[PATCH v6 5/5] x86/kvm: Avoid dynamic allocation of pvclock data when SEV is active

[Brijesh Singh]

Currently, the per-cpu pvclock data is allocated dynamically when
cpu > HVC_BOOT_ARRAY_SIZE. The physical address of this variable is
shared between the guest and the hypervisor hence it must be mapped as
unencrypted (ie. C=0) when SEV is active.

The C-bit works on a page, hence we will be required to perform a
full 4k page allocation to store a single 32-byte pvclock variable. It
will waste fairly sizeable amount of memory since each CPU will be doing
a separate 4k allocation. Let's define a second array for the SEV case to
statically allocate for NR_CPUS and put this array in .data..decrypted
section so that its mapped with C=0 during boot. The .data..decrypted
section has a big chunk of memory that is currently unused. And since
second array will be used only when memory encryption is active hence
free it when encryption is not active.

Signed-off-by: Brijesh Singh <brijesh.singh@xxxxxxx>
Suggested-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Cc: Tom Lendacky <thomas.lendacky@xxxxxxx>
Cc: kvm@xxxxxxxxxxxxxxx
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Cc: kvm@xxxxxxxxxxxxxxx
Cc: "Radim KrÄmÃÅ" <rkrcmar@xxxxxxxxxx>
---
 arch/x86/include/asm/mem_encrypt.h |  4 ++++
 arch/x86/kernel/kvmclock.c         | 14 ++++++++++++++
 arch/x86/kernel/vmlinux.lds.S      |  3 +++
 arch/x86/mm/init.c                 |  3 +++
 arch/x86/mm/mem_encrypt.c          | 10 ++++++++++
 5 files changed, 34 insertions(+)

diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 802b2eb..cc46584 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -48,11 +48,13 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size);
 
 /* Architecture __weak replacement functions */
 void __init mem_encrypt_init(void);
+void __init free_decrypted_mem(void);
 
 bool sme_active(void);
 bool sev_active(void);
 
 #define __decrypted __attribute__((__section__(".data..decrypted")))
+#define __decrypted_aux __attribute__((__section__(".data..decrypted.aux")))
 
 #else	/* !CONFIG_AMD_MEM_ENCRYPT */
 
@@ -80,6 +82,7 @@ static inline int __init
 early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; }
 
 #define __decrypted
+#define __decrypted_aux
 
 #endif	/* CONFIG_AMD_MEM_ENCRYPT */
 
@@ -93,6 +96,7 @@ early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0;
 #define __sme_pa_nodebug(x)	(__pa_nodebug(x) | sme_me_mask)
 
 extern char __start_data_decrypted[], __end_data_decrypted[];
+extern char __start_data_decrypted_aux[];
 
 #endif	/* __ASSEMBLY__ */
 
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 376fd3a..6086b56 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -65,6 +65,15 @@ static struct pvclock_vsyscall_time_info
 static struct pvclock_wall_clock wall_clock __decrypted;
 static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
 
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+/*
+ * The auxiliary array will be used when SEV is active. In non-SEV case,
+ * it will be freed by free_decrypted_mem().
+ */
+static struct pvclock_vsyscall_time_info
+			hv_clock_aux[NR_CPUS] __decrypted_aux;
+#endif
+
 static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
 {
 	return &this_cpu_read(hv_clock_per_cpu)->pvti;
@@ -269,6 +278,11 @@ static int kvmclock_setup_percpu(unsigned int cpu)
 	/* Use the static page for the first CPUs, allocate otherwise */
 	if (cpu < HVC_BOOT_ARRAY_SIZE)
 		p = &hv_clock_boot[cpu];
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	/* Use the static page from auxiliary array instead of allocating it. */
+	else if (sev_active())
+		p = &hv_clock_aux[cpu - HVC_BOOT_ARRAY_SIZE];
+#endif
 	else
 		p = kzalloc(sizeof(*p), GFP_KERNEL);
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 4cb1064..bde287a 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -77,6 +77,9 @@ jiffies_64 = jiffies;
 	. = ALIGN(PMD_SIZE);					\
 	__start_data_decrypted = .;				\
 	*(.data..decrypted);					\
+	. = ALIGN(PAGE_SIZE);					\
+	__start_data_decrypted_aux = .;				\
+	*(.data..decrypted.aux);				\
 	. = ALIGN(PMD_SIZE);					\
 	__end_data_decrypted = .;				\
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 7a8fc26..052b279 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -815,9 +815,12 @@ void free_kernel_image_pages(void *begin, void *end)
 		set_memory_np_noalias(begin_ul, len_pages);
 }
 
+void __weak free_decrypted_mem(void) { }
+
 void __ref free_initmem(void)
 {
 	e820__reallocate_tables();
+	free_decrypted_mem();
 
 	free_kernel_image_pages(&__init_begin, &__init_end);
 }
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index b2de398..9a08c52 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -348,6 +348,16 @@ bool sev_active(void)
 EXPORT_SYMBOL(sev_active);
 
 /* Architecture __weak replacement functions */
+void __init free_decrypted_mem(void)
+{
+	if (mem_encrypt_active())
+		return;
+
+	free_init_pages("unused decrypted",
+			(unsigned long)__start_data_decrypted_aux,
+			(unsigned long)__end_data_decrypted);
+}
+
 void __init mem_encrypt_init(void)
 {
 	if (!sme_me_mask)
-- 
2.7.4