mm: x86: Invoke hypercall when page encryption status is changed

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@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: x86@kernel.org
Cc: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Steve Rutherford <srutherford@google.com>
Reviewed-by: Venu Busireddy <venu.busireddy@oracle.com>
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Reviewed-by: Borislav Petkov <bp@suse.de>
Message-Id: <0a237d5bb08793916c7790a3e653a2cbe7485761.1629726117.git.ashish.kalra@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index da3a1ac82be58a5234325f36e6f52855a7d31bc0..540bf8cb37dbad8b314130c24d0eca2672985467 100644 (file)
--- 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 d9d6b0203ec41744cde38f5316129d872a88c453..66419982023920fa2b050480f09984dd910956b8 100644 (file)
--- 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 43fa081a1adb236daf9c2f4de4e89616285ed40f..872617542bbc0039cf4d2bc327d76d5e9e7fac6b 100644 (file)
--- 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 04cafc057bed4df4e22468095f7637bb57824ce2..1cc20ac9a54ffe8b350873f5cfb13636388ec667 100644 (file)
--- 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 ff08dc4636347c2bcda58803728e891383eb0fb0..455ac487cb9d261d010b55da71248066df8d4873 100644 (file)
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -228,29 +228,76 @@ 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 +332,13 @@ 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 +393,7 @@ 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 ad8a5c586a353a92454484fdbc7b29276a06e15c..4f0cd505f9246ec1241cd84103afa508420db08b 100644 (file)
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -2020,6 +2020,12 @@ 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.
+        */
+       notify_range_enc_status_changed(addr, numpages, enc);
+
        return ret;
 }