From: Brijesh Singh <brijesh.singh@xxxxxxx>
Invoke a hypercall when a memory region is changed from encrypted ->
decrypted and vice versa. Hypervisor needs to know the page encryption
status during the guest migration.
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Joerg Roedel <joro@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxx>
Cc: Tom Lendacky <thomas.lendacky@xxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: kvm@xxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Reviewed-by: Steve Rutherford <srutherford@xxxxxxxxxx>
Reviewed-by: Venu Busireddy <venu.busireddy@xxxxxxxxxx>
Signed-off-by: Brijesh Singh <brijesh.singh@xxxxxxx>
Signed-off-by: Ashish Kalra <ashish.kalra@xxxxxxx>
---
arch/x86/include/asm/paravirt.h | 6 +++
arch/x86/include/asm/paravirt_types.h | 1 +
arch/x86/include/asm/set_memory.h | 1 +
arch/x86/kernel/paravirt.c | 1 +
arch/x86/mm/mem_encrypt.c | 69 +++++++++++++++++++++++----
arch/x86/mm/pat/set_memory.c | 7 +++
6 files changed, 76 insertions(+), 9 deletions(-)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index da3a1ac82be5..540bf8cb37db 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -97,6 +97,12 @@ static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
PVOP_VCALL1(mmu.exit_mmap, mm);
}
+static inline void notify_page_enc_status_changed(unsigned long pfn,
+ int npages, bool enc)
+{
+ PVOP_VCALL3(mmu.notify_page_enc_status_changed, pfn, npages, enc);
+}
+
#ifdef CONFIG_PARAVIRT_XXL
static inline void load_sp0(unsigned long sp0)
{
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index d9d6b0203ec4..664199820239 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -168,6 +168,7 @@ struct pv_mmu_ops {
/* Hook for intercepting the destruction of an mm_struct. */
void (*exit_mmap)(struct mm_struct *mm);
+ void (*notify_page_enc_status_changed)(unsigned long pfn, int npages, bool enc);
#ifdef CONFIG_PARAVIRT_XXL
struct paravirt_callee_save read_cr2;
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 43fa081a1adb..872617542bbc 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -83,6 +83,7 @@ int set_pages_rw(struct page *page, int numpages);
int set_direct_map_invalid_noflush(struct page *page);
int set_direct_map_default_noflush(struct page *page);
bool kernel_page_present(struct page *page);
+void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc);
extern int kernel_set_to_readonly;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 04cafc057bed..1cc20ac9a54f 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -296,6 +296,7 @@ struct paravirt_patch_template pv_ops = {
(void (*)(struct mmu_gather *, void *))tlb_remove_page,
.mmu.exit_mmap = paravirt_nop,
+ .mmu.notify_page_enc_status_changed = paravirt_nop,
#ifdef CONFIG_PARAVIRT_XXL
.mmu.read_cr2 = __PV_IS_CALLEE_SAVE(native_read_cr2),
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index ff08dc463634..6b12620376a4 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -228,29 +228,77 @@ void __init sev_setup_arch(void)
swiotlb_adjust_size(size);
}
-static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
+static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot)
{
- pgprot_t old_prot, new_prot;
- unsigned long pfn, pa, size;
- pte_t new_pte;
+ unsigned long pfn = 0;
+ pgprot_t prot;
switch (level) {
case PG_LEVEL_4K:
pfn = pte_pfn(*kpte);
- old_prot = pte_pgprot(*kpte);
+ prot = pte_pgprot(*kpte);
break;
case PG_LEVEL_2M:
pfn = pmd_pfn(*(pmd_t *)kpte);
- old_prot = pmd_pgprot(*(pmd_t *)kpte);
+ prot = pmd_pgprot(*(pmd_t *)kpte);
break;
case PG_LEVEL_1G:
pfn = pud_pfn(*(pud_t *)kpte);
- old_prot = pud_pgprot(*(pud_t *)kpte);
+ prot = pud_pgprot(*(pud_t *)kpte);
break;
default:
- return;
+ WARN_ONCE(1, "Invalid level for kpte\n");
+ return 0;
}
+ if (ret_prot)
+ *ret_prot = prot;
+
+ return pfn;
+}
+
+void notify_range_enc_status_changed(unsigned long vaddr, int npages,
+ bool enc)
+{
+#ifdef CONFIG_PARAVIRT
+ unsigned long sz = npages << PAGE_SHIFT;
+ unsigned long vaddr_end = vaddr + sz;
+
+ while (vaddr < vaddr_end) {
+ int psize, pmask, level;
+ unsigned long pfn;
+ pte_t *kpte;
+
+ kpte = lookup_address(vaddr, &level);
+ if (!kpte || pte_none(*kpte)) {
+ WARN_ONCE(1, "kpte lookup for vaddr\n");
+ return;
+ }
+
+ pfn = pg_level_to_pfn(level, kpte, NULL);
+ if (!pfn)
+ continue;
+
+ psize = page_level_size(level);
+ pmask = page_level_mask(level);
+
+ notify_page_enc_status_changed(pfn, psize >> PAGE_SHIFT, enc);
+
+ vaddr = (vaddr & pmask) + psize;
+ }
+#endif
+}
+
+static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
+{
+ pgprot_t old_prot, new_prot;
+ unsigned long pfn, pa, size;
+ pte_t new_pte;
+
+ pfn = pg_level_to_pfn(level, kpte, &old_prot);
+ if (!pfn)
+ return;
+
new_prot = old_prot;
if (enc)
pgprot_val(new_prot) |= _PAGE_ENC;
@@ -285,12 +333,13 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
static int __init early_set_memory_enc_dec(unsigned long vaddr,
unsigned long size, bool enc)
{
- unsigned long vaddr_end, vaddr_next;
+ unsigned long vaddr_end, vaddr_next, start;
unsigned long psize, pmask;
int split_page_size_mask;
int level, ret;
pte_t *kpte;
+ start = vaddr;
vaddr_next = vaddr;
vaddr_end = vaddr + size;
@@ -345,6 +394,8 @@ static int __init early_set_memory_enc_dec(unsigned long vaddr,
ret = 0;
+ notify_range_enc_status_changed(start, PAGE_ALIGN(size) >> PAGE_SHIFT,
+ enc);
out:
__flush_tlb_all();
return ret;
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 156cd235659f..9729cb0d99e3 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -2020,6 +2020,13 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
*/
cpa_flush(&cpa, 0);
+ /*
+ * Notify hypervisor that a given memory range is mapped encrypted
+ * or decrypted. The hypervisor will use this information during the
+ * VM migration.
+ */
+ notify_range_enc_status_changed(addr, numpages, enc);
+
return ret;
}
--
2.17.1
