The following commit:
368a540e0232 (x86/kvmclock: Remove memblock dependency)
caused SEV guest regression. When SEV is active, we map the shared variables (wall_clock and hv_clock_boot) with C=0 to ensure that both the guest and the hypervisor is able to access the data. To map the variables we use kernel_physical_mapping_init() to split the large pages, but this routine fails to allocate a new page. Before the above commit, kvmclock initialization was called after memory allocator was available but now its called very early in the boot process.
Recently we added a special .data..decrypted section to hold the shared variables. This section is mapped with C=0 very early. Use __decrypted attribute to put the wall_clock and hv_clock_boot in .data..decrypted section so that they are mapped with C=0.
Signed-off-by: Brijesh Singh brijesh.singh@amd.com Fixes: 368a540e0232 ("x86/kvmclock: Remove memblock dependency") Cc: stable@vger.kernel.org Cc: Tom Lendacky thomas.lendacky@amd.com Cc: kvm@vger.kernel.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Borislav Petkov bp@suse.de Cc: "H. Peter Anvin" hpa@zytor.com Cc: linux-kernel@vger.kernel.org Cc: Paolo Bonzini pbonzini@redhat.com Cc: Sean Christopherson sean.j.christopherson@intel.com Cc: kvm@vger.kernel.org Cc: "Radim Krčmář" rkrcmar@redhat.com --- arch/x86/kernel/kvmclock.c | 30 +++++++++++++++++++++++++----- 1 file changed, 25 insertions(+), 5 deletions(-)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 1e67646..08f5f8a 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -28,6 +28,7 @@ #include <linux/sched/clock.h> #include <linux/mm.h> #include <linux/slab.h> +#include <linux/set_memory.h>
#include <asm/hypervisor.h> #include <asm/mem_encrypt.h> @@ -61,8 +62,8 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); (PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info))
static struct pvclock_vsyscall_time_info - hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE); -static struct pvclock_wall_clock wall_clock; + hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __decrypted __aligned(PAGE_SIZE); +static struct pvclock_wall_clock wall_clock __decrypted; static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) @@ -267,10 +268,29 @@ static int kvmclock_setup_percpu(unsigned int cpu) return 0;
/* Use the static page for the first CPUs, allocate otherwise */ - if (cpu < HVC_BOOT_ARRAY_SIZE) + if (cpu < HVC_BOOT_ARRAY_SIZE) { p = &hv_clock_boot[cpu]; - else - p = kzalloc(sizeof(*p), GFP_KERNEL); + } else { + int rc; + unsigned int sz = sizeof(*p); + + if (sev_active()) + sz = PAGE_ALIGN(sz); + + p = kzalloc(sz, GFP_KERNEL); + + /* + * The physical address of per-cpu variable will be shared with + * the hypervisor. Let's clear the C-bit before we assign the + * memory to per_cpu variable. + */ + if (p && sev_active()) { + rc = set_memory_decrypted((unsigned long)p, sz >> PAGE_SHIFT); + if (rc) + return rc; + memset(p, 0, sz); + } + }
per_cpu(hv_clock_per_cpu, cpu) = p; return p ? 0 : -ENOMEM;