From cf87ac739e488055a6046a410caa8f4da108948f Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 10 Nov 2022 18:49:08 +0800 Subject: KVM: x86: Introduce KVM_REQ_DIRTY_RING_SOFT_FULL The VCPU isn't expected to be runnable when the dirty ring becomes soft full, until the dirty pages are harvested and the dirty ring is reset from userspace. So there is a check in each guest's entrace to see if the dirty ring is soft full or not. The VCPU is stopped from running if its dirty ring has been soft full. The similar check will be needed when the feature is going to be supported on ARM64. As Marc Zyngier suggested, a new event will avoid pointless overhead to check the size of the dirty ring ('vcpu->kvm->dirty_ring_size') in each guest's entrance. Add KVM_REQ_DIRTY_RING_SOFT_FULL. The event is raised when the dirty ring becomes soft full in kvm_dirty_ring_push(). The event is only cleared in the check, done in the newly added helper kvm_dirty_ring_check_request(). Since the VCPU is not runnable when the dirty ring becomes soft full, the KVM_REQ_DIRTY_RING_SOFT_FULL event is always set to prevent the VCPU from running until the dirty pages are harvested and the dirty ring is reset by userspace. kvm_dirty_ring_soft_full() becomes a private function with the newly added helper kvm_dirty_ring_check_request(). The alignment for the various event definitions in kvm_host.h is changed to tab character by the way. In order to avoid using 'container_of()', the argument @ring is replaced by @vcpu in kvm_dirty_ring_push(). Link: https://lore.kernel.org/kvmarm/87lerkwtm5.wl-maz@kernel.org Suggested-by: Marc Zyngier Signed-off-by: Gavin Shan Reviewed-by: Peter Xu Reviewed-by: Sean Christopherson Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221110104914.31280-2-gshan@redhat.com --- include/linux/kvm_dirty_ring.h | 12 ++++-------- include/linux/kvm_host.h | 9 +++++---- 2 files changed, 9 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h index 906f899813dc..9c13c4c3d30c 100644 --- a/include/linux/kvm_dirty_ring.h +++ b/include/linux/kvm_dirty_ring.h @@ -49,7 +49,7 @@ static inline int kvm_dirty_ring_reset(struct kvm *kvm, return 0; } -static inline void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, +static inline void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset) { } @@ -64,11 +64,6 @@ static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring) { } -static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) -{ - return true; -} - #else /* CONFIG_HAVE_KVM_DIRTY_RING */ u32 kvm_dirty_ring_get_rsvd_entries(void); @@ -84,13 +79,14 @@ int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring); * returns =0: successfully pushed * <0: unable to push, need to wait */ -void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset); +void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset); + +bool kvm_dirty_ring_check_request(struct kvm_vcpu *vcpu); /* for use in vm_operations_struct */ struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset); void kvm_dirty_ring_free(struct kvm_dirty_ring *ring); -bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring); #endif /* CONFIG_HAVE_KVM_DIRTY_RING */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 00c3448ba7f8..648d663f32c4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -153,10 +153,11 @@ static inline bool is_error_page(struct page *page) * Architecture-independent vcpu->requests bit members * Bits 3-7 are reserved for more arch-independent bits. */ -#define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_UNBLOCK 2 -#define KVM_REQUEST_ARCH_BASE 8 +#define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_UNBLOCK 2 +#define KVM_REQ_DIRTY_RING_SOFT_FULL 3 +#define KVM_REQUEST_ARCH_BASE 8 /* * KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to -- cgit v1.2.3 From e8a18565e59303ac12c626a161d72bd890bd2062 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 10 Nov 2022 18:49:09 +0800 Subject: KVM: Move declaration of kvm_cpu_dirty_log_size() to kvm_dirty_ring.h Not all architectures like ARM64 need to override the function. Move its declaration to kvm_dirty_ring.h to avoid the following compiling warning on ARM64 when the feature is enabled. arch/arm64/kvm/../../../virt/kvm/dirty_ring.c:14:12: \ warning: no previous prototype for 'kvm_cpu_dirty_log_size' \ [-Wmissing-prototypes] \ int __weak kvm_cpu_dirty_log_size(void) Reported-by: kernel test robot Signed-off-by: Gavin Shan Reviewed-by: Peter Xu Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221110104914.31280-3-gshan@redhat.com --- arch/x86/include/asm/kvm_host.h | 2 -- include/linux/kvm_dirty_ring.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 7551b6f9c31c..b4dbde7d9eb1 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2090,8 +2090,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #define GET_SMSTATE(type, buf, offset) \ (*(type *)((buf) + (offset) - 0x7e00)) -int kvm_cpu_dirty_log_size(void); - int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); #define KVM_CLOCK_VALID_FLAGS \ diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h index 9c13c4c3d30c..199ead37b104 100644 --- a/include/linux/kvm_dirty_ring.h +++ b/include/linux/kvm_dirty_ring.h @@ -66,6 +66,7 @@ static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring) #else /* CONFIG_HAVE_KVM_DIRTY_RING */ +int kvm_cpu_dirty_log_size(void); u32 kvm_dirty_ring_get_rsvd_entries(void); int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size); -- cgit v1.2.3 From 86bdf3ebcfe1ded055282536fecce13001874740 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 10 Nov 2022 18:49:10 +0800 Subject: KVM: Support dirty ring in conjunction with bitmap ARM64 needs to dirty memory outside of a VCPU context when VGIC/ITS is enabled. It's conflicting with that ring-based dirty page tracking always requires a running VCPU context. Introduce a new flavor of dirty ring that requires the use of both VCPU dirty rings and a dirty bitmap. The expectation is that for non-VCPU sources of dirty memory (such as the VGIC/ITS on arm64), KVM writes to the dirty bitmap. Userspace should scan the dirty bitmap before migrating the VM to the target. Use an additional capability to advertise this behavior. The newly added capability (KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP) can't be enabled before KVM_CAP_DIRTY_LOG_RING_ACQ_REL on ARM64. In this way, the newly added capability is treated as an extension of KVM_CAP_DIRTY_LOG_RING_ACQ_REL. Suggested-by: Marc Zyngier Suggested-by: Peter Xu Co-developed-by: Oliver Upton Signed-off-by: Oliver Upton Signed-off-by: Gavin Shan Acked-by: Peter Xu Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221110104914.31280-4-gshan@redhat.com --- Documentation/virt/kvm/api.rst | 34 +++++++++++--- Documentation/virt/kvm/devices/arm-vgic-its.rst | 5 +- include/linux/kvm_dirty_ring.h | 7 +++ include/linux/kvm_host.h | 1 + include/uapi/linux/kvm.h | 1 + virt/kvm/Kconfig | 6 +++ virt/kvm/dirty_ring.c | 14 ++++++ virt/kvm/kvm_main.c | 61 +++++++++++++++++++++---- 8 files changed, 112 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index eee9f857a986..1f1b09aa6db4 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8003,13 +8003,6 @@ flushing is done by the KVM_GET_DIRTY_LOG ioctl). To achieve that, one needs to kick the vcpu out of KVM_RUN using a signal. The resulting vmexit ensures that all dirty GFNs are flushed to the dirty rings. -NOTE: the capability KVM_CAP_DIRTY_LOG_RING and the corresponding -ioctl KVM_RESET_DIRTY_RINGS are mutual exclusive to the existing ioctls -KVM_GET_DIRTY_LOG and KVM_CLEAR_DIRTY_LOG. After enabling -KVM_CAP_DIRTY_LOG_RING with an acceptable dirty ring size, the virtual -machine will switch to ring-buffer dirty page tracking and further -KVM_GET_DIRTY_LOG or KVM_CLEAR_DIRTY_LOG ioctls will fail. - NOTE: KVM_CAP_DIRTY_LOG_RING_ACQ_REL is the only capability that should be exposed by weakly ordered architecture, in order to indicate the additional memory ordering requirements imposed on userspace when @@ -8018,6 +8011,33 @@ Architecture with TSO-like ordering (such as x86) are allowed to expose both KVM_CAP_DIRTY_LOG_RING and KVM_CAP_DIRTY_LOG_RING_ACQ_REL to userspace. +After enabling the dirty rings, the userspace needs to detect the +capability of KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP to see whether the +ring structures can be backed by per-slot bitmaps. With this capability +advertised, it means the architecture can dirty guest pages without +vcpu/ring context, so that some of the dirty information will still be +maintained in the bitmap structure. KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP +can't be enabled if the capability of KVM_CAP_DIRTY_LOG_RING_ACQ_REL +hasn't been enabled, or any memslot has been existing. + +Note that the bitmap here is only a backup of the ring structure. The +use of the ring and bitmap combination is only beneficial if there is +only a very small amount of memory that is dirtied out of vcpu/ring +context. Otherwise, the stand-alone per-slot bitmap mechanism needs to +be considered. + +To collect dirty bits in the backup bitmap, userspace can use the same +KVM_GET_DIRTY_LOG ioctl. KVM_CLEAR_DIRTY_LOG isn't needed as long as all +the generation of the dirty bits is done in a single pass. Collecting +the dirty bitmap should be the very last thing that the VMM does before +considering the state as complete. VMM needs to ensure that the dirty +state is final and avoid missing dirty pages from another ioctl ordered +after the bitmap collection. + +NOTE: One example of using the backup bitmap is saving arm64 vgic/its +tables through KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} command on +KVM device "kvm-arm-vgic-its" when dirty ring is enabled. + 8.30 KVM_CAP_XEN_HVM -------------------- diff --git a/Documentation/virt/kvm/devices/arm-vgic-its.rst b/Documentation/virt/kvm/devices/arm-vgic-its.rst index d257eddbae29..e053124f77c4 100644 --- a/Documentation/virt/kvm/devices/arm-vgic-its.rst +++ b/Documentation/virt/kvm/devices/arm-vgic-its.rst @@ -52,7 +52,10 @@ KVM_DEV_ARM_VGIC_GRP_CTRL KVM_DEV_ARM_ITS_SAVE_TABLES save the ITS table data into guest RAM, at the location provisioned - by the guest in corresponding registers/table entries. + by the guest in corresponding registers/table entries. Should userspace + require a form of dirty tracking to identify which pages are modified + by the saving process, it should use a bitmap even if using another + mechanism to track the memory dirtied by the vCPUs. The layout of the tables in guest memory defines an ABI. The entries are laid out in little endian format as described in the last paragraph. diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h index 199ead37b104..4862c98d80d3 100644 --- a/include/linux/kvm_dirty_ring.h +++ b/include/linux/kvm_dirty_ring.h @@ -37,6 +37,11 @@ static inline u32 kvm_dirty_ring_get_rsvd_entries(void) return 0; } +static inline bool kvm_use_dirty_bitmap(struct kvm *kvm) +{ + return true; +} + static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size) { @@ -67,6 +72,8 @@ static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring) #else /* CONFIG_HAVE_KVM_DIRTY_RING */ int kvm_cpu_dirty_log_size(void); +bool kvm_use_dirty_bitmap(struct kvm *kvm); +bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm); u32 kvm_dirty_ring_get_rsvd_entries(void); int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 648d663f32c4..db83f63f4e61 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -779,6 +779,7 @@ struct kvm { pid_t userspace_pid; unsigned int max_halt_poll_ns; u32 dirty_ring_size; + bool dirty_ring_with_bitmap; bool vm_bugged; bool vm_dead; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 0d5d4419139a..c87b5882d7ae 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1178,6 +1178,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_ZPCI_OP 221 #define KVM_CAP_S390_CPU_TOPOLOGY 222 #define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223 +#define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 224 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 800f9470e36b..9fb1ff6f19e5 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -33,6 +33,12 @@ config HAVE_KVM_DIRTY_RING_ACQ_REL bool select HAVE_KVM_DIRTY_RING +# Allow enabling both the dirty bitmap and dirty ring. Only architectures +# that need to dirty memory outside of a vCPU context should select this. +config NEED_KVM_DIRTY_RING_WITH_BITMAP + bool + depends on HAVE_KVM_DIRTY_RING + config HAVE_KVM_EVENTFD bool select EVENTFD diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c index fecbb7d75ad2..c1cd7dfe4a90 100644 --- a/virt/kvm/dirty_ring.c +++ b/virt/kvm/dirty_ring.c @@ -21,6 +21,20 @@ u32 kvm_dirty_ring_get_rsvd_entries(void) return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size(); } +bool kvm_use_dirty_bitmap(struct kvm *kvm) +{ + lockdep_assert_held(&kvm->slots_lock); + + return !kvm->dirty_ring_size || kvm->dirty_ring_with_bitmap; +} + +#ifndef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP +bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) +{ + return false; +} +#endif + static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring) { return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 04b22d2f99d8..be40d1ce6e91 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1617,7 +1617,7 @@ static int kvm_prepare_memory_region(struct kvm *kvm, new->dirty_bitmap = NULL; else if (old && old->dirty_bitmap) new->dirty_bitmap = old->dirty_bitmap; - else if (!kvm->dirty_ring_size) { + else if (kvm_use_dirty_bitmap(kvm)) { r = kvm_alloc_dirty_bitmap(new); if (r) return r; @@ -2060,8 +2060,8 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, unsigned long n; unsigned long any = 0; - /* Dirty ring tracking is exclusive to dirty log tracking */ - if (kvm->dirty_ring_size) + /* Dirty ring tracking may be exclusive to dirty log tracking */ + if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; *memslot = NULL; @@ -2125,8 +2125,8 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log) unsigned long *dirty_bitmap_buffer; bool flush; - /* Dirty ring tracking is exclusive to dirty log tracking */ - if (kvm->dirty_ring_size) + /* Dirty ring tracking may be exclusive to dirty log tracking */ + if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; as_id = log->slot >> 16; @@ -2237,8 +2237,8 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm, unsigned long *dirty_bitmap_buffer; bool flush; - /* Dirty ring tracking is exclusive to dirty log tracking */ - if (kvm->dirty_ring_size) + /* Dirty ring tracking may be exclusive to dirty log tracking */ + if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; as_id = log->slot >> 16; @@ -3305,7 +3305,10 @@ void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); #ifdef CONFIG_HAVE_KVM_DIRTY_RING - if (WARN_ON_ONCE(!vcpu) || WARN_ON_ONCE(vcpu->kvm != kvm)) + if (WARN_ON_ONCE(vcpu && vcpu->kvm != kvm)) + return; + + if (WARN_ON_ONCE(!kvm_arch_allow_write_without_running_vcpu(kvm) && !vcpu)) return; #endif @@ -3313,7 +3316,7 @@ void mark_page_dirty_in_slot(struct kvm *kvm, unsigned long rel_gfn = gfn - memslot->base_gfn; u32 slot = (memslot->as_id << 16) | memslot->id; - if (kvm->dirty_ring_size) + if (kvm->dirty_ring_size && vcpu) kvm_dirty_ring_push(vcpu, slot, rel_gfn); else set_bit_le(rel_gfn, memslot->dirty_bitmap); @@ -4482,6 +4485,9 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); #else return 0; +#endif +#ifdef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP + case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: #endif case KVM_CAP_BINARY_STATS_FD: case KVM_CAP_SYSTEM_EVENT_DATA: @@ -4558,6 +4564,20 @@ int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm, return -EINVAL; } +static bool kvm_are_all_memslots_empty(struct kvm *kvm) +{ + int i; + + lockdep_assert_held(&kvm->slots_lock); + + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + if (!kvm_memslots_empty(__kvm_memslots(kvm, i))) + return false; + } + + return true; +} + static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, struct kvm_enable_cap *cap) { @@ -4588,6 +4608,29 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, return -EINVAL; return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]); + case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: { + int r = -EINVAL; + + if (!IS_ENABLED(CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP) || + !kvm->dirty_ring_size || cap->flags) + return r; + + mutex_lock(&kvm->slots_lock); + + /* + * For simplicity, allow enabling ring+bitmap if and only if + * there are no memslots, e.g. to ensure all memslots allocate + * a bitmap after the capability is enabled. + */ + if (kvm_are_all_memslots_empty(kvm)) { + kvm->dirty_ring_with_bitmap = true; + r = 0; + } + + mutex_unlock(&kvm->slots_lock); + + return r; + } default: return kvm_vm_ioctl_enable_cap(kvm, cap); } -- cgit v1.2.3 From b0284cd29a957e62d60c2886fd663be93c56f9c0 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Thu, 3 Nov 2022 18:10:34 -0700 Subject: mm: Do not enable PG_arch_2 for all 64-bit architectures Commit 4beba9486abd ("mm: Add PG_arch_2 page flag") introduced a new page flag for all 64-bit architectures. However, even if an architecture is 64-bit, it may still have limited spare bits in the 'flags' member of 'struct page'. This may happen if an architecture enables SPARSEMEM without SPARSEMEM_VMEMMAP as is the case with the newly added loongarch. This architecture port needs 19 more bits for the sparsemem section information and, while it is currently fine with PG_arch_2, adding any more PG_arch_* flags will trigger build-time warnings. Add a new CONFIG_ARCH_USES_PG_ARCH_X option which can be selected by architectures that need more PG_arch_* flags beyond PG_arch_1. Select it on arm64. Signed-off-by: Catalin Marinas [pcc@google.com: fix build with CONFIG_ARM64_MTE disabled] Signed-off-by: Peter Collingbourne Reported-by: kernel test robot Cc: Andrew Morton Cc: Steven Price Reviewed-by: Steven Price Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221104011041.290951-2-pcc@google.com --- arch/arm64/Kconfig | 1 + fs/proc/page.c | 2 +- include/linux/page-flags.h | 2 +- include/trace/events/mmflags.h | 8 ++++---- mm/Kconfig | 8 ++++++++ mm/huge_memory.c | 2 +- 6 files changed, 16 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 505c8a1ccbe0..cd93d0738425 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1965,6 +1965,7 @@ config ARM64_MTE depends on ARM64_PAN select ARCH_HAS_SUBPAGE_FAULTS select ARCH_USES_HIGH_VMA_FLAGS + select ARCH_USES_PG_ARCH_X help Memory Tagging (part of the ARMv8.5 Extensions) provides architectural support for run-time, always-on detection of diff --git a/fs/proc/page.c b/fs/proc/page.c index f2273b164535..882525c8e94c 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -219,7 +219,7 @@ u64 stable_page_flags(struct page *page) u |= kpf_copy_bit(k, KPF_PRIVATE_2, PG_private_2); u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE, PG_owner_priv_1); u |= kpf_copy_bit(k, KPF_ARCH, PG_arch_1); -#ifdef CONFIG_64BIT +#ifdef CONFIG_ARCH_USES_PG_ARCH_X u |= kpf_copy_bit(k, KPF_ARCH_2, PG_arch_2); #endif diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 0b0ae5084e60..5dc7977edf9d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -132,7 +132,7 @@ enum pageflags { PG_young, PG_idle, #endif -#ifdef CONFIG_64BIT +#ifdef CONFIG_ARCH_USES_PG_ARCH_X PG_arch_2, #endif #ifdef CONFIG_KASAN_HW_TAGS diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index e87cb2b80ed3..d9f6d35fb150 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -91,10 +91,10 @@ #define IF_HAVE_PG_IDLE(flag,string) #endif -#ifdef CONFIG_64BIT -#define IF_HAVE_PG_ARCH_2(flag,string) ,{1UL << flag, string} +#ifdef CONFIG_ARCH_USES_PG_ARCH_X +#define IF_HAVE_PG_ARCH_X(flag,string) ,{1UL << flag, string} #else -#define IF_HAVE_PG_ARCH_2(flag,string) +#define IF_HAVE_PG_ARCH_X(flag,string) #endif #ifdef CONFIG_KASAN_HW_TAGS @@ -130,7 +130,7 @@ IF_HAVE_PG_UNCACHED(PG_uncached, "uncached" ) \ IF_HAVE_PG_HWPOISON(PG_hwpoison, "hwpoison" ) \ IF_HAVE_PG_IDLE(PG_young, "young" ) \ IF_HAVE_PG_IDLE(PG_idle, "idle" ) \ -IF_HAVE_PG_ARCH_2(PG_arch_2, "arch_2" ) \ +IF_HAVE_PG_ARCH_X(PG_arch_2, "arch_2" ) \ IF_HAVE_PG_SKIP_KASAN_POISON(PG_skip_kasan_poison, "skip_kasan_poison") #define show_page_flags(flags) \ diff --git a/mm/Kconfig b/mm/Kconfig index 57e1d8c5b505..807bd7192f51 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1005,6 +1005,14 @@ config ARCH_USES_HIGH_VMA_FLAGS config ARCH_HAS_PKEYS bool +config ARCH_USES_PG_ARCH_X + bool + help + Enable the definition of PG_arch_x page flags with x > 1. Only + suitable for 64-bit architectures with CONFIG_FLATMEM or + CONFIG_SPARSEMEM_VMEMMAP enabled, otherwise there may not be + enough room for additional bits in page->flags. + config VM_EVENT_COUNTERS default y bool "Enable VM event counters for /proc/vmstat" if EXPERT diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 561a42567477..76e7b973919c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2444,7 +2444,7 @@ static void __split_huge_page_tail(struct page *head, int tail, (1L << PG_workingset) | (1L << PG_locked) | (1L << PG_unevictable) | -#ifdef CONFIG_64BIT +#ifdef CONFIG_ARCH_USES_PG_ARCH_X (1L << PG_arch_2) | #endif (1L << PG_dirty) | -- cgit v1.2.3 From ef6458b1b6ca3fdb991ce4182e981a88d4c58c0f Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 3 Nov 2022 18:10:37 -0700 Subject: mm: Add PG_arch_3 page flag As with PG_arch_2, this flag is only allowed on 64-bit architectures due to the shortage of bits available. It will be used by the arm64 MTE code in subsequent patches. Signed-off-by: Peter Collingbourne Cc: Will Deacon Cc: Marc Zyngier Cc: Steven Price [catalin.marinas@arm.com: added flag preserving in __split_huge_page_tail()] Signed-off-by: Catalin Marinas Reviewed-by: Steven Price Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221104011041.290951-5-pcc@google.com --- fs/proc/page.c | 1 + include/linux/kernel-page-flags.h | 1 + include/linux/page-flags.h | 1 + include/trace/events/mmflags.h | 1 + mm/huge_memory.c | 1 + 5 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/fs/proc/page.c b/fs/proc/page.c index 882525c8e94c..6249c347809a 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -221,6 +221,7 @@ u64 stable_page_flags(struct page *page) u |= kpf_copy_bit(k, KPF_ARCH, PG_arch_1); #ifdef CONFIG_ARCH_USES_PG_ARCH_X u |= kpf_copy_bit(k, KPF_ARCH_2, PG_arch_2); + u |= kpf_copy_bit(k, KPF_ARCH_3, PG_arch_3); #endif return u; diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h index eee1877a354e..859f4b0c1b2b 100644 --- a/include/linux/kernel-page-flags.h +++ b/include/linux/kernel-page-flags.h @@ -18,5 +18,6 @@ #define KPF_UNCACHED 39 #define KPF_SOFTDIRTY 40 #define KPF_ARCH_2 41 +#define KPF_ARCH_3 42 #endif /* LINUX_KERNEL_PAGE_FLAGS_H */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 5dc7977edf9d..c50ce2812f17 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -134,6 +134,7 @@ enum pageflags { #endif #ifdef CONFIG_ARCH_USES_PG_ARCH_X PG_arch_2, + PG_arch_3, #endif #ifdef CONFIG_KASAN_HW_TAGS PG_skip_kasan_poison, diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index d9f6d35fb150..412b5a46374c 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -131,6 +131,7 @@ IF_HAVE_PG_HWPOISON(PG_hwpoison, "hwpoison" ) \ IF_HAVE_PG_IDLE(PG_young, "young" ) \ IF_HAVE_PG_IDLE(PG_idle, "idle" ) \ IF_HAVE_PG_ARCH_X(PG_arch_2, "arch_2" ) \ +IF_HAVE_PG_ARCH_X(PG_arch_3, "arch_3" ) \ IF_HAVE_PG_SKIP_KASAN_POISON(PG_skip_kasan_poison, "skip_kasan_poison") #define show_page_flags(flags) \ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 76e7b973919c..dfe72ea23c5f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2446,6 +2446,7 @@ static void __split_huge_page_tail(struct page *head, int tail, (1L << PG_unevictable) | #ifdef CONFIG_ARCH_USES_PG_ARCH_X (1L << PG_arch_2) | + (1L << PG_arch_3) | #endif (1L << PG_dirty) | LRU_GEN_MASK | LRU_REFS_MASK)); -- cgit v1.2.3