- Add shared confidential computing code which will be used by both

vendors instead of proliferating home-grown solutions for technologies
 which are pretty similar
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmI4kiQACgkQEsHwGGHe
 VUojvA//QD5VxsqPq+RAQWAFiWGHCpFed2szc2Q5eAZj6CEmXcqBOdTqaoHpJpVl
 L1uvB6oLq8WTOea0V3xGu1kfiLRuq1fo0mqZeTxe3iZ3kUk/SU0wGfTLDECB58mI
 P5A+CZFiAk4XJ/kRqJWNxmd5kIDjhlCx4ysVbPl1vm/qfS6FEGb5HUr317kbOYwK
 zw5cEajnYu2KA6bI8nGuy30vmvn97gpy98vCiCzKrcBPggO8WHiJ+kqD72BhP5em
 z7mh4aFrAPVbIMqd/Xb5La3zvP7Vii4Tz9mSUsKy/Ige+ghFZQ18LPk2yANvmWeN
 hIFDqSsESR2go0tKvSrzPln8h93hKx/TPbiF9jVMISBZFdWCGQvzCrYDHqzHFQJ1
 zHw0lxdFQimfhs5YlEumZCqq2Dc7w3OGCVfP22+t7pNhnixPT3Dlie0Ya6z/aXV3
 VNcqckDDZLijQlf0iPhbw2fBs9ErTcB3OXHKmX78Zxb4hP4WJx8QK4lMPzFkPd9H
 bTEquYQWIPsjdRTlMl50nCpNHtAzo56H01G6ZPPx/5Y7Lt38UXJERfdqBhQjNF6F
 ILPMrOn/BHU9snlqSCh7SxhRiRdafThIJHsi5zQrDC4rPvlwi5kinIzGnPyOuDbO
 qwwnPOzx855/Zw0swKrQRXaxU7lwGKo529yKZWt7r8WB12tSOao=
 =zWVD
 -----END PGP SIGNATURE-----

Merge tag 'x86_cc_for_v5.18_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 confidential computing updates from Borislav Petkov:

 - Add shared confidential computing code which will be used by both
   vendors instead of proliferating home-grown solutions for
   technologies (SEV/SNP and TDX) which are pretty similar

* tag 'x86_cc_for_v5.18_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm/cpa: Generalize __set_memory_enc_pgtable()
  x86/coco: Add API to handle encryption mask
  x86/coco: Explicitly declare type of confidential computing platform
  x86/cc: Move arch/x86/{kernel/cc_platform.c => coco/core.c}

arch/x86/Kbuild

@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_ARCH_HAS_CC_PLATFORM) += coco/
+
 obj-y += entry/
 
 obj-$(CONFIG_PERF_EVENTS) += events/

arch/x86/coco/Makefile

@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS_REMOVE_core.o	= -pg
+KASAN_SANITIZE_core.o	:= n
+CFLAGS_core.o		+= -fno-stack-protector
+
+obj-y += core.o

arch/x86/coco/core.c

@@ -9,18 +9,16 @@
 
 #include <linux/export.h>
 #include <linux/cc_platform.h>
-#include <linux/mem_encrypt.h>
 
-#include <asm/mshyperv.h>
+#include <asm/coco.h>
 #include <asm/processor.h>
 
-static bool __maybe_unused intel_cc_platform_has(enum cc_attr attr)
+static enum cc_vendor vendor __ro_after_init;
+static u64 cc_mask __ro_after_init;
+
+static bool intel_cc_platform_has(enum cc_attr attr)
 {
-#ifdef CONFIG_INTEL_TDX_GUEST
 	return false;
-#else
-	return false;
-#endif
 }
 
 /*
@@ -74,12 +72,46 @@ static bool hyperv_cc_platform_has(enum cc_attr attr)
 
 bool cc_platform_has(enum cc_attr attr)
 {
-	if (sme_me_mask)
+	switch (vendor) {
+	case CC_VENDOR_AMD:
 		return amd_cc_platform_has(attr);
-
-	if (hv_is_isolation_supported())
+	case CC_VENDOR_INTEL:
+		return intel_cc_platform_has(attr);
+	case CC_VENDOR_HYPERV:
 		return hyperv_cc_platform_has(attr);
-
-	return false;
+	default:
+		return false;
+	}
 }
 EXPORT_SYMBOL_GPL(cc_platform_has);
+
+u64 cc_mkenc(u64 val)
+{
+	switch (vendor) {
+	case CC_VENDOR_AMD:
+		return val | cc_mask;
+	default:
+		return val;
+	}
+}
+
+u64 cc_mkdec(u64 val)
+{
+	switch (vendor) {
+	case CC_VENDOR_AMD:
+		return val & ~cc_mask;
+	default:
+		return val;
+	}
+}
+EXPORT_SYMBOL_GPL(cc_mkdec);
+
+__init void cc_set_vendor(enum cc_vendor v)
+{
+	vendor = v;
+}
+
+__init void cc_set_mask(u64 mask)
+{
+	cc_mask = mask;
+}

arch/x86/include/asm/coco.h

@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_COCO_H
+#define _ASM_X86_COCO_H
+
+#include <asm/types.h>
+
+enum cc_vendor {
+	CC_VENDOR_NONE,
+	CC_VENDOR_AMD,
+	CC_VENDOR_HYPERV,
+	CC_VENDOR_INTEL,
+};
+
+void cc_set_vendor(enum cc_vendor v);
+void cc_set_mask(u64 mask);
+
+#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
+u64 cc_mkenc(u64 val);
+u64 cc_mkdec(u64 val);
+#else
+static inline u64 cc_mkenc(u64 val)
+{
+	return val;
+}
+
+static inline u64 cc_mkdec(u64 val)
+{
+	return val;
+}
+#endif
+
+#endif /* _ASM_X86_COCO_H */

arch/x86/include/asm/pgtable.h

@@ -15,17 +15,12 @@
 		     cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS)))	\
 	 : (prot))
 
-/*
- * Macros to add or remove encryption attribute
- */
-#define pgprot_encrypted(prot)	__pgprot(__sme_set(pgprot_val(prot)))
-#define pgprot_decrypted(prot)	__pgprot(__sme_clr(pgprot_val(prot)))
-
 #ifndef __ASSEMBLY__
 #include <linux/spinlock.h>
 #include <asm/x86_init.h>
 #include <asm/pkru.h>
 #include <asm/fpu/api.h>
+#include <asm/coco.h>
 #include <asm-generic/pgtable_uffd.h>
 #include <linux/page_table_check.h>
 
@@ -38,6 +33,12 @@ void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm,
 void ptdump_walk_pgd_level_checkwx(void);
 void ptdump_walk_user_pgd_level_checkwx(void);
 
+/*
+ * Macros to add or remove encryption attribute
+ */
+#define pgprot_encrypted(prot)	__pgprot(cc_mkenc(pgprot_val(prot)))
+#define pgprot_decrypted(prot)	__pgprot(cc_mkdec(pgprot_val(prot)))
+
 #ifdef CONFIG_DEBUG_WX
 #define debug_checkwx()		ptdump_walk_pgd_level_checkwx()
 #define debug_checkwx_user()	ptdump_walk_user_pgd_level_checkwx()

arch/x86/include/asm/set_memory.h

@@ -84,7 +84,6 @@ 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;
 

arch/x86/include/asm/x86_init.h

@@ -141,6 +141,21 @@ struct x86_init_acpi {
 	void (*reduced_hw_early_init)(void);
 };
 
+/**
+ * struct x86_guest - Functions used by misc guest incarnations like SEV, TDX, etc.
+ *
+ * @enc_status_change_prepare	Notify HV before the encryption status of a range is changed
+ * @enc_status_change_finish	Notify HV after the encryption status of a range is changed
+ * @enc_tlb_flush_required	Returns true if a TLB flush is needed before changing page encryption status
+ * @enc_cache_flush_required	Returns true if a cache flush is needed before changing page encryption status
+ */
+struct x86_guest {
+	void (*enc_status_change_prepare)(unsigned long vaddr, int npages, bool enc);
+	bool (*enc_status_change_finish)(unsigned long vaddr, int npages, bool enc);
+	bool (*enc_tlb_flush_required)(bool enc);
+	bool (*enc_cache_flush_required)(void);
+};
+
 /**
  * struct x86_init_ops - functions for platform specific setup
  *
@@ -287,6 +302,7 @@ struct x86_platform_ops {
 	struct x86_legacy_features legacy;
 	void (*set_legacy_features)(void);
 	struct x86_hyper_runtime hyper;
+	struct x86_guest guest;
 };
 
 struct x86_apic_ops {

arch/x86/kernel/Makefile

@@ -21,7 +21,6 @@ CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 CFLAGS_REMOVE_head64.o = -pg
 CFLAGS_REMOVE_sev.o = -pg
-CFLAGS_REMOVE_cc_platform.o = -pg
 endif
 
 KASAN_SANITIZE_head$(BITS).o				:= n
@@ -30,7 +29,6 @@ KASAN_SANITIZE_dumpstack_$(BITS).o			:= n
 KASAN_SANITIZE_stacktrace.o				:= n
 KASAN_SANITIZE_paravirt.o				:= n
 KASAN_SANITIZE_sev.o					:= n
-KASAN_SANITIZE_cc_platform.o				:= n
 
 # With some compiler versions the generated code results in boot hangs, caused
 # by several compilation units. To be safe, disable all instrumentation.
@@ -49,7 +47,6 @@ endif
 KCOV_INSTRUMENT		:= n
 
 CFLAGS_head$(BITS).o	+= -fno-stack-protector
-CFLAGS_cc_platform.o	+= -fno-stack-protector
 
 CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace
 
@@ -151,8 +148,6 @@ obj-$(CONFIG_UNWINDER_GUESS)		+= unwind_guess.o
 
 obj-$(CONFIG_AMD_MEM_ENCRYPT)		+= sev.o
 
-obj-$(CONFIG_ARCH_HAS_CC_PLATFORM)	+= cc_platform.o
-
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)

arch/x86/kernel/cpu/mshyperv.c

@@ -33,6 +33,7 @@
 #include <asm/nmi.h>
 #include <clocksource/hyperv_timer.h>
 #include <asm/numa.h>
+#include <asm/coco.h>
 
 /* Is Linux running as the root partition? */
 bool hv_root_partition;
@@ -344,6 +345,11 @@ static void __init ms_hyperv_init_platform(void)
 		 */
 		swiotlb_force = SWIOTLB_FORCE;
 #endif
+		/* Isolation VMs are unenlightened SEV-based VMs, thus this check: */
+		if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
+			if (hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE)
+				cc_set_vendor(CC_VENDOR_HYPERV);
+		}
 	}
 
 	if (hv_max_functions_eax >= HYPERV_CPUID_NESTED_FEATURES) {

arch/x86/kernel/x86_init.c

@@ -129,6 +129,11 @@ struct x86_cpuinit_ops x86_cpuinit = {
 
 static void default_nmi_init(void) { };
 
+static void enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { }
+static bool enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return false; }
+static bool enc_tlb_flush_required_noop(bool enc) { return false; }
+static bool enc_cache_flush_required_noop(void) { return false; }
+
 struct x86_platform_ops x86_platform __ro_after_init = {
 	.calibrate_cpu			= native_calibrate_cpu_early,
 	.calibrate_tsc			= native_calibrate_tsc,
@@ -138,9 +143,16 @@ struct x86_platform_ops x86_platform __ro_after_init = {
 	.is_untracked_pat_range		= is_ISA_range,
 	.nmi_init			= default_nmi_init,
 	.get_nmi_reason			= default_get_nmi_reason,
-	.save_sched_clock_state 	= tsc_save_sched_clock_state,
-	.restore_sched_clock_state 	= tsc_restore_sched_clock_state,
+	.save_sched_clock_state		= tsc_save_sched_clock_state,
+	.restore_sched_clock_state	= tsc_restore_sched_clock_state,
 	.hyper.pin_vcpu			= x86_op_int_noop,
+
+	.guest = {
+		.enc_status_change_prepare = enc_status_change_prepare_noop,
+		.enc_status_change_finish  = enc_status_change_finish_noop,
+		.enc_tlb_flush_required	   = enc_tlb_flush_required_noop,
+		.enc_cache_flush_required  = enc_cache_flush_required_noop,
+	},
 };
 
 EXPORT_SYMBOL_GPL(x86_platform);

arch/x86/mm/mem_encrypt_amd.c

@@ -177,25 +177,6 @@ void __init sme_map_bootdata(char *real_mode_data)
 	__sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, true);
 }
 
-void __init sme_early_init(void)
-{
-	unsigned int i;
-
-	if (!sme_me_mask)
-		return;
-
-	early_pmd_flags = __sme_set(early_pmd_flags);
-
-	__supported_pte_mask = __sme_set(__supported_pte_mask);
-
-	/* Update the protection map with memory encryption mask */
-	for (i = 0; i < ARRAY_SIZE(protection_map); i++)
-		protection_map[i] = pgprot_encrypted(protection_map[i]);
-
-	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
-		swiotlb_force = SWIOTLB_FORCE;
-}
-
 void __init sev_setup_arch(void)
 {
 	phys_addr_t total_mem = memblock_phys_mem_size();
@@ -256,7 +237,17 @@ static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot)
 	return pfn;
 }
 
-void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc)
+static bool amd_enc_tlb_flush_required(bool enc)
+{
+	return true;
+}
+
+static bool amd_enc_cache_flush_required(void)
+{
+	return !cpu_feature_enabled(X86_FEATURE_SME_COHERENT);
+}
+
+static void enc_dec_hypercall(unsigned long vaddr, int npages, bool enc)
 {
 #ifdef CONFIG_PARAVIRT
 	unsigned long sz = npages << PAGE_SHIFT;
@@ -287,6 +278,19 @@ void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc)
 #endif
 }
 
+static void amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc)
+{
+}
+
+/* Return true unconditionally: return value doesn't matter for the SEV side */
+static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc)
+{
+	if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+		enc_dec_hypercall(vaddr, npages, enc);
+
+	return true;
+}
+
 static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
 {
 	pgprot_t old_prot, new_prot;
@@ -392,7 +396,7 @@ 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);
+	early_set_mem_enc_dec_hypercall(start, PAGE_ALIGN(size) >> PAGE_SHIFT, enc);
 out:
 	__flush_tlb_all();
 	return ret;
@@ -410,7 +414,31 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size)
 
 void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc)
 {
-	notify_range_enc_status_changed(vaddr, npages, enc);
+	enc_dec_hypercall(vaddr, npages, enc);
+}
+
+void __init sme_early_init(void)
+{
+	unsigned int i;
+
+	if (!sme_me_mask)
+		return;
+
+	early_pmd_flags = __sme_set(early_pmd_flags);
+
+	__supported_pte_mask = __sme_set(__supported_pte_mask);
+
+	/* Update the protection map with memory encryption mask */
+	for (i = 0; i < ARRAY_SIZE(protection_map); i++)
+		protection_map[i] = pgprot_encrypted(protection_map[i]);
+
+	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+		swiotlb_force = SWIOTLB_FORCE;
+
+	x86_platform.guest.enc_status_change_prepare = amd_enc_status_change_prepare;
+	x86_platform.guest.enc_status_change_finish  = amd_enc_status_change_finish;
+	x86_platform.guest.enc_tlb_flush_required    = amd_enc_tlb_flush_required;
+	x86_platform.guest.enc_cache_flush_required  = amd_enc_cache_flush_required;
 }
 
 void __init mem_encrypt_free_decrypted_mem(void)

arch/x86/mm/mem_encrypt_identity.c

@@ -44,6 +44,7 @@
 #include <asm/setup.h>
 #include <asm/sections.h>
 #include <asm/cmdline.h>
+#include <asm/coco.h>
 
 #include "mm_internal.h"
 
@@ -565,8 +566,7 @@ void __init sme_enable(struct boot_params *bp)
 	} else {
 		/* SEV state cannot be controlled by a command line option */
 		sme_me_mask = me_mask;
-		physical_mask &= ~sme_me_mask;
-		return;
+		goto out;
 	}
 
 	/*
@@ -600,6 +600,10 @@ void __init sme_enable(struct boot_params *bp)
 		sme_me_mask = 0;
 	else
 		sme_me_mask = active_by_default ? me_mask : 0;
-
-	physical_mask &= ~sme_me_mask;
+out:
+	if (sme_me_mask) {
+		physical_mask &= ~sme_me_mask;
+		cc_set_vendor(CC_VENDOR_AMD);
+		cc_set_mask(sme_me_mask);
+	}
 }

arch/x86/mm/pat/set_memory.c

@@ -1989,6 +1989,7 @@ int set_memory_global(unsigned long addr, int numpages)
  */
 static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
 {
+	pgprot_t empty = __pgprot(0);
 	struct cpa_data cpa;
 	int ret;
 
@@ -1999,18 +2000,20 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
 	memset(&cpa, 0, sizeof(cpa));
 	cpa.vaddr = &addr;
 	cpa.numpages = numpages;
-	cpa.mask_set = enc ? __pgprot(_PAGE_ENC) : __pgprot(0);
-	cpa.mask_clr = enc ? __pgprot(0) : __pgprot(_PAGE_ENC);
+	cpa.mask_set = enc ? pgprot_encrypted(empty) : pgprot_decrypted(empty);
+	cpa.mask_clr = enc ? pgprot_decrypted(empty) : pgprot_encrypted(empty);
 	cpa.pgd = init_mm.pgd;
 
 	/* Must avoid aliasing mappings in the highmem code */
 	kmap_flush_unused();
 	vm_unmap_aliases();
 
-	/*
-	 * Before changing the encryption attribute, we need to flush caches.
-	 */
-	cpa_flush(&cpa, !this_cpu_has(X86_FEATURE_SME_COHERENT));
+	/* Flush the caches as needed before changing the encryption attribute. */
+	if (x86_platform.guest.enc_tlb_flush_required(enc))
+		cpa_flush(&cpa, x86_platform.guest.enc_cache_flush_required());
+
+	/* Notify hypervisor that we are about to set/clr encryption attribute. */
+	x86_platform.guest.enc_status_change_prepare(addr, numpages, enc);
 
 	ret = __change_page_attr_set_clr(&cpa, 1);
 
@@ -2023,11 +2026,11 @@ static int __set_memory_enc_pgtable(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);
+	/* Notify hypervisor that we have successfully set/clr encryption attribute. */
+	if (!ret) {
+		if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc))
+			ret = -EIO;
+	}
 
 	return ret;
 }