From 647daca25d24fb6eadc7b6cd680ad3e6eed0f3d5 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 4 Jan 2021 14:20:01 -0600 Subject: KVM: SVM: Add support for booting APs in an SEV-ES guest Typically under KVM, an AP is booted using the INIT-SIPI-SIPI sequence, where the guest vCPU register state is updated and then the vCPU is VMRUN to begin execution of the AP. For an SEV-ES guest, this won't work because the guest register state is encrypted. Following the GHCB specification, the hypervisor must not alter the guest register state, so KVM must track an AP/vCPU boot. Should the guest want to park the AP, it must use the AP Reset Hold exit event in place of, for example, a HLT loop. First AP boot (first INIT-SIPI-SIPI sequence): Execute the AP (vCPU) as it was initialized and measured by the SEV-ES support. It is up to the guest to transfer control of the AP to the proper location. Subsequent AP boot: KVM will expect to receive an AP Reset Hold exit event indicating that the vCPU is being parked and will require an INIT-SIPI-SIPI sequence to awaken it. When the AP Reset Hold exit event is received, KVM will place the vCPU into a simulated HLT mode. Upon receiving the INIT-SIPI-SIPI sequence, KVM will make the vCPU runnable. It is again up to the guest to then transfer control of the AP to the proper location. To differentiate between an actual HLT and an AP Reset Hold, a new MP state is introduced, KVM_MP_STATE_AP_RESET_HOLD, which the vCPU is placed in upon receiving the AP Reset Hold exit event. Additionally, to communicate the AP Reset Hold exit event up to userspace (if needed), a new exit reason is introduced, KVM_EXIT_AP_RESET_HOLD. A new x86 ops function is introduced, vcpu_deliver_sipi_vector, in order to accomplish AP booting. For VMX, vcpu_deliver_sipi_vector is set to the original SIPI delivery function, kvm_vcpu_deliver_sipi_vector(). SVM adds a new function that, for non SEV-ES guests, invokes the original SIPI delivery function, kvm_vcpu_deliver_sipi_vector(), but for SEV-ES guests, implements the logic above. Signed-off-by: Tom Lendacky Message-Id: Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 886802b8ffba..374c67875cdb 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -251,6 +251,7 @@ struct kvm_hyperv_exit { #define KVM_EXIT_X86_RDMSR 29 #define KVM_EXIT_X86_WRMSR 30 #define KVM_EXIT_DIRTY_RING_FULL 31 +#define KVM_EXIT_AP_RESET_HOLD 32 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -573,6 +574,7 @@ struct kvm_vapic_addr { #define KVM_MP_STATE_CHECK_STOP 6 #define KVM_MP_STATE_OPERATING 7 #define KVM_MP_STATE_LOAD 8 +#define KVM_MP_STATE_AP_RESET_HOLD 9 struct kvm_mp_state { __u32 mp_state; -- cgit v1.2.3 From b16671e8f493e3df40b1fb0dff4078f391c5099a Mon Sep 17 00:00:00 2001 From: Coly Li Date: Mon, 4 Jan 2021 15:41:21 +0800 Subject: bcache: introduce BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE for large bucket When large bucket feature was added, BCH_FEATURE_INCOMPAT_LARGE_BUCKET was introduced into the incompat feature set. It used bucket_size_hi (which was added at the tail of struct cache_sb_disk) to extend current 16bit bucket size to 32bit with existing bucket_size in struct cache_sb_disk. This is not a good idea, there are two obvious problems, - Bucket size is always value power of 2, if store log2(bucket size) in existing bucket_size of struct cache_sb_disk, it is unnecessary to add bucket_size_hi. - Macro csum_set() assumes d[SB_JOURNAL_BUCKETS] is the last member in struct cache_sb_disk, bucket_size_hi was added after d[] which makes csum_set calculate an unexpected super block checksum. To fix the above problems, this patch introduces a new incompat feature bit BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE, when this bit is set, it means bucket_size in struct cache_sb_disk stores the order of power-of-2 bucket size value. When user specifies a bucket size larger than 32768 sectors, BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE will be set to incompat feature set, and bucket_size stores log2(bucket size) more than store the real bucket size value. The obsoleted BCH_FEATURE_INCOMPAT_LARGE_BUCKET won't be used anymore, it is renamed to BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET and still only recognized by kernel driver for legacy compatible purpose. The previous bucket_size_hi is renmaed to obso_bucket_size_hi in struct cache_sb_disk and not used in bcache-tools anymore. For cache device created with BCH_FEATURE_INCOMPAT_LARGE_BUCKET feature, bcache-tools and kernel driver still recognize the feature string and display it as "obso_large_bucket". With this change, the unnecessary extra space extend of bcache on-disk super block can be avoided, and csum_set() may generate expected check sum as well. Fixes: ffa470327572 ("bcache: add bucket_size_hi into struct cache_sb_disk for large bucket") Signed-off-by: Coly Li Cc: stable@vger.kernel.org # 5.9+ Signed-off-by: Jens Axboe --- drivers/md/bcache/features.c | 2 +- drivers/md/bcache/features.h | 11 ++++++++--- drivers/md/bcache/super.c | 22 +++++++++++++++++++--- include/uapi/linux/bcache.h | 2 +- 4 files changed, 29 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/md/bcache/features.c b/drivers/md/bcache/features.c index 6469223f0b77..d636b7b2d070 100644 --- a/drivers/md/bcache/features.c +++ b/drivers/md/bcache/features.c @@ -17,7 +17,7 @@ struct feature { }; static struct feature feature_list[] = { - {BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LARGE_BUCKET, + {BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE, "large_bucket"}, {0, 0, 0 }, }; diff --git a/drivers/md/bcache/features.h b/drivers/md/bcache/features.h index e73724c2b49b..84fc2c0f0101 100644 --- a/drivers/md/bcache/features.h +++ b/drivers/md/bcache/features.h @@ -13,11 +13,15 @@ /* Feature set definition */ /* Incompat feature set */ -#define BCH_FEATURE_INCOMPAT_LARGE_BUCKET 0x0001 /* 32bit bucket size */ +/* 32bit bucket size, obsoleted */ +#define BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET 0x0001 +/* real bucket size is (1 << bucket_size) */ +#define BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE 0x0002 #define BCH_FEATURE_COMPAT_SUPP 0 #define BCH_FEATURE_RO_COMPAT_SUPP 0 -#define BCH_FEATURE_INCOMPAT_SUPP BCH_FEATURE_INCOMPAT_LARGE_BUCKET +#define BCH_FEATURE_INCOMPAT_SUPP (BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET| \ + BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE) #define BCH_HAS_COMPAT_FEATURE(sb, mask) \ ((sb)->feature_compat & (mask)) @@ -77,7 +81,8 @@ static inline void bch_clear_feature_##name(struct cache_sb *sb) \ ~BCH##_FEATURE_INCOMPAT_##flagname; \ } -BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LARGE_BUCKET); +BCH_FEATURE_INCOMPAT_FUNCS(obso_large_bucket, OBSO_LARGE_BUCKET); +BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LOG_LARGE_BUCKET_SIZE); static inline bool bch_has_unknown_compat_features(struct cache_sb *sb) { diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index f4674a3298af..3999641f1775 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -64,9 +64,25 @@ static unsigned int get_bucket_size(struct cache_sb *sb, struct cache_sb_disk *s { unsigned int bucket_size = le16_to_cpu(s->bucket_size); - if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES && - bch_has_feature_large_bucket(sb)) - bucket_size |= le16_to_cpu(s->bucket_size_hi) << 16; + if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES) { + if (bch_has_feature_large_bucket(sb)) { + unsigned int max, order; + + max = sizeof(unsigned int) * BITS_PER_BYTE - 1; + order = le16_to_cpu(s->bucket_size); + /* + * bcache tool will make sure the overflow won't + * happen, an error message here is enough. + */ + if (order > max) + pr_err("Bucket size (1 << %u) overflows\n", + order); + bucket_size = 1 << order; + } else if (bch_has_feature_obso_large_bucket(sb)) { + bucket_size += + le16_to_cpu(s->obso_bucket_size_hi) << 16; + } + } return bucket_size; } diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h index 52e8bcb33981..cf7399f03b71 100644 --- a/include/uapi/linux/bcache.h +++ b/include/uapi/linux/bcache.h @@ -213,7 +213,7 @@ struct cache_sb_disk { __le16 keys; }; __le64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */ - __le16 bucket_size_hi; + __le16 obso_bucket_size_hi; /* obsoleted */ }; /* -- cgit v1.2.3