize) populate_cache(tcache, this_leaf, 3, CACHE_TYPE_UNIFIED); diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 1109924560d8..2606f3f02b54 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -156,7 +156,7 @@ void kvm_mips_free_vcpus(struct kvm *kvm) struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { - kvm_arch_vcpu_free(vcpu); + kvm_vcpu_destroy(vcpu); } mutex_lock(&kvm->lock); @@ -280,25 +280,27 @@ static inline void dump_handler(const char *symbol, void *start, void *end) pr_debug("\tEND(%s)\n", symbol); } -struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) +{ + return 0; +} + +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { int err, size; void *gebase, *p, *handler, *refill_start, *refill_end; int i; - struct kvm_vcpu *vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL); - - if (!vcpu) { - err = -ENOMEM; - goto out; - } - - err = kvm_vcpu_init(vcpu, kvm, id); + kvm_debug("kvm @ %p: create cpu %d at %p\n", + vcpu->kvm, vcpu->vcpu_id, vcpu); + err = kvm_mips_callbacks->vcpu_init(vcpu); if (err) - goto out_free_cpu; + return err; - kvm_debug("kvm @ %p: create cpu %d at %p\n", kvm, id, vcpu); + hrtimer_init(&vcpu->arch.comparecount_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); + vcpu->arch.comparecount_timer.function = kvm_mips_comparecount_wakeup; /* * Allocate space for host mode exception handlers that handle @@ -313,7 +315,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) if (!gebase) { err = -ENOMEM; - goto out_uninit_cpu; + goto out_uninit_vcpu; } kvm_debug("Allocated %d bytes for KVM Exception Handlers @ %p\n", ALIGN(size, PAGE_SIZE), gebase); @@ -392,38 +394,33 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) vcpu->arch.last_sched_cpu = -1; vcpu->arch.last_exec_cpu = -1; - return vcpu; + /* Initial guest state */ + err = kvm_mips_callbacks->vcpu_setup(vcpu); + if (err) + goto out_free_commpage; + + return 0; +out_free_commpage: + kfree(vcpu->arch.kseg0_commpage); out_free_gebase: kfree(gebase); - -out_uninit_cpu: - kvm_vcpu_uninit(vcpu); - -out_free_cpu: - kfree(vcpu); - -out: - return ERR_PTR(err); +out_uninit_vcpu: + kvm_mips_callbacks->vcpu_uninit(vcpu); + return err; } -void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) +void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { hrtimer_cancel(&vcpu->arch.comparecount_timer); - kvm_vcpu_uninit(vcpu); - kvm_mips_dump_stats(vcpu); kvm_mmu_free_memory_caches(vcpu); kfree(vcpu->arch.guest_ebase); kfree(vcpu->arch.kseg0_commpage); - kfree(vcpu); -} -void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) -{ - kvm_arch_vcpu_free(vcpu); + kvm_mips_callbacks->vcpu_uninit(vcpu); } int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, @@ -1233,37 +1230,12 @@ static enum hrtimer_restart kvm_mips_comparecount_wakeup(struct hrtimer *timer) return kvm_mips_count_timeout(vcpu); } -int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) -{ - int err; - - err = kvm_mips_callbacks->vcpu_init(vcpu); - if (err) - return err; - - hrtimer_init(&vcpu->arch.comparecount_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL); - vcpu->arch.comparecount_timer.function = kvm_mips_comparecount_wakeup; - return 0; -} - -void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) -{ - kvm_mips_callbacks->vcpu_uninit(vcpu); -} - int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr) { return 0; } -/* Initial guest state */ -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) -{ - return kvm_mips_callbacks->vcpu_setup(vcpu); -} - static void kvm_mips_set_c0_status(void) { u32 status = read_c0_status(); diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 3ec69d9cbe88..561154cbcc40 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -1804,7 +1804,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) unsigned int image_size; u8 *image_ptr; - if (!prog->jit_requested || MIPS_ISA_REV < 2) + if (!prog->jit_requested) return prog; tmp = bpf_jit_blind_constants(prog); diff --git a/arch/mips/vdso/vgettimeofday.c b/arch/mips/vdso/vgettimeofday.c index 6ebdc37c89fc..6b83b6376a4b 100644 --- a/arch/mips/vdso/vgettimeofday.c +++ b/arch/mips/vdso/vgettimeofday.c @@ -17,12 +17,22 @@ int __vdso_clock_gettime(clockid_t clock, return __cvdso_clock_gettime32(clock, ts); } +#ifdef CONFIG_MIPS_CLOCK_VSYSCALL + +/* + * This is behind the ifdef so that we don't provide the symbol when there's no + * possibility of there being a usable clocksource, because there's nothing we + * can do without it. When libc fails the symbol lookup it should fall back on + * the standard syscall path. + */ int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { return __cvdso_gettimeofday(tv, tz); } +#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */ + int __vdso_clock_getres(clockid_t clock_id, struct old_timespec32 *res) { @@ -43,12 +53,22 @@ int __vdso_clock_gettime(clockid_t clock, return __cvdso_clock_gettime(clock, ts); } +#ifdef CONFIG_MIPS_CLOCK_VSYSCALL + +/* + * This is behind the ifdef so that we don't provide the symbol when there's no + * possibility of there being a usable clocksource, because there's nothing we + * can do without it. When libc fails the symbol lookup it should fall back on + * the standard syscall path. + */ int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { return __cvdso_gettimeofday(tv, tz); } +#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */ + int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res) { diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 3d2f871241a8..bc2494e5710a 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -119,8 +119,7 @@ extern int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, enum xlate_instdata xlid, enum xlate_readwrite xlrw, struct kvmppc_pte *pte); -extern struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, - unsigned int id); +extern int kvmppc_core_vcpu_create(struct kvm_vcpu *vcpu); extern void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu); extern int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu); extern int kvmppc_core_check_processor_compat(void); @@ -274,7 +273,7 @@ struct kvmppc_ops { void (*inject_interrupt)(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags); void (*set_msr)(struct kvm_vcpu *vcpu, u64 msr); int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu); - struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned int id); + int (*vcpu_create)(struct kvm_vcpu *vcpu); void (*vcpu_free)(struct kvm_vcpu *vcpu); int (*check_requests)(struct kvm_vcpu *vcpu); int (*get_dirty_log)(struct kvm *kvm, struct kvm_dirty_log *log); diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 1b55fc08f853..860228e917dc 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -15,6 +15,7 @@ * * (the type definitions are in asm/spinlock_types.h) */ +#include <linux/jump_label.h> #include <linux/irqflags.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 58a59ee998e2..d07a8e12fa15 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -471,11 +471,6 @@ int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(kvmppc_load_last_inst); -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) -{ - return 0; -} - int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu) { return 0; @@ -789,9 +784,9 @@ void kvmppc_decrementer_func(struct kvm_vcpu *vcpu) kvm_vcpu_kick(vcpu); } -struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +int kvmppc_core_vcpu_create(struct kvm_vcpu *vcpu) { - return kvm->arch.kvm_ops->vcpu_create(kvm, id); + return vcpu->kvm->arch.kvm_ops->vcpu_create(vcpu); } void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 6ff3f896d908..f4b72cef09d5 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2271,22 +2271,16 @@ static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id) } #endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */ -static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, - unsigned int id) +static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu; int err; int core; struct kvmppc_vcore *vcore; + struct kvm *kvm; + unsigned int id; - err = -ENOMEM; - vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); - if (!vcpu) - goto out; - - err = kvm_vcpu_init(vcpu, kvm, id); - if (err) - goto free_vcpu; + kvm = vcpu->kvm; + id = vcpu->vcpu_id; vcpu->arch.shared = &vcpu->arch.shregs; #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE @@ -2368,7 +2362,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, mutex_unlock(&kvm->lock); if (!vcore) - goto free_vcpu; + return err; spin_lock(&vcore->lock); ++vcore->num_threads; @@ -2383,12 +2377,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, debugfs_vcpu_init(vcpu, id); - return vcpu; - -free_vcpu: - kmem_cache_free(kvm_vcpu_cache, vcpu); -out: - return ERR_PTR(err); + return 0; } static int kvmhv_set_smt_mode(struct kvm *kvm, unsigned long smt_mode, @@ -2442,8 +2431,6 @@ static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu) unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow); unpin_vpa(vcpu->kvm, &vcpu->arch.vpa); spin_unlock(&vcpu->arch.vpa_update_lock); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(kvm_vcpu_cache, vcpu); } static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu) diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index ce4fcf76e53e..d88f708d5be3 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1744,21 +1744,17 @@ static int kvmppc_set_one_reg_pr(struct kvm_vcpu *vcpu, u64 id, return r; } -static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm, - unsigned int id) +static int kvmppc_core_vcpu_create_pr(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_book3s *vcpu_book3s; - struct kvm_vcpu *vcpu; - int err = -ENOMEM; unsigned long p; + int err; - vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); - if (!vcpu) - goto out; + err = -ENOMEM; vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s)); if (!vcpu_book3s) - goto free_vcpu; + goto out; vcpu->arch.book3s = vcpu_book3s; #ifdef CONFIG_KVM_BOOK3S_32_HANDLER @@ -1768,14 +1764,9 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm, goto free_vcpu3s; #endif - err = kvm_vcpu_init(vcpu, kvm, id); - if (err) - goto free_shadow_vcpu; - - err = -ENOMEM; p = __get_free_page(GFP_KERNEL|__GFP_ZERO); if (!p) - goto uninit_vcpu; + goto free_shadow_vcpu; vcpu->arch.shared = (void *)p; #ifdef CONFIG_PPC_BOOK3S_64 /* Always start the shared struct in native endian mode */ @@ -1806,22 +1797,20 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm, err = kvmppc_mmu_init(vcpu); if (err < 0) - goto uninit_vcpu; + goto free_shared_page; - return vcpu; + return 0; -uninit_vcpu: - kvm_vcpu_uninit(vcpu); +free_shared_page: + free_page((unsigned long)vcpu->arch.shared); free_shadow_vcpu: #ifdef CONFIG_KVM_BOOK3S_32_HANDLER kfree(vcpu->arch.shadow_vcpu); free_vcpu3s: #endif vfree(vcpu_book3s); -free_vcpu: - kmem_cache_free(kvm_vcpu_cache, vcpu); out: - return ERR_PTR(err); + return err; } static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu) @@ -1829,12 +1818,10 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu) struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); free_page((unsigned long)vcpu->arch.shared & PAGE_MASK); - kvm_vcpu_uninit(vcpu); #ifdef CONFIG_KVM_BOOK3S_32_HANDLER kfree(vcpu->arch.shadow_vcpu); #endif vfree(vcpu_book3s); - kmem_cache_free(kvm_vcpu_cache, vcpu); } static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index d83adb1e1490..6ef0151ff70a 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -631,7 +631,7 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, srcu_idx = srcu_read_lock(&kvm->srcu); gfn = gpa_to_gfn(kvm_eq.qaddr); - page_size = kvm_host_page_size(kvm, gfn); + page_size = kvm_host_page_size(vcpu, gfn); if (1ull << kvm_eq.qshift > page_size) { srcu_read_unlock(&kvm->srcu, srcu_idx); pr_warn("Incompatible host page size %lx!\n", page_size); diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index be9a45874194..9cb8257b4118 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -1377,36 +1377,6 @@ static void kvmppc_set_tsr(struct kvm_vcpu *vcpu, u32 new_tsr) update_timer_ints(vcpu); } -/* Initial guest state: 16MB mapping 0 -> 0, PC = 0, MSR = 0, R1 = 16MB */ -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) -{ - int i; - int r; - - vcpu->arch.regs.nip = 0; - vcpu->arch.shared->pir = vcpu->vcpu_id; - kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */ - kvmppc_set_msr(vcpu, 0); - -#ifndef CONFIG_KVM_BOOKE_HV - vcpu->arch.shadow_msr = MSR_USER | MSR_IS | MSR_DS; - vcpu->arch.shadow_pid = 1; - vcpu->arch.shared->msr = 0; -#endif - - /* Eye-catching numbers so we know if the guest takes an interrupt - * before it's programmed its own IVPR/IVORs. */ - vcpu->arch.ivpr = 0x55550000; - for (i = 0; i < BOOKE_IRQPRIO_MAX; i++) - vcpu->arch.ivor[i] = 0x7700 | i * 4; - - kvmppc_init_timing_stats(vcpu); - - r = kvmppc_core_vcpu_setup(vcpu); - kvmppc_sanity_check(vcpu); - return r; -} - int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu) { /* setup watchdog timer once */ @@ -2114,9 +2084,40 @@ int kvmppc_core_init_vm(struct kvm *kvm) return kvm->arch.kvm_ops->init_vm(kvm); } -struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) +int kvmppc_core_vcpu_create(struct kvm_vcpu *vcpu) { - return kvm->arch.kvm_ops->vcpu_create(kvm, id); + int i; + int r; + + r = vcpu->kvm->arch.kvm_ops->vcpu_create(vcpu); + if (r) + return r; + + /* Initial guest state: 16MB mapping 0 -> 0, PC = 0, MSR = 0, R1 = 16MB */ + vcpu->arch.regs.nip = 0; + vcpu->arch.shared->pir = vcpu->vcpu_id; + kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */ + kvmppc_set_msr(vcpu, 0); + +#ifndef CONFIG_KVM_BOOKE_HV + vcpu->arch.shadow_msr = MSR_USER | MSR_IS | MSR_DS; + vcpu->arch.shadow_pid = 1; + vcpu->arch.shared->msr = 0; +#endif + + /* Eye-catching numbers so we know if the guest takes an interrupt + * before it's programmed its own IVPR/IVORs. */ + vcpu->arch.ivpr = 0x55550000; + for (i = 0; i < BOOKE_IRQPRIO_MAX; i++) + vcpu->arch.ivor[i] = 0x7700 | i * 4; + + kvmppc_init_timing_stats(vcpu); + + r = kvmppc_core_vcpu_setup(vcpu); + if (r) + vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu); + kvmppc_sanity_check(vcpu); + return r; } void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index 00649ca5fa9a..f2b4feaff6d2 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -433,31 +433,16 @@ static int kvmppc_set_one_reg_e500(struct kvm_vcpu *vcpu, u64 id, return r; } -static struct kvm_vcpu *kvmppc_core_vcpu_create_e500(struct kvm *kvm, - unsigned int id) +static int kvmppc_core_vcpu_create_e500(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_e500 *vcpu_e500; - struct kvm_vcpu *vcpu; int err; - BUILD_BUG_ON_MSG(offsetof(struct kvmppc_vcpu_e500, vcpu) != 0, - "struct kvm_vcpu must be at offset 0 for arch usercopy region"); + BUILD_BUG_ON(offsetof(struct kvmppc_vcpu_e500, vcpu) != 0); + vcpu_e500 = to_e500(vcpu); - vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); - if (!vcpu_e500) { - err = -ENOMEM; - goto out; - } - - vcpu = &vcpu_e500->vcpu; - err = kvm_vcpu_init(vcpu, kvm, id); - if (err) - goto free_vcpu; - - if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL) { - err = -ENOMEM; - goto uninit_vcpu; - } + if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL) + return -ENOMEM; err = kvmppc_e500_tlb_init(vcpu_e500); if (err) @@ -469,18 +454,13 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_e500(struct kvm *kvm, goto uninit_tlb; } - return vcpu; + return 0; uninit_tlb: kvmppc_e500_tlb_uninit(vcpu_e500); uninit_id: kvmppc_e500_id_table_free(vcpu_e500); -uninit_vcpu: - kvm_vcpu_uninit(vcpu); -free_vcpu: - kmem_cache_free(kvm_vcpu_cache, vcpu_e500); -out: - return ERR_PTR(err); + return err; } static void kvmppc_core_vcpu_free_e500(struct kvm_vcpu *vcpu) @@ -490,8 +470,6 @@ static void kvmppc_core_vcpu_free_e500(struct kvm_vcpu *vcpu) free_page((unsigned long)vcpu->arch.shared); kvmppc_e500_tlb_uninit(vcpu_e500); kvmppc_e500_id_table_free(vcpu_e500); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(kvm_vcpu_cache, vcpu_e500); } static int kvmppc_core_init_vm_e500(struct kvm *kvm) diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 318e65c65999..e6b06cb2b92c 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -301,30 +301,20 @@ static int kvmppc_set_one_reg_e500mc(struct kvm_vcpu *vcpu, u64 id, return r; } -static struct kvm_vcpu *kvmppc_core_vcpu_create_e500mc(struct kvm *kvm, - unsigned int id) +static int kvmppc_core_vcpu_create_e500mc(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_e500 *vcpu_e500; - struct kvm_vcpu *vcpu; int err; - vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); - if (!vcpu_e500) { - err = -ENOMEM; - goto out; - } - vcpu = &vcpu_e500->vcpu; + BUILD_BUG_ON(offsetof(struct kvmppc_vcpu_e500, vcpu) != 0); + vcpu_e500 = to_e500(vcpu); /* Invalid PIR value -- this LPID dosn't have valid state on any cpu */ vcpu->arch.oldpir = 0xffffffff; - err = kvm_vcpu_init(vcpu, kvm, id); - if (err) - goto free_vcpu; - err = kvmppc_e500_tlb_init(vcpu_e500); if (err) - goto uninit_vcpu; + return err; vcpu->arch.shared = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO); if (!vcpu->arch.shared) { @@ -332,17 +322,11 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_e500mc(struct kvm *kvm, goto uninit_tlb; } - return vcpu; + return 0; uninit_tlb: kvmppc_e500_tlb_uninit(vcpu_e500); -uninit_vcpu: - kvm_vcpu_uninit(vcpu); - -free_vcpu: - kmem_cache_free(kvm_vcpu_cache, vcpu_e500); -out: - return ERR_PTR(err); + return err; } static void kvmppc_core_vcpu_free_e500mc(struct kvm_vcpu *vcpu) @@ -351,8 +335,6 @@ static void kvmppc_core_vcpu_free_e500mc(struct kvm_vcpu *vcpu) free_page((unsigned long)vcpu->arch.shared); kvmppc_e500_tlb_uninit(vcpu_e500); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(kvm_vcpu_cache, vcpu_e500); } static int kvmppc_core_init_vm_e500mc(struct kvm *kvm) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 416fb3d2a1d0..1af96fb5dc6f 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -475,7 +475,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) #endif kvm_for_each_vcpu(i, vcpu, kvm) - kvm_arch_vcpu_free(vcpu); + kvm_vcpu_destroy(vcpu); mutex_lock(&kvm->lock); for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) @@ -720,22 +720,55 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, kvmppc_core_flush_memslot(kvm, slot); } -struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) +{ + return 0; +} + +static enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer) { struct kvm_vcpu *vcpu; - vcpu = kvmppc_core_vcpu_create(kvm, id); - if (!IS_ERR(vcpu)) { - vcpu->arch.wqp = &vcpu->wq; - kvmppc_create_vcpu_debugfs(vcpu, id); - } - return vcpu; + + vcpu = container_of(timer, struct kvm_vcpu, arch.dec_timer); + kvmppc_decrementer_func(vcpu); + + return HRTIMER_NORESTART; +} + +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) +{ + int err; + + hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); + vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup; + vcpu->arch.dec_expires = get_tb(); + +#ifdef CONFIG_KVM_EXIT_TIMING + mutex_init(&vcpu->arch.exit_timing_lock); +#endif + err = kvmppc_subarch_vcpu_init(vcpu); + if (err) + return err; + + err = kvmppc_core_vcpu_create(vcpu); + if (err) + goto out_vcpu_uninit; + + vcpu->arch.wqp = &vcpu->wq; + kvmppc_create_vcpu_debugfs(vcpu, vcpu->vcpu_id); + return 0; + +out_vcpu_uninit: + kvmppc_mmu_destroy(vcpu); + kvmppc_subarch_vcpu_uninit(vcpu); + return err; } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { } -void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) +void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { /* Make sure we're not using the vcpu anymore */ hrtimer_cancel(&vcpu->arch.dec_timer); @@ -758,11 +791,9 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) } kvmppc_core_vcpu_free(vcpu); -} -void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) -{ - kvm_arch_vcpu_free(vcpu); + kvmppc_mmu_destroy(vcpu); + kvmppc_subarch_vcpu_uninit(vcpu); } int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) @@ -770,37 +801,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) return kvmppc_core_pending_dec(vcpu); } -static enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer) -{ - struct kvm_vcpu *vcpu; - - vcpu = container_of(timer, struct kvm_vcpu, arch.dec_timer); - kvmppc_decrementer_func(vcpu); - - return HRTIMER_NORESTART; -} - -int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) -{ - int ret; - - hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); - vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup; - vcpu->arch.dec_expires = get_tb(); - -#ifdef CONFIG_KVM_EXIT_TIMING - mutex_init(&vcpu->arch.exit_timing_lock); -#endif - ret = kvmppc_subarch_vcpu_init(vcpu); - return ret; -} - -void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) -{ - kvmppc_mmu_destroy(vcpu); - kvmppc_subarch_vcpu_uninit(vcpu); -} - void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { #ifdef CONFIG_BOOKE diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 617c2777926f..f5535eae637f 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -151,10 +151,9 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap); int ret; - __remove_pages(page_zone(page), start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); /* Remove htab bolted mappings for this section of memory */ start = (unsigned long)__va(start); diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 42bbcd47cc85..dffe1a45b6ed 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -50,7 +50,7 @@ static void slice_print_mask(const char *label, const struct slice_mask *mask) { #endif -static inline bool slice_addr_is_low(unsigned long addr) +static inline notrace bool slice_addr_is_low(unsigned long addr) { u64 tmp = (u64)addr; @@ -659,7 +659,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, mm_ctx_user_psize(¤t->mm->context), 1); } -unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr) +unsigned int notrace get_slice_psize(struct mm_struct *mm, unsigned long addr) { unsigned char *psizes; int index, mask_index; diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index d8efbaa78d67..a31169b02ec0 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -64,6 +64,7 @@ config RISCV select SPARSEMEM_STATIC if 32BIT select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU select HAVE_ARCH_MMAP_RND_BITS if MMU + select ARCH_HAS_GCOV_PROFILE_ALL config ARCH_MMAP_RND_BITS_MIN default 18 if 64BIT diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi index 70a1891e7cd0..a2e3d54e830c 100644 --- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -54,6 +54,7 @@ reg = <1>; riscv,isa = "rv64imafdc"; tlb-split; + next-level-cache = <&l2cache>; cpu1_intc: interrupt-controller { #interrupt-cells = <1>; compatible = "riscv,cpu-intc"; @@ -77,6 +78,7 @@ reg = <2>; riscv,isa = "rv64imafdc"; tlb-split; + next-level-cache = <&l2cache>; cpu2_intc: interrupt-controller { #interrupt-cells = <1>; compatible = "riscv,cpu-intc"; @@ -100,6 +102,7 @@ reg = <3>; riscv,isa = "rv64imafdc"; tlb-split; + next-level-cache = <&l2cache>; cpu3_intc: interrupt-controller { #interrupt-cells = <1>; compatible = "riscv,cpu-intc"; @@ -123,6 +126,7 @@ reg = <4>; riscv,isa = "rv64imafdc"; tlb-split; + next-level-cache = <&l2cache>; cpu4_intc: interrupt-controller { #interrupt-cells = <1>; compatible = "riscv,cpu-intc"; @@ -253,6 +257,17 @@ #pwm-cells = <3>; status = "disabled"; }; + l2cache: cache-controller@2010000 { + compatible = "sifive,fu540-c000-ccache", "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-sets = <1024>; + cache-size = <2097152>; + cache-unified; + interrupt-parent = <&plic0>; + interrupts = <1 2 3>; + reg = <0x0 0x2010000 0x0 0x1000>; + }; }; }; diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 0a62d2d68455..435b65532e29 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -116,9 +116,9 @@ # define SR_PIE SR_MPIE # define SR_PP SR_MPP -# define IRQ_SOFT IRQ_M_SOFT -# define IRQ_TIMER IRQ_M_TIMER -# define IRQ_EXT IRQ_M_EXT +# define RV_IRQ_SOFT IRQ_M_SOFT +# define RV_IRQ_TIMER IRQ_M_TIMER +# define RV_IRQ_EXT IRQ_M_EXT #else /* CONFIG_RISCV_M_MODE */ # define CSR_STATUS CSR_SSTATUS # define CSR_IE CSR_SIE @@ -133,15 +133,15 @@ # define SR_PIE SR_SPIE # define SR_PP SR_SPP -# define IRQ_SOFT IRQ_S_SOFT -# define IRQ_TIMER IRQ_S_TIMER -# define IRQ_EXT IRQ_S_EXT +# define RV_IRQ_SOFT IRQ_S_SOFT +# define RV_IRQ_TIMER IRQ_S_TIMER +# define RV_IRQ_EXT IRQ_S_EXT #endif /* CONFIG_RISCV_M_MODE */ /* IE/IP (Supervisor/Machine Interrupt Enable/Pending) flags */ -#define IE_SIE (_AC(0x1, UL) << IRQ_SOFT) -#define IE_TIE (_AC(0x1, UL) << IRQ_TIMER) -#define IE_EIE (_AC(0x1, UL) << IRQ_EXT) +#define IE_SIE (_AC(0x1, UL) << RV_IRQ_SOFT) +#define IE_TIE (_AC(0x1, UL) << RV_IRQ_TIMER) +#define IE_EIE (_AC(0x1, UL) << RV_IRQ_EXT) #ifndef __ASSEMBLY__ diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index b94d8db5ddcc..c40fdcdeb950 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -142,7 +142,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, */ old = *parent; - if (function_graph_enter(old, self_addr, frame_pointer, parent)) + if (!function_graph_enter(old, self_addr, frame_pointer, parent)) *parent = return_hooker; } diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c index 3f07a91d5afb..345c4f2eba13 100644 --- a/arch/riscv/kernel/irq.c +++ b/arch/riscv/kernel/irq.c @@ -23,11 +23,11 @@ asmlinkage __visible void __irq_entry do_IRQ(struct pt_regs *regs) irq_enter(); switch (regs->cause & ~CAUSE_IRQ_FLAG) { - case IRQ_TIMER: + case RV_IRQ_TIMER: riscv_timer_interrupt(); break; #ifdef CONFIG_SMP - case IRQ_SOFT: + case RV_IRQ_SOFT: /* * We only use software interrupts to pass IPIs, so if a non-SMP * system gets one, then we don't know what to do. @@ -35,7 +35,7 @@ asmlinkage __visible void __irq_entry do_IRQ(struct pt_regs *regs) riscv_software_interrupt(); break; #endif - case IRQ_EXT: + case RV_IRQ_EXT: handle_arch_irq(regs); break; default: diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 69f6678db7f3..965a8cf4829c 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -99,13 +99,13 @@ static void __init setup_initrd(void) pr_info("initrd not found or empty"); goto disable; } - if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) { + if (__pa_symbol(initrd_end) > PFN_PHYS(max_low_pfn)) { pr_err("initrd extends beyond end of memory"); goto disable; } size = initrd_end - initrd_start; - memblock_reserve(__pa(initrd_start), size); + memblock_reserve(__pa_symbol(initrd_start), size); initrd_below_start_ok = 1; pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n", @@ -124,8 +124,8 @@ void __init setup_bootmem(void) { struct memblock_region *reg; phys_addr_t mem_size = 0; - phys_addr_t vmlinux_end = __pa(&_end); - phys_addr_t vmlinux_start = __pa(&_start); + phys_addr_t vmlinux_end = __pa_symbol(&_end); + phys_addr_t vmlinux_start = __pa_symbol(&_start); /* Find the memory region containing the kernel */ for_each_memblock(memory, reg) { @@ -445,7 +445,7 @@ static void __init setup_vm_final(void) /* Setup swapper PGD for fixmap */ create_pgd_mapping(swapper_pg_dir, FIXADDR_START, - __pa(fixmap_pgd_next), + __pa_symbol(fixmap_pgd_next), PGDIR_SIZE, PAGE_TABLE); /* Map all memory banks */ @@ -474,7 +474,7 @@ static void __init setup_vm_final(void) clear_fixmap(FIX_PMD); /* Move to swapper page table */ - csr_write(CSR_SATP, PFN_DOWN(__pa(swapper_pg_dir)) | SATP_MODE); + csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | SATP_MODE); local_flush_tlb_all(); } #else diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 02f4c21c57f6..11ecc4071a29 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -914,7 +914,6 @@ extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc); static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} -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) {} diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d9e6bf3d54f0..8646c99217f2 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2530,9 +2530,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) if (vcpu->kvm->arch.use_cmma) kvm_s390_vcpu_unsetup_cmma(vcpu); free_page((unsigned long)(vcpu->arch.sie_block)); - - kvm_vcpu_uninit(vcpu); - kmem_cache_free(kvm_vcpu_cache, vcpu); } static void kvm_free_vcpus(struct kvm *kvm) @@ -2541,7 +2538,7 @@ static void kvm_free_vcpus(struct kvm *kvm) struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) - kvm_arch_vcpu_destroy(vcpu); + kvm_vcpu_destroy(vcpu); mutex_lock(&kvm->lock); for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) @@ -2703,39 +2700,6 @@ static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id) return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS; } -int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) -{ - vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; - kvm_clear_async_pf_completion_queue(vcpu); - vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX | - KVM_SYNC_GPRS | - KVM_SYNC_ACRS | - KVM_SYNC_CRS | - KVM_SYNC_ARCH0 | - KVM_SYNC_PFAULT; - kvm_s390_set_prefix(vcpu, 0); - if (test_kvm_facility(vcpu->kvm, 64)) - vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; - if (test_kvm_facility(vcpu->kvm, 82)) - vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC; - if (test_kvm_facility(vcpu->kvm, 133)) - vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB; - if (test_kvm_facility(vcpu->kvm, 156)) - vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN; - /* fprs can be synchronized via vrs, even if the guest has no vx. With - * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format. - */ - if (MACHINE_HAS_VX) - vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; - else - vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS; - - if (kvm_is_ucontrol(vcpu->kvm)) - return __kvm_ucontrol_vcpu_init(vcpu); - - return 0; -} - /* needs disabled preemption to protect from TOD sync and vcpu_load/put */ static void __start_cpu_timer_accounting(struct kvm_vcpu *vcpu) { @@ -2962,7 +2926,7 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->fac = (u32)(u64) model->fac_list; } -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) +static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu) { int rc = 0; @@ -3035,26 +2999,22 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) return rc; } -struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, - unsigned int id) +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { - struct kvm_vcpu *vcpu; - struct sie_page *sie_page; - int rc = -EINVAL; - if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id)) - goto out; - - rc = -ENOMEM; + return -EINVAL; + return 0; +} - vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); - if (!vcpu) - goto out; +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) +{ + struct sie_page *sie_page; + int rc; BUILD_BUG_ON(sizeof(struct sie_page) != 4096); sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL); if (!sie_page) - goto out_free_cpu; + return -ENOMEM; vcpu->arch.sie_block = &sie_page->sie_block; vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb; @@ -3063,27 +3023,59 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.sie_block->mso = 0; vcpu->arch.sie_block->msl = sclp.hamax; - vcpu->arch.sie_block->icpua = id; + vcpu->arch.sie_block->icpua = vcpu->vcpu_id; spin_lock_init(&vcpu->arch.local_int.lock); - vcpu->arch.sie_block->gd = (u32)(u64)kvm->arch.gisa_int.origin; + vcpu->arch.sie_block->gd = (u32)(u64)vcpu->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); - rc = kvm_vcpu_init(vcpu, kvm, id); + vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; + kvm_clear_async_pf_completion_queue(vcpu); + vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX | + KVM_SYNC_GPRS | + KVM_SYNC_ACRS | + KVM_SYNC_CRS | + KVM_SYNC_ARCH0 | + KVM_SYNC_PFAULT; + kvm_s390_set_prefix(vcpu, 0); + if (test_kvm_facility(vcpu->kvm, 64)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; + if (test_kvm_facility(vcpu->kvm, 82)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC; + if (test_kvm_facility(vcpu->kvm, 133)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB; + if (test_kvm_facility(vcpu->kvm, 156)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN; + /* fprs can be synchronized via vrs, even if the guest has no vx. With + * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format. + */ + if (MACHINE_HAS_VX) + vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; + else + vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS; + + if (kvm_is_ucontrol(vcpu->kvm)) { + rc = __kvm_ucontrol_vcpu_init(vcpu); + if (rc) + goto out_free_sie_block; + } + + VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", + vcpu->vcpu_id, vcpu, vcpu->arch.sie_block); + trace_kvm_s390_create_vcpu(vcpu->vcpu_id, vcpu, vcpu->arch.sie_block); + + rc = kvm_s390_vcpu_setup(vcpu); if (rc) - goto out_free_sie_block; - VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu, - vcpu->arch.sie_block); - trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block); + goto out_ucontrol_uninit; + return 0; - return vcpu; +out_ucontrol_uninit: + if (kvm_is_ucontrol(vcpu->kvm)) + gmap_remove(vcpu->arch.gmap); out_free_sie_block: free_page((unsigned long)(vcpu->arch.sie_block)); -out_free_cpu: - kmem_cache_free(kvm_vcpu_cache, vcpu); -out: - return ERR_PTR(rc); + return rc; } int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index f0ce22220565..ac44bd76db4b 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -292,10 +292,8 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); vmem_remove_mapping(start, size); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index dfdbaa50946e..d1b1ff2be17a 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -434,9 +434,7 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = PFN_DOWN(start); unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 77cf6c11f66b..03946eb3e2b9 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -222,6 +222,10 @@ struct x86_emulate_ops { bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool check_limit); + bool (*guest_has_long_mode)(struct x86_emulate_ctxt *ctxt); + bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt); + bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt); + void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked); unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b79cd6aa4075..69e31dbdfdc2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -175,6 +175,11 @@ enum { VCPU_SREG_LDTR, }; +enum exit_fastpath_completion { + EXIT_FASTPATH_NONE, + EXIT_FASTPATH_SKIP_EMUL_INS, +}; + #include <asm/kvm_emulate.h> #define KVM_NR_MEM_OBJS 40 @@ -378,12 +383,12 @@ struct kvm_mmu { void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root); unsigned long (*get_cr3)(struct kvm_vcpu *vcpu); u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); - int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err, + int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err, bool prefault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); - gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access, - struct x86_exception *exception); + gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa, + u32 access, struct x86_exception *exception); gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception); int (*sync_page)(struct kvm_vcpu *vcpu, @@ -606,7 +611,7 @@ struct kvm_vcpu_arch { * Paging state of an L2 guest (used for nested npt) * * This context will save all necessary information to walk page tables - * of the an L2 guest. This context is only initialized for page table + * of an L2 guest. This context is only initialized for page table * walking and not for faulting since we never handle l2 page faults on * the host. */ @@ -1022,6 +1027,11 @@ struct kvm_lapic_irq { bool msi_redir_hint; }; +static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical) +{ + return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL; +} + struct kvm_x86_ops { int (*cpu_has_kvm_support)(void); /* __init */ int (*disabled_by_bios)(void); /* __init */ @@ -1040,7 +1050,7 @@ struct kvm_x86_ops { void (*vm_destroy)(struct kvm *kvm); /* Create, but do not attach this VCPU */ - struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id); + int (*vcpu_create)(struct kvm_vcpu *vcpu); void (*vcpu_free)(struct kvm_vcpu *vcpu); void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event); @@ -1090,7 +1100,8 @@ struct kvm_x86_ops { void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr); void (*run)(struct kvm_vcpu *vcpu); - int (*handle_exit)(struct kvm_vcpu *vcpu); + int (*handle_exit)(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion exit_fastpath); int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu); @@ -1140,11 +1151,13 @@ struct kvm_x86_ops { int (*check_intercept)(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage); - void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu); + void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion *exit_fastpath); bool (*mpx_supported)(void); bool (*xsaves_supported)(void); bool (*umip_emulated)(void); bool (*pt_supported)(void); + bool (*pku_supported)(void); int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); void (*request_immediate_exit)(struct kvm_vcpu *vcpu); @@ -1468,7 +1481,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu); int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); -int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code, +int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); @@ -1614,7 +1627,6 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu); int kvm_is_in_guest(void); int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); -int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu); bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index b5e49e6bac63..b68f72adb53e 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -561,6 +561,10 @@ static inline void update_page_count(int level, unsigned long pages) { } extern pte_t *lookup_address(unsigned long address, unsigned int *level); extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level); + +struct mm_struct; +extern pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, + unsigned int *level); extern pmd_t *lookup_pmd_address(unsigned long address); extern phys_addr_t slow_virt_to_phys(void *__address); extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 1835767aa335..d716fe938fc0 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -19,8 +19,8 @@ /* * Definitions of Primary Processor-Based VM-Execution Controls. */ -#define CPU_BASED_VIRTUAL_INTR_PENDING 0x00000004 -#define CPU_BASED_USE_TSC_OFFSETING 0x00000008 +#define CPU_BASED_INTR_WINDOW_EXITING 0x00000004 +#define CPU_BASED_USE_TSC_OFFSETTING 0x00000008 #define CPU_BASED_HLT_EXITING 0x00000080 #define CPU_BASED_INVLPG_EXITING 0x00000200 #define CPU_BASED_MWAIT_EXITING 0x00000400 @@ -31,7 +31,7 @@ #define CPU_BASED_CR8_LOAD_EXITING 0x00080000 #define CPU_BASED_CR8_STORE_EXITING 0x00100000 #define CPU_BASED_TPR_SHADOW 0x00200000 -#define CPU_BASED_VIRTUAL_NMI_PENDING 0x00400000 +#define CPU_BASED_NMI_WINDOW_EXITING 0x00400000 #define CPU_BASED_MOV_DR_EXITING 0x00800000 #define CPU_BASED_UNCOND_IO_EXITING 0x01000000 #define CPU_BASED_USE_IO_BITMAPS 0x02000000 diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index 3eb8411ab60e..e95b72ec19bc 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -33,7 +33,7 @@ #define EXIT_REASON_TRIPLE_FAULT 2 #define EXIT_REASON_INIT_SIGNAL 3 -#define EXIT_REASON_PENDING_INTERRUPT 7 +#define EXIT_REASON_INTERRUPT_WINDOW 7 #define EXIT_REASON_NMI_WINDOW 8 #define EXIT_REASON_TASK_SWITCH 9 #define EXIT_REASON_CPUID 10 @@ -94,7 +94,7 @@ { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ { EXIT_REASON_INIT_SIGNAL, "INIT_SIGNAL" }, \ - { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \ + { EXIT_REASON_INTERRUPT_WINDOW, "INTERRUPT_WINDOW" }, \ { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ { EXIT_REASON_CPUID, "CPUID" }, \ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index cf55629ff0ff..b1c469446b07 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -62,7 +62,7 @@ u64 kvm_supported_xcr0(void) return xcr0; } -#define F(x) bit(X86_FEATURE_##x) +#define F feature_bit int kvm_update_cpuid(struct kvm_vcpu *vcpu) { @@ -281,8 +281,9 @@ out: return r; } -static void cpuid_mask(u32 *word, int wordnum) +static __always_inline void cpuid_mask(u32 *word, int wordnum) { + reverse_cpuid_check(wordnum); *word &= boot_cpu_data.x86_capability[wordnum]; } @@ -352,6 +353,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0; unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0; unsigned f_la57; + unsigned f_pku = kvm_x86_ops->pku_supported() ? F(PKU) : 0; /* cpuid 7.0.ebx */ const u32 kvm_cpuid_7_0_ebx_x86_features = @@ -363,7 +365,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) | + F(AVX512VBMI) | F(LA57) | 0 /*PKU*/ | 0 /*OSPKE*/ | F(RDPID) | F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/; @@ -392,6 +394,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) /* Set LA57 based on hardware capability. */ entry->ecx |= f_la57; entry->ecx |= f_umip; + entry->ecx |= f_pku; /* PKU is not yet implemented for shadow paging. */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index d78a61408243..7366c618aa04 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -53,15 +53,46 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_7_ECX] = { 7, 0, CPUID_ECX}, [CPUID_8000_0007_EBX] = {0x80000007, 0, CPUID_EBX}, [CPUID_7_EDX] = { 7, 0, CPUID_EDX}, + [CPUID_7_1_EAX] = { 7, 1, CPUID_EAX}, }; -static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) +/* + * Reverse CPUID and its derivatives can only be used for hardware-defined + * feature words, i.e. words whose bits directly correspond to a CPUID leaf. + * Retrieving a feature bit or masking guest CPUID from a Linux-defined word + * is nonsensical as the bit number/mask is an arbitrary software-defined value + * and can't be used by KVM to query/control guest capabilities. And obviously + * the leaf being queried must have an entry in the lookup table. + */ +static __always_inline void reverse_cpuid_check(unsigned x86_leaf) { - unsigned x86_leaf = x86_feature / 32; - + BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_3); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_4); BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid)); BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0); +} + +/* + * Retrieve the bit mask from an X86_FEATURE_* definition. Features contain + * the hardware defined bit number (stored in bits 4:0) and a software defined + * "word" (stored in bits 31:5). The word is used to index into arrays of + * bit masks that hold the per-cpu feature capabilities, e.g. this_cpu_has(). + */ +static __always_inline u32 __feature_bit(int x86_feature) +{ + reverse_cpuid_check(x86_feature / 32); + return 1 << (x86_feature & 31); +} +#define feature_bit(name) __feature_bit(X86_FEATURE_##name) + +static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) +{ + unsigned x86_leaf = x86_feature / 32; + + reverse_cpuid_check(x86_leaf); return reverse_cpuid[x86_leaf]; } @@ -93,15 +124,11 @@ static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, unsigned x86_ { int *reg; - if (x86_feature == X86_FEATURE_XSAVE && - !static_cpu_has(X86_FEATURE_XSAVE)) - return false; - reg = guest_cpuid_get_register(vcpu, x86_feature); if (!reg) return false; - return *reg & bit(x86_feature); + return *reg & __feature_bit(x86_feature); } static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, unsigned x86_feature) @@ -110,7 +137,7 @@ static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, unsigned x8 reg = guest_cpuid_get_register(vcpu, x86_feature); if (reg) - *reg &= ~bit(x86_feature); + *reg &= ~__feature_bit(x86_feature); } static inline bool guest_cpuid_is_amd(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 952d1a4f4d7e..ddbc61984227 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -22,6 +22,7 @@ #include "kvm_cache_regs.h" #include <asm/kvm_emulate.h> #include <linux/stringify.h> +#include <asm/fpu/api.h> #include <asm/debugreg.h> #include <asm/nospec-branch.h> @@ -310,7 +311,9 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) #define ON64(x) #endif -static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); +typedef void (*fastop_t)(struct fastop *); + +static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); #define __FOP_FUNC(name) \ ".align " __stringify(FASTOP_SIZE) " \n\t" \ @@ -1075,8 +1078,23 @@ static void fetch_register_operand(struct operand *op) } } -static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) +static void emulator_get_fpu(void) +{ + fpregs_lock(); + + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); +} + +static void emulator_put_fpu(void) { + fpregs_unlock(); +} + +static void read_sse_reg(sse128_t *data, int reg) +{ + emulator_get_fpu(); switch (reg) { case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break; case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break; @@ -1098,11 +1116,12 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) #endif default: BUG(); } + emulator_put_fpu(); } -static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, - int reg) +static void write_sse_reg(sse128_t *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break; case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break; @@ -1124,10 +1143,12 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, #endif default: BUG(); } + emulator_put_fpu(); } -static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) +static void read_mmx_reg(u64 *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movq %%mm0, %0" : "=m"(*data)); break; case 1: asm("movq %%mm1, %0" : "=m"(*data)); break; @@ -1139,10 +1160,12 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) case 7: asm("movq %%mm7, %0" : "=m"(*data)); break; default: BUG(); } + emulator_put_fpu(); } -static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) +static void write_mmx_reg(u64 *data, int reg) { + emulator_get_fpu(); switch (reg) { case 0: asm("movq %0, %%mm0" : : "m"(*data)); break; case 1: asm("movq %0, %%mm1" : : "m"(*data)); break; @@ -1154,6 +1177,7 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) case 7: asm("movq %0, %%mm7" : : "m"(*data)); break; default: BUG(); } + emulator_put_fpu(); } static int em_fninit(struct x86_emulate_ctxt *ctxt) @@ -1161,7 +1185,9 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fninit"); + emulator_put_fpu(); return X86EMUL_CONTINUE; } @@ -1172,7 +1198,9 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fnstcw %0": "+m"(fcw)); + emulator_put_fpu(); ctxt->dst.val = fcw; @@ -1186,7 +1214,9 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt) if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); + emulator_get_fpu(); asm volatile("fnstsw %0": "+m"(fsw)); + emulator_put_fpu(); ctxt->dst.val = fsw; @@ -1205,7 +1235,7 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, op->type = OP_XMM; op->bytes = 16; op->addr.xmm = reg; - read_sse_reg(ctxt, &op->vec_val, reg); + read_sse_reg(&op->vec_val, reg); return; } if (ctxt->d & Mmx) { @@ -1256,7 +1286,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, op->type = OP_XMM; op->bytes = 16; op->addr.xmm = ctxt->modrm_rm; - read_sse_reg(ctxt, &op->vec_val, ctxt->modrm_rm); + read_sse_reg(&op->vec_val, ctxt->modrm_rm); return rc; } if (ctxt->d & Mmx) { @@ -1833,10 +1863,10 @@ static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) op->bytes * op->count); break; case OP_XMM: - write_sse_reg(ctxt, &op->vec_val, op->addr.xmm); + write_sse_reg(&op->vec_val, op->addr.xmm); break; case OP_MM: - write_mmx_reg(ctxt, &op->mm_val, op->addr.mm); + write_mmx_reg(&op->mm_val, op->addr.mm); break; case OP_NONE: /* no writeback */ @@ -2348,12 +2378,7 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt) static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt) { #ifdef CONFIG_X86_64 - u32 eax, ebx, ecx, edx; - - eax = 0x80000001; - ecx = 0; - ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); - return edx & bit(X86_FEATURE_LM); + return ctxt->ops->guest_has_long_mode(ctxt); #else return false; #endif @@ -3618,18 +3643,11 @@ static int em_mov(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -#define FFL(x) bit(X86_FEATURE_##x) - static int em_movbe(struct x86_emulate_ctxt *ctxt) { - u32 ebx, ecx, edx, eax = 1; u16 tmp; - /* - * Check MOVBE is set in the guest-visible CPUID leaf. - */ - ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); - if (!(ecx & FFL(MOVBE))) + if (!ctxt->ops->guest_has_movbe(ctxt)) return emulate_ud(ctxt); switch (ctxt->op_bytes) { @@ -4027,10 +4045,7 @@ static int em_movsxd(struct x86_emulate_ctxt *ctxt) static int check_fxsr(struct x86_emulate_ctxt *ctxt) { - u32 eax = 1, ebx, ecx = 0, edx; - - ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); - if (!(edx & FFL(FXSR))) + if (!ctxt->ops->guest_has_fxsr(ctxt)) return emulate_ud(ctxt); if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) @@ -4092,8 +4107,12 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; + emulator_get_fpu(); + rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); + emulator_put_fpu(); + if (rc != X86EMUL_CONTINUE) return rc; @@ -4136,6 +4155,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; + emulator_get_fpu(); + if (size < __fxstate_size(16)) { rc = fxregs_fixup(&fx_state, size); if (rc != X86EMUL_CONTINUE) @@ -4151,6 +4172,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); out: + emulator_put_fpu(); + return rc; } @@ -5210,16 +5233,28 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) ctxt->ad_bytes = def_ad_bytes ^ 6; break; case 0x26: /* ES override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_ES; + break; case 0x2e: /* CS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_CS; + break; case 0x36: /* SS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_SS; + break; case 0x3e: /* DS override */ has_seg_override = true; - ctxt->seg_override = (ctxt->b >> 3) & 3; + ctxt->seg_override = VCPU_SREG_DS; break; case 0x64: /* FS override */ + has_seg_override = true; + ctxt->seg_override = VCPU_SREG_FS; + break; case 0x65: /* GS override */ has_seg_override = true; - ctxt->seg_override = ctxt->b & 7; + ctxt->seg_override = VCPU_SREG_GS; break; case 0x40 ... 0x4f: /* REX */ if (mode != X86EMUL_MODE_PROT64) @@ -5303,10 +5338,15 @@ done_prefixes: } break; case Escape: - if (ctxt->modrm > 0xbf) - opcode = opcode.u.esc->high[ctxt->modrm - 0xc0]; - else + if (ctxt->modrm > 0xbf) { + size_t size = ARRAY_SIZE(opcode.u.esc->high); + u32 index = array_index_nospec( + ctxt->modrm - 0xc0, size); + + opcode = opcode.u.esc->high[index]; + } else { opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7]; + } break; case InstrDual: if ((ctxt->modrm >> 6) == 3) @@ -5448,7 +5488,9 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) { int rc; + emulator_get_fpu(); rc = asm_safe("fwait"); + emulator_put_fpu(); if (unlikely(rc != X86EMUL_CONTINUE)) return emulate_exception(ctxt, MF_VECTOR, 0, false); @@ -5456,14 +5498,13 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, - struct operand *op) +static void fetch_possible_mmx_operand(struct operand *op) { if (op->type == OP_MM) - read_mmx_reg(ctxt, &op->mm_val, op->addr.mm); + read_mmx_reg(&op->mm_val, op->addr.mm); } -static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) +static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop) { ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; @@ -5539,10 +5580,10 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) * Now that we know the fpu is exception safe, we can fetch * operands from it. */ - fetch_possible_mmx_operand(ctxt, &ctxt->src); - fetch_possible_mmx_operand(ctxt, &ctxt->src2); + fetch_possible_mmx_operand(&ctxt->src); + fetch_possible_mmx_operand(&ctxt->src2); if (!(ctxt->d & Mov)) - fetch_possible_mmx_operand(ctxt, &ctxt->dst); + fetch_possible_mmx_operand(&ctxt->dst); } if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) { @@ -5641,14 +5682,10 @@ special_insn: ctxt->eflags &= ~X86_EFLAGS_RF; if (ctxt->execute) { - if (ctxt->d & Fastop) { - void (*fop)(struct fastop *) = (void *)ctxt->execute; - rc = fastop(ctxt, fop); - if (rc != X86EMUL_CONTINUE) - goto done; - goto writeback; - } - rc = ctxt->execute(ctxt); + if (ctxt->d & Fastop) + rc = fastop(ctxt, (fastop_t)ctxt->execute); + else + rc = ctxt->execute(ctxt); if (rc != X86EMUL_CONTINUE) goto done; goto writeback; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 23ff65504d7e..4df1c965bf1a 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -33,6 +33,7 @@ #include <trace/events/kvm.h> #include "trace.h" +#include "irq.h" #define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64) @@ -809,11 +810,12 @@ static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu, u32 index, u64 *pdata) { struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + size_t size = ARRAY_SIZE(hv->hv_crash_param); - if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + if (WARN_ON_ONCE(index >= size)) return -EINVAL; - *pdata = hv->hv_crash_param[index]; + *pdata = hv->hv_crash_param[array_index_nospec(index, size)]; return 0; } @@ -852,11 +854,12 @@ static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu, u32 index, u64 data) { struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + size_t size = ARRAY_SIZE(hv->hv_crash_param); - if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + if (WARN_ON_ONCE(index >= size)) return -EINVAL; - hv->hv_crash_param[index] = data; + hv->hv_crash_param[array_index_nospec(index, size)] = data; return 0; } @@ -1058,7 +1061,7 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, return 1; break; default: - vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", + vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", msr, data); return 1; } @@ -1121,7 +1124,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; /* - * Clear apic_assist portion of f(struct hv_vp_assist_page + * Clear apic_assist portion of struct hv_vp_assist_page * only, there can be valuable data in the rest which needs * to be preserved e.g. on migration. */ @@ -1178,7 +1181,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; break; default: - vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", + vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", msr, data); return 1; } diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 8b38bb4868a6..629a09ca9860 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -460,10 +460,14 @@ static int picdev_write(struct kvm_pic *s, switch (addr) { case 0x20: case 0x21: + pic_lock(s); + pic_ioport_write(&s->pics[0], addr, data); + pic_unlock(s); + break; case 0xa0: case 0xa1: pic_lock(s); - pic_ioport_write(&s->pics[addr >> 7], addr, data); + pic_ioport_write(&s->pics[1], addr, data); pic_unlock(s); break; case 0x4d0: diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 9fd2dd89a1c5..26aa22cb9b29 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -36,6 +36,7 @@ #include <linux/io.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/nospec.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/current.h> @@ -68,13 +69,14 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, default: { u32 redir_index = (ioapic->ioregsel - 0x10) >> 1; - u64 redir_content; + u64 redir_content = ~0ULL; - if (redir_index < IOAPIC_NUM_PINS) - redir_content = - ioapic->redirtbl[redir_index].bits; - else - redir_content = ~0ULL; + if (redir_index < IOAPIC_NUM_PINS) { + u32 index = array_index_nospec( + redir_index, IOAPIC_NUM_PINS); + + redir_content = ioapic->redirtbl[index].bits; + } result = (ioapic->ioregsel & 0x1) ? (redir_content >> 32) & 0xffffffff : @@ -108,8 +110,9 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu) union kvm_ioapic_redirect_entry *e; e = &ioapic->redirtbl[RTC_GSI]; - if (!kvm_apic_match_dest(vcpu, NULL, 0, e->fields.dest_id, - e->fields.dest_mode)) + if (!kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, + e->fields.dest_id, + kvm_lapic_irq_dest_mode(!!e->fields.dest_mode))) return; new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector); @@ -188,7 +191,7 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, /* * Return 0 for coalesced interrupts; for edge-triggered interrupts, * this only happens if a previous edge has not been delivered due - * do masking. For level interrupts, the remote_irr field tells + * to masking. For level interrupts, the remote_irr field tells * us if the interrupt is waiting for an EOI. * * RTC is special: it is edge-triggered, but userspace likes to know @@ -250,8 +253,10 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors) if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG || kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) || index == RTC_GSI) { - if (kvm_apic_match_dest(vcpu, NULL, 0, - e->fields.dest_id, e->fields.dest_mode) || + u16 dm = kvm_lapic_irq_dest_mode(!!e->fields.dest_mode); + + if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, + e->fields.dest_id, dm) || kvm_apic_pending_eoi(vcpu, e->fields.vector)) __set_bit(e->fields.vector, ioapic_handled_vectors); @@ -292,6 +297,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) if (index >= IOAPIC_NUM_PINS) return; + index = array_index_nospec(index, IOAPIC_NUM_PINS); e = &ioapic->redirtbl[index]; mask_before = e->fields.mask; /* Preserve read-only fields */ @@ -327,11 +333,12 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) if (e->fields.delivery_mode == APIC_DM_FIXED) { struct kvm_lapic_irq irq; - irq.shorthand = 0; + irq.shorthand = APIC_DEST_NOSHORT; irq.vector = e->fields.vector; irq.delivery_mode = e->fields.delivery_mode << 8; irq.dest_id = e->fields.dest_id; - irq.dest_mode = e->fields.dest_mode; + irq.dest_mode = + kvm_lapic_irq_dest_mode(!!e->fields.dest_mode); bitmap_zero(&vcpu_bitmap, 16); kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, &vcpu_bitmap); @@ -343,7 +350,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) * keep ioapic_handled_vectors synchronized. */ irq.dest_id = old_dest_id; - irq.dest_mode = old_dest_mode; + irq.dest_mode = + kvm_lapic_irq_dest_mode( + !!e->fields.dest_mode); kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, &vcpu_bitmap); } @@ -369,11 +378,11 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status) irqe.dest_id = entry->fields.dest_id; irqe.vector = entry->fields.vector; - irqe.dest_mode = entry->fields.dest_mode; + irqe.dest_mode = kvm_lapic_irq_dest_mode(!!entry->fields.dest_mode); irqe.trig_mode = entry->fields.trig_mode; irqe.delivery_mode = entry->fields.delivery_mode << 8; irqe.level = 1; - irqe.shorthand = 0; + irqe.shorthand = APIC_DEST_NOSHORT; irqe.msi_redir_hint = false; if (irqe.trig_mode == IOAPIC_EDGE_TRIG) diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index ea1a4e0297da..2fb2e3c80724 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -116,9 +116,6 @@ static inline int ioapic_in_kernel(struct kvm *kvm) } void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); -bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, - int short_hand, unsigned int dest, int dest_mode); -int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode); int kvm_ioapic_init(struct kvm *kvm); @@ -126,9 +123,6 @@ void kvm_ioapic_destroy(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, int level, bool line_status); void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id); -int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, - struct dest_map *dest_map); void kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); void kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 7c6233d37c64..f173ab6b407e 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -113,5 +113,8 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu); int kvm_setup_default_irq_routing(struct kvm *kvm); int kvm_setup_empty_irq_routing(struct kvm *kvm); +int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, + struct kvm_lapic_irq *irq, + struct dest_map *dest_map); #endif diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 8ecd48d31800..79afa0bb5f41 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -52,15 +52,15 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; unsigned int dest_vcpus = 0; - if (irq->dest_mode == 0 && irq->dest_id == 0xff && - kvm_lowest_prio_delivery(irq)) { + if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) + return r; + + if (irq->dest_mode == APIC_DEST_PHYSICAL && + irq->dest_id == 0xff && kvm_lowest_prio_delivery(irq)) { printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); irq->delivery_mode = APIC_DM_FIXED; } - if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) - return r; - memset(dest_vcpu_bitmap, 0, sizeof(dest_vcpu_bitmap)); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -114,13 +114,14 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, irq->dest_id |= MSI_ADDR_EXT_DEST_ID(e->msi.address_hi); irq->vector = (e->msi.data & MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT; - irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo; + irq->dest_mode = kvm_lapic_irq_dest_mode( + !!((1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo)); irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data; irq->delivery_mode = e->msi.data & 0x700; irq->msi_redir_hint = ((e->msi.address_lo & MSI_ADDR_REDIRECTION_LOWPRI) > 0); irq->level = 1; - irq->shorthand = 0; + irq->shorthand = APIC_DEST_NOSHORT; } EXPORT_SYMBOL_GPL(kvm_set_msi_irq); @@ -416,7 +417,8 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); - if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0, + if (irq.level && + kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, irq.dest_id, irq.dest_mode)) __set_bit(irq.vector, ioapic_handled_vectors); } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index cf9177b4a07f..cce1e6b204c8 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -56,9 +56,6 @@ #define APIC_VERSION (0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16)) #define LAPIC_MMIO_LENGTH (1 << 12) /* followed define is not in apicdef.h */ -#define APIC_SHORT_MASK 0xc0000 -#define APIC_DEST_NOSHORT 0x0 -#define APIC_DEST_MASK 0x800 #define MAX_APIC_VECTOR 256 #define APIC_VECTORS_PER_REG 32 @@ -792,13 +789,13 @@ static u32 kvm_apic_mda(struct kvm_vcpu *vcpu, unsigned int dest_id, } bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, - int short_hand, unsigned int dest, int dest_mode) + int shorthand, unsigned int dest, int dest_mode) { struct kvm_lapic *target = vcpu->arch.apic; u32 mda = kvm_apic_mda(vcpu, dest, source, target); ASSERT(target); - switch (short_hand) { + switch (shorthand) { case APIC_DEST_NOSHORT: if (dest_mode == APIC_DEST_PHYSICAL) return kvm_apic_match_physical_addr(target, mda); @@ -967,12 +964,12 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, } /* - * This routine tries to handler interrupts in posted mode, here is how + * This routine tries to handle interrupts in posted mode, here is how * it deals with different cases: * - For single-destination interrupts, handle it in posted mode * - Else if vector hashing is enabled and it is a lowest-priority * interrupt, handle it in posted mode and use the following mechanism - * to find the destinaiton vCPU. + * to find the destination vCPU. * 1. For lowest-priority interrupts, store all the possible * destination vCPUs in an array. * 2. Use "guest vector % max number of destination vCPUs" to find @@ -1151,7 +1148,7 @@ void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, if (!kvm_apic_present(vcpu)) continue; if (!kvm_apic_match_dest(vcpu, NULL, - irq->delivery_mode, + irq->shorthand, irq->dest_id, irq->dest_mode)) continue; @@ -1574,9 +1571,9 @@ static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic) struct kvm_timer *ktimer = &apic->lapic_timer; kvm_apic_local_deliver(apic, APIC_LVTT); - if (apic_lvtt_tscdeadline(apic)) + if (apic_lvtt_tscdeadline(apic)) { ktimer->tscdeadline = 0; - if (apic_lvtt_oneshot(apic)) { + } else if (apic_lvtt_oneshot(apic)) { ktimer->tscdeadline = 0; ktimer->target_expiration = 0; } @@ -1963,15 +1960,20 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_LVTTHMR: case APIC_LVTPC: case APIC_LVT1: - case APIC_LVTERR: + case APIC_LVTERR: { /* TODO: Check vector */ + size_t size; + u32 index; + if (!kvm_apic_sw_enabled(apic)) val |= APIC_LVT_MASKED; - - val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4]; + size = ARRAY_SIZE(apic_lvt_mask); + index = array_index_nospec( + (reg - APIC_LVTT) >> 4, size); + val &= apic_lvt_mask[index]; kvm_lapic_set_reg(apic, reg, val); - break; + } case APIC_LVTT: if (!kvm_apic_sw_enabled(apic)) @@ -2373,14 +2375,13 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) { u32 lvt0 = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LVT0); - int r = 0; if (!kvm_apic_hw_enabled(vcpu->arch.apic)) - r = 1; + return 1; if ((lvt0 & APIC_LVT_MASKED) == 0 && GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT) - r = 1; - return r; + return 1; + return 0; } void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 39925afdfcdc..ec730ce7a344 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -10,8 +10,9 @@ #define KVM_APIC_SIPI 1 #define KVM_APIC_LVT_NUM 6 -#define KVM_APIC_SHORT_MASK 0xc0000 -#define KVM_APIC_DEST_MASK 0x800 +#define APIC_SHORT_MASK 0xc0000 +#define APIC_DEST_NOSHORT 0x0 +#define APIC_DEST_MASK 0x800 #define APIC_BUS_CYCLE_NS 1 #define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS) @@ -82,8 +83,8 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val); int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, void *data); bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, - int short_hand, unsigned int dest, int dest_mode); - + int shorthand, unsigned int dest, int dest_mode); +int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr); bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr); void kvm_apic_update_ppr(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6f92b40d798c..84eeb61d06aa 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -418,22 +418,24 @@ static inline bool is_access_track_spte(u64 spte) * requires a full MMU zap). The flag is instead explicitly queried when * checking for MMIO spte cache hits. */ -#define MMIO_SPTE_GEN_MASK GENMASK_ULL(18, 0) +#define MMIO_SPTE_GEN_MASK GENMASK_ULL(17, 0) #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) -#define MMIO_SPTE_GEN_HIGH_START 52 -#define MMIO_SPTE_GEN_HIGH_END 61 +#define MMIO_SPTE_GEN_HIGH_START PT64_SECOND_AVAIL_BITS_SHIFT +#define MMIO_SPTE_GEN_HIGH_END 62 #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_SPTE_GEN_MASK); + BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK); mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK; mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK; @@ -444,8 +446,6 @@ static u64 get_mmio_spte_generation(u64 spte) { u64 gen; - spte &= ~shadow_mmio_mask; - 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; @@ -538,16 +538,20 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); static u8 kvm_get_shadow_phys_bits(void) { /* - * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected - * in CPU detection code, but MKTME treats those reduced bits as - * 'keyID' thus they are not reserved bits. Therefore for MKTME - * we should still return physical address bits reported by CPUID. + * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected + * in CPU detection code, but the processor treats those reduced bits as + * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at + * the physical address bits reported by CPUID. */ - if (!boot_cpu_has(X86_FEATURE_TME) || - WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008)) - return boot_cpu_data.x86_phys_bits; + if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008)) + return cpuid_eax(0x80000008) & 0xff; - return cpuid_eax(0x80000008) & 0xff; + /* + * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with + * custom CPUID. Proceed with whatever the kernel found since these features + * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008). + */ + return boot_cpu_data.x86_phys_bits; } static void kvm_mmu_reset_all_pte_masks(void) @@ -1260,56 +1264,6 @@ static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) list_del(&sp->lpage_disallowed_link); } -static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level, - struct kvm_memory_slot *slot) -{ - struct kvm_lpage_info *linfo; - - if (slot) { - linfo = lpage_info_slot(gfn, slot, level); - return !!linfo->disallow_lpage; - } - - return true; -} - -static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn, - int level) -{ - struct kvm_memory_slot *slot; - - slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - return __mmu_gfn_lpage_is_disallowed(gfn, level, slot); -} - -static int host_mapping_level(struct kvm *kvm, gfn_t gfn) -{ - unsigned long page_size; - int i, ret = 0; - - page_size = kvm_host_page_size(kvm, gfn); - - for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { - if (page_size >= KVM_HPAGE_SIZE(i)) - ret = i; - else - break; - } - - return ret; -} - -static inline bool memslot_valid_for_gpte(struct kvm_memory_slot *slot, - bool no_dirty_log) -{ - if (!slot || slot->flags & KVM_MEMSLOT_INVALID) - return false; - if (no_dirty_log && slot->dirty_bitmap) - return false; - - return true; -} - static struct kvm_memory_slot * gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) @@ -1317,40 +1271,14 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_memory_slot *slot; slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - if (!memslot_valid_for_gpte(slot, no_dirty_log)) - slot = NULL; + if (!slot || slot->flags & KVM_MEMSLOT_INVALID) + return NULL; + if (no_dirty_log && slot->dirty_bitmap) + return NULL; return slot; } -static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn, - bool *force_pt_level) -{ - int host_level, level, max_level; - struct kvm_memory_slot *slot; - - if (unlikely(*force_pt_level)) - return PT_PAGE_TABLE_LEVEL; - - slot = kvm_vcpu_gfn_to_memslot(vcpu, large_gfn); - *force_pt_level = !memslot_valid_for_gpte(slot, true); - if (unlikely(*force_pt_level)) - return PT_PAGE_TABLE_LEVEL; - - host_level = host_mapping_level(vcpu->kvm, large_gfn); - - if (host_level == PT_PAGE_TABLE_LEVEL) - return host_level; - - max_level = min(kvm_x86_ops->get_lpage_level(), host_level); - - for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level) - if (__mmu_gfn_lpage_is_disallowed(large_gfn, level, slot)) - break; - - return level - 1; -} - /* * About rmap_head encoding: * @@ -1410,7 +1338,7 @@ pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, if (j != 0) return; if (!prev_desc && !desc->more) - rmap_head->val = (unsigned long)desc->sptes[0]; + rmap_head->val = 0; else if (prev_desc) prev_desc->more = desc->more; @@ -1525,7 +1453,7 @@ struct rmap_iterator { /* * Iteration must be started by this function. This should also be used after * removing/dropping sptes from the rmap link because in such cases the - * information in the itererator may not be valid. + * information in the iterator may not be valid. * * Returns sptep if found, NULL otherwise. */ @@ -2899,6 +2827,26 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm, return kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); } +static int make_mmu_pages_available(struct kvm_vcpu *vcpu) +{ + LIST_HEAD(invalid_list); + + if (likely(kvm_mmu_available_pages(vcpu->kvm) >= KVM_MIN_FREE_MMU_PAGES)) + return 0; + + while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES) { + if (!prepare_zap_oldest_mmu_page(vcpu->kvm, &invalid_list)) + break; + + ++vcpu->kvm->stat.mmu_recycled; + } + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); + + if (!kvm_mmu_available_pages(vcpu->kvm)) + return -ENOSPC; + return 0; +} + /* * Changing the number of mmu pages allocated to the vm * Note: if goal_nr_mmu_pages is too small, you will get dead lock @@ -3099,17 +3047,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= (u64)pfn << PAGE_SHIFT; if (pte_access & ACC_WRITE_MASK) { - - /* - * Other vcpu creates new sp in the window between - * mapping_level() and acquiring mmu-lock. We can - * allow guest to retry the access, the mapping can - * be fixed if guest refault. - */ - if (level > PT_PAGE_TABLE_LEVEL && - mmu_gfn_lpage_is_disallowed(vcpu, gfn, level)) - goto done; - spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE; /* @@ -3141,7 +3078,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, set_pte: if (mmu_spte_update(sptep, spte)) ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH; -done: return ret; } @@ -3294,6 +3230,83 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) __direct_pte_prefetch(vcpu, sp, sptep); } +static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn, + kvm_pfn_t pfn, struct kvm_memory_slot *slot) +{ + unsigned long hva; + pte_t *pte; + int level; + + BUILD_BUG_ON(PT_PAGE_TABLE_LEVEL != (int)PG_LEVEL_4K || + PT_DIRECTORY_LEVEL != (int)PG_LEVEL_2M || + PT_PDPE_LEVEL != (int)PG_LEVEL_1G); + + if (!PageCompound(pfn_to_page(pfn)) && !kvm_is_zone_device_pfn(pfn)) + return PT_PAGE_TABLE_LEVEL; + + /* + * Note, using the already-retrieved memslot and __gfn_to_hva_memslot() + * is not solely for performance, it's also necessary to avoid the + * "writable" check in __gfn_to_hva_many(), which will always fail on + * read-only memslots due to gfn_to_hva() assuming writes. Earlier + * page fault steps have already verified the guest isn't writing a + * read-only memslot. + */ + hva = __gfn_to_hva_memslot(slot, gfn); + + pte = lookup_address_in_mm(vcpu->kvm->mm, hva, &level); + if (unlikely(!pte)) + return PT_PAGE_TABLE_LEVEL; + + return level; +} + +static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, + int max_level, kvm_pfn_t *pfnp) +{ + struct kvm_memory_slot *slot; + struct kvm_lpage_info *linfo; + kvm_pfn_t pfn = *pfnp; + kvm_pfn_t mask; + int level; + + if (unlikely(max_level == PT_PAGE_TABLE_LEVEL)) + return PT_PAGE_TABLE_LEVEL; + + if (is_error_noslot_pfn(pfn) || kvm_is_reserved_pfn(pfn)) + return PT_PAGE_TABLE_LEVEL; + + slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, true); + if (!slot) + return PT_PAGE_TABLE_LEVEL; + + max_level = min(max_level, kvm_x86_ops->get_lpage_level()); + for ( ; max_level > PT_PAGE_TABLE_LEVEL; max_level--) { + linfo = lpage_info_slot(gfn, slot, max_level); + if (!linfo->disallow_lpage) + break; + } + + if (max_level == PT_PAGE_TABLE_LEVEL) + return PT_PAGE_TABLE_LEVEL; + + level = host_pfn_mapping_level(vcpu, gfn, pfn, slot); + if (level == PT_PAGE_TABLE_LEVEL) + return level; + + level = min(level, max_level); + + /* + * mmu_notifier_retry() was successful and mmu_lock is held, so + * the pmd can't be split from under us. + */ + mask = KVM_PAGES_PER_HPAGE(level) - 1; + VM_BUG_ON((gfn & mask) != (pfn & mask)); + *pfnp = pfn & ~mask; + + return level; +} + static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it, gfn_t gfn, kvm_pfn_t *pfnp, int *levelp) { @@ -3318,18 +3331,20 @@ static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it, } static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, - int map_writable, int level, kvm_pfn_t pfn, - bool prefault, bool lpage_disallowed) + int map_writable, int max_level, kvm_pfn_t pfn, + bool prefault, bool account_disallowed_nx_lpage) { struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; - int ret; + int level, ret; gfn_t gfn = gpa >> PAGE_SHIFT; gfn_t base_gfn = gfn; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) + if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) return RET_PF_RETRY; + level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn); + trace_kvm_mmu_spte_requested(gpa, level, pfn); for_each_shadow_entry(vcpu, gpa, it) { /* @@ -3348,7 +3363,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, it.level - 1, true, ACC_ALL); link_shadow_page(vcpu, it.sptep, sp); - if (lpage_disallowed) + if (account_disallowed_nx_lpage) account_huge_nx_page(vcpu->kvm, sp); } } @@ -3384,45 +3399,6 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) return -EFAULT; } -static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, - gfn_t gfn, kvm_pfn_t *pfnp, - int *levelp) -{ - kvm_pfn_t pfn = *pfnp; - int level = *levelp; - - /* - * Check if it's a transparent hugepage. If this would be an - * hugetlbfs page, level wouldn't be set to - * PT_PAGE_TABLE_LEVEL and there would be no adjustment done - * here. - */ - if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && - !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && - PageTransCompoundMap(pfn_to_page(pfn)) && - !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) { - unsigned long mask; - /* - * mmu_notifier_retry was successful and we hold the - * mmu_lock here, so the pmd can't become splitting - * from under us, and in turn - * __split_huge_page_refcount() can't run from under - * us and we can safely transfer the refcount from - * PG_tail to PG_head as we switch the pfn to tail to - * head. - */ - *levelp = level = PT_DIRECTORY_LEVEL; - mask = KVM_PAGES_PER_HPAGE(level) - 1; - VM_BUG_ON((gfn & mask) != (pfn & mask)); - if (pfn & mask) { - kvm_release_pfn_clean(pfn); - pfn &= ~mask; - kvm_get_pfn(pfn); - *pfnp = pfn; - } - } -} - static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, kvm_pfn_t pfn, unsigned access, int *ret_val) { @@ -3528,7 +3504,7 @@ static bool is_access_allowed(u32 fault_err_code, u64 spte) * - true: let the vcpu to access on the same address again. * - false: let the real page fault path to fix it. */ -static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, +static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code) { struct kvm_shadow_walk_iterator iterator; @@ -3537,9 +3513,6 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, u64 spte = 0ull; uint retry_count = 0; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) - return false; - if (!page_fault_can_be_fast(error_code)) return false; @@ -3548,9 +3521,8 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, do { u64 new_spte; - for_each_shadow_entry_lockless(vcpu, gva, iterator, spte) - if (!is_shadow_present_pte(spte) || - iterator.level < level) + for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte) + if (!is_shadow_present_pte(spte)) break; sp = page_header(__pa(iterator.sptep)); @@ -3626,71 +3598,13 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, } while (true); - trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep, + trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep, spte, fault_handled); walk_shadow_page_lockless_end(vcpu); return fault_handled; } -static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable); -static int make_mmu_pages_available(struct kvm_vcpu *vcpu); - -static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, - gfn_t gfn, bool prefault) -{ - int r; - int level; - bool force_pt_level; - kvm_pfn_t pfn; - unsigned long mmu_seq; - bool map_writable, write = error_code & PFERR_WRITE_MASK; - bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && - is_nx_huge_page_enabled(); - - force_pt_level = lpage_disallowed; - level = mapping_level(vcpu, gfn, &force_pt_level); - if (likely(!force_pt_level)) { - /* - * This path builds a PAE pagetable - so we can map - * 2mb pages at maximum. Therefore check if the level - * is larger than that. - */ - if (level > PT_DIRECTORY_LEVEL) - level = PT_DIRECTORY_LEVEL; - - gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); - } - - if (fast_page_fault(vcpu, v, level, error_code)) - return RET_PF_RETRY; - - mmu_seq = vcpu->kvm->mmu_notifier_seq; - smp_rmb(); - - if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable)) - return RET_PF_RETRY; - - if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r)) - return r; - - r = RET_PF_RETRY; - spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) - goto out_unlock; - if (make_mmu_pages_available(vcpu) < 0) - goto out_unlock; - if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); - r = __direct_map(vcpu, v, write, map_writable, level, pfn, - prefault, false); -out_unlock: - spin_unlock(&vcpu->kvm->mmu_lock); - kvm_release_pfn_clean(pfn); - return r; -} - static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, struct list_head *invalid_list) { @@ -3981,7 +3895,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots); -static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, +static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { if (exception) @@ -3989,7 +3903,7 @@ static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, return vaddr; } -static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, +static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { @@ -4001,20 +3915,14 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, static bool __is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check, u64 pte, int level) { - int bit7 = (pte >> 7) & 1, low6 = pte & 0x3f; + int bit7 = (pte >> 7) & 1; - return (pte & rsvd_check->rsvd_bits_mask[bit7][level-1]) | - ((rsvd_check->bad_mt_xwr & (1ull << low6)) != 0); + return pte & rsvd_check->rsvd_bits_mask[bit7][level-1]; } -static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level) +static bool __is_bad_mt_xwr(struct rsvd_bits_validate *rsvd_check, u64 pte) { - return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level); -} - -static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level) -{ - return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level); + return rsvd_check->bad_mt_xwr & BIT_ULL(pte & 0x3f); } static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) @@ -4038,11 +3946,11 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { struct kvm_shadow_walk_iterator iterator; u64 sptes[PT64_ROOT_MAX_LEVEL], spte = 0ull; + struct rsvd_bits_validate *rsvd_check; int root, leaf; bool reserved = false; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) - goto exit; + rsvd_check = &vcpu->arch.mmu->shadow_zero_check; walk_shadow_page_lockless_begin(vcpu); @@ -4058,8 +3966,13 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) if (!is_shadow_present_pte(spte)) break; - reserved |= is_shadow_zero_bits_set(vcpu->arch.mmu, spte, - iterator.level); + /* + * Use a bitwise-OR instead of a logical-OR to aggregate the + * reserved bit and EPT's invalid memtype/XWR checks to avoid + * adding a Jcc in the loop. + */ + reserved |= __is_bad_mt_xwr(rsvd_check, spte) | + __is_rsvd_bits_set(rsvd_check, spte, iterator.level); } walk_shadow_page_lockless_end(vcpu); @@ -4073,7 +3986,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) root--; } } -exit: + *sptep = spte; return reserved; } @@ -4137,9 +4050,6 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) struct kvm_shadow_walk_iterator iterator; u64 spte; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) - return; - walk_shadow_page_lockless_begin(vcpu); for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) { clear_sp_write_flooding_count(iterator.sptep); @@ -4149,29 +4059,8 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) walk_shadow_page_lockless_end(vcpu); } -static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, - u32 error_code, bool prefault) -{ - gfn_t gfn = gva >> PAGE_SHIFT; - int r; - - pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); - - if (page_fault_handle_page_track(vcpu, error_code, gfn)) - return RET_PF_EMULATE; - - r = mmu_topup_memory_caches(vcpu); - if (r) - return r; - - MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)); - - - return nonpaging_map(vcpu, gva & PAGE_MASK, - error_code, gfn, prefault); -} - -static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) +static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + gfn_t gfn) { struct kvm_arch_async_pf arch; @@ -4180,11 +4069,13 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) arch.direct_map = vcpu->arch.mmu->direct_map; arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu); - return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); + return kvm_setup_async_pf(vcpu, cr2_or_gpa, + kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable) + gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, + bool *writable) { struct kvm_memory_slot *slot; bool async; @@ -4204,12 +4095,12 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return false; /* *pfn has correct page already */ if (!prefault && kvm_can_do_async_pf(vcpu)) { - trace_kvm_try_async_get_page(gva, gfn); + trace_kvm_try_async_get_page(cr2_or_gpa, gfn); if (kvm_find_async_pf_gfn(vcpu, gfn)) { - trace_kvm_async_pf_doublefault(gva, gfn); + trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn); kvm_make_request(KVM_REQ_APF_HALT, vcpu); return true; - } else if (kvm_arch_setup_async_pf(vcpu, gva, gfn)) + } else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn)) return true; } @@ -4217,11 +4108,77 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return false; } +static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, + bool prefault, int max_level, bool is_tdp) +{ + bool write = error_code & PFERR_WRITE_MASK; + bool exec = error_code & PFERR_FETCH_MASK; + bool lpage_disallowed = exec && is_nx_huge_page_enabled(); + bool map_writable; + + gfn_t gfn = gpa >> PAGE_SHIFT; + unsigned long mmu_seq; + kvm_pfn_t pfn; + int r; + + if (page_fault_handle_page_track(vcpu, error_code, gfn)) + return RET_PF_EMULATE; + + r = mmu_topup_memory_caches(vcpu); + if (r) + return r; + + if (lpage_disallowed) + max_level = PT_PAGE_TABLE_LEVEL; + + if (fast_page_fault(vcpu, gpa, error_code)) + return RET_PF_RETRY; + + mmu_seq = vcpu->kvm->mmu_notifier_seq; + smp_rmb(); + + if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) + return RET_PF_RETRY; + + if (handle_abnormal_pfn(vcpu, is_tdp ? 0 : gpa, gfn, pfn, ACC_ALL, &r)) + return r; + + r = RET_PF_RETRY; + spin_lock(&vcpu->kvm->mmu_lock); + if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) + goto out_unlock; + if (make_mmu_pages_available(vcpu) < 0) + goto out_unlock; + r = __direct_map(vcpu, gpa, write, map_writable, max_level, pfn, + prefault, is_tdp && lpage_disallowed); + +out_unlock: + spin_unlock(&vcpu->kvm->mmu_lock); + kvm_release_pfn_clean(pfn); + return r; +} + +static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, + u32 error_code, bool prefault) +{ + pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code); + + /* This path builds a PAE pagetable, we can map 2mb pages at maximum. */ + return direct_page_fault(vcpu, gpa & PAGE_MASK, error_code, prefault, + PT_DIRECTORY_LEVEL, false); +} + int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len) { int r = 1; +#ifndef CONFIG_X86_64 + /* A 64-bit CR2 should be impossible on 32-bit KVM. */ + if (WARN_ON_ONCE(fault_address >> 32)) + return -EFAULT; +#endif + vcpu->arch.l1tf_flush_l1d = true; switch (vcpu->arch.apf.host_apf_reason) { default: @@ -4249,76 +4206,23 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, } EXPORT_SYMBOL_GPL(kvm_handle_page_fault); -static bool -check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) -{ - int page_num = KVM_PAGES_PER_HPAGE(level); - - gfn &= ~(page_num - 1); - - return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num); -} - -static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, +static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, bool prefault) { - kvm_pfn_t pfn; - int r; - int level; - bool force_pt_level; - gfn_t gfn = gpa >> PAGE_SHIFT; - unsigned long mmu_seq; - int write = error_code & PFERR_WRITE_MASK; - bool map_writable; - bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && - is_nx_huge_page_enabled(); - - MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)); + int max_level; - if (page_fault_handle_page_track(vcpu, error_code, gfn)) - return RET_PF_EMULATE; + for (max_level = PT_MAX_HUGEPAGE_LEVEL; + max_level > PT_PAGE_TABLE_LEVEL; + max_level--) { + int page_num = KVM_PAGES_PER_HPAGE(max_level); + gfn_t base = (gpa >> PAGE_SHIFT) & ~(page_num - 1); - r = mmu_topup_memory_caches(vcpu); - if (r) - return r; - - force_pt_level = - lpage_disallowed || - !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL); - level = mapping_level(vcpu, gfn, &force_pt_level); - if (likely(!force_pt_level)) { - if (level > PT_DIRECTORY_LEVEL && - !check_hugepage_cache_consistency(vcpu, gfn, level)) - level = PT_DIRECTORY_LEVEL; - gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); + if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num)) + break; } - if (fast_page_fault(vcpu, gpa, level, error_code)) - return RET_PF_RETRY; - - mmu_seq = vcpu->kvm->mmu_notifier_seq; - smp_rmb(); - - if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) - return RET_PF_RETRY; - - if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r)) - return r; - - r = RET_PF_RETRY; - spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) - goto out_unlock; - if (make_mmu_pages_available(vcpu) < 0) - goto out_unlock; - if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); - r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, - prefault, lpage_disallowed); -out_unlock: - spin_unlock(&vcpu->kvm->mmu_lock); - kvm_release_pfn_clean(pfn); - return r; + return direct_page_fault(vcpu, gpa, error_code, prefault, + max_level, true); } static void nonpaging_init_context(struct kvm_vcpu *vcpu, @@ -5496,47 +5400,30 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) } EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); -static int make_mmu_pages_available(struct kvm_vcpu *vcpu) -{ - LIST_HEAD(invalid_list); - - if (likely(kvm_mmu_available_pages(vcpu->kvm) >= KVM_MIN_FREE_MMU_PAGES)) - return 0; - - while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES) { - if (!prepare_zap_oldest_mmu_page(vcpu->kvm, &invalid_list)) - break; - - ++vcpu->kvm->stat.mmu_recycled; - } - kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); - - if (!kvm_mmu_available_pages(vcpu->kvm)) - return -ENOSPC; - return 0; -} - -int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, +int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { int r, emulation_type = 0; bool direct = vcpu->arch.mmu->direct_map; + if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) + return RET_PF_RETRY; + /* With shadow page tables, fault_address contains a GVA or nGPA. */ if (vcpu->arch.mmu->direct_map) { vcpu->arch.gpa_available = true; - vcpu->arch.gpa_val = cr2; + vcpu->arch.gpa_val = cr2_or_gpa; } r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, cr2, direct); + r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct); if (r == RET_PF_EMULATE) goto emulate; } if (r == RET_PF_INVALID) { - r = vcpu->arch.mmu->page_fault(vcpu, cr2, + r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, lower_32_bits(error_code), false); WARN_ON(r == RET_PF_INVALID); @@ -5556,7 +5443,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, */ if (vcpu->arch.mmu->direct_map && (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) { - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2)); + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa)); return 1; } @@ -5571,7 +5458,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, * explicitly shadowing L1's page tables, i.e. unprotecting something * for L1 isn't going to magically fix whatever issue cause L2 to fail. */ - if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu)) + if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu)) emulation_type = EMULTYPE_ALLOW_RETRY; emulate: /* @@ -5586,7 +5473,7 @@ emulate: return 1; } - return x86_emulate_instruction(vcpu, cr2, emulation_type, insn, + return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, insn_len); } EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); @@ -6015,8 +5902,8 @@ restart: * mapping if the indirect sp has level = 1. */ if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && - !kvm_is_zone_device_pfn(pfn) && - PageTransCompoundMap(pfn_to_page(pfn))) { + (kvm_is_zone_device_pfn(pfn) || + PageCompound(pfn_to_page(pfn)))) { pte_list_remove(rmap_head, sptep); if (kvm_available_flush_tlb_with_range()) @@ -6249,7 +6136,7 @@ static void kvm_set_mmio_spte_mask(void) * If reserved bit is not supported, clear the present bit to disable * mmio page fault. */ - if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52) + if (shadow_phys_bits == 52) mask &= ~1ull; kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 97b21e7fd013..4e1ef0473663 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -128,6 +128,21 @@ static inline int FNAME(is_present_gpte)(unsigned long pte) #endif } +static bool FNAME(is_bad_mt_xwr)(struct rsvd_bits_validate *rsvd_check, u64 gpte) +{ +#if PTTYPE != PTTYPE_EPT + return false; +#else + return __is_bad_mt_xwr(rsvd_check, gpte); +#endif +} + +static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level) +{ + return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level) || + FNAME(is_bad_mt_xwr)(&mmu->guest_rsvd_check, gpte); +} + static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, pt_element_t __user *ptep_user, unsigned index, pt_element_t orig_pte, pt_element_t new_pte) @@ -175,9 +190,6 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, u64 gpte) { - if (is_rsvd_bits_set(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) - goto no_present; - if (!FNAME(is_present_gpte)(gpte)) goto no_present; @@ -186,6 +198,9 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, !(gpte & PT_GUEST_ACCESSED_MASK)) goto no_present; + if (FNAME(is_rsvd_bits_set)(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) + goto no_present; + return false; no_present: @@ -291,11 +306,11 @@ static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte) } /* - * Fetch a guest pte for a guest virtual address + * Fetch a guest pte for a guest virtual address, or for an L2's GPA. */ static int FNAME(walk_addr_generic)(struct guest_walker *walker, struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gva_t addr, u32 access) + gpa_t addr, u32 access) { int ret; pt_element_t pte; @@ -400,7 +415,7 @@ retry_walk: if (unlikely(!FNAME(is_present_gpte)(pte))) goto error; - if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) { + if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte, walker->level))) { errcode = PFERR_RSVD_MASK | PFERR_PRESENT_MASK; goto error; } @@ -496,7 +511,7 @@ error: } static int FNAME(walk_addr)(struct guest_walker *walker, - struct kvm_vcpu *vcpu, gva_t addr, u32 access) + struct kvm_vcpu *vcpu, gpa_t addr, u32 access) { return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr, access); @@ -611,17 +626,17 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, * If the guest tries to write a write-protected page, we need to * emulate this operation, return 1 to indicate this case. */ -static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, +static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, struct guest_walker *gw, - int write_fault, int hlevel, + int write_fault, int max_level, kvm_pfn_t pfn, bool map_writable, bool prefault, bool lpage_disallowed) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; - int top_level, ret; - gfn_t gfn, base_gfn; + int top_level, hlevel, ret; + gfn_t base_gfn = gw->gfn; direct_access = gw->pte_access; @@ -637,7 +652,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, if (FNAME(gpte_changed)(vcpu, gw, top_level)) goto out_gpte_changed; - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) + if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) goto out_gpte_changed; for (shadow_walk_init(&it, vcpu, addr); @@ -666,12 +681,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, link_shadow_page(vcpu, it.sptep, sp); } - /* - * FNAME(page_fault) might have clobbered the bottom bits of - * gw->gfn, restore them from the virtual address. - */ - gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT); - base_gfn = gfn; + hlevel = kvm_mmu_hugepage_adjust(vcpu, gw->gfn, max_level, &pfn); trace_kvm_mmu_spte_requested(addr, gw->level, pfn); @@ -682,9 +692,9 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, * We cannot overwrite existing page tables with an NX * large page, as the leaf could be executable. */ - disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel); + disallowed_hugepage_adjust(it, gw->gfn, &pfn, &hlevel); - base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); if (it.level == hlevel) break; @@ -765,7 +775,7 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, * Returns: 1 if we need to emulate the instruction, 0 otherwise, or * a negative value on error. */ -static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, +static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, bool prefault) { int write_fault = error_code & PFERR_WRITE_MASK; @@ -773,12 +783,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, struct guest_walker walker; int r; kvm_pfn_t pfn; - int level = PT_PAGE_TABLE_LEVEL; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && is_nx_huge_page_enabled(); - bool force_pt_level = lpage_disallowed; + int max_level; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); @@ -818,14 +827,10 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu, &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable); - if (walker.level >= PT_DIRECTORY_LEVEL && !is_self_change_mapping) { - level = mapping_level(vcpu, walker.gfn, &force_pt_level); - if (likely(!force_pt_level)) { - level = min(walker.level, level); - walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1); - } - } else - force_pt_level = true; + if (lpage_disallowed || is_self_change_mapping) + max_level = PT_PAGE_TABLE_LEVEL; + else + max_level = walker.level; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); @@ -865,10 +870,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); if (make_mmu_pages_available(vcpu) < 0) goto out_unlock; - if (!force_pt_level) - transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level); - r = FNAME(fetch)(vcpu, addr, &walker, write_fault, - level, pfn, map_writable, prefault, lpage_disallowed); + r = FNAME(fetch)(vcpu, addr, &walker, write_fault, max_level, pfn, + map_writable, prefault, lpage_disallowed); kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); out_unlock: @@ -945,18 +948,19 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) spin_unlock(&vcpu->kvm->mmu_lock); } -static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, +/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */ +static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access, struct x86_exception *exception) { struct guest_walker walker; gpa_t gpa = UNMAPPED_GVA; int r; - r = FNAME(walk_addr)(&walker, vcpu, vaddr, access); + r = FNAME(walk_addr)(&walker, vcpu, addr, access); if (r) { gpa = gfn_to_gpa(walker.gfn); - gpa |= vaddr & ~PAGE_MASK; + gpa |= addr & ~PAGE_MASK; } else if (exception) *exception = walker.fault; @@ -964,7 +968,8 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, } #if PTTYPE != PTTYPE_EPT -static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, +/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */ +static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) { @@ -972,6 +977,11 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, gpa_t gpa = UNMAPPED_GVA; int r; +#ifndef CONFIG_X86_64 + /* A 64-bit GVA should be impossible on 32-bit KVM. */ + WARN_ON_ONCE(vaddr >> 32); +#endif + r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access); if (r) { diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 7ca8831c7d1a..3c6522b84ff1 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -249,13 +249,13 @@ TRACE_EVENT( TRACE_EVENT( fast_page_fault, - TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, + TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code, u64 *sptep, u64 old_spte, bool retry), - TP_ARGS(vcpu, gva, error_code, sptep, old_spte, retry), + TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, retry), TP_STRUCT__entry( __field(int, vcpu_id) - __field(gva_t, gva) + __field(gpa_t, cr2_or_gpa) __field(u32, error_code) __field(u64 *, sptep) __field(u64, old_spte) @@ -265,7 +265,7 @@ TRACE_EVENT( TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; - __entry->gva = gva; + __entry->cr2_or_gpa = cr2_or_gpa; __entry->error_code = error_code; __entry->sptep = sptep; __entry->old_spte = old_spte; @@ -273,9 +273,9 @@ TRACE_EVENT( __entry->retry = retry; ), - TP_printk("vcpu %d gva %lx error_code %s sptep %p old %#llx" + TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx" " new %llx spurious %d fixed %d", __entry->vcpu_id, - __entry->gva, __print_flags(__entry->error_code, "|", + __entry->cr2_or_gpa, __print_flags(__entry->error_code, "|", kvm_mmu_trace_pferr_flags), __entry->sptep, __entry->old_spte, __entry->new_spte, __spte_satisfied(old_spte), __spte_satisfied(new_spte) diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 25ce3edd1872..7f0059aa30e1 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -192,11 +192,15 @@ static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit) break; case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000: *seg = 1; - *unit = msr - MSR_MTRRfix16K_80000; + *unit = array_index_nospec( + msr - MSR_MTRRfix16K_80000, + MSR_MTRRfix16K_A0000 - MSR_MTRRfix16K_80000 + 1); break; case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: *seg = 2; - *unit = msr - MSR_MTRRfix4K_C0000; + *unit = array_index_nospec( + msr - MSR_MTRRfix4K_C0000, + MSR_MTRRfix4K_F8000 - MSR_MTRRfix4K_C0000 + 1); break; default: return false; diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 7ebb62326c14..13332984b6d5 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -2,6 +2,8 @@ #ifndef __KVM_X86_PMU_H #define __KVM_X86_PMU_H +#include <linux/nospec.h> + #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu) #define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu)) #define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu) @@ -102,8 +104,12 @@ static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu, static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, u32 base) { - if (msr >= base && msr < base + pmu->nr_arch_gp_counters) - return &pmu->gp_counters[msr - base]; + if (msr >= base && msr < base + pmu->nr_arch_gp_counters) { + u32 index = array_index_nospec(msr - base, + pmu->nr_arch_gp_counters); + + return &pmu->gp_counters[index]; + } return NULL; } @@ -113,8 +119,12 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) { int base = MSR_CORE_PERF_FIXED_CTR0; - if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) - return &pmu->fixed_counters[msr - base]; + if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) { + u32 index = array_index_nospec(msr - base, + pmu->nr_arch_fixed_counters); + + return &pmu->fixed_counters[index]; + } return NULL; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 122d4ce3b1ab..9dbb990c319a 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1307,6 +1307,47 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu) } } +/* + * The default MMIO mask is a single bit (excluding the present bit), + * which could conflict with the memory encryption bit. Check for + * memory encryption support and override the default MMIO mask if + * memory encryption is enabled. + */ +static __init void svm_adjust_mmio_mask(void) +{ + unsigned int enc_bit, mask_bit; + u64 msr, mask; + + /* If there is no memory encryption support, use existing mask */ + if (cpuid_eax(0x80000000) < 0x8000001f) + return; + + /* If memory encryption is not enabled, use existing mask */ + rdmsrl(MSR_K8_SYSCFG, msr); + if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + return; + + enc_bit = cpuid_ebx(0x8000001f) & 0x3f; + mask_bit = boot_cpu_data.x86_phys_bits; + + /* Increment the mask bit if it is the same as the encryption bit */ + if (enc_bit == mask_bit) + mask_bit++; + + /* + * If the mask bit location is below 52, then some bits above the + * physical addressing limit will always be reserved, so use the + * rsvd_bits() function to generate the mask. This mask, along with + * the present bit, will be used to generate a page fault with + * PFER.RSV = 1. + * + * If the mask bit location is 52 (or above), then clear the mask. + */ + mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0; + + kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK); +} + static __init int svm_hardware_setup(void) { int cpu; @@ -1361,6 +1402,8 @@ static __init int svm_hardware_setup(void) } } + svm_adjust_mmio_mask(); + for_each_possible_cpu(cpu) { r = svm_cpu_init(cpu); if (r) @@ -2144,7 +2187,7 @@ static int avic_init_vcpu(struct vcpu_svm *svm) return ret; } -static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) +static int svm_create_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm; struct page *page; @@ -2153,39 +2196,13 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) struct page *nested_msrpm_pages; int err; - BUILD_BUG_ON_MSG(offsetof(struct vcpu_svm, vcpu) != 0, - "struct kvm_vcpu must be at offset 0 for arch usercopy region"); - - svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); - if (!svm) { - err = -ENOMEM; - goto out; - } - - svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!svm->vcpu.arch.user_fpu) { - printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); - err = -ENOMEM; - goto free_partial_svm; - } - - 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; - goto free_user_fpu; - } - - err = kvm_vcpu_init(&svm->vcpu, kvm, id); - if (err) - goto free_svm; + BUILD_BUG_ON(offsetof(struct vcpu_svm, vcpu) != 0); + svm = to_svm(vcpu); err = -ENOMEM; page = alloc_page(GFP_KERNEL_ACCOUNT); if (!page) - goto uninit; + goto out; msrpm_pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER); if (!msrpm_pages) @@ -2222,9 +2239,9 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->asid_generation = 0; init_vmcb(svm); - svm_init_osvw(&svm->vcpu); + svm_init_osvw(vcpu); - return &svm->vcpu; + return 0; free_page4: __free_page(hsave_page); @@ -2234,16 +2251,8 @@ free_page2: __free_pages(msrpm_pages, MSRPM_ALLOC_ORDER); free_page1: __free_page(page); -uninit: - kvm_vcpu_uninit(&svm->vcpu); -free_svm: - kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); -free_user_fpu: - kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); -free_partial_svm: - kmem_cache_free(kvm_vcpu_cache, svm); out: - return ERR_PTR(err); + return err; } static void svm_clear_current_vmcb(struct vmcb *vmcb) @@ -2269,10 +2278,6 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); __free_page(virt_to_page(svm->nested.hsave)); __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); - kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); - kmem_cache_free(kvm_vcpu_cache, svm); } static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -4281,12 +4286,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) return 1; - /* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) + if (data & ~kvm_spec_ctrl_valid_bits(vcpu)) return 1; svm->spec_ctrl = data; - if (!data) break; @@ -4310,13 +4313,12 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) if (data & ~PRED_CMD_IBPB) return 1; - + if (!boot_cpu_has(X86_FEATURE_AMD_IBPB)) + return 1; if (!data) break; wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - if (is_guest_mode(vcpu)) - break; set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); break; case MSR_AMD64_VIRT_SPEC_CTRL: @@ -4519,9 +4521,9 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm) */ kvm_for_each_vcpu(i, vcpu, kvm) { bool m = kvm_apic_match_dest(vcpu, apic, - icrl & KVM_APIC_SHORT_MASK, + icrl & APIC_SHORT_MASK, GET_APIC_DEST_FIELD(icrh), - icrl & KVM_APIC_DEST_MASK); + icrl & APIC_DEST_MASK); if (m && !avic_vcpu_is_running(vcpu)) kvm_vcpu_wake_up(vcpu); @@ -4935,7 +4937,8 @@ static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) *info2 = control->exit_info_2; } -static int handle_exit(struct kvm_vcpu *vcpu) +static int handle_exit(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion exit_fastpath) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_run *kvm_run = vcpu->run; @@ -4993,7 +4996,10 @@ static int handle_exit(struct kvm_vcpu *vcpu) __func__, svm->vmcb->control.exit_int_info, exit_code); - if (exit_code >= ARRAY_SIZE(svm_exit_handlers) + if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) { + kvm_skip_emulated_instruction(vcpu); + return 1; + } else if (exit_code >= ARRAY_SIZE(svm_exit_handlers) || !svm_exit_handlers[exit_code]) { vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%x\n", exit_code); dump_vmcb(vcpu); @@ -5913,6 +5919,7 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && + boot_cpu_has(X86_FEATURE_XSAVE) && boot_cpu_has(X86_FEATURE_XSAVES); /* Update nrips enabled cache */ @@ -5924,14 +5931,14 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu) guest_cpuid_clear(vcpu, X86_FEATURE_X2APIC); } -#define F(x) bit(X86_FEATURE_##x) +#define F feature_bit static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) { switch (func) { case 0x1: if (avic) - entry->ecx &= ~bit(X86_FEATURE_X2APIC); + entry->ecx &= ~F(X2APIC); break; case 0x80000001: if (nested) @@ -6001,6 +6008,11 @@ static bool svm_has_wbinvd_exit(void) return true; } +static bool svm_pku_supported(void) +{ + return false; +} + #define PRE_EX(exit) { .exit_code = (exit), \ .stage = X86_ICPT_PRE_EXCEPT, } #define POST_EX(exit) { .exit_code = (exit), \ @@ -6186,9 +6198,12 @@ out: return ret; } -static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) +static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion *exit_fastpath) { - + if (!is_guest_mode(vcpu) && + to_svm(vcpu)->vmcb->control.exit_code == EXIT_REASON_MSR_WRITE) + *exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu); } static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) @@ -7341,6 +7356,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .xsaves_supported = svm_xsaves_supported, .umip_emulated = svm_umip_emulated, .pt_supported = svm_pt_supported, + .pku_supported = svm_pku_supported, .set_supported_cpuid = svm_set_supported_cpuid, diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 7aa69716d516..283bdb7071af 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -145,6 +145,11 @@ static inline bool vmx_umip_emulated(void) SECONDARY_EXEC_DESC; } +static inline bool vmx_pku_supported(void) +{ + return boot_cpu_has(X86_FEATURE_PKU); +} + static inline bool cpu_has_vmx_rdtscp(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 72359709cdc1..89c3e0caf39f 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -350,17 +350,12 @@ int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version) { struct vcpu_vmx *vmx = to_vmx(vcpu); - bool evmcs_already_enabled = vmx->nested.enlightened_vmcs_enabled; vmx->nested.enlightened_vmcs_enabled = true; if (vmcs_version) *vmcs_version = nested_get_evmcs_version(vcpu); - /* We don't support disabling the feature for simplicity. */ - if (evmcs_already_enabled) - return 0; - vmx->nested.msrs.pinbased_ctls_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; vmx->nested.msrs.entry_ctls_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; vmx->nested.msrs.exit_ctls_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 4aea7d304beb..95b3f4306ac2 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -28,16 +28,6 @@ module_param(nested_early_check, bool, S_IRUGO); failed; \ }) -#define SET_MSR_OR_WARN(vcpu, idx, data) \ -({ \ - bool failed = kvm_set_msr(vcpu, idx, data); \ - if (failed) \ - pr_warn_ratelimited( \ - "%s cannot write MSR (0x%x, 0x%llx)\n", \ - __func__, idx, data); \ - failed; \ -}) - /* * Hyper-V requires all of these, so mark them as supported even though * they are just treated the same as all-context. @@ -2172,8 +2162,8 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * EXEC CONTROLS */ exec_control = vmx_exec_control(vmx); /* L0's desires */ - exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; - exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING; + exec_control &= ~CPU_BASED_INTR_WINDOW_EXITING; + exec_control &= ~CPU_BASED_NMI_WINDOW_EXITING; exec_control &= ~CPU_BASED_TPR_SHADOW; exec_control |= vmcs12->cpu_based_vm_exec_control; @@ -2550,8 +2540,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && - SET_MSR_OR_WARN(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, - vmcs12->guest_ia32_perf_global_ctrl)) + WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, + vmcs12->guest_ia32_perf_global_ctrl))) return -EINVAL; kvm_rsp_write(vcpu, vmcs12->guest_rsp); @@ -2566,7 +2556,7 @@ static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12) return -EINVAL; if (CC(!nested_cpu_has_virtual_nmis(vmcs12) && - nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING))) + nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING))) return -EINVAL; return 0; @@ -2823,7 +2813,6 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, CC(vmcs12->host_ss_selector == 0 && !ia32e)) return -EINVAL; -#ifdef CONFIG_X86_64 if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) || CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) || CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) || @@ -2831,7 +2820,6 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) || CC(is_noncanonical_address(vmcs12->host_rip, vcpu))) return -EINVAL; -#endif /* * If the load IA32_EFER VM-exit control is 1, bits reserved in the @@ -2899,6 +2887,10 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, CC(!nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4))) return -EINVAL; + if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) && + CC(!kvm_dr7_valid(vmcs12->guest_dr7))) + return -EINVAL; + if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) && CC(!kvm_pat_valid(vmcs12->guest_ia32_pat))) return -EINVAL; @@ -3048,9 +3040,6 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) return 0; } -static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12); - static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); @@ -3183,7 +3172,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, u32 exit_qual; evaluate_pending_interrupts = exec_controls_get(vmx) & - (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING); + (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu)) evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu); @@ -3230,7 +3219,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, } enter_guest_mode(vcpu); - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset += vmcs12->tsc_offset; if (prepare_vmcs02(vcpu, vmcs12, &exit_qual)) @@ -3294,7 +3283,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, * 26.7 "VM-entry failures during or after loading guest state". */ vmentry_fail_vmexit_guest_mode: - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset -= vmcs12->tsc_offset; leave_guest_mode(vcpu); @@ -3407,8 +3396,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) */ if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) && !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) && - !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_NMI_PENDING) && - !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_INTR_PENDING) && + !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_NMI_WINDOW_EXITING) && + !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_INTR_WINDOW_EXITING) && (vmcs12->guest_rflags & X86_EFLAGS_IF))) { vmx->nested.nested_run_pending = 0; return kvm_vcpu_halt(vcpu); @@ -3427,7 +3416,7 @@ vmentry_failed: /* * On a nested exit from L2 to L1, vmcs12.guest_cr0 might not be up-to-date - * because L2 may have changed some cr0 bits directly (CRO_GUEST_HOST_MASK). + * because L2 may have changed some cr0 bits directly (CR0_GUEST_HOST_MASK). * This function returns the new value we should put in vmcs12.guest_cr0. * It's not enough to just return the vmcs02 GUEST_CR0. Rather, * 1. Bits that neither L0 nor L1 trapped, were set directly by L2 and are now @@ -3999,8 +3988,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vcpu->arch.pat = vmcs12->host_ia32_pat; } if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) - SET_MSR_OR_WARN(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, - vmcs12->host_ia32_perf_global_ctrl); + WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, + vmcs12->host_ia32_perf_global_ctrl)); /* Set L1 segment info according to Intel SDM 27.5.2 Loading Host Segment and Descriptor-Table Registers */ @@ -4209,7 +4198,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, 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) + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset -= vmcs12->tsc_offset; if (likely(!vmx->fail)) { @@ -4751,36 +4740,32 @@ static int handle_vmresume(struct kvm_vcpu *vcpu) static int handle_vmread(struct kvm_vcpu *vcpu) { - unsigned long field; - u64 field_value; + struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu) + : get_vmcs12(vcpu); unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - int len; - gva_t gva = 0; - struct vmcs12 *vmcs12; + u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); + struct vcpu_vmx *vmx = to_vmx(vcpu); struct x86_exception e; + unsigned long field; + u64 value; + gva_t gva = 0; short offset; + int len; if (!nested_vmx_check_permission(vcpu)) return 1; - if (to_vmx(vcpu)->nested.current_vmptr == -1ull) + /* + * In VMX non-root operation, when the VMCS-link pointer is -1ull, + * any VMREAD sets the ALU flags for VMfailInvalid. + */ + if (vmx->nested.current_vmptr == -1ull || + (is_guest_mode(vcpu) && + get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)) return nested_vmx_failInvalid(vcpu); - if (!is_guest_mode(vcpu)) - vmcs12 = get_vmcs12(vcpu); - else { - /* - * When vmcs->vmcs_link_pointer is -1ull, any VMREAD - * to shadowed-field sets the ALU flags for VMfailInvalid. - */ - if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) - return nested_vmx_failInvalid(vcpu); - vmcs12 = get_shadow_vmcs12(vcpu); - } - /* Decode instruction info and find the field to read */ - field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); + field = kvm_register_readl(vcpu, (((instr_info) >> 28) & 0xf)); offset = vmcs_field_to_offset(field); if (offset < 0) @@ -4790,25 +4775,26 @@ static int handle_vmread(struct kvm_vcpu *vcpu) if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field)) copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - /* Read the field, zero-extended to a u64 field_value */ - field_value = vmcs12_read_any(vmcs12, field, offset); + /* Read the field, zero-extended to a u64 value */ + value = vmcs12_read_any(vmcs12, field, offset); /* * Now copy part of this value to register or memory, as requested. * Note that the number of bits actually copied is 32 or 64 depending * on the guest's mode (32 or 64 bit), not on the given field's length. */ - if (vmx_instruction_info & (1u << 10)) { - kvm_register_writel(vcpu, (((vmx_instruction_info) >> 3) & 0xf), - field_value); + if (instr_info & BIT(10)) { + kvm_register_writel(vcpu, (((instr_info) >> 3) & 0xf), value); } else { len = is_64_bit_mode(vcpu) ? 8 : 4; if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, true, len, &gva)) + instr_info, true, len, &gva)) return 1; /* _system ok, nested_vmx_check_permission has verified cpl=0 */ - if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e)) + if (kvm_write_guest_virt_system(vcpu, gva, &value, len, &e)) { kvm_inject_page_fault(vcpu, &e); + return 1; + } } return nested_vmx_succeed(vcpu); @@ -4840,46 +4826,58 @@ static bool is_shadow_field_ro(unsigned long field) static int handle_vmwrite(struct kvm_vcpu *vcpu) { + struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu) + : get_vmcs12(vcpu); + unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct x86_exception e; unsigned long field; - int len; + short offset; gva_t gva; - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + int len; - /* The value to write might be 32 or 64 bits, depending on L1's long + /* + * The value to write might be 32 or 64 bits, depending on L1's long * mode, and eventually we need to write that into a field of several * possible lengths. The code below first zero-extends the value to 64 - * bit (field_value), and then copies only the appropriate number of + * bit (value), and then copies only the appropriate number of * bits into the vmcs12 field. */ - u64 field_value = 0; - struct x86_exception e; - struct vmcs12 *vmcs12; - short offset; + u64 value = 0; if (!nested_vmx_check_permission(vcpu)) return 1; - if (vmx->nested.current_vmptr == -1ull) + /* + * In VMX non-root operation, when the VMCS-link pointer is -1ull, + * any VMWRITE sets the ALU flags for VMfailInvalid. + */ + if (vmx->nested.current_vmptr == -1ull || + (is_guest_mode(vcpu) && + get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)) return nested_vmx_failInvalid(vcpu); - if (vmx_instruction_info & (1u << 10)) - field_value = kvm_register_readl(vcpu, - (((vmx_instruction_info) >> 3) & 0xf)); + if (instr_info & BIT(10)) + value = kvm_register_readl(vcpu, (((instr_info) >> 3) & 0xf)); else { len = is_64_bit_mode(vcpu) ? 8 : 4; if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, false, len, &gva)) + instr_info, false, len, &gva)) return 1; - if (kvm_read_guest_virt(vcpu, gva, &field_value, len, &e)) { + if (kvm_read_guest_virt(vcpu, gva, &value, len, &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } } + field = kvm_register_readl(vcpu, (((instr_info) >> 28) & 0xf)); + + offset = vmcs_field_to_offset(field); + if (offset < 0) + return nested_vmx_failValid(vcpu, + VMXERR_UNSUPPORTED_VMCS_COMPONENT); - field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); /* * If the vCPU supports "VMWRITE to any supported field in the * VMCS," then the "read-only" fields are actually read/write. @@ -4889,29 +4887,12 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return nested_vmx_failValid(vcpu, VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT); - if (!is_guest_mode(vcpu)) { - vmcs12 = get_vmcs12(vcpu); - - /* - * Ensure vmcs12 is up-to-date before any VMWRITE that dirties - * vmcs12, else we may crush a field or consume a stale value. - */ - if (!is_shadow_field_rw(field)) - copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - } else { - /* - * When vmcs->vmcs_link_pointer is -1ull, any VMWRITE - * to shadowed-field sets the ALU flags for VMfailInvalid. - */ - if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) - return nested_vmx_failInvalid(vcpu); - vmcs12 = get_shadow_vmcs12(vcpu); - } - - offset = vmcs_field_to_offset(field); - if (offset < 0) - return nested_vmx_failValid(vcpu, - VMXERR_UNSUPPORTED_VMCS_COMPONENT); + /* + * Ensure vmcs12 is up-to-date before any VMWRITE that dirties + * vmcs12, else we may crush a field or consume a stale value. + */ + if (!is_guest_mode(vcpu) && !is_shadow_field_rw(field)) + copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); /* * Some Intel CPUs intentionally drop the reserved bits of the AR byte @@ -4922,9 +4903,9 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) * the stripped down value, L2 sees the full value as stored by KVM). */ if (field >= GUEST_ES_AR_BYTES && field <= GUEST_TR_AR_BYTES) - field_value &= 0x1f0ff; + value &= 0x1f0ff; - vmcs12_write_any(vmcs12, field, offset, field_value); + vmcs12_write_any(vmcs12, field, offset, value); /* * Do not track vmcs12 dirty-state if in guest-mode as we actually @@ -4941,7 +4922,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) preempt_disable(); vmcs_load(vmx->vmcs01.shadow_vmcs); - __vmcs_writel(field, field_value); + __vmcs_writel(field, value); vmcs_clear(vmx->vmcs01.shadow_vmcs); vmcs_load(vmx->loaded_vmcs->vmcs); @@ -5524,10 +5505,10 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) return false; case EXIT_REASON_TRIPLE_FAULT: return true; - case EXIT_REASON_PENDING_INTERRUPT: - return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING); + case EXIT_REASON_INTERRUPT_WINDOW: + return nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING); case EXIT_REASON_NMI_WINDOW: - return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING); + return nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING); case EXIT_REASON_TASK_SWITCH: return true; case EXIT_REASON_CPUID: @@ -6015,8 +5996,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, msrs->procbased_ctls_low = CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR; msrs->procbased_ctls_high &= - CPU_BASED_VIRTUAL_INTR_PENDING | - CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING | + CPU_BASED_INTR_WINDOW_EXITING | + CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING | CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING | CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 7023138b1cb0..34a3a17bb6d7 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -86,10 +86,14 @@ static unsigned intel_find_arch_event(struct kvm_pmu *pmu, static unsigned intel_find_fixed_event(int idx) { - if (idx >= ARRAY_SIZE(fixed_pmc_events)) + u32 event; + size_t size = ARRAY_SIZE(fixed_pmc_events); + + if (idx >= size) return PERF_COUNT_HW_MAX; - return intel_arch_events[fixed_pmc_events[idx]].event_type; + event = fixed_pmc_events[array_index_nospec(idx, size)]; + return intel_arch_events[event].event_type; } /* check if a PMC is enabled by comparing it with globl_ctrl bits. */ @@ -130,16 +134,20 @@ static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = idx & (1u << 30); struct kvm_pmc *counters; + unsigned int num_counters; idx &= ~(3u << 30); - if (!fixed && idx >= pmu->nr_arch_gp_counters) - return NULL; - if (fixed && idx >= pmu->nr_arch_fixed_counters) + if (fixed) { + counters = pmu->fixed_counters; + num_counters = pmu->nr_arch_fixed_counters; + } else { + counters = pmu->gp_counters; + num_counters = pmu->nr_arch_gp_counters; + } + if (idx >= num_counters) return NULL; - counters = fixed ? pmu->fixed_counters : pmu->gp_counters; *mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP]; - - return &counters[idx]; + return &counters[array_index_nospec(idx, num_counters)]; } static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) diff --git a/arch/x86/kvm/vmx/vmcs_shadow_fields.h b/arch/x86/kvm/vmx/vmcs_shadow_fields.h index eb1ecd16fd22..cad128d1657b 100644 --- a/arch/x86/kvm/vmx/vmcs_shadow_fields.h +++ b/arch/x86/kvm/vmx/vmcs_shadow_fields.h @@ -23,12 +23,12 @@ BUILD_BUG_ON(1) * * When adding or removing fields here, note that shadowed * fields must always be synced by prepare_vmcs02, not just - * prepare_vmcs02_full. + * prepare_vmcs02_rare. */ /* * Keeping the fields ordered by size is an attempt at improving - * branch prediction in vmcs_read_any and vmcs_write_any. + * branch prediction in vmcs12_read_any and vmcs12_write_any. */ /* 16-bits */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e3394c839dea..802ba97ac7f2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1057,6 +1057,12 @@ static unsigned long segment_base(u16 selector) } #endif +static inline bool pt_can_write_msr(struct vcpu_vmx *vmx) +{ + return (pt_mode == PT_MODE_HOST_GUEST) && + !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN); +} + static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range) { u32 i; @@ -1716,7 +1722,7 @@ static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)) + (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) return vcpu->arch.tsc_offset - vmcs12->tsc_offset; return vcpu->arch.tsc_offset; @@ -1734,7 +1740,7 @@ static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) * to the newly set TSC to get L2's TSC. */ if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)) + (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) g_tsc_offset = vmcs12->tsc_offset; trace_kvm_write_tsc_offset(vcpu->vcpu_id, @@ -1773,8 +1779,6 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) default: return 1; } - - return 0; } /* @@ -1916,7 +1920,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } /* - * Writes msr value into into the appropriate "register". + * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ @@ -1994,12 +1998,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) return 1; - /* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) + if (data & ~kvm_spec_ctrl_valid_bits(vcpu)) return 1; vmx->spec_ctrl = data; - if (!data) break; @@ -2010,7 +2012,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * * For nested: * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_merge_msr_bitmap. We should not touch the + * nested_vmx_prepare_msr_bitmap. We should not touch the * vmcs02.msr_bitmap here since it gets completely overwritten * in the merging. We update the vmcs01 here for L1 as well * since it will end up touching the MSR anyway now. @@ -2033,7 +2035,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & ~PRED_CMD_IBPB) return 1; - + if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL)) + return 1; if (!data) break; @@ -2046,7 +2049,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * * For nested: * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_merge_msr_bitmap. We should not touch the + * nested_vmx_prepare_msr_bitmap. We should not touch the * vmcs02.msr_bitmap here since it gets completely overwritten * in the merging. */ @@ -2104,47 +2107,50 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) pt_update_intercept_for_msr(vmx); break; case MSR_IA32_RTIT_STATUS: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (data & MSR_IA32_RTIT_STATUS_MASK)) + if (!pt_can_write_msr(vmx)) + return 1; + if (data & MSR_IA32_RTIT_STATUS_MASK) return 1; vmx->pt_desc.guest.status = data; break; case MSR_IA32_RTIT_CR3_MATCH: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_cr3_filtering)) + if (!pt_can_write_msr(vmx)) + return 1; + if (!intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_cr3_filtering)) return 1; vmx->pt_desc.guest.cr3_match = data; break; case MSR_IA32_RTIT_OUTPUT_BASE: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output)) || - (data & MSR_IA32_RTIT_OUTPUT_BASE_MASK)) + if (!pt_can_write_msr(vmx)) + return 1; + if (!intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_topa_output) && + !intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_single_range_output)) + return 1; + if (data & MSR_IA32_RTIT_OUTPUT_BASE_MASK) return 1; vmx->pt_desc.guest.output_base = data; break; case MSR_IA32_RTIT_OUTPUT_MASK: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output))) + if (!pt_can_write_msr(vmx)) + return 1; + if (!intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_topa_output) && + !intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_single_range_output)) return 1; vmx->pt_desc.guest.output_mask = data; break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: + if (!pt_can_write_msr(vmx)) + return 1; index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_num_address_ranges))) + if (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, + PT_CAP_num_address_ranges)) + return 1; + if (is_noncanonical_address(data, vcpu)) return 1; if (index % 2) vmx->pt_desc.guest.addr_b[index / 2] = data; @@ -2355,7 +2361,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, CPU_BASED_CR3_STORE_EXITING | CPU_BASED_UNCOND_IO_EXITING | CPU_BASED_MOV_DR_EXITING | - CPU_BASED_USE_TSC_OFFSETING | + CPU_BASED_USE_TSC_OFFSETTING | CPU_BASED_MWAIT_EXITING | CPU_BASED_MONITOR_EXITING | CPU_BASED_INVLPG_EXITING | @@ -2690,8 +2696,6 @@ static void enter_pmode(struct kvm_vcpu *vcpu) vmx->rmode.vm86_active = 0; - vmx_segment_cache_clear(vmx); - vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); flags = vmcs_readl(GUEST_RFLAGS); @@ -3477,7 +3481,7 @@ out: static int init_rmode_identity_map(struct kvm *kvm) { struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); - int i, idx, r = 0; + int i, r = 0; kvm_pfn_t identity_map_pfn; u32 tmp; @@ -3485,7 +3489,7 @@ static int init_rmode_identity_map(struct kvm *kvm) mutex_lock(&kvm->slots_lock); if (likely(kvm_vmx->ept_identity_pagetable_done)) - goto out2; + goto out; if (!kvm_vmx->ept_identity_map_addr) kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; @@ -3494,9 +3498,8 @@ static int init_rmode_identity_map(struct kvm *kvm) r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, kvm_vmx->ept_identity_map_addr, PAGE_SIZE); if (r < 0) - goto out2; + goto out; - idx = srcu_read_lock(&kvm->srcu); r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE); if (r < 0) goto out; @@ -3512,9 +3515,6 @@ static int init_rmode_identity_map(struct kvm *kvm) kvm_vmx->ept_identity_pagetable_done = true; out: - srcu_read_unlock(&kvm->srcu, idx); - -out2: mutex_unlock(&kvm->slots_lock); return r; } @@ -4042,6 +4042,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) if (vmx_xsaves_supported()) { /* Exposing XSAVES only when XSAVE is exposed */ bool xsaves_enabled = + boot_cpu_has(X86_FEATURE_XSAVE) && guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && guest_cpuid_has(vcpu, X86_FEATURE_XSAVES); @@ -4352,7 +4353,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) static void enable_irq_window(struct kvm_vcpu *vcpu) { - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING); + exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); } static void enable_nmi_window(struct kvm_vcpu *vcpu) @@ -4363,7 +4364,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) return; } - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING); + exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); } static void vmx_inject_irq(struct kvm_vcpu *vcpu) @@ -4488,8 +4489,11 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) if (enable_unrestricted_guest) return 0; - ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, - PAGE_SIZE * 3); + mutex_lock(&kvm->slots_lock); + ret = __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, + PAGE_SIZE * 3); + mutex_unlock(&kvm->slots_lock); + if (ret) return ret; to_kvm_vmx(kvm)->tss_addr = addr; @@ -4971,7 +4975,7 @@ static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) static int handle_interrupt_window(struct kvm_vcpu *vcpu) { - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING); + exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -5184,7 +5188,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) static int handle_nmi_window(struct kvm_vcpu *vcpu) { WARN_ON_ONCE(!enable_vnmi); - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING); + exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); ++vcpu->stat.nmi_window_exits; kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -5205,7 +5209,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) WARN_ON_ONCE(vmx->emulation_required && vmx->nested.nested_run_pending); intr_window_requested = exec_controls_get(vmx) & - CPU_BASED_VIRTUAL_INTR_PENDING; + CPU_BASED_INTR_WINDOW_EXITING; while (vmx->emulation_required && count-- != 0) { if (intr_window_requested && vmx_interrupt_allowed(vcpu)) @@ -5529,7 +5533,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_CPUID] = kvm_emulate_cpuid, [EXIT_REASON_MSR_READ] = kvm_emulate_rdmsr, [EXIT_REASON_MSR_WRITE] = kvm_emulate_wrmsr, - [EXIT_REASON_PENDING_INTERRUPT] = handle_interrupt_window, + [EXIT_REASON_INTERRUPT_WINDOW] = handle_interrupt_window, [EXIT_REASON_HLT] = kvm_emulate_halt, [EXIT_REASON_INVD] = handle_invd, [EXIT_REASON_INVLPG] = handle_invlpg, @@ -5816,7 +5820,8 @@ void dump_vmcs(void) * The guest has exited. See if we can fix it or if we need userspace * assistance. */ -static int vmx_handle_exit(struct kvm_vcpu *vcpu) +static int vmx_handle_exit(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exit_reason = vmx->exit_reason; @@ -5902,34 +5907,44 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) } } - if (exit_reason < kvm_vmx_max_exit_handlers - && kvm_vmx_exit_handlers[exit_reason]) { + if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) { + kvm_skip_emulated_instruction(vcpu); + return 1; + } + + if (exit_reason >= kvm_vmx_max_exit_handlers) + goto unexpected_vmexit; #ifdef CONFIG_RETPOLINE - if (exit_reason == EXIT_REASON_MSR_WRITE) - return kvm_emulate_wrmsr(vcpu); - else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER) - return handle_preemption_timer(vcpu); - else if (exit_reason == EXIT_REASON_PENDING_INTERRUPT) - return handle_interrupt_window(vcpu); - else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) - return handle_external_interrupt(vcpu); - else if (exit_reason == EXIT_REASON_HLT) - return kvm_emulate_halt(vcpu); - else if (exit_reason == EXIT_REASON_EPT_MISCONFIG) - return handle_ept_misconfig(vcpu); + if (exit_reason == EXIT_REASON_MSR_WRITE) + return kvm_emulate_wrmsr(vcpu); + else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER) + return handle_preemption_timer(vcpu); + else if (exit_reason == EXIT_REASON_INTERRUPT_WINDOW) + return handle_interrupt_window(vcpu); + else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) + return handle_external_interrupt(vcpu); + else if (exit_reason == EXIT_REASON_HLT) + return kvm_emulate_halt(vcpu); + else if (exit_reason == EXIT_REASON_EPT_MISCONFIG) + return handle_ept_misconfig(vcpu); #endif - return kvm_vmx_exit_handlers[exit_reason](vcpu); - } else { - vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", - exit_reason); - dump_vmcs(); - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = + + exit_reason = array_index_nospec(exit_reason, + kvm_vmx_max_exit_handlers); + if (!kvm_vmx_exit_handlers[exit_reason]) + goto unexpected_vmexit; + + return kvm_vmx_exit_handlers[exit_reason](vcpu); + +unexpected_vmexit: + vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", exit_reason); + dump_vmcs(); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; - vcpu->run->internal.ndata = 1; - vcpu->run->internal.data[0] = exit_reason; - return 0; - } + vcpu->run->internal.ndata = 1; + vcpu->run->internal.data[0] = exit_reason; + return 0; } /* @@ -6250,7 +6265,8 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) } STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff); -static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) +static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion *exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6258,6 +6274,9 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) handle_external_interrupt_irqoff(vcpu); else if (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI) handle_exception_nmi_irqoff(vmx); + else if (!is_guest_mode(vcpu) && + vmx->exit_reason == EXIT_REASON_MSR_WRITE) + *exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu); } static bool vmx_has_emulated_msr(int index) @@ -6666,60 +6685,31 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) free_vpid(vmx->vpid); nested_vmx_free_vcpu(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); - kmem_cache_free(kvm_vcpu_cache, vmx); } -static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) +static int vmx_create_vcpu(struct kvm_vcpu *vcpu) { - int err; struct vcpu_vmx *vmx; unsigned long *msr_bitmap; - int i, cpu; - - BUILD_BUG_ON_MSG(offsetof(struct vcpu_vmx, vcpu) != 0, - "struct kvm_vcpu must be at offset 0 for arch usercopy region"); - - vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); - if (!vmx) - return ERR_PTR(-ENOMEM); + int i, cpu, err; - vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!vmx->vcpu.arch.user_fpu) { - printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); - err = -ENOMEM; - goto free_partial_vcpu; - } + BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0); + vmx = to_vmx(vcpu); - 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; - goto free_user_fpu; - } + err = -ENOMEM; vmx->vpid = allocate_vpid(); - err = kvm_vcpu_init(&vmx->vcpu, kvm, id); - if (err) - goto free_vcpu; - - err = -ENOMEM; - /* * If PML is turned on, failure on enabling PML just results in failure * of creating the vcpu, therefore we can simplify PML logic (by * avoiding dealing with cases, such as enabling PML partially on vcpus - * for the guest, etc. + * for the guest), etc. */ if (enable_pml) { vmx->pml_pg = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!vmx->pml_pg) - goto uninit_vcpu; + goto free_vpid; } BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) != NR_SHARED_MSRS); @@ -6764,7 +6754,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); - if (kvm_cstate_in_guest(kvm)) { + if (kvm_cstate_in_guest(vcpu->kvm)) { vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C1_RES, MSR_TYPE_R); vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R); vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R); @@ -6774,19 +6764,19 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->loaded_vmcs = &vmx->vmcs01; cpu = get_cpu(); - vmx_vcpu_load(&vmx->vcpu, cpu); - vmx->vcpu.cpu = cpu; + vmx_vcpu_load(vcpu, cpu); + vcpu->cpu = cpu; init_vmcs(vmx); - vmx_vcpu_put(&vmx->vcpu); + vmx_vcpu_put(vcpu); put_cpu(); - if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { - err = alloc_apic_access_page(kvm); + if (cpu_need_virtualize_apic_accesses(vcpu)) { + err = alloc_apic_access_page(vcpu->kvm); if (err) goto free_vmcs; } if (enable_ept && !enable_unrestricted_guest) { - err = init_rmode_identity_map(kvm); + err = init_rmode_identity_map(vcpu->kvm); if (err) goto free_vmcs; } @@ -6794,7 +6784,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, vmx_capability.ept, - kvm_vcpu_apicv_active(&vmx->vcpu)); + kvm_vcpu_apicv_active(vcpu)); else memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs)); @@ -6812,22 +6802,15 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->ept_pointer = INVALID_PAGE; - return &vmx->vcpu; + return 0; free_vmcs: free_loaded_vmcs(vmx->loaded_vmcs); free_pml: vmx_destroy_pml_buffer(vmx); -uninit_vcpu: - kvm_vcpu_uninit(&vmx->vcpu); -free_vcpu: +free_vpid: free_vpid(vmx->vpid); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); -free_user_fpu: - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); -free_partial_vcpu: - kmem_cache_free(kvm_vcpu_cache, vmx); - return ERR_PTR(err); + return err; } #define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" @@ -6973,28 +6956,28 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) } while (0) entry = kvm_find_cpuid_entry(vcpu, 0x1, 0); - cr4_fixed1_update(X86_CR4_VME, edx, bit(X86_FEATURE_VME)); - cr4_fixed1_update(X86_CR4_PVI, edx, bit(X86_FEATURE_VME)); - cr4_fixed1_update(X86_CR4_TSD, edx, bit(X86_FEATURE_TSC)); - cr4_fixed1_update(X86_CR4_DE, edx, bit(X86_FEATURE_DE)); - cr4_fixed1_update(X86_CR4_PSE, edx, bit(X86_FEATURE_PSE)); - cr4_fixed1_update(X86_CR4_PAE, edx, bit(X86_FEATURE_PAE)); - cr4_fixed1_update(X86_CR4_MCE, edx, bit(X86_FEATURE_MCE)); - cr4_fixed1_update(X86_CR4_PGE, edx, bit(X86_FEATURE_PGE)); - cr4_fixed1_update(X86_CR4_OSFXSR, edx, bit(X86_FEATURE_FXSR)); - cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, bit(X86_FEATURE_XMM)); - cr4_fixed1_update(X86_CR4_VMXE, ecx, bit(X86_FEATURE_VMX)); - cr4_fixed1_update(X86_CR4_SMXE, ecx, bit(X86_FEATURE_SMX)); - cr4_fixed1_update(X86_CR4_PCIDE, ecx, bit(X86_FEATURE_PCID)); - cr4_fixed1_update(X86_CR4_OSXSAVE, ecx, bit(X86_FEATURE_XSAVE)); + cr4_fixed1_update(X86_CR4_VME, edx, feature_bit(VME)); + cr4_fixed1_update(X86_CR4_PVI, edx, feature_bit(VME)); + cr4_fixed1_update(X86_CR4_TSD, edx, feature_bit(TSC)); + cr4_fixed1_update(X86_CR4_DE, edx, feature_bit(DE)); + cr4_fixed1_update(X86_CR4_PSE, edx, feature_bit(PSE)); + cr4_fixed1_update(X86_CR4_PAE, edx, feature_bit(PAE)); + cr4_fixed1_update(X86_CR4_MCE, edx, feature_bit(MCE)); + cr4_fixed1_update(X86_CR4_PGE, edx, feature_bit(PGE)); + cr4_fixed1_update(X86_CR4_OSFXSR, edx, feature_bit(FXSR)); + cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, feature_bit(XMM)); + cr4_fixed1_update(X86_CR4_VMXE, ecx, feature_bit(VMX)); + cr4_fixed1_update(X86_CR4_SMXE, ecx, feature_bit(SMX)); + cr4_fixed1_update(X86_CR4_PCIDE, ecx, feature_bit(PCID)); + cr4_fixed1_update(X86_CR4_OSXSAVE, ecx, feature_bit(XSAVE)); entry = kvm_find_cpuid_entry(vcpu, 0x7, 0); - cr4_fixed1_update(X86_CR4_FSGSBASE, ebx, bit(X86_FEATURE_FSGSBASE)); - cr4_fixed1_update(X86_CR4_SMEP, ebx, bit(X86_FEATURE_SMEP)); - cr4_fixed1_update(X86_CR4_SMAP, ebx, bit(X86_FEATURE_SMAP)); - cr4_fixed1_update(X86_CR4_PKE, ecx, bit(X86_FEATURE_PKU)); - cr4_fixed1_update(X86_CR4_UMIP, ecx, bit(X86_FEATURE_UMIP)); - cr4_fixed1_update(X86_CR4_LA57, ecx, bit(X86_FEATURE_LA57)); + cr4_fixed1_update(X86_CR4_FSGSBASE, ebx, feature_bit(FSGSBASE)); + cr4_fixed1_update(X86_CR4_SMEP, ebx, feature_bit(SMEP)); + cr4_fixed1_update(X86_CR4_SMAP, ebx, feature_bit(SMAP)); + cr4_fixed1_update(X86_CR4_PKE, ecx, feature_bit(PKU)); + cr4_fixed1_update(X86_CR4_UMIP, ecx, feature_bit(UMIP)); + cr4_fixed1_update(X86_CR4_LA57, ecx, feature_bit(LA57)); #undef cr4_fixed1_update } @@ -7128,7 +7111,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) { if (func == 1 && nested) - entry->ecx |= bit(X86_FEATURE_VMX); + entry->ecx |= feature_bit(VMX); } static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) @@ -7870,6 +7853,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .xsaves_supported = vmx_xsaves_supported, .umip_emulated = vmx_umip_emulated, .pt_supported = vmx_pt_supported, + .pku_supported = vmx_pku_supported, .request_immediate_exit = vmx_request_immediate_exit, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cf917139de6b..7e118883d8f1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -93,6 +93,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif +static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; + #define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ #define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ @@ -879,30 +881,44 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) } EXPORT_SYMBOL_GPL(kvm_set_xcr); -static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) -{ - if (cr4 & CR4_RESERVED_BITS) - return -EINVAL; +#define __cr4_reserved_bits(__cpu_has, __c) \ +({ \ + u64 __reserved_bits = CR4_RESERVED_BITS; \ + \ + if (!__cpu_has(__c, X86_FEATURE_XSAVE)) \ + __reserved_bits |= X86_CR4_OSXSAVE; \ + if (!__cpu_has(__c, X86_FEATURE_SMEP)) \ + __reserved_bits |= X86_CR4_SMEP; \ + if (!__cpu_has(__c, X86_FEATURE_SMAP)) \ + __reserved_bits |= X86_CR4_SMAP; \ + if (!__cpu_has(__c, X86_FEATURE_FSGSBASE)) \ + __reserved_bits |= X86_CR4_FSGSBASE; \ + if (!__cpu_has(__c, X86_FEATURE_PKU)) \ + __reserved_bits |= X86_CR4_PKE; \ + if (!__cpu_has(__c, X86_FEATURE_LA57)) \ + __reserved_bits |= X86_CR4_LA57; \ + __reserved_bits; \ +}) - if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE)) - return -EINVAL; +static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c) +{ + u64 reserved_bits = __cr4_reserved_bits(cpu_has, c); - if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP)) - return -EINVAL; + if (cpuid_ecx(0x7) & feature_bit(LA57)) + reserved_bits &= ~X86_CR4_LA57; - if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP)) - return -EINVAL; + if (kvm_x86_ops->umip_emulated()) + reserved_bits &= ~X86_CR4_UMIP; - if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE)) - return -EINVAL; - - if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE)) - return -EINVAL; + return reserved_bits; +} - if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57)) +static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + if (cr4 & cr4_reserved_bits) return -EINVAL; - if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP)) + if (cr4 & __cr4_reserved_bits(guest_cpuid_has, vcpu)) return -EINVAL; return 0; @@ -1047,9 +1063,11 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) { + size_t size = ARRAY_SIZE(vcpu->arch.db); + switch (dr) { case 0 ... 3: - vcpu->arch.db[dr] = val; + vcpu->arch.db[array_index_nospec(dr, size)] = val; if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) vcpu->arch.eff_db[dr] = val; break; @@ -1064,7 +1082,7 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) case 5: /* fall through */ default: /* 7 */ - if (val & 0xffffffff00000000ULL) + if (!kvm_dr7_valid(val)) return -1; /* #GP */ vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; kvm_update_dr7(vcpu); @@ -1086,9 +1104,11 @@ EXPORT_SYMBOL_GPL(kvm_set_dr); int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) { + size_t size = ARRAY_SIZE(vcpu->arch.db); + switch (dr) { case 0 ... 3: - *val = vcpu->arch.db[dr]; + *val = vcpu->arch.db[array_index_nospec(dr, size)]; break; case 4: /* fall through */ @@ -1212,6 +1232,7 @@ static const u32 emulated_msrs_all[] = { MSR_MISC_FEATURES_ENABLES, MSR_AMD64_VIRT_SPEC_CTRL, MSR_IA32_POWER_CTL, + MSR_IA32_UCODE_REV, /* * The following list leaves out MSRs whose values are determined @@ -1526,6 +1547,49 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr); /* + * The fast path for frequent and performance sensitive wrmsr emulation, + * i.e. the sending of IPI, sending IPI early in the VM-Exit flow reduces + * the latency of virtual IPI by avoiding the expensive bits of transitioning + * from guest to host, e.g. reacquiring KVM's SRCU lock. In contrast to the + * other cases which must be called after interrupts are enabled on the host. + */ +static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data) +{ + if (lapic_in_kernel(vcpu) && apic_x2apic_mode(vcpu->arch.apic) && + ((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) && + ((data & APIC_MODE_MASK) == APIC_DM_FIXED)) { + + kvm_lapic_set_reg(vcpu->arch.apic, APIC_ICR2, (u32)(data >> 32)); + return kvm_lapic_reg_write(vcpu->arch.apic, APIC_ICR, (u32)data); + } + + return 1; +} + +enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) +{ + u32 msr = kvm_rcx_read(vcpu); + u64 data = kvm_read_edx_eax(vcpu); + int ret = 0; + + switch (msr) { + case APIC_BASE_MSR + (APIC_ICR >> 4): + ret = handle_fastpath_set_x2apic_icr_irqoff(vcpu, data); + break; + default: + return EXIT_FASTPATH_NONE; + } + + if (!ret) { + trace_kvm_msr_write(msr, data); + return EXIT_FASTPATH_SKIP_EMUL_INS; + } + + return EXIT_FASTPATH_NONE; +} +EXPORT_SYMBOL_GPL(handle_fastpath_set_msr_irqoff); + +/* * Adapt set_msr() to msr_io()'s calling convention */ static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) @@ -2485,7 +2549,10 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; + u32 offset = array_index_nospec( + msr - MSR_IA32_MC0_CTL, + MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL); + /* only 0 or all 1s can be written to IA32_MCi_CTL * some Linux kernels though clear bit 10 in bank 4 to * workaround a BIOS/GART TBL issue on AMD K8s, ignore @@ -2926,7 +2993,10 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) default: if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MCx_CTL(bank_num)) { - u32 offset = msr - MSR_IA32_MC0_CTL; + u32 offset = array_index_nospec( + msr - MSR_IA32_MC0_CTL, + MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL); + data = vcpu->arch.mce_banks[offset]; break; } @@ -3458,10 +3528,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_x86_ops->vcpu_load(vcpu, cpu); - fpregs_assert_state_consistent(); - if (test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_return(); - /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); @@ -4660,9 +4726,6 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, { struct kvm_pit *pit = kvm->arch.vpit; - if (!pit) - return -ENXIO; - /* pit->pit_state.lock was overloaded to prevent userspace from getting * an inconsistent state after running multiple KVM_REINJECT_CONTROL * ioctls in parallel. Use a separate lock if that ioctl isn't rare. @@ -5029,6 +5092,9 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&control, argp, sizeof(control))) goto out; + r = -ENXIO; + if (!kvm->arch.vpit) + goto out; r = kvm_vm_ioctl_reinject(kvm, &control); break; } @@ -6186,6 +6252,21 @@ static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, check_limit); } +static bool emulator_guest_has_long_mode(struct x86_emulate_ctxt *ctxt) +{ + return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_LM); +} + +static bool emulator_guest_has_movbe(struct x86_emulate_ctxt *ctxt) +{ + return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE); +} + +static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt) +{ + return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); +} + static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg) { return kvm_register_read(emul_to_vcpu(ctxt), reg); @@ -6263,6 +6344,9 @@ static const struct x86_emulate_ops emulate_ops = { .fix_hypercall = emulator_fix_hypercall, .intercept = emulator_intercept, .get_cpuid = emulator_get_cpuid, + .guest_has_long_mode = emulator_guest_has_long_mode, + .guest_has_movbe = emulator_guest_has_movbe, + .guest_has_fxsr = emulator_guest_has_fxsr, .set_nmi_mask = emulator_set_nmi_mask, .get_hflags = emulator_get_hflags, .set_hflags = emulator_set_hflags, @@ -6379,11 +6463,11 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) return 1; } -static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, +static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool write_fault_to_shadow_pgtable, int emulation_type) { - gpa_t gpa = cr2; + gpa_t gpa = cr2_or_gpa; kvm_pfn_t pfn; if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) @@ -6397,7 +6481,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, * Write permission should be allowed since only * write access need to be emulated. */ - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); /* * If the mapping is invalid in guest, let cpu retry @@ -6454,10 +6538,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, } static bool retry_instruction(struct x86_emulate_ctxt *ctxt, - unsigned long cr2, int emulation_type) + gpa_t cr2_or_gpa, int emulation_type) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - unsigned long last_retry_eip, last_retry_addr, gpa = cr2; + unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa; last_retry_eip = vcpu->arch.last_retry_eip; last_retry_addr = vcpu->arch.last_retry_addr; @@ -6486,14 +6570,14 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, if (x86_page_table_writing_insn(ctxt)) return false; - if (ctxt->eip == last_retry_eip && last_retry_addr == cr2) + if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa) return false; vcpu->arch.last_retry_eip = ctxt->eip; - vcpu->arch.last_retry_addr = cr2; + vcpu->arch.last_retry_addr = cr2_or_gpa; if (!vcpu->arch.mmu->direct_map) - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); @@ -6639,11 +6723,8 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) return false; } -int x86_emulate_instruction(struct kvm_vcpu *vcpu, - unsigned long cr2, - int emulation_type, - void *insn, - int insn_len) +int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + int emulation_type, void *insn, int insn_len) { int r; struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; @@ -6689,8 +6770,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, kvm_queue_exception(vcpu, UD_VECTOR); return 1; } - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, - emulation_type)) + if (reexecute_instruction(vcpu, cr2_or_gpa, + write_fault_to_spt, + emulation_type)) return 1; if (ctxt->have_exception) { /* @@ -6724,7 +6806,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, return 1; } - if (retry_instruction(ctxt, cr2, emulation_type)) + if (retry_instruction(ctxt, cr2_or_gpa, emulation_type)) return 1; /* this is needed for vmware backdoor interface to work since it @@ -6736,7 +6818,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, restart: /* Save the faulting GPA (cr2) in the address field */ - ctxt->exception.address = cr2; + ctxt->exception.address = cr2_or_gpa; r = x86_emulate_insn(ctxt); @@ -6744,7 +6826,7 @@ restart: return 1; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2, write_fault_to_spt, + if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt, emulation_type)) return 1; @@ -7357,8 +7439,8 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) { struct kvm_lapic_irq lapic_irq; - lapic_irq.shorthand = 0; - lapic_irq.dest_mode = 0; + lapic_irq.shorthand = APIC_DEST_NOSHORT; + lapic_irq.dest_mode = APIC_DEST_PHYSICAL; lapic_irq.level = 0; lapic_irq.dest_id = apicid; lapic_irq.msi_redir_hint = false; @@ -7997,6 +8079,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) bool req_int_win = dm_request_for_irq_injection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); + enum exit_fastpath_completion exit_fastpath = EXIT_FASTPATH_NONE; bool req_immediate_exit = false; @@ -8198,8 +8281,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) trace_kvm_entry(vcpu->vcpu_id); guest_enter_irqoff(); - /* The preempt notifier should have taken care of the FPU already. */ - WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD)); + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); @@ -8243,7 +8327,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_x86_ops->handle_exit_irqoff(vcpu); + kvm_x86_ops->handle_exit_irqoff(vcpu, &exit_fastpath); /* * Consume any pending interrupts, including the possible source of @@ -8287,7 +8371,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_lapic_sync_from_vapic(vcpu); vcpu->arch.gpa_available = false; - r = kvm_x86_ops->handle_exit(vcpu); + r = kvm_x86_ops->handle_exit(vcpu, exit_fastpath); return r; cancel_injection: @@ -8471,12 +8555,26 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) return 0; } +static void kvm_save_current_fpu(struct fpu *fpu) +{ + /* + * If the target FPU state is not resident in the CPU registers, just + * memcpy() from current, else save CPU state directly to the target. + */ + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + memcpy(&fpu->state, ¤t->thread.fpu.state, + fpu_kernel_xstate_size); + else + copy_fpregs_to_fpstate(fpu); +} + /* Swap (qemu) user FPU context for the guest FPU context. */ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(vcpu->arch.user_fpu); + kvm_save_current_fpu(vcpu->arch.user_fpu); + /* PKRU is separately restored in kvm_x86_ops->run. */ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, ~XFEATURE_MASK_PKRU); @@ -8492,7 +8590,8 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(vcpu->arch.guest_fpu); + kvm_save_current_fpu(vcpu->arch.guest_fpu); + copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state); fpregs_mark_activate(); @@ -8714,6 +8813,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { vcpu_load(vcpu); + if (kvm_mpx_supported()) + kvm_load_guest_fpu(vcpu); kvm_apic_accept_events(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && @@ -8722,6 +8823,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, else mp_state->mp_state = vcpu->arch.mp_state; + if (kvm_mpx_supported()) + kvm_put_guest_fpu(vcpu); vcpu_put(vcpu); return 0; } @@ -9082,33 +9185,90 @@ static void fx_init(struct kvm_vcpu *vcpu) vcpu->arch.cr0 |= X86_CR0_ET; } -void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { - void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; - - kvmclock_reset(vcpu); + if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) + pr_warn_once("kvm: SMP vm created on host with unstable TSC; " + "guest TSC will not be reliable\n"); - kvm_x86_ops->vcpu_free(vcpu); - free_cpumask_var(wbinvd_dirty_mask); + return 0; } -struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, - unsigned int id) +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu; + struct page *page; + int r; - if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) - printk_once(KERN_WARNING - "kvm: SMP vm created on host with unstable TSC; " - "guest TSC will not be reliable\n"); + 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; + else + vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; - vcpu = kvm_x86_ops->vcpu_create(kvm, id); + kvm_set_tsc_khz(vcpu, max_tsc_khz); - return vcpu; -} + r = kvm_mmu_create(vcpu); + if (r < 0) + return r; + + if (irqchip_in_kernel(vcpu->kvm)) { + vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu->kvm); + r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); + if (r < 0) + goto fail_mmu_destroy; + } else + static_key_slow_inc(&kvm_no_apic_vcpu); + + r = -ENOMEM; + + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) + goto fail_free_lapic; + vcpu->arch.pio_data = page_address(page); + + vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4, + GFP_KERNEL_ACCOUNT); + if (!vcpu->arch.mce_banks) + goto fail_free_pio_data; + vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; + + if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, + GFP_KERNEL_ACCOUNT)) + goto fail_free_mce_banks; + + vcpu->arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!vcpu->arch.user_fpu) { + pr_err("kvm: failed to allocate userspace's fpu\n"); + goto free_wbinvd_dirty_mask; + } + + vcpu->arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!vcpu->arch.guest_fpu) { + pr_err("kvm: failed to allocate vcpu's fpu\n"); + goto free_user_fpu; + } + fx_init(vcpu); + + vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + + vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + + vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; + + kvm_async_pf_hash_reset(vcpu); + kvm_pmu_init(vcpu); + + vcpu->arch.pending_external_vector = -1; + vcpu->arch.preempted_in_kernel = false; + + kvm_hv_vcpu_init(vcpu); + + r = kvm_x86_ops->vcpu_create(vcpu); + if (r) + goto free_guest_fpu; -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) -{ vcpu->arch.arch_capabilities = kvm_get_arch_capabilities(); vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; kvm_vcpu_mtrr_init(vcpu); @@ -9117,6 +9277,22 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) kvm_init_mmu(vcpu, false); vcpu_put(vcpu); return 0; + +free_guest_fpu: + kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); +free_user_fpu: + kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); +free_wbinvd_dirty_mask: + free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); +fail_free_mce_banks: + kfree(vcpu->arch.mce_banks); +fail_free_pio_data: + free_page((unsigned long)vcpu->arch.pio_data); +fail_free_lapic: + kvm_free_lapic(vcpu); +fail_mmu_destroy: + kvm_mmu_destroy(vcpu); + return r; } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) @@ -9149,13 +9325,26 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - vcpu->arch.apf.msr_val = 0; + int idx; - vcpu_load(vcpu); - kvm_mmu_unload(vcpu); - vcpu_put(vcpu); + kvmclock_reset(vcpu); kvm_x86_ops->vcpu_free(vcpu); + + free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); + kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu); + kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu); + + kvm_hv_vcpu_uninit(vcpu); + kvm_pmu_destroy(vcpu); + kfree(vcpu->arch.mce_banks); + kvm_free_lapic(vcpu); + idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_mmu_destroy(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + free_page((unsigned long)vcpu->arch.pio_data); + if (!lapic_in_kernel(vcpu)) + static_key_slow_dec(&kvm_no_apic_vcpu); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -9171,7 +9360,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.nmi_injected = false; kvm_clear_interrupt_queue(vcpu); kvm_clear_exception_queue(vcpu); - vcpu->arch.exception.pending = false; memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); @@ -9347,6 +9535,8 @@ int kvm_arch_hardware_setup(void) if (r != 0) return r; + cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data); + if (kvm_has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that @@ -9375,6 +9565,13 @@ void kvm_arch_hardware_unsetup(void) int kvm_arch_check_processor_compat(void) { + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + + WARN_ON(!irqs_disabled()); + + if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits) + return -EIO; + return kvm_x86_ops->check_processor_compatibility(); } @@ -9392,98 +9589,6 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) struct static_key kvm_no_apic_vcpu __read_mostly; EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu); -int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) -{ - struct page *page; - int r; - - 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; - else - vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; - - page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) { - r = -ENOMEM; - goto fail; - } - vcpu->arch.pio_data = page_address(page); - - kvm_set_tsc_khz(vcpu, max_tsc_khz); - - r = kvm_mmu_create(vcpu); - if (r < 0) - goto fail_free_pio_data; - - if (irqchip_in_kernel(vcpu->kvm)) { - vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu->kvm); - r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); - if (r < 0) - goto fail_mmu_destroy; - } else - static_key_slow_inc(&kvm_no_apic_vcpu); - - vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4, - 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_ACCOUNT)) { - r = -ENOMEM; - goto fail_free_mce_banks; - } - - fx_init(vcpu); - - vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; - - vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - - vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; - - kvm_async_pf_hash_reset(vcpu); - kvm_pmu_init(vcpu); - - vcpu->arch.pending_external_vector = -1; - vcpu->arch.preempted_in_kernel = false; - - kvm_hv_vcpu_init(vcpu); - - return 0; - -fail_free_mce_banks: - kfree(vcpu->arch.mce_banks); -fail_free_lapic: - kvm_free_lapic(vcpu); -fail_mmu_destroy: - kvm_mmu_destroy(vcpu); -fail_free_pio_data: - free_page((unsigned long)vcpu->arch.pio_data); -fail: - return r; -} - -void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) -{ - int idx; - - kvm_hv_vcpu_uninit(vcpu); - kvm_pmu_destroy(vcpu); - kfree(vcpu->arch.mce_banks); - kvm_free_lapic(vcpu); - idx = srcu_read_lock(&vcpu->kvm->srcu); - kvm_mmu_destroy(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - free_page((unsigned long)vcpu->arch.pio_data); - if (!lapic_in_kernel(vcpu)) - static_key_slow_dec(&kvm_no_apic_vcpu); -} - void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -9558,7 +9663,7 @@ static void kvm_free_vcpus(struct kvm *kvm) kvm_unload_vcpu_mmu(vcpu); } kvm_for_each_vcpu(i, vcpu, kvm) - kvm_arch_vcpu_free(vcpu); + kvm_vcpu_destroy(vcpu); mutex_lock(&kvm->lock); for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) @@ -9627,18 +9732,6 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) } EXPORT_SYMBOL_GPL(__x86_set_memory_region); -int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) -{ - int r; - - mutex_lock(&kvm->slots_lock); - r = __x86_set_memory_region(kvm, id, gpa, size); - mutex_unlock(&kvm->slots_lock); - - return r; -} -EXPORT_SYMBOL_GPL(x86_set_memory_region); - void kvm_arch_pre_destroy_vm(struct kvm *kvm) { kvm_mmu_pre_destroy_vm(kvm); @@ -9652,9 +9745,13 @@ void kvm_arch_destroy_vm(struct kvm *kvm) * unless the the memory map has changed due to process exit * or fd copying. */ - x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); - x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0); - x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); + mutex_lock(&kvm->slots_lock); + __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + 0, 0); + __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, + 0, 0); + __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); + mutex_unlock(&kvm->slots_lock); } if (kvm_x86_ops->vm_destroy) kvm_x86_ops->vm_destroy(kvm); @@ -9792,7 +9889,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, * * The reason is, in case of PML, we need to set D-bit for any slots * with dirty logging disabled in order to eliminate unnecessary GPA - * logging in PML buffer (and potential PML buffer full VMEXT). This + * logging in PML buffer (and potential PML buffer full VMEXIT). This * guarantees leaving PML enabled during guest's lifetime won't have * any additional overhead from PML when guest is running with dirty * logging disabled for memory slots. @@ -10014,7 +10111,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu)) return; - vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true); + vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true); } static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) @@ -10127,7 +10224,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, { struct x86_exception fault; - trace_kvm_async_pf_not_present(work->arch.token, work->gva); + trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa); kvm_add_async_pf_gfn(vcpu, work->arch.gfn); if (kvm_can_deliver_async_pf(vcpu) && @@ -10162,7 +10259,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); - trace_kvm_async_pf_ready(work->arch.token, work->gva); + trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa); if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED && !apf_get_user(vcpu, &val)) { @@ -10284,7 +10381,6 @@ bool kvm_vector_hashing_enabled(void) { return vector_hashing; } -EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled); bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { @@ -10292,6 +10388,28 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_arch_no_poll); +u64 kvm_spec_ctrl_valid_bits(struct kvm_vcpu *vcpu) +{ + uint64_t bits = SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS)) + bits &= ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP); + if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL) && + !boot_cpu_has(X86_FEATURE_AMD_IBRS)) + bits &= ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP); + + if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL_SSBD) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)) + bits &= ~SPEC_CTRL_SSBD; + if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) && + !boot_cpu_has(X86_FEATURE_AMD_SSBD)) + bits &= ~SPEC_CTRL_SSBD; + + return bits; +} +EXPORT_SYMBOL_GPL(kvm_spec_ctrl_valid_bits); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 29391af8871d..2d2ff855773b 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -144,11 +144,6 @@ static inline bool is_pae_paging(struct kvm_vcpu *vcpu) return !is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu); } -static inline u32 bit(int bitno) -{ - return 1 << (bitno & 31); -} - static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu) { return kvm_read_cr4_bits(vcpu, X86_CR4_LA57) ? 57 : 48; @@ -166,21 +161,13 @@ static inline u64 get_canonical(u64 la, u8 vaddr_bits) static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu) { -#ifdef CONFIG_X86_64 return get_canonical(la, vcpu_virt_addr_bits(vcpu)) != la; -#else - return false; -#endif } static inline bool emul_is_noncanonical_address(u64 la, struct x86_emulate_ctxt *ctxt) { -#ifdef CONFIG_X86_64 return get_canonical(la, ctxt_virt_addr_bits(ctxt)) != la; -#else - return false; -#endif } static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, @@ -289,8 +276,9 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int page_num); bool kvm_vector_hashing_enabled(void); -int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, +int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len); +enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ @@ -369,7 +357,14 @@ static inline bool kvm_pat_valid(u64 data) return (data | ((data & 0x0202020202020202ull) << 1)) == data; } +static inline bool kvm_dr7_valid(unsigned long data) +{ + /* Bits [63:32] are reserved */ + return !(data >> 32); +} + void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu); void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu); +u64 kvm_spec_ctrl_valid_bits(struct kvm_vcpu *vcpu); #endif diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 930edeb41ec3..0a74407ef92e 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -865,10 +865,8 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index dcb9bc961b39..bcfede46fe02 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1212,10 +1212,8 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap); - struct zone *zone = page_zone(page); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); kernel_physical_mapping_remove(start, start + size); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 1b99ad05b117..2c70a8b20b04 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -618,6 +618,17 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) } EXPORT_SYMBOL_GPL(lookup_address); +/* + * Lookup the page table entry for a virtual address in a given mm. Return a + * pointer to the entry and the level of the mapping. + */ +pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, + unsigned int *level) +{ + return lookup_address_in_pgd(pgd_offset(mm, address), address, level); +} +EXPORT_SYMBOL_GPL(lookup_address_in_mm); + static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, unsigned int *level) { diff --git a/block/bio.c b/block/bio.c index a5d75f6bf4c7..006bcc52a77e 100644 --- a/block/bio.c +++ b/block/bio.c @@ -538,6 +538,45 @@ void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start) } EXPORT_SYMBOL(zero_fill_bio_iter); +void bio_truncate(struct bio *bio, unsigned new_size) +{ + struct bio_vec bv; + struct bvec_iter iter; + unsigned int done = 0; + bool truncated = false; + + if (new_size >= bio->bi_iter.bi_size) + return; + + if (bio_data_dir(bio) != READ) + goto exit; + + bio_for_each_segment(bv, bio, iter) { + if (done + bv.bv_len > new_size) { + unsigned offset; + + if (!truncated) + offset = new_size - done; + else + offset = 0; + zero_user(bv.bv_page, offset, bv.bv_len - offset); + truncated = true; + } + done += bv.bv_len; + } + + exit: + /* + * Don't touch bvec table here and make it really immutable, since + * fs bio user has to retrieve all pages via bio_for_each_segment_all + * in its .end_bio() callback. + * + * It is enough to truncate bio by updating .bi_size since we can make + * correct bvec with the updated .bi_size for drivers. + */ + bio->bi_iter.bi_size = new_size; +} + /** * bio_put - release a reference to a bio * @bio: bio to release reference to diff --git a/block/blk-merge.c b/block/blk-merge.c index d783bdc4559b..347782a24a35 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -157,16 +157,14 @@ static inline unsigned get_max_io_size(struct request_queue *q, return sectors & (lbs - 1); } -static unsigned get_max_segment_size(const struct request_queue *q, - unsigned offset) +static inline unsigned get_max_segment_size(const struct request_queue *q, + struct page *start_page, + unsigned long offset) { unsigned long mask = queue_segment_boundary(q); - /* default segment boundary mask means no boundary limit */ - if (mask == BLK_SEG_BOUNDARY_MASK) - return queue_max_segment_size(q); - - return min_t(unsigned long, mask - (mask & offset) + 1, + offset = mask & (page_to_phys(start_page) + offset); + return min_t(unsigned long, mask - offset + 1, queue_max_segment_size(q)); } @@ -201,7 +199,8 @@ static bool bvec_split_segs(const struct request_queue *q, unsigned seg_size = 0; while (len && *nsegs < max_segs) { - seg_size = get_max_segment_size(q, bv->bv_offset + total_len); + seg_size = get_max_segment_size(q, bv->bv_page, + bv->bv_offset + total_len); seg_size = min(seg_size, len); (*nsegs)++; @@ -419,7 +418,8 @@ static unsigned blk_bvec_map_sg(struct request_queue *q, while (nbytes > 0) { unsigned offset = bvec->bv_offset + total; - unsigned len = min(get_max_segment_size(q, offset), nbytes); + unsigned len = min(get_max_segment_size(q, bvec->bv_page, + offset), nbytes); struct page *page = bvec->bv_page; /* diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index d4d88b581822..5cf49d9db95e 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -186,7 +186,10 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op, if (zone->cond == BLK_ZONE_COND_FULL) return BLK_STS_IOERR; - zone->cond = BLK_ZONE_COND_CLOSED; + if (zone->wp == zone->start) + zone->cond = BLK_ZONE_COND_EMPTY; + else + zone->cond = BLK_ZONE_COND_CLOSED; break; case REQ_OP_ZONE_FINISH: if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) diff --git a/drivers/char/agp/isoch.c b/drivers/char/agp/isoch.c index 31c374b1b91b..7ecf20a6d19c 100644 --- a/drivers/char/agp/isoch.c +++ b/drivers/char/agp/isoch.c @@ -84,7 +84,6 @@ static int agp_3_5_isochronous_node_enable(struct agp_bridge_data *bridge, unsigned int cdev = 0; u32 mnistat, tnistat, tstatus, mcmd; u16 tnicmd, mnicmd; - u8 mcapndx; u32 tot_bw = 0, tot_n = 0, tot_rq = 0, y_max, rq_isoch, rq_async; u32 step, rem, rem_isoch, rem_async; int ret = 0; @@ -138,8 +137,6 @@ static int agp_3_5_isochronous_node_enable(struct agp_bridge_data *bridge, cur = list_entry(pos, struct agp_3_5_dev, list); dev = cur->dev; - mcapndx = cur->capndx; - pci_read_config_dword(dev, cur->capndx+AGPNISTAT, &mnistat); master[cdev].maxbw = (mnistat >> 16) & 0xff; @@ -251,8 +248,6 @@ static int agp_3_5_isochronous_node_enable(struct agp_bridge_data *bridge, cur = master[cdev].dev; dev = cur->dev; - mcapndx = cur->capndx; - master[cdev].rq += (cdev == ndevs - 1) ? (rem_async + rem_isoch) : step; @@ -319,7 +314,7 @@ int agp_3_5_enable(struct agp_bridge_data *bridge) { struct pci_dev *td = bridge->dev, *dev = NULL; u8 mcapndx; - u32 isoch, arqsz; + u32 isoch; u32 tstatus, mstatus, ncapid; u32 mmajor; u16 mpstat; @@ -334,8 +329,6 @@ int agp_3_5_enable(struct agp_bridge_data *bridge) if (isoch == 0) /* isoch xfers not available, bail out. */ return -ENODEV; - arqsz = (tstatus >> 13) & 0x7; - /* * Allocate a head for our AGP 3.5 device list * (multiple AGP v3 devices are allowed behind a single bridge). diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c index 4e54856ce2a5..c4f15c4068c0 100644 --- a/drivers/clocksource/timer-riscv.c +++ b/drivers/clocksource/timer-riscv.c @@ -56,7 +56,7 @@ static unsigned long long riscv_clocksource_rdtime(struct clocksource *cs) return get_cycles64(); } -static u64 riscv_sched_clock(void) +static u64 notrace riscv_sched_clock(void) { return get_cycles64(); } diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c index fa626acdc9b9..44af435628f8 100644 --- a/drivers/dma/dma-jz4780.c +++ b/drivers/dma/dma-jz4780.c @@ -999,7 +999,8 @@ static const struct jz4780_dma_soc_data jz4740_dma_soc_data = { static const struct jz4780_dma_soc_data jz4725b_dma_soc_data = { .nb_channels = 6, .transfer_ord_max = 5, - .flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC, + .flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC | + JZ_SOC_DATA_BREAK_LINKS, }; static const struct jz4780_dma_soc_data jz4770_dma_soc_data = { diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index 1a422a8b43cf..18c011e57592 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -377,10 +377,11 @@ ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags) descs->virt = dma_alloc_coherent(to_dev(ioat_chan), SZ_2M, &descs->hw, flags); - if (!descs->virt && (i > 0)) { + if (!descs->virt) { int idx; for (idx = 0; idx < i; idx++) { + descs = &ioat_chan->descs[idx]; dma_free_coherent(to_dev(ioat_chan), SZ_2M, descs->virt, descs->hw); descs->virt = NULL; diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c index adecea51814f..c5c1aa0dcaed 100644 --- a/drivers/dma/k3dma.c +++ b/drivers/dma/k3dma.c @@ -229,9 +229,11 @@ static irqreturn_t k3_dma_int_handler(int irq, void *dev_id) c = p->vchan; if (c && (tc1 & BIT(i))) { spin_lock_irqsave(&c->vc.lock, flags); - vchan_cookie_complete(&p->ds_run->vd); - p->ds_done = p->ds_run; - p->ds_run = NULL; + if (p->ds_run != NULL) { + vchan_cookie_complete(&p->ds_run->vd); + p->ds_done = p->ds_run; + p->ds_run = NULL; + } spin_unlock_irqrestore(&c->vc.lock, flags); } if (c && (tc2 & BIT(i))) { @@ -271,6 +273,10 @@ static int k3_dma_start_txd(struct k3_dma_chan *c) if (BIT(c->phy->idx) & k3_dma_get_chan_stat(d)) return -EAGAIN; + /* Avoid losing track of ds_run if a transaction is in flight */ + if (c->phy->ds_run) + return -EAGAIN; + if (vd) { struct k3_dma_desc_sw *ds = container_of(vd, struct k3_dma_desc_sw, vd); diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c index ec4adf4260a0..256fc662c500 100644 --- a/drivers/dma/virt-dma.c +++ b/drivers/dma/virt-dma.c @@ -104,9 +104,8 @@ static void vchan_complete(unsigned long arg) dmaengine_desc_get_callback(&vd->tx, &cb); list_del(&vd->node); - vchan_vdesc_fini(vd); - dmaengine_desc_callback_invoke(&cb, &vd->tx_result); + vchan_vdesc_fini(vd); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index a97fb759e2f4..3e35a8f2c5e5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -613,7 +613,17 @@ static bool amdgpu_atpx_detect(void) bool d3_supported = false; struct pci_dev *parent_pdev; - while ((pdev = pci_get_class(PCI_BASE_CLASS_DISPLAY << 16, pdev)) != NULL) { + while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) { + vga_count++; + + has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true); + + parent_pdev = pci_upstream_bridge(pdev); + d3_supported |= parent_pdev && parent_pdev->bridge_d3; + amdgpu_atpx_get_quirks(pdev); + } + + while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) { vga_count++; has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 44be3a45b25e..e1b8d8daeafc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -1488,7 +1488,7 @@ out: /* Start rlc autoload after psp recieved all the gfx firmware */ if (psp->autoload_supported && ucode->ucode_id == (amdgpu_sriov_vf(adev) ? - AMDGPU_UCODE_ID_CP_MEC2 : AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM)) { + AMDGPU_UCODE_ID_CP_MEC2 : AMDGPU_UCODE_ID_RLC_G)) { ret = psp_rlc_autoload(psp); if (ret) { DRM_ERROR("Failed to start rlc autoload\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 410587b950f3..914acecda5cf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -292,10 +292,10 @@ enum AMDGPU_UCODE_ID { AMDGPU_UCODE_ID_CP_MEC2_JT, AMDGPU_UCODE_ID_CP_MES, AMDGPU_UCODE_ID_CP_MES_DATA, - AMDGPU_UCODE_ID_RLC_G, AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL, AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM, AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM, + AMDGPU_UCODE_ID_RLC_G, AMDGPU_UCODE_ID_STORAGE, AMDGPU_UCODE_ID_SMC, AMDGPU_UCODE_ID_UVD, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 66328ffa395a..97105a5bb246 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1052,17 +1052,10 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev) case CHIP_VEGA20: break; case CHIP_RAVEN: - /* Disable GFXOFF on original raven. There are combinations - * of sbios and platforms that are not stable. - */ - if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)) - adev->pm.pp_feature &= ~PP_GFXOFF_MASK; - else if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8) - &&((adev->gfx.rlc_fw_version != 106 && - adev->gfx.rlc_fw_version < 531) || - (adev->gfx.rlc_fw_version == 53815) || - (adev->gfx.rlc_feature_version < 1) || - !adev->gfx.rlc.is_rlc_v2_1)) + if (!(adev->rev_id >= 0x8 || + adev->pdev->device == 0x15d8) && + (adev->pm.fw_version < 0x41e2b || /* not raven1 fresh */ + !adev->gfx.rlc.is_rlc_v2_1)) /* without rlc save restore ucodes */ adev->pm.pp_feature &= ~PP_GFXOFF_MASK; if (adev->pm.pp_feature & PP_GFXOFF_MASK) diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index 5ff7ccedfbed..a23729d3174b 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -866,6 +866,7 @@ static int smu_sw_init(void *handle) smu->smu_baco.platform_support = false; mutex_init(&smu->sensor_lock); + mutex_init(&smu->metrics_lock); smu->watermarks_bitmap = 0; smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT; diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c index cc71a1078a7a..472e9fed411a 100644 --- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c @@ -862,18 +862,21 @@ static int arcturus_get_metrics_table(struct smu_context *smu, struct smu_table_context *smu_table= &smu->smu_table; int ret = 0; + mutex_lock(&smu->metrics_lock); if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) { ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0, (void *)smu_table->metrics_table, false); if (ret) { pr_info("Failed to export SMU metrics table!\n"); + mutex_unlock(&smu->metrics_lock); return ret; } smu_table->metrics_time = jiffies; } memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t)); + mutex_unlock(&smu->metrics_lock); return ret; } diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h index ac9758305ab3..41fce75b263f 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h @@ -349,6 +349,7 @@ struct smu_context const struct pptable_funcs *ppt_funcs; struct mutex mutex; struct mutex sensor_lock; + struct mutex metrics_lock; uint64_t pool_size; struct smu_table_context smu_table; diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 4a14fd1f9fd5..ca62e92e5a4f 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -562,17 +562,20 @@ static int navi10_get_metrics_table(struct smu_context *smu, struct smu_table_context *smu_table= &smu->smu_table; int ret = 0; + mutex_lock(&smu->metrics_lock); if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(100))) { ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0, (void *)smu_table->metrics_table, false); if (ret) { pr_info("Failed to export SMU metrics table!\n"); + mutex_unlock(&smu->metrics_lock); return ret; } smu_table->metrics_time = jiffies; } memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t)); + mutex_unlock(&smu->metrics_lock); return ret; } diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c index 60b9ff097142..0d3a3b0a934e 100644 --- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c @@ -1678,17 +1678,20 @@ static int vega20_get_metrics_table(struct smu_context *smu, struct smu_table_context *smu_table= &smu->smu_table; int ret = 0; + mutex_lock(&smu->metrics_lock); if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) { ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0, (void *)smu_table->metrics_table, false); if (ret) { pr_info("Failed to export SMU metrics table!\n"); + mutex_unlock(&smu->metrics_lock); return ret; } smu_table->metrics_time = jiffies; } memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t)); + mutex_unlock(&smu->metrics_lock); return ret; } diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c index 875a3a9eabfa..7d0e7b031e44 100644 --- a/drivers/gpu/drm/arm/malidp_mw.c +++ b/drivers/gpu/drm/arm/malidp_mw.c @@ -56,7 +56,7 @@ malidp_mw_connector_mode_valid(struct drm_connector *connector, return MODE_OK; } -const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = { +static const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = { .get_modes = malidp_mw_connector_get_modes, .mode_valid = malidp_mw_connector_mode_valid, }; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index f80a8ba75977..3305a94fc930 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -215,11 +215,12 @@ struct mtk_ddp_comp *mtk_drm_ddp_comp_for_plane(struct drm_crtc *crtc, struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); struct mtk_ddp_comp *comp; int i, count = 0; + unsigned int local_index = plane - mtk_crtc->planes; for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) { comp = mtk_crtc->ddp_comp[i]; - if (plane->index < (count + mtk_ddp_comp_layer_nr(comp))) { - *local_layer = plane->index - count; + if (local_index < (count + mtk_ddp_comp_layer_nr(comp))) { + *local_layer = local_index - count; return comp; } count += mtk_ddp_comp_layer_nr(comp); @@ -310,7 +311,9 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc) plane_state = to_mtk_plane_state(plane->state); comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer); - mtk_ddp_comp_layer_config(comp, local_layer, plane_state); + if (comp) + mtk_ddp_comp_layer_config(comp, local_layer, + plane_state); } return 0; @@ -386,8 +389,9 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc) comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer); - mtk_ddp_comp_layer_config(comp, local_layer, - plane_state); + if (comp) + mtk_ddp_comp_layer_config(comp, local_layer, + plane_state); plane_state->pending.config = false; } mtk_crtc->pending_planes = false; @@ -401,7 +405,9 @@ int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane, struct mtk_ddp_comp *comp; comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer); - return mtk_ddp_comp_layer_check(comp, local_layer, state); + if (comp) + return mtk_ddp_comp_layer_check(comp, local_layer, state); + return 0; } static void mtk_drm_crtc_atomic_enable(struct drm_crtc *crtc, diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index e9931bbbe846..d77c9f484ce3 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -230,28 +230,25 @@ static void mtk_dsi_mask(struct mtk_dsi *dsi, u32 offset, u32 mask, u32 data) static void mtk_dsi_phy_timconfig(struct mtk_dsi *dsi) { u32 timcon0, timcon1, timcon2, timcon3; - u32 ui, cycle_time; + u32 data_rate_mhz = DIV_ROUND_UP(dsi->data_rate, 1000000); struct mtk_phy_timing *timing = &dsi->phy_timing; - ui = DIV_ROUND_UP(1000000000, dsi->data_rate); - cycle_time = div_u64(8000000000ULL, dsi->data_rate); + timing->lpx = (60 * data_rate_mhz / (8 * 1000)) + 1; + timing->da_hs_prepare = (80 * data_rate_mhz + 4 * 1000) / 8000; + timing->da_hs_zero = (170 * data_rate_mhz + 10 * 1000) / 8000 + 1 - + timing->da_hs_prepare; + timing->da_hs_trail = timing->da_hs_prepare + 1; - timing->lpx = NS_TO_CYCLE(60, cycle_time); - timing->da_hs_prepare = NS_TO_CYCLE(50 + 5 * ui, cycle_time); - timing->da_hs_zero = NS_TO_CYCLE(110 + 6 * ui, cycle_time); - timing->da_hs_trail = NS_TO_CYCLE(77 + 4 * ui, cycle_time); + timing->ta_go = 4 * timing->lpx - 2; + timing->ta_sure = timing->lpx + 2; + timing->ta_get = 4 * timing->lpx; + timing->da_hs_exit = 2 * timing->lpx + 1; - timing->ta_go = 4 * timing->lpx; - timing->ta_sure = 3 * timing->lpx / 2; - timing->ta_get = 5 * timing->lpx; - timing->da_hs_exit = 2 * timing->lpx; - - timing->clk_hs_zero = NS_TO_CYCLE(336, cycle_time); - timing->clk_hs_trail = NS_TO_CYCLE(100, cycle_time) + 10; - - timing->clk_hs_prepare = NS_TO_CYCLE(64, cycle_time); - timing->clk_hs_post = NS_TO_CYCLE(80 + 52 * ui, cycle_time); - timing->clk_hs_exit = 2 * timing->lpx; + timing->clk_hs_prepare = 70 * data_rate_mhz / (8 * 1000); + timing->clk_hs_post = timing->clk_hs_prepare + 8; + timing->clk_hs_trail = timing->clk_hs_prepare; + timing->clk_hs_zero = timing->clk_hs_trail * 4; + timing->clk_hs_exit = 2 * timing->clk_hs_trail; timcon0 = timing->lpx | timing->da_hs_prepare << 8 | timing->da_hs_zero << 16 | timing->da_hs_trail << 24; @@ -482,27 +479,39 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi) dsi_tmp_buf_bpp - 10); data_phy_cycles = timing->lpx + timing->da_hs_prepare + - timing->da_hs_zero + timing->da_hs_exit + 2; + timing->da_hs_zero + timing->da_hs_exit + 3; if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) { - if (vm->hfront_porch * dsi_tmp_buf_bpp > + if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp > data_phy_cycles * dsi->lanes + 18) { - horizontal_frontporch_byte = vm->hfront_porch * - dsi_tmp_buf_bpp - - data_phy_cycles * - dsi->lanes - 18; + horizontal_frontporch_byte = + vm->hfront_porch * dsi_tmp_buf_bpp - + (data_phy_cycles * dsi->lanes + 18) * + vm->hfront_porch / + (vm->hfront_porch + vm->hback_porch); + + horizontal_backporch_byte = + horizontal_backporch_byte - + (data_phy_cycles * dsi->lanes + 18) * + vm->hback_porch / + (vm->hfront_porch + vm->hback_porch); } else { DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n"); horizontal_frontporch_byte = vm->hfront_porch * dsi_tmp_buf_bpp; } } else { - if (vm->hfront_porch * dsi_tmp_buf_bpp > + if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp > data_phy_cycles * dsi->lanes + 12) { - horizontal_frontporch_byte = vm->hfront_porch * - dsi_tmp_buf_bpp - - data_phy_cycles * - dsi->lanes - 12; + horizontal_frontporch_byte = + vm->hfront_porch * dsi_tmp_buf_bpp - + (data_phy_cycles * dsi->lanes + 12) * + vm->hfront_porch / + (vm->hfront_porch + vm->hback_porch); + horizontal_backporch_byte = horizontal_backporch_byte - + (data_phy_cycles * dsi->lanes + 12) * + vm->hback_porch / + (vm->hfront_porch + vm->hback_porch); } else { DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n"); horizontal_frontporch_byte = vm->hfront_porch * diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index a7c4654445c7..68d4644ac2dc 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -685,8 +685,6 @@ static void sun4i_hdmi_unbind(struct device *dev, struct device *master, struct sun4i_hdmi *hdmi = dev_get_drvdata(dev); cec_unregister_adapter(hdmi->cec_adap); - drm_connector_cleanup(&hdmi->connector); - drm_encoder_cleanup(&hdmi->encoder); i2c_del_adapter(hdmi->i2c); i2c_put_adapter(hdmi->ddc_i2c); clk_disable_unprepare(hdmi->mod_clk); diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c index 8df547d2d935..0aca5807a119 100644 --- a/drivers/irqchip/irq-sifive-plic.c +++ b/drivers/irqchip/irq-sifive-plic.c @@ -256,7 +256,7 @@ static int __init plic_init(struct device_node *node, * Skip contexts other than external interrupts for our * privilege level. */ - if (parent.args[0] != IRQ_EXT) + if (parent.args[0] != RV_IRQ_EXT) continue; hartid = plic_find_hart_id(parent.np); diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c index 9340435a94a0..6c95dc471d4c 100644 --- a/drivers/media/cec/cec-adap.c +++ b/drivers/media/cec/cec-adap.c @@ -380,7 +380,8 @@ static void cec_data_cancel(struct cec_data *data, u8 tx_status) } else { list_del_init(&data->list); if (!(data->msg.tx_status & CEC_TX_STATUS_OK)) - data->adap->transmit_queue_sz--; + if (!WARN_ON(!data->adap->transmit_queue_sz)) + data->adap->transmit_queue_sz--; } if (data->msg.tx_status & CEC_TX_STATUS_OK) { @@ -432,6 +433,14 @@ static void cec_flush(struct cec_adapter *adap) * need to do anything special in that case. */ } + /* + * If something went wrong and this counter isn't what it should + * be, then this will reset it back to 0. Warn if it is not 0, + * since it indicates a bug, either in this framework or in a + * CEC driver. + */ + if (WARN_ON(adap->transmit_queue_sz)) + adap->transmit_queue_sz = 0; } /* @@ -456,7 +465,7 @@ int cec_thread_func(void *_adap) bool timeout = false; u8 attempts; - if (adap->transmitting) { + if (adap->transmit_in_progress) { int err; /* @@ -491,7 +500,7 @@ int cec_thread_func(void *_adap) goto unlock; } - if (adap->transmitting && timeout) { + if (adap->transmit_in_progress && timeout) { /* * If we timeout, then log that. Normally this does * not happen and it is an indication of a faulty CEC @@ -500,14 +509,18 @@ int cec_thread_func(void *_adap) * so much traffic on the bus that the adapter was * unable to transmit for CEC_XFER_TIMEOUT_MS (2.1s). */ - pr_warn("cec-%s: message %*ph timed out\n", adap->name, - adap->transmitting->msg.len, - adap->transmitting->msg.msg); + if (adap->transmitting) { + pr_warn("cec-%s: message %*ph timed out\n", adap->name, + adap->transmitting->msg.len, + adap->transmitting->msg.msg); + /* Just give up on this. */ + cec_data_cancel(adap->transmitting, + CEC_TX_STATUS_TIMEOUT); + } else { + pr_warn("cec-%s: transmit timed out\n", adap->name); + } adap->transmit_in_progress = false; adap->tx_timeouts++; - /* Just give up on this. */ - cec_data_cancel(adap->transmitting, - CEC_TX_STATUS_TIMEOUT); goto unlock; } @@ -522,7 +535,8 @@ int cec_thread_func(void *_adap) data = list_first_entry(&adap->transmit_queue, struct cec_data, list); list_del_init(&data->list); - adap->transmit_queue_sz--; + if (!WARN_ON(!data->adap->transmit_queue_sz)) + adap->transmit_queue_sz--; /* Make this the current transmitting message */ adap->transmitting = data; @@ -1085,11 +1099,11 @@ void cec_received_msg_ts(struct cec_adapter *adap, valid_la = false; else if (!cec_msg_is_broadcast(msg) && !(dir_fl & DIRECTED)) valid_la = false; - else if (cec_msg_is_broadcast(msg) && !(dir_fl & BCAST1_4)) + else if (cec_msg_is_broadcast(msg) && !(dir_fl & BCAST)) valid_la = false; else if (cec_msg_is_broadcast(msg) && - adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0 && - !(dir_fl & BCAST2_0)) + adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0 && + !(dir_fl & BCAST1_4)) valid_la = false; } if (valid_la && min_len) { diff --git a/drivers/media/usb/pulse8-cec/pulse8-cec.c b/drivers/media/usb/pulse8-cec/pulse8-cec.c index ac88ade94cda..59609556d969 100644 --- a/drivers/media/usb/pulse8-cec/pulse8-cec.c +++ b/drivers/media/usb/pulse8-cec/pulse8-cec.c @@ -116,6 +116,7 @@ struct pulse8 { unsigned int vers; struct completion cmd_done; struct work_struct work; + u8 work_result; struct delayed_work ping_eeprom_work; struct cec_msg rx_msg; u8 data[DATA_SIZE]; @@ -137,8 +138,10 @@ static void pulse8_irq_work_handler(struct work_struct *work) { struct pulse8 *pulse8 = container_of(work, struct pulse8, work); + u8 result = pulse8->work_result; - switch (pulse8->data[0] & 0x3f) { + pulse8->work_result = 0; + switch (result & 0x3f) { case MSGCODE_FRAME_DATA: cec_received_msg(pulse8->adap, &pulse8->rx_msg); break; @@ -172,12 +175,12 @@ static irqreturn_t pulse8_interrupt(struct serio *serio, unsigned char data, pulse8->escape = false; } else if (data == MSGEND) { struct cec_msg *msg = &pulse8->rx_msg; + u8 msgcode = pulse8->buf[0]; if (debug) dev_info(pulse8->dev, "received: %*ph\n", pulse8->idx, pulse8->buf); - pulse8->data[0] = pulse8->buf[0]; - switch (pulse8->buf[0] & 0x3f) { + switch (msgcode & 0x3f) { case MSGCODE_FRAME_START: msg->len = 1; msg->msg[0] = pulse8->buf[1]; @@ -186,14 +189,20 @@ static irqreturn_t pulse8_interrupt(struct serio *serio, unsigned char data, if (msg->len == CEC_MAX_MSG_SIZE) break; msg->msg[msg->len++] = pulse8->buf[1]; - if (pulse8->buf[0] & MSGCODE_FRAME_EOM) + if (msgcode & MSGCODE_FRAME_EOM) { + WARN_ON(pulse8->work_result); + pulse8->work_result = msgcode; schedule_work(&pulse8->work); + break; + } break; case MSGCODE_TRANSMIT_SUCCEEDED: case MSGCODE_TRANSMIT_FAILED_LINE: case MSGCODE_TRANSMIT_FAILED_ACK: case MSGCODE_TRANSMIT_FAILED_TIMEOUT_DATA: case MSGCODE_TRANSMIT_FAILED_TIMEOUT_LINE: + WARN_ON(pulse8->work_result); + pulse8->work_result = msgcode; schedule_work(&pulse8->work); break; case MSGCODE_HIGH_ERROR: diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index f3f0c3f07391..1962c8330daa 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -358,7 +358,7 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port, return -EINVAL; } - ip_frag = be32_to_cpu(fs->m_ext.data[0]); + ip_frag = !!(be32_to_cpu(fs->h_ext.data[0]) & 1); /* Locate the first rule available */ if (fs->location == RX_CLS_LOC_ANY) @@ -569,7 +569,7 @@ static int bcm_sf2_cfp_rule_cmp(struct bcm_sf2_priv *priv, int port, if (rule->fs.flow_type != fs->flow_type || rule->fs.ring_cookie != fs->ring_cookie || - rule->fs.m_ext.data[0] != fs->m_ext.data[0]) + rule->fs.h_ext.data[0] != fs->h_ext.data[0]) continue; switch (fs->flow_type & ~FLOW_EXT) { @@ -621,7 +621,7 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, return -EINVAL; } - ip_frag = be32_to_cpu(fs->m_ext.data[0]); + ip_frag = !!(be32_to_cpu(fs->h_ext.data[0]) & 1); layout = &udf_tcpip6_layout; slice_num = bcm_sf2_get_slice_number(layout, 0); diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index a51ac088c0bc..1da5ac111499 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1569,8 +1569,8 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled) if (enabled) { /* Enable VLAN filtering. */ - tpid = ETH_P_8021AD; - tpid2 = ETH_P_8021Q; + tpid = ETH_P_8021Q; + tpid2 = ETH_P_8021AD; } else { /* Disable VLAN filtering. */ tpid = ETH_P_SJA1105; @@ -1579,9 +1579,9 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled) table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS]; general_params = table->entries; - /* EtherType used to identify outer tagged (S-tag) VLAN traffic */ - general_params->tpid = tpid; /* EtherType used to identify inner tagged (C-tag) VLAN traffic */ + general_params->tpid = tpid; + /* EtherType used to identify outer tagged (S-tag) VLAN traffic */ general_params->tpid2 = tpid2; /* When VLAN filtering is on, we need to at least be able to * decode management traffic through the "backup plan". @@ -1855,7 +1855,7 @@ static netdev_tx_t sja1105_port_deferred_xmit(struct dsa_switch *ds, int port, if (!clone) goto out; - sja1105_ptp_txtstamp_skb(ds, slot, clone); + sja1105_ptp_txtstamp_skb(ds, port, clone); out: mutex_unlock(&priv->mgmt_lock); diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index 54258a25031d..43ab7589d0d0 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -234,7 +234,7 @@ int sja1105_ptp_commit(struct dsa_switch *ds, struct sja1105_ptp_cmd *cmd, if (rw == SPI_WRITE) priv->info->ptp_cmd_packing(buf, cmd, PACK); - rc = sja1105_xfer_buf(priv, SPI_WRITE, regs->ptp_control, buf, + rc = sja1105_xfer_buf(priv, rw, regs->ptp_control, buf, SJA1105_SIZE_PTP_CMD); if (rw == SPI_READ) @@ -659,7 +659,7 @@ void sja1105_ptp_clock_unregister(struct dsa_switch *ds) ptp_data->clock = NULL; } -void sja1105_ptp_txtstamp_skb(struct dsa_switch *ds, int slot, +void sja1105_ptp_txtstamp_skb(struct dsa_switch *ds, int port, struct sk_buff *skb) { struct sja1105_private *priv = ds->priv; @@ -679,7 +679,7 @@ void sja1105_ptp_txtstamp_skb(struct dsa_switch *ds, int slot, goto out; } - rc = sja1105_ptpegr_ts_poll(ds, slot, &ts); + rc = sja1105_ptpegr_ts_poll(ds, port, &ts); if (rc < 0) { dev_err(ds->dev, "timed out polling for tstamp\n"); kfree_skb(skb); diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c index 0d03e13e9909..63d2311817c4 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.c +++ b/drivers/net/dsa/sja1105/sja1105_static_config.c @@ -142,6 +142,9 @@ static size_t sja1105et_general_params_entry_packing(void *buf, void *entry_ptr, return size; } +/* TPID and TPID2 are intentionally reversed so that semantic + * compatibility with E/T is kept. + */ static size_t sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr, enum packing_op op) @@ -166,9 +169,9 @@ sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr, sja1105_packing(buf, &entry->mirr_port, 141, 139, size, op); sja1105_packing(buf, &entry->vlmarker, 138, 107, size, op); sja1105_packing(buf, &entry->vlmask, 106, 75, size, op); - sja1105_packing(buf, &entry->tpid, 74, 59, size, op); + sja1105_packing(buf, &entry->tpid2, 74, 59, size, op); sja1105_packing(buf, &entry->ignore2stf, 58, 58, size, op); - sja1105_packing(buf, &entry->tpid2, 57, 42, size, op); + sja1105_packing(buf, &entry->tpid, 57, 42, size, op); sja1105_packing(buf, &entry->queue_ts, 41, 41, size, op); sja1105_packing(buf, &entry->egrmirrvid, 40, 29, size, op); sja1105_packing(buf, &entry->egrmirrpcp, 28, 26, size, op); diff --git a/drivers/net/dsa/sja1105/sja1105_tas.c b/drivers/net/dsa/sja1105/sja1105_tas.c index 26b925b5dace..fa6750d973d7 100644 --- a/drivers/net/dsa/sja1105/sja1105_tas.c +++ b/drivers/net/dsa/sja1105/sja1105_tas.c @@ -477,11 +477,6 @@ int sja1105_setup_tc_taprio(struct dsa_switch *ds, int port, if (admin->cycle_time_extension) return -ENOTSUPP; - if (!ns_to_sja1105_delta(admin->base_time)) { - dev_err(ds->dev, "A base time of zero is not hardware-allowed\n"); - return -ERANGE; - } - for (i = 0; i < admin->num_entries; i++) { s64 delta_ns = admin->entries[i].interval; s64 delta_cycles = ns_to_sja1105_delta(delta_ns); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h index 7a6e82db4231..bacc8552bce1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h @@ -1536,8 +1536,11 @@ void bnx2x_get_rss_ind_table(struct bnx2x_rss_config_obj *rss_obj, ((MAX_MAC_CREDIT_E2 - GET_NUM_VFS_PER_PATH(bp) * VF_MAC_CREDIT_CNT) / \ func_num + GET_NUM_VFS_PER_PF(bp) * VF_MAC_CREDIT_CNT) +#define BNX2X_VFS_VLAN_CREDIT(bp) \ + (GET_NUM_VFS_PER_PATH(bp) * VF_VLAN_CREDIT_CNT) + #define PF_VLAN_CREDIT_E2(bp, func_num) \ - ((MAX_MAC_CREDIT_E2 - GET_NUM_VFS_PER_PATH(bp) * VF_VLAN_CREDIT_CNT) / \ + ((MAX_VLAN_CREDIT_E2 - 1 - BNX2X_VFS_VLAN_CREDIT(bp)) / \ func_num + GET_NUM_VFS_PER_PF(bp) * VF_VLAN_CREDIT_CNT) #endif /* BNX2X_SP_VERBS */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index a70ac2097892..becee29f5df7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -504,6 +504,7 @@ struct link_config { enum cc_pause requested_fc; /* flow control user has requested */ enum cc_pause fc; /* actual link flow control */ + enum cc_pause advertised_fc; /* actual advertised flow control */ enum cc_fec requested_fec; /* Forward Error Correction: */ enum cc_fec fec; /* requested and actual in use */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 20ab3b6285a2..c837382ee522 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -807,8 +807,8 @@ static void get_pauseparam(struct net_device *dev, struct port_info *p = netdev_priv(dev); epause->autoneg = (p->link_cfg.requested_fc & PAUSE_AUTONEG) != 0; - epause->rx_pause = (p->link_cfg.fc & PAUSE_RX) != 0; - epause->tx_pause = (p->link_cfg.fc & PAUSE_TX) != 0; + epause->rx_pause = (p->link_cfg.advertised_fc & PAUSE_RX) != 0; + epause->tx_pause = (p->link_cfg.advertised_fc & PAUSE_TX) != 0; } static int set_pauseparam(struct net_device *dev, diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 19d18acfc9a6..844fdcf55118 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -4089,7 +4089,8 @@ static inline fw_port_cap32_t cc_to_fwcap_pause(enum cc_pause cc_pause) if (cc_pause & PAUSE_TX) fw_pause |= FW_PORT_CAP32_802_3_PAUSE; else - fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR; + fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR | + FW_PORT_CAP32_802_3_PAUSE; } else if (cc_pause & PAUSE_TX) { fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR; } @@ -8563,17 +8564,17 @@ static fw_port_cap32_t lstatus_to_fwcap(u32 lstatus) void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) { const struct fw_port_cmd *cmd = (const void *)rpl; - int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); - struct adapter *adapter = pi->adapter; + fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; struct link_config *lc = &pi->link_cfg; - int link_ok, linkdnrc; - enum fw_port_type port_type; + struct adapter *adapter = pi->adapter; + unsigned int speed, fc, fec, adv_fc; enum fw_port_module_type mod_type; - unsigned int speed, fc, fec; - fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; + int action, link_ok, linkdnrc; + enum fw_port_type port_type; /* Extract the various fields from the Port Information message. */ + action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); switch (action) { case FW_PORT_ACTION_GET_PORT_INFO: { u32 lstatus = be32_to_cpu(cmd->u.info.lstatus_to_modtype); @@ -8611,6 +8612,7 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) } fec = fwcap_to_cc_fec(acaps); + adv_fc = fwcap_to_cc_pause(acaps); fc = fwcap_to_cc_pause(linkattr); speed = fwcap_to_speed(linkattr); @@ -8667,7 +8669,9 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) } if (link_ok != lc->link_ok || speed != lc->speed || - fc != lc->fc || fec != lc->fec) { /* something changed */ + fc != lc->fc || adv_fc != lc->advertised_fc || + fec != lc->fec) { + /* something changed */ if (!link_ok && lc->link_ok) { lc->link_down_rc = linkdnrc; dev_warn_ratelimited(adapter->pdev_dev, @@ -8677,6 +8681,7 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) } lc->link_ok = link_ok; lc->speed = speed; + lc->advertised_fc = adv_fc; lc->fc = fc; lc->fec = fec; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index f6fc0875d5b0..f4d41f968afa 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -1690,8 +1690,8 @@ static void cxgb4vf_get_pauseparam(struct net_device *dev, struct port_info *pi = netdev_priv(dev); pauseparam->autoneg = (pi->link_cfg.requested_fc & PAUSE_AUTONEG) != 0; - pauseparam->rx_pause = (pi->link_cfg.fc & PAUSE_RX) != 0; - pauseparam->tx_pause = (pi->link_cfg.fc & PAUSE_TX) != 0; + pauseparam->rx_pause = (pi->link_cfg.advertised_fc & PAUSE_RX) != 0; + pauseparam->tx_pause = (pi->link_cfg.advertised_fc & PAUSE_TX) != 0; } /* diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h index ccca67cf4487..57cfd10a99ec 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h @@ -135,6 +135,7 @@ struct link_config { enum cc_pause requested_fc; /* flow control user has requested */ enum cc_pause fc; /* actual link flow control */ + enum cc_pause advertised_fc; /* actual advertised flow control */ enum cc_fec auto_fec; /* Forward Error Correction: */ enum cc_fec requested_fec; /* "automatic" (IEEE 802.3), */ diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c index 8a389d617a23..9d49ff211cc1 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c @@ -1913,16 +1913,16 @@ static const char *t4vf_link_down_rc_str(unsigned char link_down_rc) static void t4vf_handle_get_port_info(struct port_info *pi, const struct fw_port_cmd *cmd) { - int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); - struct adapter *adapter = pi->adapter; + fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; struct link_config *lc = &pi->link_cfg; - int link_ok, linkdnrc; - enum fw_port_type port_type; + struct adapter *adapter = pi->adapter; + unsigned int speed, fc, fec, adv_fc; enum fw_port_module_type mod_type; - unsigned int speed, fc, fec; - fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; + int action, link_ok, linkdnrc; + enum fw_port_type port_type; /* Extract the various fields from the Port Information message. */ + action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); switch (action) { case FW_PORT_ACTION_GET_PORT_INFO: { u32 lstatus = be32_to_cpu(cmd->u.info.lstatus_to_modtype); @@ -1982,6 +1982,7 @@ static void t4vf_handle_get_port_info(struct port_info *pi, } fec = fwcap_to_cc_fec(acaps); + adv_fc = fwcap_to_cc_pause(acaps); fc = fwcap_to_cc_pause(linkattr); speed = fwcap_to_speed(linkattr); @@ -2012,7 +2013,9 @@ static void t4vf_handle_get_port_info(struct port_info *pi, } if (link_ok != lc->link_ok || speed != lc->speed || - fc != lc->fc || fec != lc->fec) { /* something changed */ + fc != lc->fc || adv_fc != lc->advertised_fc || + fec != lc->fec) { + /* something changed */ if (!link_ok && lc->link_ok) { lc->link_down_rc = linkdnrc; dev_warn_ratelimited(adapter->pdev_dev, @@ -2022,6 +2025,7 @@ static void t4vf_handle_get_port_info(struct port_info *pi, } lc->link_ok = link_ok; lc->speed = speed; + lc->advertised_fc = adv_fc; lc->fc = fc; lc->fec = fec; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 6a9d12dad5d9..a301f0095223 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -1719,7 +1719,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, int page_offset; unsigned int sz; int *count_ptr; - int i; + int i, j; vaddr = phys_to_virt(addr); WARN_ON(!IS_ALIGNED((unsigned long)vaddr, SMP_CACHE_BYTES)); @@ -1736,14 +1736,14 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, WARN_ON(!IS_ALIGNED((unsigned long)sg_vaddr, SMP_CACHE_BYTES)); + dma_unmap_page(priv->rx_dma_dev, sg_addr, + DPAA_BP_RAW_SIZE, DMA_FROM_DEVICE); + /* We may use multiple Rx pools */ dpaa_bp = dpaa_bpid2pool(sgt[i].bpid); if (!dpaa_bp) goto free_buffers; - count_ptr = this_cpu_ptr(dpaa_bp->percpu_count); - dma_unmap_page(priv->rx_dma_dev, sg_addr, - DPAA_BP_RAW_SIZE, DMA_FROM_DEVICE); if (!skb) { sz = dpaa_bp->size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); @@ -1786,7 +1786,9 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, skb_add_rx_frag(skb, i - 1, head_page, frag_off, frag_len, dpaa_bp->size); } + /* Update the pool count for the current {cpu x bpool} */ + count_ptr = this_cpu_ptr(dpaa_bp->percpu_count); (*count_ptr)--; if (qm_sg_entry_is_final(&sgt[i])) @@ -1800,26 +1802,25 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, return skb; free_buffers: - /* compensate sw bpool counter changes */ - for (i--; i >= 0; i--) { - dpaa_bp = dpaa_bpid2pool(sgt[i].bpid); - if (dpaa_bp) { - count_ptr = this_cpu_ptr(dpaa_bp->percpu_count); - (*count_ptr)++; - } - } /* free all the SG entries */ - for (i = 0; i < DPAA_SGT_MAX_ENTRIES ; i++) { - sg_addr = qm_sg_addr(&sgt[i]); + for (j = 0; j < DPAA_SGT_MAX_ENTRIES ; j++) { + sg_addr = qm_sg_addr(&sgt[j]); sg_vaddr = phys_to_virt(sg_addr); + /* all pages 0..i were unmaped */ + if (j > i) + dma_unmap_page(priv->rx_dma_dev, qm_sg_addr(&sgt[j]), + DPAA_BP_RAW_SIZE, DMA_FROM_DEVICE); free_pages((unsigned long)sg_vaddr, 0); - dpaa_bp = dpaa_bpid2pool(sgt[i].bpid); - if (dpaa_bp) { - count_ptr = this_cpu_ptr(dpaa_bp->percpu_count); - (*count_ptr)--; + /* counters 0..i-1 were decremented */ + if (j >= i) { + dpaa_bp = dpaa_bpid2pool(sgt[j].bpid); + if (dpaa_bp) { + count_ptr = this_cpu_ptr(dpaa_bp->percpu_count); + (*count_ptr)--; + } } - if (qm_sg_entry_is_final(&sgt[i])) + if (qm_sg_entry_is_final(&sgt[j])) break; } /* free the SGT fragment */ diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c index 544344ac4894..79057af4fe99 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/netlink.h> +#include <linux/vmalloc.h> #include <linux/xz.h> #include "mlxfw_mfa2.h" #include "mlxfw_mfa2_file.h" @@ -548,7 +549,7 @@ mlxfw_mfa2_file_component_get(const struct mlxfw_mfa2_file *mfa2_file, comp_size = be32_to_cpu(comp->size); comp_buf_size = comp_size + mlxfw_mfa2_comp_magic_len; - comp_data = kmalloc(sizeof(*comp_data) + comp_buf_size, GFP_KERNEL); + comp_data = vzalloc(sizeof(*comp_data) + comp_buf_size); if (!comp_data) return ERR_PTR(-ENOMEM); comp_data->comp.data_size = comp_size; @@ -570,7 +571,7 @@ mlxfw_mfa2_file_component_get(const struct mlxfw_mfa2_file *mfa2_file, comp_data->comp.data = comp_data->buff + mlxfw_mfa2_comp_magic_len; return &comp_data->comp; err_out: - kfree(comp_data); + vfree(comp_data); return ERR_PTR(err); } @@ -579,7 +580,7 @@ void mlxfw_mfa2_file_component_put(struct mlxfw_mfa2_component *comp) const struct mlxfw_mfa2_comp_data *comp_data; comp_data = container_of(comp, struct mlxfw_mfa2_comp_data, comp); - kfree(comp_data); + vfree(comp_data); } void mlxfw_mfa2_file_fini(struct mlxfw_mfa2_file *mfa2_file) diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 5294a1622643..af30e8a76682 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5472,6 +5472,7 @@ enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR, MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0, MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1, + MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP, __MLXSW_REG_HTGT_TRAP_GROUP_MAX, MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1 diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 556dca328bb5..f7fd5e8fbf96 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4542,8 +4542,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, ROUTER_EXP, false), MLXSW_SP_RXL_MARK(IPIP_DECAP_ERROR, TRAP_TO_CPU, ROUTER_EXP, false), MLXSW_SP_RXL_MARK(DECAP_ECN0, TRAP_TO_CPU, ROUTER_EXP, false), - MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, ROUTER_EXP, false), - MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, ROUTER_EXP, false), + MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, VRRP, false), + MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, VRRP, false), /* PKT Sample trap */ MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU, false, SP_IP2ME, DISCARD), @@ -4626,6 +4626,10 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core) rate = 19 * 1024; burst_size = 12; break; + case MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP: + rate = 360; + burst_size = 7; + break; default: continue; } @@ -4665,6 +4669,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core) case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF: case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM: case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0: + case MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP: priority = 5; tc = 5; break; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 08b7e9f964da..8290e82240fc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -7079,6 +7079,9 @@ static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp, for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { rif = mlxsw_sp->router->rifs[i]; + if (rif && rif->ops && + rif->ops->type == MLXSW_SP_RIF_TYPE_IPIP_LB) + continue; if (rif && rif->dev && rif->dev != dev && !ether_addr_equal_masked(rif->dev->dev_addr, dev_addr, mlxsw_sp->mac_mask)) { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index bd6c01004913..0e2fa14f1423 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -112,6 +112,14 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) struct device *dev = dwmac->dev; const char *parent_name, *mux_parent_names[MUX_CLK_NUM_PARENTS]; struct meson8b_dwmac_clk_configs *clk_configs; + static const struct clk_div_table div_table[] = { + { .div = 2, .val = 2, }, + { .div = 3, .val = 3, }, + { .div = 4, .val = 4, }, + { .div = 5, .val = 5, }, + { .div = 6, .val = 6, }, + { .div = 7, .val = 7, }, + }; clk_configs = devm_kzalloc(dev, sizeof(*clk_configs), GFP_KERNEL); if (!clk_configs) @@ -146,9 +154,9 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) clk_configs->m250_div.reg = dwmac->regs + PRG_ETH0; clk_configs->m250_div.shift = PRG_ETH0_CLK_M250_DIV_SHIFT; clk_configs->m250_div.width = PRG_ETH0_CLK_M250_DIV_WIDTH; - clk_configs->m250_div.flags = CLK_DIVIDER_ONE_BASED | - CLK_DIVIDER_ALLOW_ZERO | - CLK_DIVIDER_ROUND_CLOSEST; + clk_configs->m250_div.table = div_table; + clk_configs->m250_div.flags = CLK_DIVIDER_ALLOW_ZERO | + CLK_DIVIDER_ROUND_CLOSEST; clk = meson8b_dwmac_register_clk(dwmac, "m250_div", &parent_name, 1, &clk_divider_ops, &clk_configs->m250_div.hw); diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index e5b7d6d2286e..fca471e27f39 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -540,7 +540,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, mtu = dst_mtu(&rt->dst); } - rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu); + rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, false); if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) && mtu < ntohs(iph->tot_len)) { diff --git a/drivers/net/phy/aquantia_main.c b/drivers/net/phy/aquantia_main.c index 3b29d381116f..975789d9349d 100644 --- a/drivers/net/phy/aquantia_main.c +++ b/drivers/net/phy/aquantia_main.c @@ -627,6 +627,8 @@ static struct phy_driver aqr_driver[] = { .config_intr = aqr_config_intr, .ack_interrupt = aqr_ack_interrupt, .read_status = aqr_read_status, + .suspend = aqr107_suspend, + .resume = aqr107_resume, }, { PHY_ID_MATCH_MODEL(PHY_ID_AQR106), diff --git a/drivers/platform/mips/Kconfig b/drivers/platform/mips/Kconfig index f4d0a86c00d0..5e77b0dc5fd6 100644 --- a/drivers/platform/mips/Kconfig +++ b/drivers/platform/mips/Kconfig @@ -18,7 +18,7 @@ if MIPS_PLATFORM_DEVICES config CPU_HWMON tristate "Loongson-3 CPU HWMon Driver" - depends on CONFIG_MACH_LOONGSON64 + depends on MACH_LOONGSON64 select HWMON default y help diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index e60eab7f8a61..61fafe0374ce 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -166,9 +166,9 @@ static struct posix_clock_operations ptp_clock_ops = { .read = ptp_read, }; -static void delete_ptp_clock(struct posix_clock *pc) +static void ptp_clock_release(struct device *dev) { - struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); + struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev); mutex_destroy(&ptp->tsevq_mux); mutex_destroy(&ptp->pincfg_mux); @@ -213,7 +213,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, } ptp->clock.ops = ptp_clock_ops; - ptp->clock.release = delete_ptp_clock; ptp->info = info; ptp->devid = MKDEV(major, index); ptp->index = index; @@ -236,15 +235,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, if (err) goto no_pin_groups; - /* Create a new device in our class. */ - ptp->dev = device_create_with_groups(ptp_class, parent, ptp->devid, - ptp, ptp->pin_attr_groups, - "ptp%d", ptp->index); - if (IS_ERR(ptp->dev)) { - err = PTR_ERR(ptp->dev); - goto no_device; - } - /* Register a new PPS source. */ if (info->pps) { struct pps_source_info pps; @@ -260,8 +250,18 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, } } - /* Create a posix clock. */ - err = posix_clock_register(&ptp->clock, ptp->devid); + /* Initialize a new device of our class in our clock structure. */ + device_initialize(&ptp->dev); + ptp->dev.devt = ptp->devid; + ptp->dev.class = ptp_class; + ptp->dev.parent = parent; + ptp->dev.groups = ptp->pin_attr_groups; + ptp->dev.release = ptp_clock_release; + dev_set_drvdata(&ptp->dev, ptp); + dev_set_name(&ptp->dev, "ptp%d", ptp->index); + + /* Create a posix clock and link it to the device. */ + err = posix_clock_register(&ptp->clock, &ptp->dev); if (err) { pr_err("failed to create posix clock\n"); goto no_clock; @@ -273,8 +273,6 @@ no_clock: if (ptp->pps_source) pps_unregister_source(ptp->pps_source); no_pps: - device_destroy(ptp_class, ptp->devid); -no_device: ptp_cleanup_pin_groups(ptp); no_pin_groups: if (ptp->kworker) @@ -304,7 +302,6 @@ int ptp_clock_unregister(struct ptp_clock *ptp) if (ptp->pps_source) pps_unregister_source(ptp->pps_source); - device_destroy(ptp_class, ptp->devid); ptp_cleanup_pin_groups(ptp); posix_clock_unregister(&ptp->clock); diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 9171d42468fd..6b97155148f1 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -28,7 +28,7 @@ struct timestamp_event_queue { struct ptp_clock { struct posix_clock clock; - struct device *dev; + struct device dev; struct ptp_clock_info *info; dev_t devid; int index; /* index into clocks.map */ diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index bc4158888af9..29facb913671 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -2482,50 +2482,46 @@ static int qeth_mpc_initialize(struct qeth_card *card) rc = qeth_cm_enable(card); if (rc) { QETH_CARD_TEXT_(card, 2, "2err%d", rc); - goto out_qdio; + return rc; } rc = qeth_cm_setup(card); if (rc) { QETH_CARD_TEXT_(card, 2, "3err%d", rc); - goto out_qdio; + return rc; } rc = qeth_ulp_enable(card); if (rc) { QETH_CARD_TEXT_(card, 2, "4err%d", rc); - goto out_qdio; + return rc; } rc = qeth_ulp_setup(card); if (rc) { QETH_CARD_TEXT_(card, 2, "5err%d", rc); - goto out_qdio; + return rc; } rc = qeth_alloc_qdio_queues(card); if (rc) { QETH_CARD_TEXT_(card, 2, "5err%d", rc); - goto out_qdio; + return rc; } rc = qeth_qdio_establish(card); if (rc) { QETH_CARD_TEXT_(card, 2, "6err%d", rc); qeth_free_qdio_queues(card); - goto out_qdio; + return rc; } rc = qeth_qdio_activate(card); if (rc) { QETH_CARD_TEXT_(card, 2, "7err%d", rc); - goto out_qdio; + return rc; } rc = qeth_dm_act(card); if (rc) { QETH_CARD_TEXT_(card, 2, "8err%d", rc); - goto out_qdio; + return rc; } return 0; -out_qdio: - qeth_qdio_clear_card(card, !IS_IQD(card)); - qdio_free(CARD_DDEV(card)); - return rc; } void qeth_print_status_message(struct qeth_card *card) @@ -3429,11 +3425,6 @@ int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq) goto out; } - if (card->state != CARD_STATE_DOWN) { - rc = -1; - goto out; - } - qeth_free_qdio_queues(card); card->options.cq = cq; rc = 0; @@ -5035,10 +5026,8 @@ retriable: } if (qeth_adp_supported(card, IPA_SETADP_SET_DIAG_ASSIST)) { rc = qeth_query_setdiagass(card); - if (rc < 0) { + if (rc) QETH_CARD_TEXT_(card, 2, "8err%d", rc); - goto out; - } } if (!qeth_is_diagass_supported(card, QETH_DIAGS_CMD_TRAP) || diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 8c95e6019bac..47d37e75dda6 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -287,12 +287,12 @@ static void qeth_l2_stop_card(struct qeth_card *card) card->state = CARD_STATE_HARDSETUP; } if (card->state == CARD_STATE_HARDSETUP) { - qeth_qdio_clear_card(card, 0); qeth_drain_output_queues(card); qeth_clear_working_pool_list(card); card->state = CARD_STATE_DOWN; } + qeth_qdio_clear_card(card, 0); flush_workqueue(card->event_wq); card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED; card->info.promisc_mode = 0; @@ -1952,8 +1952,7 @@ int qeth_l2_vnicc_get_timeout(struct qeth_card *card, u32 *timeout) /* check if VNICC is currently enabled */ bool qeth_l2_vnicc_is_in_use(struct qeth_card *card) { - /* if everything is turned off, VNICC is not active */ - if (!card->options.vnicc.cur_chars) + if (!card->options.vnicc.sup_chars) return false; /* default values are only OK if rx_bcast was not enabled by user * or the card is offline. @@ -2040,8 +2039,9 @@ static void qeth_l2_vnicc_init(struct qeth_card *card) /* enforce assumed default values and recover settings, if changed */ error |= qeth_l2_vnicc_recover_timeout(card, QETH_VNICC_LEARNING, timeout); - chars_tmp = card->options.vnicc.wanted_chars ^ QETH_VNICC_DEFAULT; - chars_tmp |= QETH_VNICC_BRIDGE_INVISIBLE; + /* Change chars, if necessary */ + chars_tmp = card->options.vnicc.wanted_chars ^ + card->options.vnicc.cur_chars; chars_len = sizeof(card->options.vnicc.wanted_chars) * BITS_PER_BYTE; for_each_set_bit(i, &chars_tmp, chars_len) { vnicc = BIT(i); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 04e301de376f..5508ab89b518 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1307,12 +1307,12 @@ static void qeth_l3_stop_card(struct qeth_card *card) card->state = CARD_STATE_HARDSETUP; } if (card->state == CARD_STATE_HARDSETUP) { - qeth_qdio_clear_card(card, 0); qeth_drain_output_queues(card); qeth_clear_working_pool_list(card); card->state = CARD_STATE_DOWN; } + qeth_qdio_clear_card(card, 0); flush_workqueue(card->event_wq); card->info.promisc_mode = 0; } diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c index f9067ed6c7d3..e8c848f72c6d 100644 --- a/drivers/s390/net/qeth_l3_sys.c +++ b/drivers/s390/net/qeth_l3_sys.c @@ -242,21 +242,33 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct qeth_card *card = dev_get_drvdata(dev); + int rc = 0; char *tmp; - int rc; if (!IS_IQD(card)) return -EPERM; - if (card->state != CARD_STATE_DOWN) - return -EPERM; - if (card->options.sniffer) - return -EPERM; - if (card->options.cq == QETH_CQ_NOTAVAILABLE) - return -EPERM; + + mutex_lock(&card->conf_mutex); + if (card->state != CARD_STATE_DOWN) { + rc = -EPERM; + goto out; + } + + if (card->options.sniffer) { + rc = -EPERM; + goto out; + } + + if (card->options.cq == QETH_CQ_NOTAVAILABLE) { + rc = -EPERM; + goto out; + } tmp = strsep((char **)&buf, "\n"); - if (strlen(tmp) > 8) - return -EINVAL; + if (strlen(tmp) > 8) { + rc = -EINVAL; + goto out; + } if (card->options.hsuid[0]) /* delete old ip address */ @@ -267,11 +279,13 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev, card->options.hsuid[0] = '\0'; memcpy(card->dev->perm_addr, card->options.hsuid, 9); qeth_configure_cq(card, QETH_CQ_DISABLED); - return count; + goto out; } - if (qeth_configure_cq(card, QETH_CQ_ENABLED)) - return -EPERM; + if (qeth_configure_cq(card, QETH_CQ_ENABLED)) { + rc = -EPERM; + goto out; + } snprintf(card->options.hsuid, sizeof(card->options.hsuid), "%-8s", tmp); @@ -280,6 +294,8 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev, rc = qeth_l3_modify_hsuid(card, true); +out: + mutex_unlock(&card->conf_mutex); return rc ? rc : count; } diff --git a/drivers/staging/media/ipu3/include/intel-ipu3.h b/drivers/staging/media/ipu3/include/intel-ipu3.h index 08eaa0bad0de..1c9c3ba4d518 100644 --- a/drivers/staging/media/ipu3/include/intel-ipu3.h +++ b/drivers/staging/media/ipu3/include/intel-ipu3.h @@ -449,7 +449,7 @@ struct ipu3_uapi_awb_fr_config_s { __u16 reserved1; __u32 bayer_sign; __u8 bayer_nf; - __u8 reserved2[3]; + __u8 reserved2[7]; } __attribute__((aligned(32))) __packed; /** diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index ee834ef7beb4..43e1660f450f 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -447,7 +447,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, if (blkcg_css) { bio->bi_opf |= REQ_CGROUP_PUNT; - bio_associate_blkg_from_css(bio, blkcg_css); + kthread_associate_blkcg(blkcg_css); } refcount_set(&cb->pending_bios, 1); @@ -491,6 +491,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, bio->bi_opf = REQ_OP_WRITE | write_flags; bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; + if (blkcg_css) + bio->bi_opf |= REQ_CGROUP_PUNT; bio_add_page(bio, page, PAGE_SIZE, 0); } if (bytes_left < PAGE_SIZE) { @@ -517,6 +519,9 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, bio_endio(bio); } + if (blkcg_css) + kthread_associate_blkcg(NULL); + return 0; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e3c76645cad7..5509c41a4f43 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1479,10 +1479,10 @@ next_slot: disk_num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi); /* - * If extent we got ends before our range starts, skip - * to next extent + * If the extent we got ends before our current offset, + * skip to the next extent. */ - if (extent_end <= start) { + if (extent_end <= cur_offset) { path->slots[0]++; goto next_slot; } diff --git a/fs/buffer.c b/fs/buffer.c index d8c7242426bb..e94a6619464c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3034,8 +3034,6 @@ static void end_bio_bh_io_sync(struct bio *bio) void guard_bio_eod(int op, struct bio *bio) { sector_t maxsector; - struct bio_vec *bvec = bio_last_bvec_all(bio); - unsigned truncated_bytes; struct hd_struct *part; rcu_read_lock(); @@ -3061,28 +3059,7 @@ void guard_bio_eod(int op, struct bio *bio) if (likely((bio->bi_iter.bi_size >> 9) <= maxsector)) return; - /* Uhhuh. We've got a bio that straddles the device size! */ - truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9); - - /* - * The bio contains more than one segment which spans EOD, just return - * and let IO layer turn it into an EIO - */ - if (truncated_bytes > bvec->bv_len) - return; - - /* Truncate the bio.. */ - bio->bi_iter.bi_size -= truncated_bytes; - bvec->bv_len -= truncated_bytes; - - /* ..and clear the end of the buffer for reads */ - if (op == REQ_OP_READ) { - struct bio_vec bv; - - mp_bvec_last_segment(bvec, &bv); - zero_user(bv.bv_page, bv.bv_offset + bv.bv_len, - truncated_bytes); - } + bio_truncate(bio, maxsector << 9); } static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, diff --git a/fs/direct-io.c b/fs/direct-io.c index 0ec4f270139f..00b4d15bb811 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -39,6 +39,8 @@ #include <linux/atomic.h> #include <linux/prefetch.h> +#include "internal.h" + /* * How many user pages to map in one call to get_user_pages(). This determines * the size of a structure in the slab cache diff --git a/fs/file.c b/fs/file.c index 2f4fcf985079..3da91a112bab 100644 --- a/fs/file.c +++ b/fs/file.c @@ -960,7 +960,7 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) return ksys_dup3(oldfd, newfd, 0); } -SYSCALL_DEFINE1(dup, unsigned int, fildes) +int ksys_dup(unsigned int fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); @@ -975,6 +975,11 @@ SYSCALL_DEFINE1(dup, unsigned int, fildes) return ret; } +SYSCALL_DEFINE1(dup, unsigned int, fildes) +{ + return ksys_dup(fildes); +} + int f_dupfd(unsigned int from, struct file *file, unsigned flags) { int err; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d5c2a3158610..a66e425884d1 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1498,8 +1498,10 @@ static int __init init_hugetlbfs_fs(void) /* other hstates are optional */ i = 0; for_each_hstate(h) { - if (i == default_hstate_idx) + if (i == default_hstate_idx) { + i++; continue; + } mnt = mount_one_hugetlbfs(h); if (IS_ERR(mnt)) diff --git a/fs/namespace.c b/fs/namespace.c index be601d3a8008..5e1bf611a9eb 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1728,7 +1728,7 @@ static bool is_mnt_ns_file(struct dentry *dentry) dentry->d_fsdata == &mntns_operations; } -struct mnt_namespace *to_mnt_ns(struct ns_common *ns) +static struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } diff --git a/fs/nsfs.c b/fs/nsfs.c index a0431642c6b5..f75767bd623a 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -3,6 +3,7 @@ #include <linux/pseudo_fs.h> #include <linux/file.h> #include <linux/fs.h> +#include <linux/proc_fs.h> #include <linux/proc_ns.h> #include <linux/magic.h> #include <linux/ktime.h> @@ -11,6 +12,8 @@ #include <linux/nsfs.h> #include <linux/uaccess.h> +#include "internal.h" + static struct vfsmount *nsfs_mnt; static long ns_ioctl(struct file *filp, unsigned int ioctl, diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 1c4c51f3df60..cda1027d0819 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3282,6 +3282,7 @@ static void ocfs2_dlm_init_debug(struct ocfs2_super *osb) debugfs_create_u32("locking_filter", 0600, osb->osb_debug_root, &dlm_debug->d_filter_secs); + ocfs2_get_dlm_debug(dlm_debug); } static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb) diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 1afe57f425a0..68ba354cf361 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1066,6 +1066,14 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed) ocfs2_clear_journal_error(osb->sb, journal->j_journal, osb->slot_num); + if (replayed) { + jbd2_journal_lock_updates(journal->j_journal); + status = jbd2_journal_flush(journal->j_journal); + jbd2_journal_unlock_updates(journal->j_journal); + if (status < 0) + mlog_errno(status); + } + status = ocfs2_journal_toggle_dirty(osb, 1, replayed); if (status < 0) { mlog_errno(status); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 84ad1c90d535..249672bf54fe 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -631,12 +631,15 @@ EXPORT_SYMBOL_GPL(posix_acl_create); /** * posix_acl_update_mode - update mode in set_acl + * @inode: target inode + * @mode_p: mode (pointer) for update + * @acl: acl pointer * * Update the file mode when setting an ACL: compute the new file permission * bits based on the ACL. In addition, if the ACL is equivalent to the new - * file mode, set *acl to NULL to indicate that no ACL should be set. + * file mode, set *@acl to NULL to indicate that no ACL should be set. * - * As with chmod, clear the setgit bit if the caller is not in the owning group + * As with chmod, clear the setgid bit if the caller is not in the owning group * or capable of CAP_FSETID (see inode_change_ok). * * Called from set_acl inode operations. diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 8caff834f002..487ee39b438a 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -407,6 +407,17 @@ static int notrace ramoops_pstore_write(struct pstore_record *record) prz = cxt->dprzs[cxt->dump_write_cnt]; + /* + * Since this is a new crash dump, we need to reset the buffer in + * case it still has an old dump present. Without this, the new dump + * will get appended, which would seriously confuse anything trying + * to check dump file contents. Specifically, ramoops_read_kmsg_hdr() + * expects to find a dump header in the beginning of buffer data, so + * we must to reset the buffer values, in order to ensure that the + * header will be written to the beginning of the buffer. + */ + persistent_ram_zap(prz); + /* Build header and append record contents. */ hlen = ramoops_write_kmsg_hdr(prz, record); if (!hlen) @@ -577,6 +588,7 @@ static int ramoops_init_przs(const char *name, dev_err(dev, "failed to request %s mem region (0x%zx@0x%llx): %d\n", name, record_size, (unsigned long long)*paddr, err); + kfree(label); while (i > 0) { i--; @@ -622,6 +634,7 @@ static int ramoops_init_prz(const char *name, dev_err(dev, "failed to request %s mem region (0x%zx@0x%llx): %d\n", name, sz, (unsigned long long)*paddr, err); + kfree(label); return err; } diff --git a/include/linux/bio.h b/include/linux/bio.h index 3cdb84cdc488..853d92ceee64 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -470,6 +470,7 @@ extern struct bio *bio_copy_user_iov(struct request_queue *, gfp_t); extern int bio_uncopy_user(struct bio *); void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter); +void bio_truncate(struct bio *bio, unsigned new_size); static inline void zero_fill_bio(struct bio *bio) { diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 64ec82851aa3..8150f5ac176c 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -154,15 +154,6 @@ static inline void guest_exit_irqoff(void) } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ -static inline void guest_enter(void) -{ - unsigned long flags; - - local_irq_save(flags); - guest_enter_irqoff(); - local_irq_restore(flags); -} - static inline void guest_exit(void) { unsigned long flags; diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 8fcdee1c0cf9..dad4a68fa009 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1364,8 +1364,11 @@ static inline int dma_get_slave_caps(struct dma_chan *chan, static inline int dmaengine_desc_set_reuse(struct dma_async_tx_descriptor *tx) { struct dma_slave_caps caps; + int ret; - dma_get_slave_caps(tx->chan, &caps); + ret = dma_get_slave_caps(tx->chan, &caps); + if (ret) + return ret; if (caps.descriptor_reuse) { tx->flags |= DMA_CTRL_REUSE; diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 0b84e13e88e2..5aca3d1bdb32 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -160,6 +160,7 @@ extern unsigned long thp_get_unmapped_area(struct file *filp, extern void prep_transhuge_page(struct page *page); extern void free_transhuge_page(struct page *page); +bool is_transparent_hugepage(struct page *page); bool can_split_huge_page(struct page *page, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); @@ -308,6 +309,11 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, static inline void prep_transhuge_page(struct page *page) {} +static inline bool is_transparent_hugepage(struct page *page) +{ + return false; +} + #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3adcb39fa6f5..0d9db2a14f44 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -79,15 +79,6 @@ */ #define round_down(x, y) ((x) & ~__round_mask(x, y)) -/** - * FIELD_SIZEOF - get the size of a struct's field - * @t: the target struct - * @f: the target struct's field - * Return: the size of @f in the struct definition without having a - * declared instance of @t. - */ -#define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) - #define typeof_member(T, m) typeof(((T*)0)->m) #define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 538c25e778c0..6d5331b0d937 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -157,8 +157,6 @@ static inline bool is_error_page(struct page *page) #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 -extern struct kmem_cache *kvm_vcpu_cache; - extern struct mutex kvm_lock; extern struct list_head vm_list; @@ -204,7 +202,7 @@ struct kvm_async_pf { struct list_head queue; struct kvm_vcpu *vcpu; struct mm_struct *mm; - gva_t gva; + gpa_t cr2_or_gpa; unsigned long addr; struct kvm_arch_async_pf arch; bool wakeup_all; @@ -212,8 +210,8 @@ struct kvm_async_pf { void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu); -int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, - struct kvm_arch_async_pf *arch); +int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + unsigned long hva, struct kvm_arch_async_pf *arch); int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif @@ -579,8 +577,7 @@ static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\ memslot++) -int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id); -void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); +void kvm_vcpu_destroy(struct kvm_vcpu *vcpu); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); @@ -725,8 +722,6 @@ void kvm_get_pfn(kvm_pfn_t pfn); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); -int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, - unsigned long len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); @@ -767,7 +762,7 @@ int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); -unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn); +unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); @@ -867,16 +862,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run); int kvm_arch_init(void *opaque); void kvm_arch_exit(void); -int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu); -void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu); - void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu); -void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); -struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id); -int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu); +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id); +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); @@ -982,10 +973,10 @@ void kvm_arch_destroy_vm(struct kvm *kvm); void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); -void kvm_vcpu_kick(struct kvm_vcpu *vcpu); bool kvm_is_reserved_pfn(kvm_pfn_t pfn); bool kvm_is_zone_device_pfn(kvm_pfn_t pfn); +bool kvm_is_transparent_hugepage(kvm_pfn_t pfn); struct kvm_irq_ack_notifier { struct hlist_node link; @@ -1109,9 +1100,8 @@ enum kvm_stat_kind { }; struct kvm_stat_data { - int offset; - int mode; struct kvm *kvm; + struct kvm_stats_debugfs_item *dbgfs_item; }; struct kvm_stats_debugfs_item { @@ -1120,6 +1110,10 @@ struct kvm_stats_debugfs_item { enum kvm_stat_kind kind; int mode; }; + +#define KVM_DBGFS_GET_MODE(dbgfs_item) \ + ((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644) + extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; @@ -1342,6 +1336,9 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) } #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ +struct kvm_vcpu *kvm_get_running_vcpu(void); +struct kvm_vcpu __percpu **kvm_get_running_vcpus(void); + #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS bool kvm_arch_has_irq_bypass(void); int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *, diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 3a08ecdfca11..ba0dca6aac6e 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -122,8 +122,8 @@ static inline bool movable_node_is_enabled(void) extern void arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap); -extern void __remove_pages(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages, struct vmem_altmap *altmap); +extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages, + struct vmem_altmap *altmap); /* reasonably generic interface to expand the physical pages */ extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, @@ -342,6 +342,9 @@ extern int add_memory(int nid, u64 start, u64 size); extern int add_memory_resource(int nid, struct resource *resource); extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); +extern void remove_pfn_range_from_zone(struct zone *zone, + unsigned long start_pfn, + unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern int sparse_add_section(int nid, unsigned long pfn, unsigned long nr_pages, struct vmem_altmap *altmap); diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 79bc82e30c02..491a2b7e77c1 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -55,7 +55,7 @@ static inline int of_mdio_parse_addr(struct device *dev, } #else /* CONFIG_OF_MDIO */ -static bool of_mdiobus_child_is_phy(struct device_node *child) +static inline bool of_mdiobus_child_is_phy(struct device_node *child) { return false; } diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h index fe6cfdcfbc26..468328b1e1dd 100644 --- a/include/linux/posix-clock.h +++ b/include/linux/posix-clock.h @@ -69,29 +69,32 @@ struct posix_clock_operations { * * @ops: Functional interface to the clock * @cdev: Character device instance for this clock - * @kref: Reference count. + * @dev: Pointer to the clock's device. * @rwsem: Protects the 'zombie' field from concurrent access. * @zombie: If 'zombie' is true, then the hardware has disappeared. - * @release: A function to free the structure when the reference count reaches - * zero. May be NULL if structure is statically allocated. * * Drivers should embed their struct posix_clock within a private * structure, obtaining a reference to it during callbacks using * container_of(). + * + * Drivers should supply an initialized but not exposed struct device + * to posix_clock_register(). It is used to manage lifetime of the + * driver's private structure. It's 'release' field should be set to + * a release function for this private structure. */ struct posix_clock { struct posix_clock_operations ops; struct cdev cdev; - struct kref kref; + struct device *dev; struct rw_semaphore rwsem; bool zombie; - void (*release)(struct posix_clock *clk); }; /** * posix_clock_register() - register a new clock - * @clk: Pointer to the clock. Caller must provide 'ops' and 'release' - * @devid: Allocated device id + * @clk: Pointer to the clock. Caller must provide 'ops' field + * @dev: Pointer to the initialized device. Caller must provide + * 'release' field * * A clock driver calls this function to register itself with the * clock device subsystem. If 'clk' points to dynamically allocated @@ -100,7 +103,7 @@ struct posix_clock { * * Returns zero on success, non-zero otherwise. */ -int posix_clock_register(struct posix_clock *clk, dev_t devid); +int posix_clock_register(struct posix_clock *clk, struct device *dev); /** * posix_clock_unregister() - unregister a clock diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2960dedcfde8..5262b7a76d39 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1232,6 +1232,7 @@ asmlinkage long sys_ni_syscall(void); */ int ksys_umount(char __user *name, int flags); +int ksys_dup(unsigned int fildes); int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); diff --git a/include/net/dst.h b/include/net/dst.h index 8224dad2ae94..3448cf865ede 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -516,7 +516,16 @@ static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu) struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops->update_pmtu) - dst->ops->update_pmtu(dst, NULL, skb, mtu); + dst->ops->update_pmtu(dst, NULL, skb, mtu, true); +} + +/* update dst pmtu but not do neighbor confirm */ +static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) +{ + struct dst_entry *dst = skb_dst(skb); + + if (dst && dst->ops->update_pmtu) + dst->ops->update_pmtu(dst, NULL, skb, mtu, false); } static inline void skb_tunnel_check_pmtu(struct sk_buff *skb, @@ -526,7 +535,7 @@ static inline void skb_tunnel_check_pmtu(struct sk_buff *skb, u32 encap_mtu = dst_mtu(encap_dst); if (skb->len > encap_mtu - headroom) - skb_dst_update_pmtu(skb, encap_mtu - headroom); + skb_dst_update_pmtu_no_confirm(skb, encap_mtu - headroom); } #endif /* _NET_DST_H */ diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 5ec645f27ee3..443863c7b8da 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -27,7 +27,8 @@ struct dst_ops { struct dst_entry * (*negative_advice)(struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); void (*redirect)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); int (*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 144f264ea394..fceddf89592a 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -308,6 +308,7 @@ struct tcf_proto_ops { int (*delete)(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, struct netlink_ext_ack *); + bool (*delete_empty)(struct tcf_proto *tp); void (*walk)(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held); int (*reoffload)(struct tcf_proto *tp, bool add, @@ -336,6 +337,10 @@ struct tcf_proto_ops { int flags; }; +/* Classifiers setting TCF_PROTO_OPS_DOIT_UNLOCKED in tcf_proto_ops->flags + * are expected to implement tcf_proto_ops->delete_empty(), otherwise race + * conditions can occur when filters are inserted/deleted simultaneously. + */ enum tcf_proto_ops_flags { TCF_PROTO_OPS_DOIT_UNLOCKED = 1, }; diff --git a/include/uapi/linux/kcov.h b/include/uapi/linux/kcov.h index 409d3ad1e6e2..1d0350e44ae3 100644 --- a/include/uapi/linux/kcov.h +++ b/include/uapi/linux/kcov.h @@ -9,11 +9,11 @@ * and the comment before kcov_remote_start() for usage details. */ struct kcov_remote_arg { - unsigned int trace_mode; /* KCOV_TRACE_PC or KCOV_TRACE_CMP */ - unsigned int area_size; /* Length of coverage buffer in words */ - unsigned int num_handles; /* Size of handles array */ - __u64 common_handle; - __u64 handles[0]; + __u32 trace_mode; /* KCOV_TRACE_PC or KCOV_TRACE_CMP */ + __u32 area_size; /* Length of coverage buffer in words */ + __u32 num_handles; /* Size of handles array */ + __aligned_u64 common_handle; + __aligned_u64 handles[0]; }; #define KCOV_REMOTE_MAX_HANDLES 0x100 diff --git a/init/main.c b/init/main.c index 1ecfd43ed464..2cd736059416 100644 --- a/init/main.c +++ b/init/main.c @@ -93,7 +93,6 @@ #include <linux/rodata_test.h> #include <linux/jump_label.h> #include <linux/mem_encrypt.h> -#include <linux/file.h> #include <asm/io.h> #include <asm/bugs.h> @@ -1158,26 +1157,13 @@ static int __ref kernel_init(void *unused) void console_on_rootfs(void) { - struct file *file; - unsigned int i; - - /* Open /dev/console in kernelspace, this should never fail */ - file = filp_open("/dev/console", O_RDWR, 0); - if (IS_ERR(file)) - goto err_out; - - /* create stdin/stdout/stderr, this should never fail */ - for (i = 0; i < 3; i++) { - if (f_dupfd(i, file, 0) != i) - goto err_out; - } - - return; + /* Open the /dev/console as stdin, this should never fail */ + if (ksys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) + pr_err("Warning: unable to open an initial console.\n"); -err_out: - /* no panic -- this might not be fatal */ - pr_err("Warning: unable to open an initial console.\n"); - return; + /* create stdout/stderr */ + (void) ksys_dup(0); + (void) ksys_dup(0); } static noinline void __init kernel_init_freeable(void) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4983940cbdca..6f63ae7a370c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -907,7 +907,8 @@ static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; -static void __mark_reg_not_init(struct bpf_reg_state *reg); +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg); /* Mark the unknown part of a register (variable offset or scalar value) as * known to have the value @imm. @@ -945,7 +946,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env, verbose(env, "mark_reg_known_zero(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } __mark_reg_known_zero(regs + regno); @@ -1054,7 +1055,8 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg) } /* Mark a register as having a completely unknown (scalar) value. */ -static void __mark_reg_unknown(struct bpf_reg_state *reg) +static void __mark_reg_unknown(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) { /* * Clear type, id, off, and union(map_ptr, range) and @@ -1064,6 +1066,8 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg) reg->type = SCALAR_VALUE; reg->var_off = tnum_unknown; reg->frameno = 0; + reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? + true : false; __mark_reg_unbounded(reg); } @@ -1074,19 +1078,16 @@ static void mark_reg_unknown(struct bpf_verifier_env *env, verbose(env, "mark_reg_unknown(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } - regs += regno; - __mark_reg_unknown(regs); - /* constant backtracking is enabled for root without bpf2bpf calls */ - regs->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ? - true : false; + __mark_reg_unknown(env, regs + regno); } -static void __mark_reg_not_init(struct bpf_reg_state *reg) +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) { - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); reg->type = NOT_INIT; } @@ -1097,10 +1098,10 @@ static void mark_reg_not_init(struct bpf_verifier_env *env, verbose(env, "mark_reg_not_init(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); return; } - __mark_reg_not_init(regs + regno); + __mark_reg_not_init(env, regs + regno); } #define DEF_NOT_SUBREG (0) @@ -3234,7 +3235,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, } if (state->stack[spi].slot_type[0] == STACK_SPILL && state->stack[spi].spilled_ptr.type == SCALAR_VALUE) { - __mark_reg_unknown(&state->stack[spi].spilled_ptr); + __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) state->stack[spi].slot_type[j] = STACK_MISC; goto mark; @@ -3892,7 +3893,7 @@ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env, if (!reg) continue; if (reg_is_pkt_pointer_any(reg)) - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); } } @@ -3920,7 +3921,7 @@ static void release_reg_references(struct bpf_verifier_env *env, if (!reg) continue; if (reg->ref_obj_id == ref_obj_id) - __mark_reg_unknown(reg); + __mark_reg_unknown(env, reg); } } @@ -4582,7 +4583,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } @@ -4834,13 +4835,13 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } if (!src_known && opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) { - __mark_reg_unknown(dst_reg); + __mark_reg_unknown(env, dst_reg); return 0; } @@ -6982,7 +6983,7 @@ static void clean_func_state(struct bpf_verifier_env *env, /* since the register is unused, clear its state * to make further comparison simpler */ - __mark_reg_not_init(&st->regs[i]); + __mark_reg_not_init(env, &st->regs[i]); } for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) { @@ -6990,7 +6991,7 @@ static void clean_func_state(struct bpf_verifier_env *env, /* liveness must not touch this stack slot anymore */ st->stack[i].spilled_ptr.live |= REG_LIVE_DONE; if (!(live & REG_LIVE_READ)) { - __mark_reg_not_init(&st->stack[i].spilled_ptr); + __mark_reg_not_init(env, &st->stack[i].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) st->stack[i].slot_type[j] = STACK_INVALID; } diff --git a/kernel/cred.c b/kernel/cred.c index c0a4c12d38b2..9ed51b70ed80 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -223,7 +223,7 @@ struct cred *cred_alloc_blank(void) new->magic = CRED_MAGIC; #endif - if (security_cred_alloc_blank(new, GFP_KERNEL) < 0) + if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0) goto error; return new; @@ -282,7 +282,7 @@ struct cred *prepare_creds(void) new->security = NULL; #endif - if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; validate_creds(new); return new; @@ -715,7 +715,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) #ifdef CONFIG_SECURITY new->security = NULL; #endif - if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; put_cred(old); diff --git a/kernel/exit.c b/kernel/exit.c index bcbd59888e67..2833ffb0c211 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -517,10 +517,6 @@ static struct task_struct *find_child_reaper(struct task_struct *father, } write_unlock_irq(&tasklist_lock); - if (unlikely(pid_ns == &init_pid_ns)) { - panic("Attempted to kill init! exitcode=0x%08x\n", - father->signal->group_exit_code ?: father->exit_code); - } list_for_each_entry_safe(p, n, dead, ptrace_entry) { list_del_init(&p->ptrace_entry); @@ -766,6 +762,14 @@ void __noreturn do_exit(long code) acct_update_integrals(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { + /* + * If the last thread of global init has exited, panic + * immediately to get a useable coredump. + */ + if (unlikely(is_global_init(tsk))) + panic("Attempted to kill init! exitcode=0x%08x\n", + tsk->signal->group_exit_code ?: (int)code); + #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); exit_itimers(tsk->signal); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 12d2227e5786..b6ea3dcb57bf 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1026,6 +1026,13 @@ static long seccomp_notify_recv(struct seccomp_filter *filter, struct seccomp_notif unotif; ssize_t ret; + /* Verify that we're not given garbage to keep struct extensible. */ + ret = check_zeroed_user(buf, sizeof(unotif)); + if (ret < 0) + return ret; + if (!ret) + return -EINVAL; + memset(&unotif, 0, sizeof(unotif)); ret = down_interruptible(&filter->notif->request); diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 13a0f2e6ebc2..e2ac0e37c4ae 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -554,25 +554,33 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; - struct taskstats *stats; + struct taskstats *stats_new, *stats; - if (sig->stats || thread_group_empty(tsk)) - goto ret; + /* Pairs with smp_store_release() below. */ + stats = smp_load_acquire(&sig->stats); + if (stats || thread_group_empty(tsk)) + return stats; /* No problem if kmem_cache_zalloc() fails */ - stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); + stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); spin_lock_irq(&tsk->sighand->siglock); - if (!sig->stats) { - sig->stats = stats; - stats = NULL; + stats = sig->stats; + if (!stats) { + /* + * Pairs with smp_store_release() above and order the + * kmem_cache_zalloc(). + */ + smp_store_release(&sig->stats, stats_new); + stats = stats_new; + stats_new = NULL; } spin_unlock_irq(&tsk->sighand->siglock); - if (stats) - kmem_cache_free(taskstats_cache, stats); -ret: - return sig->stats; + if (stats_new) + kmem_cache_free(taskstats_cache, stats_new); + + return stats; } /* Send pid data out on exit */ diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index ec960bb939fd..200fb2d3be99 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -14,8 +14,6 @@ #include "posix-timers.h" -static void delete_clock(struct kref *kref); - /* * Returns NULL if the posix_clock instance attached to 'fp' is old and stale. */ @@ -125,7 +123,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp) err = 0; if (!err) { - kref_get(&clk->kref); + get_device(clk->dev); fp->private_data = clk; } out: @@ -141,7 +139,7 @@ static int posix_clock_release(struct inode *inode, struct file *fp) if (clk->ops.release) err = clk->ops.release(clk); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); fp->private_data = NULL; @@ -161,38 +159,35 @@ static const struct file_operations posix_clock_file_operations = { #endif }; -int posix_clock_register(struct posix_clock *clk, dev_t devid) +int posix_clock_register(struct posix_clock *clk, struct device *dev) { int err; - kref_init(&clk->kref); init_rwsem(&clk->rwsem); cdev_init(&clk->cdev, &posix_clock_file_operations); + err = cdev_device_add(&clk->cdev, dev); + if (err) { + pr_err("%s unable to add device %d:%d\n", + dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt)); + return err; + } clk->cdev.owner = clk->ops.owner; - err = cdev_add(&clk->cdev, devid, 1); + clk->dev = dev; - return err; + return 0; } EXPORT_SYMBOL_GPL(posix_clock_register); -static void delete_clock(struct kref *kref) -{ - struct posix_clock *clk = container_of(kref, struct posix_clock, kref); - - if (clk->release) - clk->release(clk); -} - void posix_clock_unregister(struct posix_clock *clk) { - cdev_del(&clk->cdev); + cdev_device_del(&clk->cdev, clk->dev); down_write(&clk->rwsem); clk->zombie = true; up_write(&clk->rwsem); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); } EXPORT_SYMBOL_GPL(posix_clock_unregister); diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c index 7dd602d7f8db..ad9d5b1c4473 100644 --- a/mm/gup_benchmark.c +++ b/mm/gup_benchmark.c @@ -26,6 +26,7 @@ static int __gup_benchmark_ioctl(unsigned int cmd, unsigned long i, nr_pages, addr, next; int nr; struct page **pages; + int ret = 0; if (gup->size > ULONG_MAX) return -EINVAL; @@ -63,7 +64,9 @@ static int __gup_benchmark_ioctl(unsigned int cmd, NULL); break; default: - return -1; + kvfree(pages); + ret = -EINVAL; + goto out; } if (nr <= 0) @@ -85,7 +88,8 @@ static int __gup_benchmark_ioctl(unsigned int cmd, gup->put_delta_usec = ktime_us_delta(end_time, start_time); kvfree(pages); - return 0; +out: + return ret; } static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 41a0fbddc96b..9b3ee79d0edf 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -527,6 +527,17 @@ void prep_transhuge_page(struct page *page) set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR); } +bool is_transparent_hugepage(struct page *page) +{ + if (!PageCompound(page)) + return 0; + + page = compound_head(page); + return is_huge_zero_page(page) || + page[1].compound_dtor == TRANSHUGE_PAGE_DTOR; +} +EXPORT_SYMBOL_GPL(is_transparent_hugepage); + static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long len, loff_t off, unsigned long flags, unsigned long size) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ac65bb5e38ac..dd8737a94bec 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -27,6 +27,7 @@ #include <linux/swapops.h> #include <linux/jhash.h> #include <linux/numa.h> +#include <linux/llist.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -1136,7 +1137,7 @@ static inline void ClearPageHugeTemporary(struct page *page) page[2].mapping = NULL; } -void free_huge_page(struct page *page) +static void __free_huge_page(struct page *page) { /* * Can't pass hstate in here because it is called from the @@ -1199,6 +1200,54 @@ void free_huge_page(struct page *page) spin_unlock(&hugetlb_lock); } +/* + * As free_huge_page() can be called from a non-task context, we have + * to defer the actual freeing in a workqueue to prevent potential + * hugetlb_lock deadlock. + * + * free_hpage_workfn() locklessly retrieves the linked list of pages to + * be freed and frees them one-by-one. As the page->mapping pointer is + * going to be cleared in __free_huge_page() anyway, it is reused as the + * llist_node structure of a lockless linked list of huge pages to be freed. + */ +static LLIST_HEAD(hpage_freelist); + +static void free_hpage_workfn(struct work_struct *work) +{ + struct llist_node *node; + struct page *page; + + node = llist_del_all(&hpage_freelist); + + while (node) { + page = container_of((struct address_space **)node, + struct page, mapping); + node = node->next; + __free_huge_page(page); + } +} +static DECLARE_WORK(free_hpage_work, free_hpage_workfn); + +void free_huge_page(struct page *page) +{ + /* + * Defer freeing if in non-task context to avoid hugetlb_lock deadlock. + */ + if (!in_task()) { + /* + * Only call schedule_work() if hpage_freelist is previously + * empty. Otherwise, schedule_work() had been called but the + * workfn hasn't retrieved the list yet. + */ + if (llist_add((struct llist_node *)&page->mapping, + &hpage_freelist)) + schedule_work(&free_hpage_work); + return; + } + + __free_huge_page(page); +} + static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { INIT_LIST_HEAD(&page->lru); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 55ac23ef11c1..a91a072f2b2c 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -483,8 +483,9 @@ static void update_pgdat_span(struct pglist_data *pgdat) pgdat->node_spanned_pages = node_end_pfn - node_start_pfn; } -static void __remove_zone(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages) +void __ref remove_pfn_range_from_zone(struct zone *zone, + unsigned long start_pfn, + unsigned long nr_pages) { struct pglist_data *pgdat = zone->zone_pgdat; unsigned long flags; @@ -499,28 +500,30 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn, return; #endif + clear_zone_contiguous(zone); + pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); update_pgdat_span(pgdat); pgdat_resize_unlock(zone->zone_pgdat, &flags); + + set_zone_contiguous(zone); } -static void __remove_section(struct zone *zone, unsigned long pfn, - unsigned long nr_pages, unsigned long map_offset, - struct vmem_altmap *altmap) +static void __remove_section(unsigned long pfn, unsigned long nr_pages, + unsigned long map_offset, + struct vmem_altmap *altmap) { struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn)); if (WARN_ON_ONCE(!valid_section(ms))) return; - __remove_zone(zone, pfn, nr_pages); sparse_remove_section(ms, pfn, nr_pages, map_offset, altmap); } /** - * __remove_pages() - remove sections of pages from a zone - * @zone: zone from which pages need to be removed + * __remove_pages() - remove sections of pages * @pfn: starting pageframe (must be aligned to start of a section) * @nr_pages: number of pages to remove (must be multiple of section size) * @altmap: alternative device page map or %NULL if default memmap is used @@ -530,16 +533,14 @@ static void __remove_section(struct zone *zone, unsigned long pfn, * sure that pages are marked reserved and zones are adjust properly by * calling offline_pages(). */ -void __remove_pages(struct zone *zone, unsigned long pfn, - unsigned long nr_pages, struct vmem_altmap *altmap) +void __remove_pages(unsigned long pfn, unsigned long nr_pages, + struct vmem_altmap *altmap) { unsigned long map_offset = 0; unsigned long nr, start_sec, end_sec; map_offset = vmem_altmap_offset(altmap); - clear_zone_contiguous(zone); - if (check_pfn_span(pfn, nr_pages, "remove")) return; @@ -551,13 +552,11 @@ void __remove_pages(struct zone *zone, unsigned long pfn, cond_resched(); pfns = min(nr_pages, PAGES_PER_SECTION - (pfn & ~PAGE_SECTION_MASK)); - __remove_section(zone, pfn, pfns, map_offset, altmap); + __remove_section(pfn, pfns, map_offset, altmap); pfn += pfns; nr_pages -= pfns; map_offset = 0; } - - set_zone_contiguous(zone); } int set_online_page_callback(online_page_callback_t callback) @@ -869,6 +868,7 @@ failed_addition: (unsigned long long) pfn << PAGE_SHIFT, (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); + remove_pfn_range_from_zone(zone, pfn, nr_pages); mem_hotplug_done(); return ret; } @@ -1628,6 +1628,7 @@ static int __ref __offline_pages(unsigned long start_pfn, writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); + remove_pfn_range_from_zone(zone, start_pfn, nr_pages); mem_hotplug_done(); return 0; diff --git a/mm/memremap.c b/mm/memremap.c index 03ccbdfeb697..c51c6bd2fe34 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -120,7 +120,7 @@ void memunmap_pages(struct dev_pagemap *pgmap) mem_hotplug_begin(); if (pgmap->type == MEMORY_DEVICE_PRIVATE) { - __remove_pages(page_zone(first_page), PHYS_PFN(res->start), + __remove_pages(PHYS_PFN(res->start), PHYS_PFN(resource_size(res)), NULL); } else { arch_remove_memory(nid, res->start, resource_size(res), diff --git a/mm/migrate.c b/mm/migrate.c index eae1565285e3..86873b6f38a7 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1512,9 +1512,11 @@ static int do_move_pages_to_node(struct mm_struct *mm, /* * Resolves the given address to a struct page, isolates it from the LRU and * puts it to the given pagelist. - * Returns -errno if the page cannot be found/isolated or 0 when it has been - * queued or the page doesn't need to be migrated because it is already on - * the target node + * Returns: + * errno - if the page cannot be found/isolated + * 0 - when it doesn't have to be migrated because it is already on the + * target node + * 1 - when it has been queued */ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, int node, struct list_head *pagelist, bool migrate_all) @@ -1553,7 +1555,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, if (PageHuge(page)) { if (PageHead(page)) { isolate_huge_page(page, pagelist); - err = 0; + err = 1; } } else { struct page *head; @@ -1563,7 +1565,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, if (err) goto out_putpage; - err = 0; + err = 1; list_add_tail(&head->lru, pagelist); mod_node_page_state(page_pgdat(head), NR_ISOLATED_ANON + page_is_file_cache(head), @@ -1640,8 +1642,17 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, */ err = add_page_for_migration(mm, addr, current_node, &pagelist, flags & MPOL_MF_MOVE_ALL); - if (!err) + + if (!err) { + /* The page is already on the target node */ + err = store_status(status, i, current_node, 1); + if (err) + goto out_flush; continue; + } else if (err > 0) { + /* The page is successfully queued for migration */ + continue; + } err = store_status(status, i, err, 1); if (err) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 71e3acea7817..d58c481b3df8 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -890,7 +890,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message) K(get_mm_counter(mm, MM_FILEPAGES)), K(get_mm_counter(mm, MM_SHMEMPAGES)), from_kuid(&init_user_ns, task_uid(victim)), - mm_pgtables_bytes(mm), victim->signal->oom_score_adj); + mm_pgtables_bytes(mm) >> 10, victim->signal->oom_score_adj); task_unlock(victim); /* diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 2b2b9aae8a3c..22d17ecfe7df 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -2069,6 +2069,11 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage, zs_pool_dec_isolated(pool); } + if (page_zone(newpage) != page_zone(page)) { + dec_zone_page_state(page, NR_ZSPAGES); + inc_zone_page_state(newpage, NR_ZSPAGES); + } + reset_page(page); put_page(page); page = newpage; diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c index 2cdfc5d6c25d..8c69f0c95a8e 100644 --- a/net/bridge/br_nf_core.c +++ b/net/bridge/br_nf_core.c @@ -22,7 +22,8 @@ #endif static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 4096d8a74a2b..e1256e03a9a8 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1867,7 +1867,7 @@ static int ebt_buf_count(struct ebt_entries_buf_state *state, unsigned int sz) } static int ebt_buf_add(struct ebt_entries_buf_state *state, - void *data, unsigned int sz) + const void *data, unsigned int sz) { if (state->buf_kern_start == NULL) goto count_only; @@ -1901,7 +1901,7 @@ enum compat_mwt { EBT_COMPAT_TARGET, }; -static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, +static int compat_mtw_from_user(const struct compat_ebt_entry_mwt *mwt, enum compat_mwt compat_mwt, struct ebt_entries_buf_state *state, const unsigned char *base) @@ -1979,22 +1979,23 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, /* return size of all matches, watchers or target, including necessary * alignment and padding. */ -static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, +static int ebt_size_mwt(const struct compat_ebt_entry_mwt *match32, unsigned int size_left, enum compat_mwt type, struct ebt_entries_buf_state *state, const void *base) { + const char *buf = (const char *)match32; int growth = 0; - char *buf; if (size_left == 0) return 0; - buf = (char *) match32; - - while (size_left >= sizeof(*match32)) { + do { struct ebt_entry_match *match_kern; int ret; + if (size_left < sizeof(*match32)) + return -EINVAL; + match_kern = (struct ebt_entry_match *) state->buf_kern_start; if (match_kern) { char *tmp; @@ -2031,22 +2032,18 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (match_kern) match_kern->match_size = ret; - /* rule should have no remaining data after target */ - if (type == EBT_COMPAT_TARGET && size_left) - return -EINVAL; - match32 = (struct compat_ebt_entry_mwt *) buf; - } + } while (size_left); return growth; } /* called for all ebt_entry structures. */ -static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, +static int size_entry_mwt(const struct ebt_entry *entry, const unsigned char *base, unsigned int *total, struct ebt_entries_buf_state *state) { - unsigned int i, j, startoff, new_offset = 0; + unsigned int i, j, startoff, next_expected_off, new_offset = 0; /* stores match/watchers/targets & offset of next struct ebt_entry: */ unsigned int offsets[4]; unsigned int *offsets_update = NULL; @@ -2132,11 +2129,13 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, return ret; } - startoff = state->buf_user_offset - startoff; + next_expected_off = state->buf_user_offset - startoff; + if (next_expected_off != entry->next_offset) + return -EINVAL; - if (WARN_ON(*total < startoff)) + if (*total < entry->next_offset) return -EINVAL; - *total -= startoff; + *total -= entry->next_offset; return 0; } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index aea918135ec3..08c3dc45f1a4 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -110,7 +110,8 @@ static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb , u32 mtu); + struct sk_buff *skb , u32 mtu, + bool confirm_neigh); static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, @@ -251,7 +252,8 @@ static int dn_dst_gc(struct dst_ops *ops) * advertise to the other end). */ static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct dn_route *rt = (struct dn_route *) dst; struct neighbour *n = rt->n; diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c index 94447974a3c0..d5f709b940ff 100644 --- a/net/hsr/hsr_debugfs.c +++ b/net/hsr/hsr_debugfs.c @@ -20,6 +20,8 @@ #include "hsr_main.h" #include "hsr_framereg.h" +static struct dentry *hsr_debugfs_root_dir; + static void print_mac_address(struct seq_file *sfp, unsigned char *mac) { seq_printf(sfp, "%02x:%02x:%02x:%02x:%02x:%02x:", @@ -63,8 +65,20 @@ hsr_node_table_open(struct inode *inode, struct file *filp) return single_open(filp, hsr_node_table_show, inode->i_private); } +void hsr_debugfs_rename(struct net_device *dev) +{ + struct hsr_priv *priv = netdev_priv(dev); + struct dentry *d; + + d = debugfs_rename(hsr_debugfs_root_dir, priv->node_tbl_root, + hsr_debugfs_root_dir, dev->name); + if (IS_ERR(d)) + netdev_warn(dev, "failed to rename\n"); + else + priv->node_tbl_root = d; +} + static const struct file_operations hsr_fops = { - .owner = THIS_MODULE, .open = hsr_node_table_open, .read = seq_read, .llseek = seq_lseek, @@ -78,15 +92,14 @@ static const struct file_operations hsr_fops = { * When debugfs is configured this routine sets up the node_table file per * hsr device for dumping the node_table entries */ -int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) +void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) { - int rc = -1; struct dentry *de = NULL; - de = debugfs_create_dir(hsr_dev->name, NULL); - if (!de) { - pr_err("Cannot create hsr debugfs root\n"); - return rc; + de = debugfs_create_dir(hsr_dev->name, hsr_debugfs_root_dir); + if (IS_ERR(de)) { + pr_err("Cannot create hsr debugfs directory\n"); + return; } priv->node_tbl_root = de; @@ -94,13 +107,13 @@ int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) de = debugfs_create_file("node_table", S_IFREG | 0444, priv->node_tbl_root, priv, &hsr_fops); - if (!de) { - pr_err("Cannot create hsr node_table directory\n"); - return rc; + if (IS_ERR(de)) { + pr_err("Cannot create hsr node_table file\n"); + debugfs_remove(priv->node_tbl_root); + priv->node_tbl_root = NULL; + return; } priv->node_tbl_file = de; - - return 0; } /* hsr_debugfs_term - Tear down debugfs intrastructure @@ -117,3 +130,18 @@ hsr_debugfs_term(struct hsr_priv *priv) debugfs_remove(priv->node_tbl_root); priv->node_tbl_root = NULL; } + +void hsr_debugfs_create_root(void) +{ + hsr_debugfs_root_dir = debugfs_create_dir("hsr", NULL); + if (IS_ERR(hsr_debugfs_root_dir)) { + pr_err("Cannot create hsr debugfs root directory\n"); + hsr_debugfs_root_dir = NULL; + } +} + +void hsr_debugfs_remove_root(void) +{ + /* debugfs_remove() internally checks NULL and ERROR */ + debugfs_remove(hsr_debugfs_root_dir); +} diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index b01e1bae4ddc..c7bd6c49fadf 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -272,6 +272,8 @@ static void send_hsr_supervision_frame(struct hsr_port *master, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); if (hsr_ver > 0) { hsr_tag = skb_put(skb, sizeof(struct hsr_tag)); @@ -368,7 +370,7 @@ static void hsr_dev_destroy(struct net_device *hsr_dev) del_timer_sync(&hsr->prune_timer); del_timer_sync(&hsr->announce_timer); - hsr_del_self_node(&hsr->self_node_db); + hsr_del_self_node(hsr); hsr_del_nodes(&hsr->node_db); } @@ -440,11 +442,12 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); INIT_LIST_HEAD(&hsr->self_node_db); + spin_lock_init(&hsr->list_lock); ether_addr_copy(hsr_dev->dev_addr, slave[0]->dev_addr); /* Make sure we recognize frames from ourselves in hsr_rcv() */ - res = hsr_create_self_node(&hsr->self_node_db, hsr_dev->dev_addr, + res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); if (res < 0) return res; @@ -477,31 +480,32 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER); if (res) - goto err_add_port; + goto err_add_master; res = register_netdevice(hsr_dev); if (res) - goto fail; + goto err_unregister; res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A); if (res) - goto fail; + goto err_add_slaves; + res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B); if (res) - goto fail; + goto err_add_slaves; + hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); - res = hsr_debugfs_init(hsr, hsr_dev); - if (res) - goto fail; return 0; -fail: +err_add_slaves: + unregister_netdevice(hsr_dev); +err_unregister: list_for_each_entry_safe(port, tmp, &hsr->ports, port_list) hsr_del_port(port); -err_add_port: - hsr_del_self_node(&hsr->self_node_db); +err_add_master: + hsr_del_self_node(hsr); return res; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 292be446007b..27dc65d7de67 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -75,10 +75,11 @@ static struct hsr_node *find_node_by_addr_A(struct list_head *node_db, /* Helper for device init; the self_node_db is used in hsr_rcv() to recognize * frames from self that's been looped over the HSR ring. */ -int hsr_create_self_node(struct list_head *self_node_db, +int hsr_create_self_node(struct hsr_priv *hsr, unsigned char addr_a[ETH_ALEN], unsigned char addr_b[ETH_ALEN]) { + struct list_head *self_node_db = &hsr->self_node_db; struct hsr_node *node, *oldnode; node = kmalloc(sizeof(*node), GFP_KERNEL); @@ -88,33 +89,33 @@ int hsr_create_self_node(struct list_head *self_node_db, ether_addr_copy(node->macaddress_A, addr_a); ether_addr_copy(node->macaddress_B, addr_b); - rcu_read_lock(); + spin_lock_bh(&hsr->list_lock); oldnode = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); if (oldnode) { list_replace_rcu(&oldnode->mac_list, &node->mac_list); - rcu_read_unlock(); - synchronize_rcu(); - kfree(oldnode); + spin_unlock_bh(&hsr->list_lock); + kfree_rcu(oldnode, rcu_head); } else { - rcu_read_unlock(); list_add_tail_rcu(&node->mac_list, self_node_db); + spin_unlock_bh(&hsr->list_lock); } return 0; } -void hsr_del_self_node(struct list_head *self_node_db) +void hsr_del_self_node(struct hsr_priv *hsr) { + struct list_head *self_node_db = &hsr->self_node_db; struct hsr_node *node; - rcu_read_lock(); + spin_lock_bh(&hsr->list_lock); node = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); - rcu_read_unlock(); if (node) { list_del_rcu(&node->mac_list); - kfree(node); + kfree_rcu(node, rcu_head); } + spin_unlock_bh(&hsr->list_lock); } void hsr_del_nodes(struct list_head *node_db) @@ -130,30 +131,43 @@ void hsr_del_nodes(struct list_head *node_db) * seq_out is used to initialize filtering of outgoing duplicate frames * originating from the newly added node. */ -struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], - u16 seq_out) +static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, + struct list_head *node_db, + unsigned char addr[], + u16 seq_out) { - struct hsr_node *node; + struct hsr_node *new_node, *node; unsigned long now; int i; - node = kzalloc(sizeof(*node), GFP_ATOMIC); - if (!node) + new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC); + if (!new_node) return NULL; - ether_addr_copy(node->macaddress_A, addr); + ether_addr_copy(new_node->macaddress_A, addr); /* We are only interested in time diffs here, so use current jiffies * as initialization. (0 could trigger an spurious ring error warning). */ now = jiffies; for (i = 0; i < HSR_PT_PORTS; i++) - node->time_in[i] = now; + new_node->time_in[i] = now; for (i = 0; i < HSR_PT_PORTS; i++) - node->seq_out[i] = seq_out; - - list_add_tail_rcu(&node->mac_list, node_db); + new_node->seq_out[i] = seq_out; + spin_lock_bh(&hsr->list_lock); + list_for_each_entry_rcu(node, node_db, mac_list) { + if (ether_addr_equal(node->macaddress_A, addr)) + goto out; + if (ether_addr_equal(node->macaddress_B, addr)) + goto out; + } + list_add_tail_rcu(&new_node->mac_list, node_db); + spin_unlock_bh(&hsr->list_lock); + return new_node; +out: + spin_unlock_bh(&hsr->list_lock); + kfree(new_node); return node; } @@ -163,6 +177,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, bool is_sup) { struct list_head *node_db = &port->hsr->node_db; + struct hsr_priv *hsr = port->hsr; struct hsr_node *node; struct ethhdr *ethhdr; u16 seq_out; @@ -196,7 +211,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, seq_out = HSR_SEQNR_START; } - return hsr_add_node(node_db, ethhdr->h_source, seq_out); + return hsr_add_node(hsr, node_db, ethhdr->h_source, seq_out); } /* Use the Supervision frame's info about an eventual macaddress_B for merging @@ -206,10 +221,11 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, struct hsr_port *port_rcv) { - struct ethhdr *ethhdr; - struct hsr_node *node_real; + struct hsr_priv *hsr = port_rcv->hsr; struct hsr_sup_payload *hsr_sp; + struct hsr_node *node_real; struct list_head *node_db; + struct ethhdr *ethhdr; int i; ethhdr = (struct ethhdr *)skb_mac_header(skb); @@ -231,7 +247,7 @@ void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, node_real = find_node_by_addr_A(node_db, hsr_sp->macaddress_A); if (!node_real) /* No frame received from AddrA of this node yet */ - node_real = hsr_add_node(node_db, hsr_sp->macaddress_A, + node_real = hsr_add_node(hsr, node_db, hsr_sp->macaddress_A, HSR_SEQNR_START - 1); if (!node_real) goto done; /* No mem */ @@ -252,7 +268,9 @@ void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, } node_real->addr_B_port = port_rcv->type; + spin_lock_bh(&hsr->list_lock); list_del_rcu(&node_curr->mac_list); + spin_unlock_bh(&hsr->list_lock); kfree_rcu(node_curr, rcu_head); done: @@ -368,12 +386,13 @@ void hsr_prune_nodes(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, prune_timer); struct hsr_node *node; + struct hsr_node *tmp; struct hsr_port *port; unsigned long timestamp; unsigned long time_a, time_b; - rcu_read_lock(); - list_for_each_entry_rcu(node, &hsr->node_db, mac_list) { + spin_lock_bh(&hsr->list_lock); + list_for_each_entry_safe(node, tmp, &hsr->node_db, mac_list) { /* Don't prune own node. Neither time_in[HSR_PT_SLAVE_A] * nor time_in[HSR_PT_SLAVE_B], will ever be updated for * the master port. Thus the master node will be repeatedly @@ -421,7 +440,7 @@ void hsr_prune_nodes(struct timer_list *t) kfree_rcu(node, rcu_head); } } - rcu_read_unlock(); + spin_unlock_bh(&hsr->list_lock); /* Restart timer */ mod_timer(&hsr->prune_timer, diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 89a3ce38151d..0f0fa12b4329 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -12,10 +12,8 @@ struct hsr_node; -void hsr_del_self_node(struct list_head *self_node_db); +void hsr_del_self_node(struct hsr_priv *hsr); void hsr_del_nodes(struct list_head *node_db); -struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], - u16 seq_out); struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, bool is_sup); void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, @@ -33,7 +31,7 @@ int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, void hsr_prune_nodes(struct timer_list *t); -int hsr_create_self_node(struct list_head *self_node_db, +int hsr_create_self_node(struct hsr_priv *hsr, unsigned char addr_a[ETH_ALEN], unsigned char addr_b[ETH_ALEN]); diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index b9988a662ee1..9e389accbfc7 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -45,6 +45,10 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, case NETDEV_CHANGE: /* Link (carrier) state changes */ hsr_check_carrier_and_operstate(hsr); break; + case NETDEV_CHANGENAME: + if (is_hsr_master(dev)) + hsr_debugfs_rename(dev); + break; case NETDEV_CHANGEADDR: if (port->type == HSR_PT_MASTER) { /* This should not happen since there's no @@ -64,7 +68,7 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, /* Make sure we recognize frames from ourselves in hsr_rcv() */ port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); - res = hsr_create_self_node(&hsr->self_node_db, + res = hsr_create_self_node(hsr, master->dev->dev_addr, port ? port->dev->dev_addr : @@ -123,6 +127,7 @@ static void __exit hsr_exit(void) { unregister_netdevice_notifier(&hsr_nb); hsr_netlink_exit(); + hsr_debugfs_remove_root(); } module_init(hsr_init); diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 96fac696a1e1..d40de84a637f 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -160,8 +160,9 @@ struct hsr_priv { int announce_count; u16 sequence_nr; u16 sup_sequence_nr; /* For HSRv1 separate seq_nr for supervision */ - u8 prot_version; /* Indicate if HSRv0 or HSRv1. */ - spinlock_t seqnr_lock; /* locking for sequence_nr */ + u8 prot_version; /* Indicate if HSRv0 or HSRv1. */ + spinlock_t seqnr_lock; /* locking for sequence_nr */ + spinlock_t list_lock; /* locking for node list */ unsigned char sup_multicast_addr[ETH_ALEN]; #ifdef CONFIG_DEBUG_FS struct dentry *node_tbl_root; @@ -184,17 +185,24 @@ static inline u16 hsr_get_skb_sequence_nr(struct sk_buff *skb) } #if IS_ENABLED(CONFIG_DEBUG_FS) -int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev); +void hsr_debugfs_rename(struct net_device *dev); +void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev); void hsr_debugfs_term(struct hsr_priv *priv); +void hsr_debugfs_create_root(void); +void hsr_debugfs_remove_root(void); #else -static inline int hsr_debugfs_init(struct hsr_priv *priv, - struct net_device *hsr_dev) +static inline void void hsr_debugfs_rename(struct net_device *dev) { - return 0; } - +static inline void hsr_debugfs_init(struct hsr_priv *priv, + struct net_device *hsr_dev) +{} static inline void hsr_debugfs_term(struct hsr_priv *priv) {} +static inline void hsr_debugfs_create_root(void) +{} +static inline void hsr_debugfs_remove_root(void) +{} #endif #endif /* __HSR_PRIVATE_H */ diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 8f8337f893ba..8dc0547f01d0 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -476,6 +476,7 @@ int __init hsr_netlink_init(void) if (rc) goto fail_genl_register_family; + hsr_debugfs_create_root(); return 0; fail_genl_register_family: diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index e4c6e8b40490..18c0d5bffe12 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1086,7 +1086,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu) if (!dst) goto out; } - dst->ops->update_pmtu(dst, sk, NULL, mtu); + dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = __sk_dst_check(sk, 0); if (!dst) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 38c02bb62e2c..0fe2a5d3e258 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -505,7 +505,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; if (skb_valid_dst(skb)) - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!skb_is_gso(skb) && diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 9b153c7fcbb4..e90b600c7a25 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -214,7 +214,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, mtu = dst_mtu(dst); if (skb->len > mtu) { - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f88c93c38f11..87e979f2b74a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -139,7 +139,8 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static void ipv4_dst_destroy(struct dst_entry *dst); @@ -1043,7 +1044,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) } static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct rtable *rt = (struct rtable *) dst; struct flowi4 fl4; @@ -2687,7 +2689,8 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) } static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1f7735ca8f22..58c92a7d671c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -72,6 +72,9 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) __skb_unlink(skb, &sk->sk_write_queue); tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); + if (tp->highest_sack == NULL) + tp->highest_sack = skb; + tp->packets_out += tcp_skb_pcount(skb); if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 4da5758cc718..93a355b6b092 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1475,7 +1475,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) * queue contains some other skb */ rmem = atomic_add_return(size, &sk->sk_rmem_alloc); - if (rmem > (size + sk->sk_rcvbuf)) + if (rmem > (size + (unsigned int)sk->sk_rcvbuf)) goto uncharge_drop; spin_lock(&list->lock); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 35b84b52b702..9ebd54752e03 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -100,12 +100,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, } static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, sk, skb, mtu); + path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk, diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index fe9cb8d1adca..e315526fa244 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -146,7 +146,7 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu) if (IS_ERR(dst)) return NULL; - dst->ops->update_pmtu(dst, sk, NULL, mtu); + dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = inet6_csk_route_socket(sk, &fl6); return IS_ERR(dst) ? NULL : dst; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 9d0965252ddf..ee968d980746 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1040,7 +1040,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) - dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu); + dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, false); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, NEXTHDR_GRE); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 754a484d35df..2f376dbc37d5 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -640,7 +640,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rel_info > dst_mtu(skb_dst(skb2))) goto out; - skb_dst_update_pmtu(skb2, rel_info); + skb_dst_update_pmtu_no_confirm(skb2, rel_info); } icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); @@ -1132,7 +1132,7 @@ route_lookup: mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ? IPV6_MIN_MTU : IPV4_MIN_MTU); - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { *pmtu = mtu; err = -EMSGSIZE; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 024db17386d2..6f08b760c2a7 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -479,7 +479,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) mtu = dst_mtu(dst); if (skb->len > mtu) { - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { if (mtu < IPV6_MIN_MTU) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b59940416cb5..affb51c11a25 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -95,7 +95,8 @@ static int ip6_pkt_prohibit(struct sk_buff *skb); static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, @@ -264,7 +265,8 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) } static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } @@ -2692,7 +2694,8 @@ static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, - const struct ipv6hdr *iph, u32 mtu) + const struct ipv6hdr *iph, u32 mtu, + bool confirm_neigh) { const struct in6_addr *daddr, *saddr; struct rt6_info *rt6 = (struct rt6_info *)dst; @@ -2710,7 +2713,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, daddr = NULL; saddr = NULL; } - dst_confirm_neigh(dst, daddr); + + if (confirm_neigh) + dst_confirm_neigh(dst, daddr); + mtu = max_t(u32, mtu, IPV6_MIN_MTU); if (mtu >= dst_mtu(dst)) return; @@ -2764,9 +2770,11 @@ out_unlock: } static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { - __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu); + __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu, + confirm_neigh); } void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, @@ -2785,7 +2793,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) - __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu)); + __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_update_pmtu); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index b2ccbc473127..98954830c40b 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -944,7 +944,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } if (tunnel->parms.iph.daddr) - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len > mtu && !skb_is_gso(skb)) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 699e0730ce8e..af7a4b8b1e9c 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -98,12 +98,13 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, } static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, sk, skb, mtu); + path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk, diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index b1e300f8881b..b00866d777fe 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -208,7 +208,7 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu) struct rtable *ort = skb_rtable(skb); if (!skb->dev && sk && sk_fullsock(sk)) - ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu); + ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu, true); } static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af, diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index de7a0d1e15c8..0d72e5ccb47b 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -88,7 +88,7 @@ static int nf_flow_rule_match(struct nf_flow_match *match, switch (tuple->l4proto) { case IPPROTO_TCP: key->tcp.flags = 0; - mask->tcp.flags = TCP_FLAG_RST | TCP_FLAG_FIN; + mask->tcp.flags = cpu_to_be16(be32_to_cpu(TCP_FLAG_RST | TCP_FLAG_FIN) >> 16); match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP); break; case IPPROTO_UDP: diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 4c33dfc9dab5..d67f83a0958d 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -50,7 +50,7 @@ static void nft_tproxy_eval_v4(const struct nft_expr *expr, taddr = nf_tproxy_laddr4(skb, taddr, iph->daddr); if (priv->sreg_port) - tport = regs->data[priv->sreg_port]; + tport = nft_reg_load16(®s->data[priv->sreg_port]); if (!tport) tport = hp->dest; @@ -117,7 +117,7 @@ static void nft_tproxy_eval_v6(const struct nft_expr *expr, taddr = *nf_tproxy_laddr6(skb, &taddr, &iph->daddr); if (priv->sreg_port) - tport = regs->data[priv->sreg_port]; + tport = nft_reg_load16(®s->data[priv->sreg_port]); if (!tport) tport = hp->dest; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 7c7d10f2e0c1..5e99df80e80a 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -209,6 +209,7 @@ struct rxrpc_skb_priv { struct rxrpc_security { const char *name; /* name of this service */ u8 security_index; /* security type provided */ + u32 no_key_abort; /* Abort code indicating no key */ /* Initialise a security service */ int (*init)(void); @@ -977,8 +978,9 @@ static inline void rxrpc_reduce_conn_timer(struct rxrpc_connection *conn, struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *, struct sk_buff *); struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *, gfp_t); -void rxrpc_new_incoming_connection(struct rxrpc_sock *, - struct rxrpc_connection *, struct sk_buff *); +void rxrpc_new_incoming_connection(struct rxrpc_sock *, struct rxrpc_connection *, + const struct rxrpc_security *, struct key *, + struct sk_buff *); void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* @@ -1103,7 +1105,9 @@ extern const struct rxrpc_security rxkad; int __init rxrpc_init_security(void); void rxrpc_exit_security(void); int rxrpc_init_client_conn_security(struct rxrpc_connection *); -int rxrpc_init_server_conn_security(struct rxrpc_connection *); +bool rxrpc_look_up_server_security(struct rxrpc_local *, struct rxrpc_sock *, + const struct rxrpc_security **, struct key **, + struct sk_buff *); /* * sendmsg.c diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 135bf5cd8dd5..70e44abf106c 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -240,6 +240,22 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) } /* + * Ping the other end to fill our RTT cache and to retrieve the rwind + * and MTU parameters. + */ +static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + ktime_t now = skb->tstamp; + + if (call->peer->rtt_usage < 3 || + ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) + rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, + true, true, + rxrpc_propose_ack_ping_for_params); +} + +/* * Allocate a new incoming call from the prealloc pool, along with a connection * and a peer as necessary. */ @@ -247,6 +263,8 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, struct rxrpc_local *local, struct rxrpc_peer *peer, struct rxrpc_connection *conn, + const struct rxrpc_security *sec, + struct key *key, struct sk_buff *skb) { struct rxrpc_backlog *b = rx->backlog; @@ -294,7 +312,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, conn->params.local = rxrpc_get_local(local); conn->params.peer = peer; rxrpc_see_connection(conn); - rxrpc_new_incoming_connection(rx, conn, skb); + rxrpc_new_incoming_connection(rx, conn, sec, key, skb); } else { rxrpc_get_connection(conn); } @@ -333,9 +351,11 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + const struct rxrpc_security *sec = NULL; struct rxrpc_connection *conn; struct rxrpc_peer *peer = NULL; - struct rxrpc_call *call; + struct rxrpc_call *call = NULL; + struct key *key = NULL; _enter(""); @@ -346,9 +366,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN); skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; skb->priority = RX_INVALID_OPERATION; - _leave(" = NULL [close]"); - call = NULL; - goto out; + goto no_call; } /* The peer, connection and call may all have sprung into existence due @@ -358,29 +376,19 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, */ conn = rxrpc_find_connection_rcu(local, skb, &peer); - call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb); + if (!conn && !rxrpc_look_up_server_security(local, rx, &sec, &key, skb)) + goto no_call; + + call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, key, skb); + key_put(key); if (!call) { skb->mark = RXRPC_SKB_MARK_REJECT_BUSY; - _leave(" = NULL [busy]"); - call = NULL; - goto out; + goto no_call; } trace_rxrpc_receive(call, rxrpc_receive_incoming, sp->hdr.serial, sp->hdr.seq); - /* Lock the call to prevent rxrpc_kernel_send/recv_data() and - * sendmsg()/recvmsg() inconveniently stealing the mutex once the - * notification is generated. - * - * The BUG should never happen because the kernel should be well - * behaved enough not to access the call before the first notification - * event and userspace is prevented from doing so until the state is - * appropriate. - */ - if (!mutex_trylock(&call->user_mutex)) - BUG(); - /* Make the call live. */ rxrpc_incoming_call(rx, call, skb); conn = call->conn; @@ -421,6 +429,9 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, BUG(); } spin_unlock(&conn->state_lock); + spin_unlock(&rx->incoming_lock); + + rxrpc_send_ping(call, skb); if (call->state == RXRPC_CALL_SERVER_ACCEPTING) rxrpc_notify_socket(call); @@ -433,9 +444,12 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, rxrpc_put_call(call, rxrpc_call_put); _leave(" = %p{%d}", call, call->debug_id); -out: - spin_unlock(&rx->incoming_lock); return call; + +no_call: + spin_unlock(&rx->incoming_lock); + _leave(" = NULL [%u]", skb->mark); + return NULL; } /* diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index a1ceef4f5cd0..808a4723f868 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -376,21 +376,7 @@ static void rxrpc_secure_connection(struct rxrpc_connection *conn) _enter("{%d}", conn->debug_id); ASSERT(conn->security_ix != 0); - - if (!conn->params.key) { - _debug("set up security"); - ret = rxrpc_init_server_conn_security(conn); - switch (ret) { - case 0: - break; - case -ENOENT: - abort_code = RX_CALL_DEAD; - goto abort; - default: - abort_code = RXKADNOAUTH; - goto abort; - } - } + ASSERT(conn->server_key); if (conn->security->issue_challenge(conn) < 0) { abort_code = RX_CALL_DEAD; diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 123d6ceab15c..21da48e3d2e5 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -148,6 +148,8 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn */ void rxrpc_new_incoming_connection(struct rxrpc_sock *rx, struct rxrpc_connection *conn, + const struct rxrpc_security *sec, + struct key *key, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -160,6 +162,8 @@ void rxrpc_new_incoming_connection(struct rxrpc_sock *rx, conn->service_id = sp->hdr.serviceId; conn->security_ix = sp->hdr.securityIndex; conn->out_clientflag = 0; + conn->security = sec; + conn->server_key = key_get(key); if (conn->security_ix) conn->state = RXRPC_CONN_SERVICE_UNSECURED; else diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 157be1ff8697..86bd133b4fa0 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -193,22 +193,6 @@ send_extra_data: } /* - * Ping the other end to fill our RTT cache and to retrieve the rwind - * and MTU parameters. - */ -static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - ktime_t now = skb->tstamp; - - if (call->peer->rtt_usage < 3 || - ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, - true, true, - rxrpc_propose_ack_ping_for_params); -} - -/* * Apply a hard ACK by advancing the Tx window. */ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, @@ -1396,8 +1380,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) call = rxrpc_new_incoming_call(local, rx, skb); if (!call) goto reject_packet; - rxrpc_send_ping(call, skb); - mutex_unlock(&call->user_mutex); } /* Process a call packet; this either discards or passes on the ref diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 8d8aa3c230b5..098f1f9ec53b 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -648,9 +648,9 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) u32 serial; int ret; - _enter("{%d,%x}", conn->debug_id, key_serial(conn->params.key)); + _enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key)); - ret = key_validate(conn->params.key); + ret = key_validate(conn->server_key); if (ret < 0) return ret; @@ -1293,6 +1293,7 @@ static void rxkad_exit(void) const struct rxrpc_security rxkad = { .name = "rxkad", .security_index = RXRPC_SECURITY_RXKAD, + .no_key_abort = RXKADUNKNOWNKEY, .init = rxkad_init, .exit = rxkad_exit, .init_connection_security = rxkad_init_connection_security, diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index a4c47d2b7054..9b1fb9ed0717 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -101,62 +101,58 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) } /* - * initialise the security on a server connection + * Find the security key for a server connection. */ -int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) +bool rxrpc_look_up_server_security(struct rxrpc_local *local, struct rxrpc_sock *rx, + const struct rxrpc_security **_sec, + struct key **_key, + struct sk_buff *skb) { const struct rxrpc_security *sec; - struct rxrpc_local *local = conn->params.local; - struct rxrpc_sock *rx; - struct key *key; - key_ref_t kref; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + key_ref_t kref = NULL; char kdesc[5 + 1 + 3 + 1]; _enter(""); - sprintf(kdesc, "%u:%u", conn->service_id, conn->security_ix); + sprintf(kdesc, "%u:%u", sp->hdr.serviceId, sp->hdr.securityIndex); - sec = rxrpc_security_lookup(conn->security_ix); + sec = rxrpc_security_lookup(sp->hdr.securityIndex); if (!sec) { - _leave(" = -ENOKEY [lookup]"); - return -ENOKEY; + trace_rxrpc_abort(0, "SVS", + sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_INVALID_OPERATION, EKEYREJECTED); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = RX_INVALID_OPERATION; + return false; } - /* find the service */ - read_lock(&local->services_lock); - rx = rcu_dereference_protected(local->service, - lockdep_is_held(&local->services_lock)); - if (rx && (rx->srx.srx_service == conn->service_id || - rx->second_service == conn->service_id)) - goto found_service; + if (sp->hdr.securityIndex == RXRPC_SECURITY_NONE) + goto out; - /* the service appears to have died */ - read_unlock(&local->services_lock); - _leave(" = -ENOENT"); - return -ENOENT; - -found_service: if (!rx->securities) { - read_unlock(&local->services_lock); - _leave(" = -ENOKEY"); - return -ENOKEY; + trace_rxrpc_abort(0, "SVR", + sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_INVALID_OPERATION, EKEYREJECTED); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = RX_INVALID_OPERATION; + return false; } /* look through the service's keyring */ kref = keyring_search(make_key_ref(rx->securities, 1UL), &key_type_rxrpc_s, kdesc, true); if (IS_ERR(kref)) { - read_unlock(&local->services_lock); - _leave(" = %ld [search]", PTR_ERR(kref)); - return PTR_ERR(kref); + trace_rxrpc_abort(0, "SVK", + sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + sec->no_key_abort, EKEYREJECTED); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = sec->no_key_abort; + return false; } - key = key_ref_to_ptr(kref); - read_unlock(&local->services_lock); - - conn->server_key = key; - conn->security = sec; - - _leave(" = 0"); - return 0; +out: + *_sec = sec; + *_key = key_ref_to_ptr(kref); + return true; } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 1e3eb3a97532..1ad300e6dbc0 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -219,8 +219,10 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, bool use_reinsert; bool want_ingress; bool is_redirect; + bool expects_nh; int m_eaction; int mac_len; + bool at_nh; rec_level = __this_cpu_inc_return(mirred_rec_level); if (unlikely(rec_level > MIRRED_RECURSION_LIMIT)) { @@ -261,19 +263,19 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } - /* If action's target direction differs than filter's direction, - * and devices expect a mac header on xmit, then mac push/pull is - * needed. - */ want_ingress = tcf_mirred_act_wants_ingress(m_eaction); - if (skb_at_tc_ingress(skb) != want_ingress && m_mac_header_xmit) { - if (!skb_at_tc_ingress(skb)) { - /* caught at egress, act ingress: pull mac */ - mac_len = skb_network_header(skb) - skb_mac_header(skb); + + expects_nh = want_ingress || !m_mac_header_xmit; + at_nh = skb->data == skb_network_header(skb); + if (at_nh != expects_nh) { + mac_len = skb_at_tc_ingress(skb) ? skb->mac_len : + skb_network_header(skb) - skb_mac_header(skb); + if (expects_nh) { + /* target device/action expect data at nh */ skb_pull_rcsum(skb2, mac_len); } else { - /* caught at ingress, act egress: push mac */ - skb_push_rcsum(skb2, skb->mac_len); + /* target device/action expect data at mac */ + skb_push_rcsum(skb2, mac_len); } } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 6a0eacafdb19..76e0d122616a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -308,33 +308,12 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, tcf_proto_destroy(tp, rtnl_held, true, extack); } -static int walker_check_empty(struct tcf_proto *tp, void *fh, - struct tcf_walker *arg) +static bool tcf_proto_check_delete(struct tcf_proto *tp) { - if (fh) { - arg->nonempty = true; - return -1; - } - return 0; -} - -static bool tcf_proto_is_empty(struct tcf_proto *tp, bool rtnl_held) -{ - struct tcf_walker walker = { .fn = walker_check_empty, }; - - if (tp->ops->walk) { - tp->ops->walk(tp, &walker, rtnl_held); - return !walker.nonempty; - } - return true; -} + if (tp->ops->delete_empty) + return tp->ops->delete_empty(tp); -static bool tcf_proto_check_delete(struct tcf_proto *tp, bool rtnl_held) -{ - spin_lock(&tp->lock); - if (tcf_proto_is_empty(tp, rtnl_held)) - tp->deleting = true; - spin_unlock(&tp->lock); + tp->deleting = true; return tp->deleting; } @@ -1751,7 +1730,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, * concurrently. * Mark tp for deletion if it is empty. */ - if (!tp_iter || !tcf_proto_check_delete(tp, rtnl_held)) { + if (!tp_iter || !tcf_proto_check_delete(tp)) { mutex_unlock(&chain->filter_chain_lock); return; } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 0d125de54285..b0f42e62dd76 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2773,6 +2773,17 @@ static void fl_bind_class(void *fh, u32 classid, unsigned long cl) f->res.class = cl; } +static bool fl_delete_empty(struct tcf_proto *tp) +{ + struct cls_fl_head *head = fl_head_dereference(tp); + + spin_lock(&tp->lock); + tp->deleting = idr_is_empty(&head->handle_idr); + spin_unlock(&tp->lock); + + return tp->deleting; +} + static struct tcf_proto_ops cls_fl_ops __read_mostly = { .kind = "flower", .classify = fl_classify, @@ -2782,6 +2793,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .put = fl_put, .change = fl_change, .delete = fl_delete, + .delete_empty = fl_delete_empty, .walk = fl_walk, .reoffload = fl_reoffload, .hw_add = fl_hw_add, diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 66c6bcec16cb..a0e6fac613de 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1108,33 +1108,10 @@ erridr: return err; } -static bool u32_hnode_empty(struct tc_u_hnode *ht, bool *non_root_ht) -{ - int i; - - if (!ht) - return true; - if (!ht->is_root) { - *non_root_ht = true; - return false; - } - if (*non_root_ht) - return false; - if (ht->refcnt < 2) - return true; - - for (i = 0; i <= ht->divisor; i++) { - if (rtnl_dereference(ht->ht[i])) - return false; - } - return true; -} - static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held) { struct tc_u_common *tp_c = tp->data; - bool non_root_ht = false; struct tc_u_hnode *ht; struct tc_u_knode *n; unsigned int h; @@ -1147,8 +1124,6 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, ht = rtnl_dereference(ht->next)) { if (ht->prio != tp->prio) continue; - if (u32_hnode_empty(ht, &non_root_ht)) - return; if (arg->count >= arg->skip) { if (arg->fn(tp, ht, arg) < 0) { arg->stop = 1; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index b1c7e726ce5d..ff4c5e9d0d77 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -301,6 +301,9 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); if (fq_flow_is_throttled(f)) fq_flow_unset_throttled(q, f); f->time_next_packet = 0ULL; @@ -322,8 +325,12 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) fq_flow_set_detached(f); f->sk = sk; - if (skb->sk == sk) + if (skb->sk == sk) { f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); + } f->credit = q->initial_quantum; rb_link_node(&f->fq_node, parent, p); @@ -428,17 +435,9 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, f->qlen++; qdisc_qstats_backlog_inc(sch, skb); if (fq_flow_is_detached(f)) { - struct sock *sk = skb->sk; - fq_flow_add_tail(&q->new_flows, f); if (time_after(jiffies, f->age + q->flow_refill_delay)) f->credit = max_t(u32, f->credit, q->quantum); - if (sk && q->rate_enable) { - if (unlikely(smp_load_acquire(&sk->sk_pacing_status) != - SK_PACING_FQ)) - smp_store_release(&sk->sk_pacing_status, - SK_PACING_FQ); - } q->inactive_flows--; } diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 6a30392068a0..c1a100d2fed3 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -84,10 +84,8 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, return 0; ret = genradix_prealloc(&stream->out, outcnt, gfp); - if (ret) { - genradix_free(&stream->out); + if (ret) return ret; - } stream->outcnt = outcnt; return 0; @@ -102,10 +100,8 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, return 0; ret = genradix_prealloc(&stream->in, incnt, gfp); - if (ret) { - genradix_free(&stream->in); + if (ret) return ret; - } stream->incnt = incnt; return 0; @@ -123,7 +119,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, * a new one with new outcnt to save memory if needed. */ if (outcnt == stream->outcnt) - goto in; + goto handle_in; /* Filter out chunks queued on streams that won't exist anymore */ sched->unsched_all(stream); @@ -132,24 +128,28 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, ret = sctp_stream_alloc_out(stream, outcnt, gfp); if (ret) - goto out; + goto out_err; for (i = 0; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; -in: +handle_in: sctp_stream_interleave_init(stream); if (!incnt) goto out; ret = sctp_stream_alloc_in(stream, incnt, gfp); - if (ret) { - sched->free(stream); - genradix_free(&stream->out); - stream->outcnt = 0; - goto out; - } + if (ret) + goto in_err; + + goto out; +in_err: + sched->free(stream); + genradix_free(&stream->in); +out_err: + genradix_free(&stream->out); + stream->outcnt = 0; out: return ret; } diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 7235a6032671..3bbe1a58ec87 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -263,7 +263,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) pf->af->from_sk(&addr, sk); pf->to_sk_daddr(&t->ipaddr, sk); - dst->ops->update_pmtu(dst, sk, NULL, pmtu); + dst->ops->update_pmtu(dst, sk, NULL, pmtu, true); pf->to_sk_daddr(&addr, sk); dst = sctp_transport_dst_check(t); diff --git a/samples/seccomp/user-trap.c b/samples/seccomp/user-trap.c index 6d0125ca8af7..20291ec6489f 100644 --- a/samples/seccomp/user-trap.c +++ b/samples/seccomp/user-trap.c @@ -298,14 +298,14 @@ int main(void) req = malloc(sizes.seccomp_notif); if (!req) goto out_close; - memset(req, 0, sizeof(*req)); resp = malloc(sizes.seccomp_notif_resp); if (!resp) goto out_req; - memset(resp, 0, sizeof(*resp)); + memset(resp, 0, sizes.seccomp_notif_resp); while (1) { + memset(req, 0, sizes.seccomp_notif); if (ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, req)) { perror("ioctl recv"); goto out_resp; diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig index d33de0b9f4f5..e3569543bdac 100644 --- a/scripts/gcc-plugins/Kconfig +++ b/scripts/gcc-plugins/Kconfig @@ -14,8 +14,8 @@ config HAVE_GCC_PLUGINS An arch should select this symbol if it supports building with GCC plugins. -config GCC_PLUGINS - bool +menuconfig GCC_PLUGINS + bool "GCC plugins" depends on HAVE_GCC_PLUGINS depends on PLUGIN_HOSTCC != "" default y @@ -25,8 +25,7 @@ config GCC_PLUGINS See Documentation/core-api/gcc-plugins.rst for details. -menu "GCC plugins" - depends on GCC_PLUGINS +if GCC_PLUGINS config GCC_PLUGIN_CYC_COMPLEXITY bool "Compute the cyclomatic complexity of a function" if EXPERT @@ -113,4 +112,4 @@ config GCC_PLUGIN_ARM_SSP_PER_TASK bool depends on GCC_PLUGINS && ARM -endmenu +endif diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index 7c230016b08d..357dc56bcf30 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -136,7 +136,7 @@ mkdir -p debian/source/ echo "1.0" > debian/source/format echo $debarch > debian/arch -extra_build_depends=", $(if_enabled_echo CONFIG_UNWINDER_ORC libelf-dev)" +extra_build_depends=", $(if_enabled_echo CONFIG_UNWINDER_ORC libelf-dev:native)" extra_build_depends="$extra_build_depends, $(if_enabled_echo CONFIG_SYSTEM_TRUSTED_KEYRING libssl-dev:native)" # Generate a simple changelog template diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 09996f2552ee..47aff8700547 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -623,7 +623,7 @@ static __poll_t ns_revision_poll(struct file *file, poll_table *pt) void __aa_bump_ns_revision(struct aa_ns *ns) { - ns->revision++; + WRITE_ONCE(ns->revision, ns->revision + 1); wake_up_interruptible(&ns->wait); } diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index 9be7ccb8379e..6ceb74e0f789 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -317,6 +317,7 @@ static int aa_xattrs_match(const struct linux_binprm *bprm, if (!bprm || !profile->xattr_count) return 0; + might_sleep(); /* transition from exec match to xattr set */ state = aa_dfa_null_transition(profile->xmatch, state); @@ -361,10 +362,11 @@ out: } /** - * __attach_match_ - find an attachment match + * find_attach - do attachment search for unconfined processes * @bprm - binprm structure of transitioning task - * @name - to match against (NOT NULL) + * @ns: the current namespace (NOT NULL) * @head - profile list to walk (NOT NULL) + * @name - to match against (NOT NULL) * @info - info message if there was an error (NOT NULL) * * Do a linear search on the profiles in the list. There is a matching @@ -374,12 +376,11 @@ out: * * Requires: @head not be shared or have appropriate locks held * - * Returns: profile or NULL if no match found + * Returns: label or NULL if no match found */ -static struct aa_profile *__attach_match(const struct linux_binprm *bprm, - const char *name, - struct list_head *head, - const char **info) +static struct aa_label *find_attach(const struct linux_binprm *bprm, + struct aa_ns *ns, struct list_head *head, + const char *name, const char **info) { int candidate_len = 0, candidate_xattrs = 0; bool conflict = false; @@ -388,6 +389,8 @@ static struct aa_profile *__attach_match(const struct linux_binprm *bprm, AA_BUG(!name); AA_BUG(!head); + rcu_read_lock(); +restart: list_for_each_entry_rcu(profile, head, base.list) { if (profile->label.flags & FLAG_NULL && &profile->label == ns_unconfined(profile->ns)) @@ -413,16 +416,32 @@ static struct aa_profile *__attach_match(const struct linux_binprm *bprm, perm = dfa_user_allow(profile->xmatch, state); /* any accepting state means a valid match. */ if (perm & MAY_EXEC) { - int ret; + int ret = 0; if (count < candidate_len) continue; - ret = aa_xattrs_match(bprm, profile, state); - /* Fail matching if the xattrs don't match */ - if (ret < 0) - continue; - + if (bprm && profile->xattr_count) { + long rev = READ_ONCE(ns->revision); + + if (!aa_get_profile_not0(profile)) + goto restart; + rcu_read_unlock(); + ret = aa_xattrs_match(bprm, profile, + state); + rcu_read_lock(); + aa_put_profile(profile); + if (rev != + READ_ONCE(ns->revision)) + /* policy changed */ + goto restart; + /* + * Fail matching if the xattrs don't + * match + */ + if (ret < 0) + continue; + } /* * TODO: allow for more flexible best match * @@ -445,43 +464,28 @@ static struct aa_profile *__attach_match(const struct linux_binprm *bprm, candidate_xattrs = ret; conflict = false; } - } else if (!strcmp(profile->base.name, name)) + } else if (!strcmp(profile->base.name, name)) { /* * old exact non-re match, without conditionals such * as xattrs. no more searching required */ - return profile; + candidate = profile; + goto out; + } } - if (conflict) { - *info = "conflicting profile attachments"; + if (!candidate || conflict) { + if (conflict) + *info = "conflicting profile attachments"; + rcu_read_unlock(); return NULL; } - return candidate; -} - -/** - * find_attach - do attachment search for unconfined processes - * @bprm - binprm structure of transitioning task - * @ns: the current namespace (NOT NULL) - * @list: list to search (NOT NULL) - * @name: the executable name to match against (NOT NULL) - * @info: info message if there was an error - * - * Returns: label or NULL if no match found - */ -static struct aa_label *find_attach(const struct linux_binprm *bprm, - struct aa_ns *ns, struct list_head *list, - const char *name, const char **info) -{ - struct aa_profile *profile; - - rcu_read_lock(); - profile = aa_get_profile(__attach_match(bprm, name, list, info)); +out: + candidate = aa_get_newest_profile(candidate); rcu_read_unlock(); - return profile ? &profile->label : NULL; + return &candidate->label; } static const char *next_name(int xtype, const char *name) diff --git a/security/apparmor/file.c b/security/apparmor/file.c index fe2ebe5e865e..f1caf3674e1c 100644 --- a/security/apparmor/file.c +++ b/security/apparmor/file.c @@ -618,8 +618,7 @@ int aa_file_perm(const char *op, struct aa_label *label, struct file *file, fctx = file_ctx(file); rcu_read_lock(); - flabel = aa_get_newest_label(rcu_dereference(fctx->label)); - rcu_read_unlock(); + flabel = rcu_dereference(fctx->label); AA_BUG(!flabel); /* revalidate access, if task is unconfined, or the cached cred @@ -631,9 +630,13 @@ int aa_file_perm(const char *op, struct aa_label *label, struct file *file, */ denied = request & ~fctx->allow; if (unconfined(label) || unconfined(flabel) || - (!denied && aa_label_is_subset(flabel, label))) + (!denied && aa_label_is_subset(flabel, label))) { + rcu_read_unlock(); goto done; + } + flabel = aa_get_newest_label(flabel); + rcu_read_unlock(); /* TODO: label cross check */ if (file->f_path.mnt && path_mediated_fs(file->f_path.dentry)) @@ -643,8 +646,9 @@ int aa_file_perm(const char *op, struct aa_label *label, struct file *file, else if (S_ISSOCK(file_inode(file)->i_mode)) error = __file_sock_perm(op, label, flabel, file, request, denied); -done: aa_put_label(flabel); + +done: return error; } diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c index 4ed6688f9d40..e0828ee7a345 100644 --- a/security/apparmor/mount.c +++ b/security/apparmor/mount.c @@ -442,7 +442,7 @@ int aa_bind_mount(struct aa_label *label, const struct path *path, buffer = aa_get_buffer(false); old_buffer = aa_get_buffer(false); error = -ENOMEM; - if (!buffer || old_buffer) + if (!buffer || !old_buffer) goto out; error = fn_for_each_confined(label, profile, diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index 03104830c913..269f2f53c0b1 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -1125,8 +1125,8 @@ ssize_t aa_remove_profiles(struct aa_ns *policy_ns, struct aa_label *subj, if (!name) { /* remove namespace - can only happen if fqname[0] == ':' */ mutex_lock_nested(&ns->parent->lock, ns->level); - __aa_remove_ns(ns); __aa_bump_ns_revision(ns); + __aa_remove_ns(ns); mutex_unlock(&ns->parent->lock); } else { /* remove profile */ @@ -1138,9 +1138,9 @@ ssize_t aa_remove_profiles(struct aa_ns *policy_ns, struct aa_label *subj, goto fail_ns_lock; } name = profile->base.hname; + __aa_bump_ns_revision(ns); __remove_profile(profile); __aa_labelset_update_subtree(ns); - __aa_bump_ns_revision(ns); mutex_unlock(&ns->lock); } diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index dd3d5942e669..c36bafbcd77e 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -951,7 +951,8 @@ static bool tomoyo_manager(void) exe = tomoyo_get_exe(); if (!exe) return false; - list_for_each_entry_rcu(ptr, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], head.list) { + list_for_each_entry_rcu(ptr, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (!ptr->head.is_deleted && (!tomoyo_pathcmp(domainname, ptr->manager) || !strcmp(exe, ptr->manager->name))) { @@ -1095,7 +1096,8 @@ static int tomoyo_delete_domain(char *domainname) if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -EINTR; /* Is there an active domain? */ - list_for_each_entry_rcu(domain, &tomoyo_domain_list, list) { + list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, + srcu_read_lock_held(&tomoyo_ss)) { /* Never delete tomoyo_kernel_domain */ if (domain == &tomoyo_kernel_domain) continue; @@ -2778,7 +2780,8 @@ void tomoyo_check_profile(void) tomoyo_policy_loaded = true; pr_info("TOMOYO: 2.6.0\n"); - list_for_each_entry_rcu(domain, &tomoyo_domain_list, list) { + list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, + srcu_read_lock_held(&tomoyo_ss)) { const u8 profile = domain->profile; struct tomoyo_policy_namespace *ns = domain->ns; diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c index 8526a0a74023..7869d6a9980b 100644 --- a/security/tomoyo/domain.c +++ b/security/tomoyo/domain.c @@ -41,7 +41,8 @@ int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -ENOMEM; - list_for_each_entry_rcu(entry, list, list) { + list_for_each_entry_rcu(entry, list, list, + srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!check_duplicate(entry, new_entry)) @@ -119,7 +120,8 @@ int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, } if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; - list_for_each_entry_rcu(entry, list, list) { + list_for_each_entry_rcu(entry, list, list, + srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!tomoyo_same_acl_head(entry, new_entry) || @@ -166,7 +168,8 @@ void tomoyo_check_acl(struct tomoyo_request_info *r, u16 i = 0; retry: - list_for_each_entry_rcu(ptr, list, list) { + list_for_each_entry_rcu(ptr, list, list, + srcu_read_lock_held(&tomoyo_ss)) { if (ptr->is_deleted || ptr->type != r->param_type) continue; if (!check_entry(r, ptr)) @@ -298,7 +301,8 @@ static inline bool tomoyo_scan_transition { const struct tomoyo_transition_control *ptr; - list_for_each_entry_rcu(ptr, list, head.list) { + list_for_each_entry_rcu(ptr, list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || ptr->type != type) continue; if (ptr->domainname) { @@ -735,7 +739,8 @@ retry: /* Check 'aggregator' directive. */ candidate = &exename; - list_for_each_entry_rcu(ptr, list, head.list) { + list_for_each_entry_rcu(ptr, list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || !tomoyo_path_matches_pattern(&exename, ptr->original_name)) diff --git a/security/tomoyo/group.c b/security/tomoyo/group.c index a37c7dc66e44..1cecdd797597 100644 --- a/security/tomoyo/group.c +++ b/security/tomoyo/group.c @@ -133,7 +133,8 @@ tomoyo_path_matches_group(const struct tomoyo_path_info *pathname, { struct tomoyo_path_group *member; - list_for_each_entry_rcu(member, &group->member_list, head.list) { + list_for_each_entry_rcu(member, &group->member_list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (member->head.is_deleted) continue; if (!tomoyo_path_matches_pattern(pathname, member->member_name)) @@ -161,7 +162,8 @@ bool tomoyo_number_matches_group(const unsigned long min, struct tomoyo_number_group *member; bool matched = false; - list_for_each_entry_rcu(member, &group->member_list, head.list) { + list_for_each_entry_rcu(member, &group->member_list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (member->head.is_deleted) continue; if (min > member->number.values[1] || @@ -191,7 +193,8 @@ bool tomoyo_address_matches_group(const bool is_ipv6, const __be32 *address, bool matched = false; const u8 size = is_ipv6 ? 16 : 4; - list_for_each_entry_rcu(member, &group->member_list, head.list) { + list_for_each_entry_rcu(member, &group->member_list, head.list, + srcu_read_lock_held(&tomoyo_ss)) { if (member->head.is_deleted) continue; if (member->address.is_ipv6 != is_ipv6) diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c index e7832448d721..bf38fc1b59b2 100644 --- a/security/tomoyo/realpath.c +++ b/security/tomoyo/realpath.c @@ -218,31 +218,6 @@ out: } /** - * tomoyo_get_socket_name - Get the name of a socket. - * - * @path: Pointer to "struct path". - * @buffer: Pointer to buffer to return value in. - * @buflen: Sizeof @buffer. - * - * Returns the buffer. - */ -static char *tomoyo_get_socket_name(const struct path *path, char * const buffer, - const int buflen) -{ - struct inode *inode = d_backing_inode(path->dentry); - struct socket *sock = inode ? SOCKET_I(inode) : NULL; - struct sock *sk = sock ? sock->sk : NULL; - - if (sk) { - snprintf(buffer, buflen, "socket:[family=%u:type=%u:protocol=%u]", - sk->sk_family, sk->sk_type, sk->sk_protocol); - } else { - snprintf(buffer, buflen, "socket:[unknown]"); - } - return buffer; -} - -/** * tomoyo_realpath_from_path - Returns realpath(3) of the given pathname but ignores chroot'ed root. * * @path: Pointer to "struct path". @@ -279,12 +254,7 @@ char *tomoyo_realpath_from_path(const struct path *path) break; /* To make sure that pos is '\0' terminated. */ buf[buf_len - 1] = '\0'; - /* Get better name for socket. */ - if (sb->s_magic == SOCKFS_MAGIC) { - pos = tomoyo_get_socket_name(path, buf, buf_len - 1); - goto encode; - } - /* For "pipe:[\$]". */ + /* For "pipe:[\$]" and "socket:[\$]". */ if (dentry->d_op && dentry->d_op->d_dname) { pos = dentry->d_op->d_dname(dentry, buf, buf_len - 1); goto encode; diff --git a/security/tomoyo/util.c b/security/tomoyo/util.c index 52752e1a84ed..eba0b3395851 100644 --- a/security/tomoyo/util.c +++ b/security/tomoyo/util.c @@ -594,7 +594,8 @@ struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname) name.name = domainname; tomoyo_fill_path_info(&name); - list_for_each_entry_rcu(domain, &tomoyo_domain_list, list) { + list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, + srcu_read_lock_held(&tomoyo_ss)) { if (!domain->is_deleted && !tomoyo_pathcmp(&name, domain->domainname)) return domain; @@ -1028,7 +1029,8 @@ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r) return false; if (!domain) return true; - list_for_each_entry_rcu(ptr, &domain->acl_info_list, list) { + list_for_each_entry_rcu(ptr, &domain->acl_info_list, list, + srcu_read_lock_held(&tomoyo_ss)) { u16 perm; u8 i; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index b856b89378ac..5b92f290cbb0 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -282,12 +282,13 @@ enum { /* quirks for old Intel chipsets */ #define AZX_DCAPS_INTEL_ICH \ - (AZX_DCAPS_OLD_SSYNC | AZX_DCAPS_NO_ALIGN_BUFSIZE) + (AZX_DCAPS_OLD_SSYNC | AZX_DCAPS_NO_ALIGN_BUFSIZE |\ + AZX_DCAPS_SYNC_WRITE) /* quirks for Intel PCH */ #define AZX_DCAPS_INTEL_PCH_BASE \ (AZX_DCAPS_NO_ALIGN_BUFSIZE | AZX_DCAPS_COUNT_LPIB_DELAY |\ - AZX_DCAPS_SNOOP_TYPE(SCH)) + AZX_DCAPS_SNOOP_TYPE(SCH) | AZX_DCAPS_SYNC_WRITE) /* PCH up to IVB; no runtime PM; bind with i915 gfx */ #define AZX_DCAPS_INTEL_PCH_NOPM \ @@ -302,13 +303,13 @@ enum { #define AZX_DCAPS_INTEL_HASWELL \ (/*AZX_DCAPS_ALIGN_BUFSIZE |*/ AZX_DCAPS_COUNT_LPIB_DELAY |\ AZX_DCAPS_PM_RUNTIME | AZX_DCAPS_I915_COMPONENT |\ - AZX_DCAPS_SNOOP_TYPE(SCH)) + AZX_DCAPS_SNOOP_TYPE(SCH) | AZX_DCAPS_SYNC_WRITE) /* Broadwell HDMI can't use position buffer reliably, force to use LPIB */ #define AZX_DCAPS_INTEL_BROADWELL \ (/*AZX_DCAPS_ALIGN_BUFSIZE |*/ AZX_DCAPS_POSFIX_LPIB |\ AZX_DCAPS_PM_RUNTIME | AZX_DCAPS_I915_COMPONENT |\ - AZX_DCAPS_SNOOP_TYPE(SCH)) + AZX_DCAPS_SNOOP_TYPE(SCH) | AZX_DCAPS_SYNC_WRITE) #define AZX_DCAPS_INTEL_BAYTRAIL \ (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_I915_COMPONENT) @@ -1410,7 +1411,17 @@ static bool atpx_present(void) acpi_handle dhandle, atpx_handle; acpi_status status; - while ((pdev = pci_get_class(PCI_BASE_CLASS_DISPLAY << 16, pdev)) != NULL) { + while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) { + dhandle = ACPI_HANDLE(&pdev->dev); + if (dhandle) { + status = acpi_get_handle(dhandle, "ATPX", &atpx_handle); + if (!ACPI_FAILURE(status)) { + pci_dev_put(pdev); + return true; + } + } + } + while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) { dhandle = ACPI_HANDLE(&pdev->dev); if (dhandle) { status = acpi_get_handle(dhandle, "ATPX", &atpx_handle); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index dbfafee97931..1cd4906a67e1 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -501,6 +501,7 @@ static void alc_shutup_pins(struct hda_codec *codec) struct alc_spec *spec = codec->spec; switch (codec->core.vendor_id) { + case 0x10ec0283: case 0x10ec0286: case 0x10ec0288: case 0x10ec0298: @@ -5904,9 +5905,12 @@ enum { ALC256_FIXUP_ASUS_HEADSET_MIC, ALC256_FIXUP_ASUS_MIC_NO_PRESENCE, ALC299_FIXUP_PREDATOR_SPK, - ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC, ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, - ALC294_FIXUP_ASUS_INTSPK_GPIO, + ALC289_FIXUP_DELL_SPK2, + ALC289_FIXUP_DUAL_SPK, + ALC294_FIXUP_SPK2_TO_DAC1, + ALC294_FIXUP_ASUS_DUAL_SPK, + }; static const struct hda_fixup alc269_fixups[] = { @@ -6981,33 +6985,45 @@ static const struct hda_fixup alc269_fixups[] = { { } } }, - [ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC] = { + [ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { - { 0x14, 0x411111f0 }, /* disable confusing internal speaker */ - { 0x19, 0x04a11150 }, /* use as headset mic, without its own jack detect */ + { 0x19, 0x04a11040 }, + { 0x21, 0x04211020 }, { } }, .chained = true, - .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + .chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE }, - [ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE] = { + [ALC289_FIXUP_DELL_SPK2] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { - { 0x19, 0x04a11040 }, - { 0x21, 0x04211020 }, + { 0x17, 0x90170130 }, /* bass spk */ { } }, .chained = true, - .chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE + .chain_id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE }, - [ALC294_FIXUP_ASUS_INTSPK_GPIO] = { + [ALC289_FIXUP_DUAL_SPK] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC289_FIXUP_DELL_SPK2 + }, + [ALC294_FIXUP_SPK2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC + }, + [ALC294_FIXUP_ASUS_DUAL_SPK] = { .type = HDA_FIXUP_FUNC, /* The GPIO must be pulled to initialize the AMP */ .v.func = alc_fixup_gpio4, .chained = true, - .chain_id = ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC + .chain_id = ALC294_FIXUP_SPK2_TO_DAC1 }, + }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7080,6 +7096,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x08ae, "Dell WYSE NB", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), + SND_PCI_QUIRK(0x1028, 0x097e, "Dell Precision", ALC289_FIXUP_DUAL_SPK), + SND_PCI_QUIRK(0x1028, 0x097d, "Dell Precision", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -7167,7 +7185,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), - SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_INTSPK_GPIO), + SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC), diff --git a/sound/pci/ice1712/ice1724.c b/sound/pci/ice1712/ice1724.c index c80a16ee6e76..242542e23d28 100644 --- a/sound/pci/ice1712/ice1724.c +++ b/sound/pci/ice1712/ice1724.c @@ -647,6 +647,7 @@ static int snd_vt1724_set_pro_rate(struct snd_ice1712 *ice, unsigned int rate, unsigned long flags; unsigned char mclk_change; unsigned int i, old_rate; + bool call_set_rate = false; if (rate > ice->hw_rates->list[ice->hw_rates->count - 1]) return -EINVAL; @@ -670,7 +671,7 @@ static int snd_vt1724_set_pro_rate(struct snd_ice1712 *ice, unsigned int rate, * setting clock rate for internal clock mode */ old_rate = ice->get_rate(ice); if (force || (old_rate != rate)) - ice->set_rate(ice, rate); + call_set_rate = true; else if (rate == ice->cur_rate) { spin_unlock_irqrestore(&ice->reg_lock, flags); return 0; @@ -678,12 +679,14 @@ static int snd_vt1724_set_pro_rate(struct snd_ice1712 *ice, unsigned int rate, } ice->cur_rate = rate; + spin_unlock_irqrestore(&ice->reg_lock, flags); + + if (call_set_rate) + ice->set_rate(ice, rate); /* setting master clock */ mclk_change = ice->set_mclk(ice, rate); - spin_unlock_irqrestore(&ice->reg_lock, flags); - if (mclk_change && ice->gpio.i2s_mclk_changed) ice->gpio.i2s_mclk_changed(ice); if (ice->gpio.set_pro_rate) diff --git a/sound/usb/card.h b/sound/usb/card.h index 2991b9986f66..395403a2d33f 100644 --- a/sound/usb/card.h +++ b/sound/usb/card.h @@ -145,6 +145,7 @@ struct snd_usb_substream { struct snd_usb_endpoint *sync_endpoint; unsigned long flags; bool need_setup_ep; /* (re)configure EP at prepare? */ + bool need_setup_fmt; /* (re)configure fmt after resume? */ unsigned int speed; /* USB_SPEED_XXX */ u64 formats; /* format bitmasks (all or'ed) */ diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 9c8930bb00c8..a11c8150af58 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -506,15 +506,15 @@ static int set_format(struct snd_usb_substream *subs, struct audioformat *fmt) if (WARN_ON(!iface)) return -EINVAL; alts = usb_altnum_to_altsetting(iface, fmt->altsetting); - altsd = get_iface_desc(alts); - if (WARN_ON(altsd->bAlternateSetting != fmt->altsetting)) + if (WARN_ON(!alts)) return -EINVAL; + altsd = get_iface_desc(alts); - if (fmt == subs->cur_audiofmt) + if (fmt == subs->cur_audiofmt && !subs->need_setup_fmt) return 0; /* close the old interface */ - if (subs->interface >= 0 && subs->interface != fmt->iface) { + if (subs->interface >= 0 && (subs->interface != fmt->iface || subs->need_setup_fmt)) { if (!subs->stream->chip->keep_iface) { err = usb_set_interface(subs->dev, subs->interface, 0); if (err < 0) { @@ -528,6 +528,9 @@ static int set_format(struct snd_usb_substream *subs, struct audioformat *fmt) subs->altset_idx = 0; } + if (subs->need_setup_fmt) + subs->need_setup_fmt = false; + /* set interface */ if (iface->cur_altsetting != alts) { err = snd_usb_select_mode_quirk(subs, fmt); @@ -1728,6 +1731,13 @@ static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substrea subs->data_endpoint->retire_data_urb = retire_playback_urb; subs->running = 0; return 0; + case SNDRV_PCM_TRIGGER_SUSPEND: + if (subs->stream->chip->setup_fmt_after_resume_quirk) { + stop_endpoints(subs, true); + subs->need_setup_fmt = true; + return 0; + } + break; } return -EINVAL; @@ -1760,6 +1770,13 @@ static int snd_usb_substream_capture_trigger(struct snd_pcm_substream *substream subs->data_endpoint->retire_data_urb = retire_capture_urb; subs->running = 1; return 0; + case SNDRV_PCM_TRIGGER_SUSPEND: + if (subs->stream->chip->setup_fmt_after_resume_quirk) { + stop_endpoints(subs, true); + subs->need_setup_fmt = true; + return 0; + } + break; } return -EINVAL; diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 70c338f3ae24..d187aa6d50db 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3466,7 +3466,8 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), .vendor_name = "Dell", .product_name = "WD19 Dock", .profile_name = "Dell-WD15-Dock", - .ifnum = QUIRK_NO_INTERFACE + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_SETUP_FMT_AFTER_RESUME } }, /* MOTU Microbook II */ diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 349e1e52996d..a81c2066499f 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -508,6 +508,16 @@ static int create_standard_mixer_quirk(struct snd_usb_audio *chip, return snd_usb_create_mixer(chip, quirk->ifnum, 0); } + +static int setup_fmt_after_resume_quirk(struct snd_usb_audio *chip, + struct usb_interface *iface, + struct usb_driver *driver, + const struct snd_usb_audio_quirk *quirk) +{ + chip->setup_fmt_after_resume_quirk = 1; + return 1; /* Continue with creating streams and mixer */ +} + /* * audio-interface quirks * @@ -546,6 +556,7 @@ int snd_usb_create_quirk(struct snd_usb_audio *chip, [QUIRK_AUDIO_EDIROL_UAXX] = create_uaxx_quirk, [QUIRK_AUDIO_ALIGN_TRANSFER] = create_align_transfer_quirk, [QUIRK_AUDIO_STANDARD_MIXER] = create_standard_mixer_quirk, + [QUIRK_SETUP_FMT_AFTER_RESUME] = setup_fmt_after_resume_quirk, }; if (quirk->type < QUIRK_TYPE_COUNT) { diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h index ff3cbf653de8..6fe3ab582ec6 100644 --- a/sound/usb/usbaudio.h +++ b/sound/usb/usbaudio.h @@ -33,7 +33,7 @@ struct snd_usb_audio { wait_queue_head_t shutdown_wait; unsigned int txfr_quirk:1; /* Subframe boundaries on transfers */ unsigned int tx_length_quirk:1; /* Put length specifier in transfers */ - + unsigned int setup_fmt_after_resume_quirk:1; /* setup the format to interface after resume */ int num_interfaces; int num_suspended_intf; int sample_rate_read_error; @@ -98,6 +98,7 @@ enum quirk_type { QUIRK_AUDIO_EDIROL_UAXX, QUIRK_AUDIO_ALIGN_TRANSFER, QUIRK_AUDIO_STANDARD_MIXER, + QUIRK_SETUP_FMT_AFTER_RESUME, QUIRK_TYPE_COUNT }; diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index 3eb8411ab60e..e95b72ec19bc 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -33,7 +33,7 @@ #define EXIT_REASON_TRIPLE_FAULT 2 #define EXIT_REASON_INIT_SIGNAL 3 -#define EXIT_REASON_PENDING_INTERRUPT 7 +#define EXIT_REASON_INTERRUPT_WINDOW 7 #define EXIT_REASON_NMI_WINDOW 8 #define EXIT_REASON_TASK_SWITCH 9 #define EXIT_REASON_CPUID 10 @@ -94,7 +94,7 @@ { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ { EXIT_REASON_INIT_SIGNAL, "INIT_SIGNAL" }, \ - { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \ + { EXIT_REASON_INTERRUPT_WINDOW, "INTERRUPT_WINDOW" }, \ { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ { EXIT_REASON_CPUID, "CPUID" }, \ diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index ad1b9e646c49..4cf93110c259 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -270,6 +270,7 @@ class ArchX86(Arch): def __init__(self, exit_reasons): self.sc_perf_evt_open = 298 self.ioctl_numbers = IOCTL_NUMBERS + self.exit_reason_field = 'exit_reason' self.exit_reasons = exit_reasons def debugfs_is_child(self, field): @@ -289,6 +290,7 @@ class ArchPPC(Arch): # numbers depend on the wordsize. char_ptr_size = ctypes.sizeof(ctypes.c_char_p) self.ioctl_numbers['SET_FILTER'] = 0x80002406 | char_ptr_size << 16 + self.exit_reason_field = 'exit_nr' self.exit_reasons = {} def debugfs_is_child(self, field): @@ -300,6 +302,7 @@ class ArchA64(Arch): def __init__(self): self.sc_perf_evt_open = 241 self.ioctl_numbers = IOCTL_NUMBERS + self.exit_reason_field = 'esr_ec' self.exit_reasons = AARCH64_EXIT_REASONS def debugfs_is_child(self, field): @@ -311,6 +314,7 @@ class ArchS390(Arch): def __init__(self): self.sc_perf_evt_open = 331 self.ioctl_numbers = IOCTL_NUMBERS + self.exit_reason_field = None self.exit_reasons = None def debugfs_is_child(self, field): @@ -541,8 +545,8 @@ class TracepointProvider(Provider): """ filters = {} filters['kvm_userspace_exit'] = ('reason', USERSPACE_EXIT_REASONS) - if ARCH.exit_reasons: - filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons) + if ARCH.exit_reason_field and ARCH.exit_reasons: + filters['kvm_exit'] = (ARCH.exit_reason_field, ARCH.exit_reasons) return filters def _get_available_fields(self): diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index defae23a0169..97830e46d1a0 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -138,6 +138,7 @@ STATIC_OBJDIR := $(OUTPUT)staticobjs/ BPF_IN_SHARED := $(SHARED_OBJDIR)libbpf-in.o BPF_IN_STATIC := $(STATIC_OBJDIR)libbpf-in.o VERSION_SCRIPT := libbpf.map +BPF_HELPER_DEFS := $(OUTPUT)bpf_helper_defs.h LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) @@ -159,7 +160,7 @@ all: fixdep all_cmd: $(CMD_TARGETS) check -$(BPF_IN_SHARED): force elfdep bpfdep bpf_helper_defs.h +$(BPF_IN_SHARED): force elfdep bpfdep $(BPF_HELPER_DEFS) @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true @@ -177,12 +178,12 @@ $(BPF_IN_SHARED): force elfdep bpfdep bpf_helper_defs.h echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" -$(BPF_IN_STATIC): force elfdep bpfdep bpf_helper_defs.h +$(BPF_IN_STATIC): force elfdep bpfdep $(BPF_HELPER_DEFS) $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) -bpf_helper_defs.h: $(srctree)/tools/include/uapi/linux/bpf.h +$(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h $(Q)$(srctree)/scripts/bpf_helpers_doc.py --header \ - --file $(srctree)/tools/include/uapi/linux/bpf.h > bpf_helper_defs.h + --file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS) $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) @@ -243,7 +244,7 @@ install_lib: all_cmd $(call do_install_mkdir,$(libdir_SQ)); \ cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ) -install_headers: bpf_helper_defs.h +install_headers: $(BPF_HELPER_DEFS) $(call QUIET_INSTALL, headers) \ $(call do_install,bpf.h,$(prefix)/include/bpf,644); \ $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \ @@ -251,7 +252,7 @@ install_headers: bpf_helper_defs.h $(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \ $(call do_install,xsk.h,$(prefix)/include/bpf,644); \ $(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \ - $(call do_install,bpf_helper_defs.h,$(prefix)/include/bpf,644); \ + $(call do_install,$(BPF_HELPER_DEFS),$(prefix)/include/bpf,644); \ $(call do_install,bpf_tracing.h,$(prefix)/include/bpf,644); \ $(call do_install,bpf_endian.h,$(prefix)/include/bpf,644); \ $(call do_install,bpf_core_read.h,$(prefix)/include/bpf,644); @@ -271,7 +272,7 @@ config-clean: clean: $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ *.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \ - *.pc LIBBPF-CFLAGS bpf_helper_defs.h \ + *.pc LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \ $(SHARED_OBJDIR) $(STATIC_OBJDIR) $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 419652458da4..1ff0a9f49c01 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -40,3 +40,4 @@ xdping test_cpp /no_alu32 /bpf_gcc +bpf_helper_defs.h diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index e0fe01d9ec33..e2fd6f8d579c 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -120,9 +120,9 @@ force: $(BPFOBJ): force $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ -BPF_HELPERS := $(BPFDIR)/bpf_helper_defs.h $(wildcard $(BPFDIR)/bpf_*.h) -$(BPFDIR)/bpf_helper_defs.h: - $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ bpf_helper_defs.h +BPF_HELPERS := $(OUTPUT)/bpf_helper_defs.h $(wildcard $(BPFDIR)/bpf_*.h) +$(OUTPUT)/bpf_helper_defs.h: + $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ $(OUTPUT)/bpf_helper_defs.h # Get Clang's default includes on this system, as opposed to those seen by # '-target bpf'. This fixes "missing" files on some architectures/distros, diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index f52e0ba84fed..3d27069b9ed9 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -18,8 +18,8 @@ /* * Definitions of Primary Processor-Based VM-Execution Controls. */ -#define CPU_BASED_VIRTUAL_INTR_PENDING 0x00000004 -#define CPU_BASED_USE_TSC_OFFSETING 0x00000008 +#define CPU_BASED_INTR_WINDOW_EXITING 0x00000004 +#define CPU_BASED_USE_TSC_OFFSETTING 0x00000008 #define CPU_BASED_HLT_EXITING 0x00000080 #define CPU_BASED_INVLPG_EXITING 0x00000200 #define CPU_BASED_MWAIT_EXITING 0x00000400 @@ -30,7 +30,7 @@ #define CPU_BASED_CR8_LOAD_EXITING 0x00080000 #define CPU_BASED_CR8_STORE_EXITING 0x00100000 #define CPU_BASED_TPR_SHADOW 0x00200000 -#define CPU_BASED_VIRTUAL_NMI_PENDING 0x00400000 +#define CPU_BASED_NMI_WINDOW_EXITING 0x00400000 #define CPU_BASED_MOV_DR_EXITING 0x00800000 #define CPU_BASED_UNCOND_IO_EXITING 0x01000000 #define CPU_BASED_USE_IO_BITMAPS 0x02000000 @@ -103,7 +103,7 @@ #define EXIT_REASON_EXCEPTION_NMI 0 #define EXIT_REASON_EXTERNAL_INTERRUPT 1 #define EXIT_REASON_TRIPLE_FAULT 2 -#define EXIT_REASON_PENDING_INTERRUPT 7 +#define EXIT_REASON_INTERRUPT_WINDOW 7 #define EXIT_REASON_NMI_WINDOW 8 #define EXIT_REASON_TASK_SWITCH 9 #define EXIT_REASON_CPUID 10 diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index 5590fd2bcf87..69e482a95c47 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -98,7 +98,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) prepare_vmcs(vmx_pages, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); control = vmreadz(CPU_BASED_VM_EXEC_CONTROL); - control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETING; + control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETTING; vmwrite(CPU_BASED_VM_EXEC_CONTROL, control); vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE); diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index 16571ac1dab4..d3e0809ab368 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -226,17 +226,19 @@ check_transfer() return 0 } -test_tcp_forwarding() +test_tcp_forwarding_ip() { local nsa=$1 local nsb=$2 + local dstip=$3 + local dstport=$4 local lret=0 ip netns exec $nsb nc -w 5 -l -p 12345 < "$ns2in" > "$ns2out" & lpid=$! sleep 1 - ip netns exec $nsa nc -w 4 10.0.2.99 12345 < "$ns1in" > "$ns1out" & + ip netns exec $nsa nc -w 4 "$dstip" "$dstport" < "$ns1in" > "$ns1out" & cpid=$! sleep 3 @@ -258,6 +260,28 @@ test_tcp_forwarding() return $lret } +test_tcp_forwarding() +{ + test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 + + return $? +} + +test_tcp_forwarding_nat() +{ + local lret + + test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 + lret=$? + + if [ $lret -eq 0 ] ; then + test_tcp_forwarding_ip "$1" "$2" 10.6.6.6 1666 + lret=$? + fi + + return $lret +} + make_file "$ns1in" "ns1" make_file "$ns2in" "ns2" @@ -283,14 +307,19 @@ ip -net ns2 route add 192.168.10.1 via 10.0.2.1 # Same, but with NAT enabled. ip netns exec nsr1 nft -f - <<EOF table ip nat { + chain prerouting { + type nat hook prerouting priority 0; policy accept; + meta iif "veth0" ip daddr 10.6.6.6 tcp dport 1666 counter dnat ip to 10.0.2.99:12345 + } + chain postrouting { type nat hook postrouting priority 0; policy accept; - meta oifname "veth1" masquerade + meta oifname "veth1" counter masquerade } } EOF -test_tcp_forwarding ns1 ns2 +test_tcp_forwarding_nat ns1 ns2 if [ $? -eq 0 ] ;then echo "PASS: flow offloaded for ns1/ns2 with NAT" @@ -313,7 +342,7 @@ fi ip netns exec ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null ip netns exec ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null -test_tcp_forwarding ns1 ns2 +test_tcp_forwarding_nat ns1 ns2 if [ $? -eq 0 ] ;then echo "PASS: flow offloaded for ns1/ns2 with NAT and pmtu discovery" else diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 6944b898bb53..ee1b727ede04 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -3158,7 +3158,18 @@ TEST(user_notification_basic) EXPECT_GT(poll(&pollfd, 1, -1), 0); EXPECT_EQ(pollfd.revents, POLLIN); - EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + /* Test that we can't pass garbage to the kernel. */ + memset(&req, 0, sizeof(req)); + req.pid = -1; + errno = 0; + ret = ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno); + + if (ret) { + req.pid = 0; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + } pollfd.fd = listener; pollfd.events = POLLIN | POLLOUT; @@ -3278,6 +3289,7 @@ TEST(user_notification_signal) close(sk_pair[1]); + memset(&req, 0, sizeof(req)); EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); EXPECT_EQ(kill(pid, SIGUSR1), 0); @@ -3296,6 +3308,7 @@ TEST(user_notification_signal) EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1); EXPECT_EQ(errno, ENOENT); + memset(&req, 0, sizeof(req)); EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); resp.id = req.id; diff --git a/usr/gen_initramfs_list.sh b/usr/gen_initramfs_list.sh index 0aad760fcd8c..2bbac73e6477 100755 --- a/usr/gen_initramfs_list.sh +++ b/usr/gen_initramfs_list.sh @@ -128,7 +128,7 @@ parse() { str="${ftype} ${name} ${location} ${str}" ;; "nod") - local dev=`LC_ALL=C ls -l "${location}"` + local dev="`LC_ALL=C ls -l "${location}"`" local maj=`field 5 ${dev}` local min=`field 6 ${dev}` maj=${maj%,} diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index c6c2a9dde00c..0d9438e9de2a 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -1023,7 +1023,7 @@ static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) bool kvm_arch_timer_get_input_level(int vintid) { - struct kvm_vcpu *vcpu = kvm_arm_get_running_vcpu(); + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); struct arch_timer_context *timer; if (vintid == vcpu_vtimer(vcpu)->irq.irq) diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index efda376ab3c5..d65a0faa46d8 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -49,9 +49,6 @@ __asm__(".arch_extension virt"); DEFINE_PER_CPU(kvm_host_data_t, kvm_host_data); static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); -/* Per-CPU variable containing the currently running vcpu. */ -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; @@ -60,31 +57,8 @@ static DEFINE_SPINLOCK(kvm_vmid_lock); static bool vgic_present; static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled); - -static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu) -{ - __this_cpu_write(kvm_arm_running_vcpu, vcpu); -} - DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use); -/** - * kvm_arm_get_running_vcpu - get the vcpu running on the current CPU. - * Must be called from non-preemptible context - */ -struct kvm_vcpu *kvm_arm_get_running_vcpu(void) -{ - return __this_cpu_read(kvm_arm_running_vcpu); -} - -/** - * kvm_arm_get_running_vcpus - get the per-CPU array of currently running vcpus. - */ -struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void) -{ - return &kvm_arm_running_vcpu; -} - int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; @@ -192,7 +166,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) for (i = 0; i < KVM_MAX_VCPUS; ++i) { if (kvm->vcpus[i]) { - kvm_arch_vcpu_free(kvm->vcpus[i]); + kvm_vcpu_destroy(kvm->vcpus[i]); kvm->vcpus[i] = NULL; } } @@ -277,49 +251,46 @@ void kvm_arch_free_vm(struct kvm *kvm) vfree(kvm); } -struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) +{ + if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) + return -EBUSY; + + if (id >= kvm->arch.max_vcpus) + return -EINVAL; + + return 0; +} + +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { int err; - struct kvm_vcpu *vcpu; - if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) { - err = -EBUSY; - goto out; - } + /* Force users to call KVM_ARM_VCPU_INIT */ + vcpu->arch.target = -1; + bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES); - if (id >= kvm->arch.max_vcpus) { - err = -EINVAL; - goto out; - } + /* Set up the timer */ + kvm_timer_vcpu_init(vcpu); - vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); - if (!vcpu) { - err = -ENOMEM; - goto out; - } + kvm_pmu_vcpu_init(vcpu); - err = kvm_vcpu_init(vcpu, kvm, id); - if (err) - goto free_vcpu; + kvm_arm_reset_debug_ptr(vcpu); + + kvm_arm_pvtime_vcpu_init(&vcpu->arch); - err = create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP); + err = kvm_vgic_vcpu_init(vcpu); if (err) - goto vcpu_uninit; + return err; - return vcpu; -vcpu_uninit: - kvm_vcpu_uninit(vcpu); -free_vcpu: - kmem_cache_free(kvm_vcpu_cache, vcpu); -out: - return ERR_PTR(err); + return create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP); } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { } -void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) +void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { if (vcpu->arch.has_run_once && unlikely(!irqchip_in_kernel(vcpu->kvm))) static_branch_dec(&userspace_irqchip_in_use); @@ -327,13 +298,8 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) kvm_mmu_free_memory_caches(vcpu); kvm_timer_vcpu_terminate(vcpu); kvm_pmu_vcpu_destroy(vcpu); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(kvm_vcpu_cache, vcpu); -} -void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) -{ - kvm_arch_vcpu_free(vcpu); + kvm_arm_vcpu_destroy(vcpu); } int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) @@ -366,24 +332,6 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) preempt_enable(); } -int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) -{ - /* Force users to call KVM_ARM_VCPU_INIT */ - vcpu->arch.target = -1; - bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES); - - /* Set up the timer */ - kvm_timer_vcpu_init(vcpu); - - kvm_pmu_vcpu_init(vcpu); - - kvm_arm_reset_debug_ptr(vcpu); - - kvm_arm_pvtime_vcpu_init(&vcpu->arch); - - return kvm_vgic_vcpu_init(vcpu); -} - void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { int *last_ran; @@ -404,7 +352,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu->cpu = cpu; vcpu->arch.host_cpu_context = &cpu_data->host_ctxt; - kvm_arm_set_running_vcpu(vcpu); kvm_vgic_load(vcpu); kvm_timer_vcpu_load(vcpu); kvm_vcpu_load_sysregs(vcpu); @@ -430,8 +377,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) kvm_vcpu_pmu_restore_host(vcpu); vcpu->cpu = -1; - - kvm_arm_set_running_vcpu(NULL); } static void vcpu_power_off(struct kvm_vcpu *vcpu) diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 8a9db95d1e42..19c961ac4e3c 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -1376,14 +1376,8 @@ static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap) { kvm_pfn_t pfn = *pfnp; gfn_t gfn = *ipap >> PAGE_SHIFT; - struct page *page = pfn_to_page(pfn); - /* - * PageTransCompoundMap() returns true for THP and - * hugetlbfs. Make sure the adjustment is done only for THP - * pages. - */ - if (!PageHuge(page) && PageTransCompoundMap(page)) { + if (kvm_is_transparent_hugepage(pfn)) { unsigned long mask; /* * The address we faulted on is backed by a transparent huge diff --git a/virt/kvm/arm/perf.c b/virt/kvm/arm/perf.c index 918cdc3839ea..d45b8b9a4415 100644 --- a/virt/kvm/arm/perf.c +++ b/virt/kvm/arm/perf.c @@ -13,14 +13,14 @@ static int kvm_is_in_guest(void) { - return kvm_arm_get_running_vcpu() != NULL; + return kvm_get_running_vcpu() != NULL; } static int kvm_is_user_mode(void) { struct kvm_vcpu *vcpu; - vcpu = kvm_arm_get_running_vcpu(); + vcpu = kvm_get_running_vcpu(); if (vcpu) return !vcpu_mode_priv(vcpu); @@ -32,7 +32,7 @@ static unsigned long kvm_get_guest_ip(void) { struct kvm_vcpu *vcpu; - vcpu = kvm_arm_get_running_vcpu(); + vcpu = kvm_get_running_vcpu(); if (vcpu) return *vcpu_pc(vcpu); diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index 0d090482720d..d656ebd5f9d4 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -190,15 +190,6 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, * value later will give us the same value as we update the per-CPU variable * in the preempt notifier handlers. */ -static struct kvm_vcpu *vgic_get_mmio_requester_vcpu(void) -{ - struct kvm_vcpu *vcpu; - - preempt_disable(); - vcpu = kvm_arm_get_running_vcpu(); - preempt_enable(); - return vcpu; -} /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, @@ -221,7 +212,7 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !vgic_get_mmio_requester_vcpu(); + bool is_uaccess = !kvm_get_running_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -274,7 +265,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !vgic_get_mmio_requester_vcpu(); + bool is_uaccess = !kvm_get_running_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -335,7 +326,7 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool active) { unsigned long flags; - struct kvm_vcpu *requester_vcpu = vgic_get_mmio_requester_vcpu(); + struct kvm_vcpu *requester_vcpu = kvm_get_running_vcpu(); raw_spin_lock_irqsave(&irq->irq_lock, flags); diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 35305d6e68cc..15e5b037f92d 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -17,21 +17,6 @@ #include "async_pf.h" #include <trace/events/kvm.h> -static inline void kvm_async_page_present_sync(struct kvm_vcpu *vcpu, - struct kvm_async_pf *work) -{ -#ifdef CONFIG_KVM_ASYNC_PF_SYNC - kvm_arch_async_page_present(vcpu, work); -#endif -} -static inline void kvm_async_page_present_async(struct kvm_vcpu *vcpu, - struct kvm_async_pf *work) -{ -#ifndef CONFIG_KVM_ASYNC_PF_SYNC - kvm_arch_async_page_present(vcpu, work); -#endif -} - static struct kmem_cache *async_pf_cache; int kvm_async_pf_init(void) @@ -64,7 +49,7 @@ static void async_pf_execute(struct work_struct *work) struct mm_struct *mm = apf->mm; struct kvm_vcpu *vcpu = apf->vcpu; unsigned long addr = apf->addr; - gva_t gva = apf->gva; + gpa_t cr2_or_gpa = apf->cr2_or_gpa; int locked = 1; might_sleep(); @@ -80,7 +65,8 @@ static void async_pf_execute(struct work_struct *work) if (locked) up_read(&mm->mmap_sem); - kvm_async_page_present_sync(vcpu, apf); + if (IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC)) + kvm_arch_async_page_present(vcpu, apf); spin_lock(&vcpu->async_pf.lock); list_add_tail(&apf->link, &vcpu->async_pf.done); @@ -92,7 +78,7 @@ static void async_pf_execute(struct work_struct *work) * this point */ - trace_kvm_async_pf_completed(addr, gva); + trace_kvm_async_pf_completed(addr, cr2_or_gpa); if (swq_has_sleeper(&vcpu->wq)) swake_up_one(&vcpu->wq); @@ -157,7 +143,8 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) spin_unlock(&vcpu->async_pf.lock); kvm_arch_async_page_ready(vcpu, work); - kvm_async_page_present_async(vcpu, work); + if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC)) + kvm_arch_async_page_present(vcpu, work); list_del(&work->queue); vcpu->async_pf.queued--; @@ -165,8 +152,8 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) } } -int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, - struct kvm_arch_async_pf *arch) +int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + unsigned long hva, struct kvm_arch_async_pf *arch) { struct kvm_async_pf *work; @@ -185,7 +172,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, work->wakeup_all = false; work->vcpu = vcpu; - work->gva = gva; + work->cr2_or_gpa = cr2_or_gpa; work->addr = hva; work->arch = *arch; work->mm = current->mm; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 00268290dcbd..eb3709d55139 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -104,16 +104,16 @@ static cpumask_var_t cpus_hardware_enabled; static int kvm_usage_count; static atomic_t hardware_enable_failed; -struct kmem_cache *kvm_vcpu_cache; -EXPORT_SYMBOL_GPL(kvm_vcpu_cache); +static struct kmem_cache *kvm_vcpu_cache; static __read_mostly struct preempt_ops kvm_preempt_ops; +static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu); struct dentry *kvm_debugfs_dir; EXPORT_SYMBOL_GPL(kvm_debugfs_dir); static int kvm_debugfs_num_entries; -static const struct file_operations *stat_fops_per_vm[]; +static const struct file_operations stat_fops_per_vm; static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); @@ -191,12 +191,24 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn) return true; } +bool kvm_is_transparent_hugepage(kvm_pfn_t pfn) +{ + struct page *page = pfn_to_page(pfn); + + if (!PageTransCompoundMap(page)) + return false; + + return is_transparent_hugepage(compound_head(page)); +} + /* * Switches to specified vcpu, until a matching vcpu_put() */ void vcpu_load(struct kvm_vcpu *vcpu) { int cpu = get_cpu(); + + __this_cpu_write(kvm_running_vcpu, vcpu); preempt_notifier_register(&vcpu->preempt_notifier); kvm_arch_vcpu_load(vcpu, cpu); put_cpu(); @@ -208,6 +220,7 @@ void vcpu_put(struct kvm_vcpu *vcpu) preempt_disable(); kvm_arch_vcpu_put(vcpu); preempt_notifier_unregister(&vcpu->preempt_notifier); + __this_cpu_write(kvm_running_vcpu, NULL); preempt_enable(); } EXPORT_SYMBOL_GPL(vcpu_put); @@ -322,11 +335,8 @@ void kvm_reload_remote_mmus(struct kvm *kvm) kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD); } -int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) +static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) { - struct page *page; - int r; - mutex_init(&vcpu->mutex); vcpu->cpu = -1; vcpu->kvm = kvm; @@ -338,42 +348,28 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->pre_pcpu = -1; INIT_LIST_HEAD(&vcpu->blocked_vcpu_list); - page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) { - r = -ENOMEM; - goto fail; - } - vcpu->run = page_address(page); - kvm_vcpu_set_in_spin_loop(vcpu, false); kvm_vcpu_set_dy_eligible(vcpu, false); vcpu->preempted = false; vcpu->ready = false; - - r = kvm_arch_vcpu_init(vcpu); - if (r < 0) - goto fail_free_run; - return 0; - -fail_free_run: - free_page((unsigned long)vcpu->run); -fail: - return r; + preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); } -EXPORT_SYMBOL_GPL(kvm_vcpu_init); -void kvm_vcpu_uninit(struct kvm_vcpu *vcpu) +void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) { + kvm_arch_vcpu_destroy(vcpu); + /* - * no need for rcu_read_lock as VCPU_RUN is the only place that - * will change the vcpu->pid pointer and on uninit all file - * descriptors are already gone. + * No need for rcu_read_lock as VCPU_RUN is the only place that changes + * the vcpu->pid pointer, and at destruction time all file descriptors + * are already gone. */ put_pid(rcu_dereference_protected(vcpu->pid, 1)); - kvm_arch_vcpu_uninit(vcpu); + free_page((unsigned long)vcpu->run); + kmem_cache_free(kvm_vcpu_cache, vcpu); } -EXPORT_SYMBOL_GPL(kvm_vcpu_uninit); +EXPORT_SYMBOL_GPL(kvm_vcpu_destroy); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) @@ -650,11 +646,11 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) return -ENOMEM; stat_data->kvm = kvm; - stat_data->offset = p->offset; - stat_data->mode = p->mode ? p->mode : 0644; + stat_data->dbgfs_item = p; kvm->debugfs_stat_data[p - debugfs_entries] = stat_data; - debugfs_create_file(p->name, stat_data->mode, kvm->debugfs_dentry, - stat_data, stat_fops_per_vm[p->kind]); + debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p), + kvm->debugfs_dentry, stat_data, + &stat_fops_per_vm); } return 0; } @@ -964,7 +960,7 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, /* * Increment the new memslot generation a second time, dropping the - * update in-progress flag and incrementing then generation based on + * update in-progress flag and incrementing the generation based on * the number of address spaces. This provides a unique and easily * identifiable generation number while the memslots are in flux. */ @@ -1117,7 +1113,7 @@ int __kvm_set_memory_region(struct kvm *kvm, * * validation of sp->gfn happens in: * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) - * - kvm_is_visible_gfn (mmu_check_roots) + * - kvm_is_visible_gfn (mmu_check_root) */ kvm_arch_flush_shadow_memslot(kvm, slot); @@ -1406,14 +1402,14 @@ bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); -unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn) +unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn) { struct vm_area_struct *vma; unsigned long addr, size; size = PAGE_SIZE; - addr = gfn_to_hva(kvm, gfn); + addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gfn, NULL); if (kvm_is_error_hva(addr)) return PAGE_SIZE; @@ -1519,7 +1515,7 @@ static inline int check_user_page_hwpoison(unsigned long addr) /* * The fast path to get the writable pfn which will be stored in @pfn, * true indicates success, otherwise false is returned. It's also the - * only part that runs if we can are in atomic context. + * only part that runs if we can in atomic context. */ static bool hva_to_pfn_fast(unsigned long addr, bool write_fault, bool *writable, kvm_pfn_t *pfn) @@ -1931,11 +1927,8 @@ EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty); void kvm_set_pfn_dirty(kvm_pfn_t pfn) { - if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) { - struct page *page = pfn_to_page(pfn); - - SetPageDirty(page); - } + if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) + SetPageDirty(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty); @@ -2051,17 +2044,6 @@ static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn, return 0; } -int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, - unsigned long len) -{ - gfn_t gfn = gpa >> PAGE_SHIFT; - struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); - int offset = offset_in_page(gpa); - - return __kvm_read_guest_atomic(slot, gfn, data, offset, len); -} -EXPORT_SYMBOL_GPL(kvm_read_guest_atomic); - int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len) { @@ -2158,33 +2140,36 @@ static int __kvm_gfn_to_hva_cache_init(struct kvm_memslots *slots, gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT; gfn_t nr_pages_needed = end_gfn - start_gfn + 1; gfn_t nr_pages_avail; - int r = start_gfn <= end_gfn ? 0 : -EINVAL; - ghc->gpa = gpa; + /* Update ghc->generation before performing any error checks. */ ghc->generation = slots->generation; - ghc->len = len; - ghc->hva = KVM_HVA_ERR_BAD; + + if (start_gfn > end_gfn) { + ghc->hva = KVM_HVA_ERR_BAD; + return -EINVAL; + } /* * If the requested region crosses two memslots, we still * verify that the entire region is valid here. */ - while (!r && start_gfn <= end_gfn) { + for ( ; start_gfn <= end_gfn; start_gfn += nr_pages_avail) { ghc->memslot = __gfn_to_memslot(slots, start_gfn); ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail); if (kvm_is_error_hva(ghc->hva)) - r = -EFAULT; - start_gfn += nr_pages_avail; + return -EFAULT; } /* Use the slow path for cross page reads and writes. */ - if (!r && nr_pages_needed == 1) + if (nr_pages_needed == 1) ghc->hva += offset; else ghc->memslot = NULL; - return r; + ghc->gpa = gpa; + ghc->len = len; + return 0; } int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, @@ -2205,15 +2190,17 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, BUG_ON(len + offset > ghc->len); - if (slots->generation != ghc->generation) - __kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len); - - if (unlikely(!ghc->memslot)) - return kvm_write_guest(kvm, gpa, data, len); + if (slots->generation != ghc->generation) { + if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) + return -EFAULT; + } if (kvm_is_error_hva(ghc->hva)) return -EFAULT; + if (unlikely(!ghc->memslot)) + return kvm_write_guest(kvm, gpa, data, len); + r = __copy_to_user((void __user *)ghc->hva + offset, data, len); if (r) return -EFAULT; @@ -2238,15 +2225,17 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, BUG_ON(len > ghc->len); - if (slots->generation != ghc->generation) - __kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len); - - if (unlikely(!ghc->memslot)) - return kvm_read_guest(kvm, ghc->gpa, data, len); + if (slots->generation != ghc->generation) { + if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) + return -EFAULT; + } if (kvm_is_error_hva(ghc->hva)) return -EFAULT; + if (unlikely(!ghc->memslot)) + return kvm_read_guest(kvm, ghc->gpa, data, len); + r = __copy_from_user(data, (void __user *)ghc->hva, len); if (r) return -EFAULT; @@ -2718,6 +2707,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) { int r; struct kvm_vcpu *vcpu; + struct page *page; if (id >= KVM_MAX_VCPU_ID) return -EINVAL; @@ -2731,17 +2721,29 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) kvm->created_vcpus++; mutex_unlock(&kvm->lock); - vcpu = kvm_arch_vcpu_create(kvm, id); - if (IS_ERR(vcpu)) { - r = PTR_ERR(vcpu); + r = kvm_arch_vcpu_precreate(kvm, id); + if (r) + goto vcpu_decrement; + + vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + if (!vcpu) { + r = -ENOMEM; goto vcpu_decrement; } - preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); + BUILD_BUG_ON(sizeof(struct kvm_run) > PAGE_SIZE); + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) { + r = -ENOMEM; + goto vcpu_free; + } + vcpu->run = page_address(page); - r = kvm_arch_vcpu_setup(vcpu); + kvm_vcpu_init(vcpu, kvm, id); + + r = kvm_arch_vcpu_create(vcpu); if (r) - goto vcpu_destroy; + goto vcpu_free_run_page; kvm_create_vcpu_debugfs(vcpu); @@ -2778,8 +2780,11 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) unlock_vcpu_destroy: mutex_unlock(&kvm->lock); debugfs_remove_recursive(vcpu->debugfs_dentry); -vcpu_destroy: kvm_arch_vcpu_destroy(vcpu); +vcpu_free_run_page: + free_page((unsigned long)vcpu->run); +vcpu_free: + kmem_cache_free(kvm_vcpu_cache, vcpu); vcpu_decrement: mutex_lock(&kvm->lock); kvm->created_vcpus--; @@ -4013,8 +4018,9 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file, return -ENOENT; if (simple_attr_open(inode, file, get, - stat_data->mode & S_IWUGO ? set : NULL, - fmt)) { + KVM_DBGFS_GET_MODE(stat_data->dbgfs_item) & 0222 + ? set : NULL, + fmt)) { kvm_put_kvm(stat_data->kvm); return -ENOMEM; } @@ -4033,105 +4039,111 @@ static int kvm_debugfs_release(struct inode *inode, struct file *file) return 0; } -static int vm_stat_get_per_vm(void *data, u64 *val) +static int kvm_get_stat_per_vm(struct kvm *kvm, size_t offset, u64 *val) { - struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data; + *val = *(ulong *)((void *)kvm + offset); + + return 0; +} - *val = *(ulong *)((void *)stat_data->kvm + stat_data->offset); +static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset) +{ + *(ulong *)((void *)kvm + offset) = 0; return 0; } -static int vm_stat_clear_per_vm(void *data, u64 val) +static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val) { - struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data; + int i; + struct kvm_vcpu *vcpu; - if (val) - return -EINVAL; + *val = 0; - *(ulong *)((void *)stat_data->kvm + stat_data->offset) = 0; + kvm_for_each_vcpu(i, vcpu, kvm) + *val += *(u64 *)((void *)vcpu + offset); return 0; } -static int vm_stat_get_per_vm_open(struct inode *inode, struct file *file) +static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset) { - __simple_attr_check_format("%llu\n", 0ull); - return kvm_debugfs_open(inode, file, vm_stat_get_per_vm, - vm_stat_clear_per_vm, "%llu\n"); -} + int i; + struct kvm_vcpu *vcpu; -static const struct file_operations vm_stat_get_per_vm_fops = { - .owner = THIS_MODULE, - .open = vm_stat_get_per_vm_open, - .release = kvm_debugfs_release, - .read = simple_attr_read, - .write = simple_attr_write, - .llseek = no_llseek, -}; + kvm_for_each_vcpu(i, vcpu, kvm) + *(u64 *)((void *)vcpu + offset) = 0; -static int vcpu_stat_get_per_vm(void *data, u64 *val) + return 0; +} + +static int kvm_stat_data_get(void *data, u64 *val) { - int i; + int r = -EFAULT; struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data; - struct kvm_vcpu *vcpu; - *val = 0; - - kvm_for_each_vcpu(i, vcpu, stat_data->kvm) - *val += *(u64 *)((void *)vcpu + stat_data->offset); + switch (stat_data->dbgfs_item->kind) { + case KVM_STAT_VM: + r = kvm_get_stat_per_vm(stat_data->kvm, + stat_data->dbgfs_item->offset, val); + break; + case KVM_STAT_VCPU: + r = kvm_get_stat_per_vcpu(stat_data->kvm, + stat_data->dbgfs_item->offset, val); + break; + } - return 0; + return r; } -static int vcpu_stat_clear_per_vm(void *data, u64 val) +static int kvm_stat_data_clear(void *data, u64 val) { - int i; + int r = -EFAULT; struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data; - struct kvm_vcpu *vcpu; if (val) return -EINVAL; - kvm_for_each_vcpu(i, vcpu, stat_data->kvm) - *(u64 *)((void *)vcpu + stat_data->offset) = 0; + switch (stat_data->dbgfs_item->kind) { + case KVM_STAT_VM: + r = kvm_clear_stat_per_vm(stat_data->kvm, + stat_data->dbgfs_item->offset); + break; + case KVM_STAT_VCPU: + r = kvm_clear_stat_per_vcpu(stat_data->kvm, + stat_data->dbgfs_item->offset); + break; + } - return 0; + return r; } -static int vcpu_stat_get_per_vm_open(struct inode *inode, struct file *file) +static int kvm_stat_data_open(struct inode *inode, struct file *file) { __simple_attr_check_format("%llu\n", 0ull); - return kvm_debugfs_open(inode, file, vcpu_stat_get_per_vm, - vcpu_stat_clear_per_vm, "%llu\n"); + return kvm_debugfs_open(inode, file, kvm_stat_data_get, + kvm_stat_data_clear, "%llu\n"); } -static const struct file_operations vcpu_stat_get_per_vm_fops = { - .owner = THIS_MODULE, - .open = vcpu_stat_get_per_vm_open, +static const struct file_operations stat_fops_per_vm = { + .owner = THIS_MODULE, + .open = kvm_stat_data_open, .release = kvm_debugfs_release, - .read = simple_attr_read, - .write = simple_attr_write, - .llseek = no_llseek, -}; - -static const struct file_operations *stat_fops_per_vm[] = { - [KVM_STAT_VCPU] = &vcpu_stat_get_per_vm_fops, - [KVM_STAT_VM] = &vm_stat_get_per_vm_fops, + .read = simple_attr_read, + .write = simple_attr_write, + .llseek = no_llseek, }; static int vm_stat_get(void *_offset, u64 *val) { unsigned offset = (long)_offset; struct kvm *kvm; - struct kvm_stat_data stat_tmp = {.offset = offset}; u64 tmp_val; *val = 0; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { - stat_tmp.kvm = kvm; - vm_stat_get_per_vm((void *)&stat_tmp, &tmp_val); + kvm_get_stat_per_vm(kvm, offset, &tmp_val); *val += tmp_val; } mutex_unlock(&kvm_lock); @@ -4142,15 +4154,13 @@ static int vm_stat_clear(void *_offset, u64 val) { unsigned offset = (long)_offset; struct kvm *kvm; - struct kvm_stat_data stat_tmp = {.offset = offset}; if (val) return -EINVAL; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { - stat_tmp.kvm = kvm; - vm_stat_clear_per_vm((void *)&stat_tmp, 0); + kvm_clear_stat_per_vm(kvm, offset); } mutex_unlock(&kvm_lock); @@ -4163,14 +4173,12 @@ static int vcpu_stat_get(void *_offset, u64 *val) { unsigned offset = (long)_offset; struct kvm *kvm; - struct kvm_stat_data stat_tmp = {.offset = offset}; u64 tmp_val; *val = 0; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { - stat_tmp.kvm = kvm; - vcpu_stat_get_per_vm((void *)&stat_tmp, &tmp_val); + kvm_get_stat_per_vcpu(kvm, offset, &tmp_val); *val += tmp_val; } mutex_unlock(&kvm_lock); @@ -4181,15 +4189,13 @@ static int vcpu_stat_clear(void *_offset, u64 val) { unsigned offset = (long)_offset; struct kvm *kvm; - struct kvm_stat_data stat_tmp = {.offset = offset}; if (val) return -EINVAL; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { - stat_tmp.kvm = kvm; - vcpu_stat_clear_per_vm((void *)&stat_tmp, 0); + kvm_clear_stat_per_vcpu(kvm, offset); } mutex_unlock(&kvm_lock); @@ -4262,9 +4268,8 @@ static void kvm_init_debug(void) kvm_debugfs_num_entries = 0; for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) { - int mode = p->mode ? p->mode : 0644; - debugfs_create_file(p->name, mode, kvm_debugfs_dir, - (void *)(long)p->offset, + debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p), + kvm_debugfs_dir, (void *)(long)p->offset, stat_fops[p->kind]); } } @@ -4304,8 +4309,8 @@ static void kvm_sched_in(struct preempt_notifier *pn, int cpu) WRITE_ONCE(vcpu->preempted, false); WRITE_ONCE(vcpu->ready, false); + __this_cpu_write(kvm_running_vcpu, vcpu); kvm_arch_sched_in(vcpu, cpu); - kvm_arch_vcpu_load(vcpu, cpu); } @@ -4319,6 +4324,25 @@ static void kvm_sched_out(struct preempt_notifier *pn, WRITE_ONCE(vcpu->ready, true); } kvm_arch_vcpu_put(vcpu); + __this_cpu_write(kvm_running_vcpu, NULL); +} + +/** + * kvm_get_running_vcpu - get the vcpu running on the current CPU. + * Thanks to preempt notifiers, this can also be called from + * preemptible context. + */ +struct kvm_vcpu *kvm_get_running_vcpu(void) +{ + return __this_cpu_read(kvm_running_vcpu); +} + +/** + * kvm_get_running_vcpus - get the per-CPU array of currently running vcpus. + */ +struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void) +{ + return &kvm_running_vcpu; } static void check_processor_compat(void *rtn) diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c index 43de8ae78fa1..28fda42e471b 100644 --- a/virt/lib/irqbypass.c +++ b/virt/lib/irqbypass.c @@ -85,6 +85,7 @@ int irq_bypass_register_producer(struct irq_bypass_producer *producer) { struct irq_bypass_producer *tmp; struct irq_bypass_consumer *consumer; + int ret; if (!producer->token) return -EINVAL; @@ -98,20 +99,16 @@ int irq_bypass_register_producer(struct irq_bypass_producer *producer) list_for_each_entry(tmp, &producers, node) { if (tmp->token == producer->token) { - mutex_unlock(&lock); - module_put(THIS_MODULE); - return -EBUSY; + ret = -EBUSY; + goto out_err; } } list_for_each_entry(consumer, &consumers, node) { if (consumer->token == producer->token) { - int ret = __connect(producer, consumer); - if (ret) { - mutex_unlock(&lock); - module_put(THIS_MODULE); - return ret; - } + ret = __connect(producer, consumer); + if (ret) + goto out_err; break; } } @@ -121,6 +118,10 @@ int irq_bypass_register_producer(struct irq_bypass_producer *producer) mutex_unlock(&lock); return 0; +out_err: + mutex_unlock(&lock); + module_put(THIS_MODULE); + return ret; } EXPORT_SYMBOL_GPL(irq_bypass_register_producer); @@ -179,6 +180,7 @@ int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer) { struct irq_bypass_consumer *tmp; struct irq_bypass_producer *producer; + int ret; if (!consumer->token || !consumer->add_producer || !consumer->del_producer) @@ -193,20 +195,16 @@ int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer) list_for_each_entry(tmp, &consumers, node) { if (tmp->token == consumer->token || tmp == consumer) { - mutex_unlock(&lock); - module_put(THIS_MODULE); - return -EBUSY; + ret = -EBUSY; + goto out_err; } } list_for_each_entry(producer, &producers, node) { if (producer->token == consumer->token) { - int ret = __connect(producer, consumer); - if (ret) { - mutex_unlock(&lock); - module_put(THIS_MODULE); - return ret; - } + ret = __connect(producer, consumer); + if (ret) + goto out_err; break; } } @@ -216,6 +214,10 @@ int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer) mutex_unlock(&lock); return 0; +out_err: + mutex_unlock(&lock); + module_put(THIS_MODULE); + return ret; } EXPORT_SYMBOL_GPL(irq_bypass_register_consumer); |