Allocate all guest ram backed by memfd/ftruncate instead of anonymous mmap. This will make it easier to use kvm with fd-based kvm guest memory proposals [*]. It also would make it easier to use ipc memory sharing should that be needed in the future. Signed-off-by: Fuad Tabba <tabba@xxxxxxxxxx> [*] https://lore.kernel.org/all/20221202061347.1070246-1-chao.p.peng@xxxxxxxxxxxxxxx/ --- include/kvm/kvm.h | 1 + include/kvm/util.h | 3 +++ kvm.c | 4 ++++ util/util.c | 30 ++++++++++++++++++------------ 4 files changed, 26 insertions(+), 12 deletions(-) diff --git a/include/kvm/kvm.h b/include/kvm/kvm.h index 3872dc6..d0d519b 100644 --- a/include/kvm/kvm.h +++ b/include/kvm/kvm.h @@ -87,6 +87,7 @@ struct kvm { struct kvm_config cfg; int sys_fd; /* For system ioctls(), i.e. /dev/kvm */ int vm_fd; /* For VM ioctls() */ + int ram_fd; /* For guest memory. */ timer_t timerid; /* Posix timer for interrupts */ int nrcpus; /* Number of cpus to run */ diff --git a/include/kvm/util.h b/include/kvm/util.h index b0c3684..74713d9 100644 --- a/include/kvm/util.h +++ b/include/kvm/util.h @@ -140,6 +140,9 @@ static inline int pow2_size(unsigned long x) } struct kvm; +int memfd_alloc(u64 size, bool hugetlb, u64 blk_size); +void *mmap_anon_or_hugetlbfs_align(struct kvm *kvm, const char *hugetlbfs_path, + u64 size, u64 align); void *mmap_anon_or_hugetlbfs(struct kvm *kvm, const char *hugetlbfs_path, u64 size); #endif /* KVM__UTIL_H */ diff --git a/kvm.c b/kvm.c index 765dc71..84a8675 100644 --- a/kvm.c +++ b/kvm.c @@ -160,6 +160,7 @@ struct kvm *kvm__new(void) mutex_init(&kvm->mem_banks_lock); kvm->sys_fd = -1; kvm->vm_fd = -1; + kvm->ram_fd = -1; #ifdef KVM_BRLOCK_DEBUG kvm->brlock_sem = (pthread_rwlock_t) PTHREAD_RWLOCK_INITIALIZER; @@ -174,6 +175,9 @@ int kvm__exit(struct kvm *kvm) kvm__arch_delete_ram(kvm); + if (kvm->ram_fd >= 0) + close(kvm->ram_fd); + list_for_each_entry_safe(bank, tmp, &kvm->mem_banks, list) { list_del(&bank->list); free(bank); diff --git a/util/util.c b/util/util.c index 93f895a..54c2b26 100644 --- a/util/util.c +++ b/util/util.c @@ -95,35 +95,36 @@ static u64 get_hugepage_blk_size(const char *hugetlbfs_path) return sfs.f_bsize; } -static void *mmap_hugetlbfs(struct kvm *kvm, const char *hugetlbfs_path, u64 size, u64 blk_size) +int memfd_alloc(u64 size, bool hugetlb, u64 blk_size) { const char *name = "kvmtool"; unsigned int flags = 0; int fd; - void *addr; - if (!is_power_of_two(blk_size)) - die("Hugepage size must be a power of 2"); + if (hugetlb) { + if (!is_power_of_two(blk_size)) + die("Hugepage size must be a power of 2"); - flags |= MFD_HUGETLB; - flags |= blk_size << MFD_HUGE_SHIFT; + flags |= MFD_HUGETLB; + flags |= blk_size << MFD_HUGE_SHIFT; + } fd = memfd_create(name, flags); if (fd < 0) - die_perror("Can't memfd_create for hugetlbfs map"); + die_perror("Can't memfd_create for memory map"); + if (ftruncate(fd, size) < 0) die("Can't ftruncate for mem mapping size %lld", (unsigned long long)size); - addr = mmap(NULL, size, PROT_RW, MAP_PRIVATE, fd, 0); - close(fd); - return addr; + return fd; } /* This function wraps the decision between hugetlbfs map (if requested) or normal mmap */ void *mmap_anon_or_hugetlbfs(struct kvm *kvm, const char *hugetlbfs_path, u64 size) { u64 blk_size = 0; + int fd; /* * We don't /need/ to map guest RAM from hugetlbfs, but we do so @@ -138,9 +139,14 @@ void *mmap_anon_or_hugetlbfs(struct kvm *kvm, const char *hugetlbfs_path, u64 si } kvm->ram_pagesize = blk_size; - return mmap_hugetlbfs(kvm, hugetlbfs_path, size, blk_size); } else { kvm->ram_pagesize = getpagesize(); - return mmap(NULL, size, PROT_RW, MAP_ANON_NORESERVE, -1, 0); } + + fd = memfd_alloc(size, hugetlbfs_path, blk_size); + if (fd < 0) + return MAP_FAILED; + + kvm->ram_fd = fd; + return mmap(NULL, size, PROT_RW, MAP_PRIVATE, kvm->ram_fd, 0); } -- 2.39.0.rc0.267.gcb52ba06e7-goog