Skip to content

L
linux
Commit 01d5e787 authored by Linus Torvalds's avatar Linus Torvalds
Browse files
Options

Merge tag 'x86_sev_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull x86 SEV updates from Borislav Petkov:
 "The accumulated pile of x86/sev generalizations and cleanups:

   - Share the SEV string unrolling logic with TDX as TDX guests need it
     too

   - Cleanups and generalzation of code shared by SEV and TDX"

* tag 'x86_sev_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/sev: Move common memory encryption code to mem_encrypt.c
  x86/sev: Rename mem_encrypt.c to mem_encrypt_amd.c
  x86/sev: Use CC_ATTR attribute to generalize string I/O unroll
  x86/sev: Remove do_early_exception() forward declarations
  x86/head64: Carve out the guest encryption postprocessing into a helper
  x86/sev: Get rid of excessive use of defines
  x86/sev: Shorten GHCB terminate macro names
parents cd36722d 20f07a04
Hide whitespace changes
Inline Side-by-side
Showing with 545 additions and 524 deletions
arch/x86/Kconfig
View file @ 01d5e787
......@@ -1523,16 +1523,20 @@ config X86_CPA_STATISTICS
helps to determine the effectiveness of preserving large and huge
page mappings when mapping protections are changed.
config X86_MEM_ENCRYPT
select ARCH_HAS_FORCE_DMA_UNENCRYPTED
select DYNAMIC_PHYSICAL_MASK
select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
def_bool n
config AMD_MEM_ENCRYPT
bool "AMD Secure Memory Encryption (SME) support"
depends on X86_64 && CPU_SUP_AMD
select DMA_COHERENT_POOL
select DYNAMIC_PHYSICAL_MASK
select ARCH_USE_MEMREMAP_PROT
select ARCH_HAS_FORCE_DMA_UNENCRYPTED
select INSTRUCTION_DECODER
select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
select ARCH_HAS_CC_PLATFORM
select X86_MEM_ENCRYPT
help
Say yes to enable support for the encryption of system memory.
This requires an AMD processor that supports Secure Memory
......
arch/x86/boot/compressed/sev.c
View file @ 01d5e787
......@@ -122,7 +122,7 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
static bool early_setup_sev_es(void)
{
if (!sev_es_negotiate_protocol())
sev_es_terminate(GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED);
sev_es_terminate(GHCB_SEV_ES_PROT_UNSUPPORTED);
if (set_page_decrypted((unsigned long)&boot_ghcb_page))
return false;
......@@ -175,7 +175,7 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
enum es_result result;
if (!boot_ghcb && !early_setup_sev_es())
sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
vc_ghcb_invalidate(boot_ghcb);
result = vc_init_em_ctxt(&ctxt, regs, exit_code);
......@@ -202,5 +202,5 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
if (result == ES_OK)
vc_finish_insn(&ctxt);
else if (result != ES_RETRY)
sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
}
arch/x86/include/asm/io.h
View file @ 01d5e787
......@@ -40,6 +40,7 @@
#include <linux/string.h>
#include <linux/compiler.h>
#include <linux/cc_platform.h>
#include <asm/page.h>
#include <asm/early_ioremap.h>
#include <asm/pgtable_types.h>
......@@ -256,21 +257,6 @@ static inline void slow_down_io(void)
#endif
#ifdef CONFIG_AMD_MEM_ENCRYPT
#include <linux/jump_label.h>
extern struct static_key_false sev_enable_key;
static inline bool sev_key_active(void)
{
return static_branch_unlikely(&sev_enable_key);
}
#else /* !CONFIG_AMD_MEM_ENCRYPT */
static inline bool sev_key_active(void) { return false; }
#endif /* CONFIG_AMD_MEM_ENCRYPT */
#define BUILDIO(bwl, bw, type) \
static inline void out##bwl(unsigned type value, int port) \
{ \
......@@ -301,7 +287,7 @@ static inline unsigned type in##bwl##_p(int port) \
\
static inline void outs##bwl(int port, const void *addr, unsigned long count) \
{ \
if (sev_key_active()) { \
if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \
unsigned type *value = (unsigned type *)addr; \
while (count) { \
out##bwl(*value, port); \
......@@ -317,7 +303,7 @@ static inline void outs##bwl(int port, const void *addr, unsigned long count) \
\
static inline void ins##bwl(int port, void *addr, unsigned long count) \
{ \
if (sev_key_active()) { \
if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \
unsigned type *value = (unsigned type *)addr; \
while (count) { \
*value = in##bwl(port); \
......
arch/x86/include/asm/sev-common.h
View file @ 01d5e787
......@@ -18,20 +18,19 @@
/* SEV Information Request/Response */
#define GHCB_MSR_SEV_INFO_RESP 0x001
#define GHCB_MSR_SEV_INFO_REQ 0x002
#define GHCB_MSR_VER_MAX_POS 48
#define GHCB_MSR_VER_MAX_MASK 0xffff
#define GHCB_MSR_VER_MIN_POS 32
#define GHCB_MSR_VER_MIN_MASK 0xffff
#define GHCB_MSR_CBIT_POS 24
#define GHCB_MSR_CBIT_MASK 0xff
#define GHCB_MSR_SEV_INFO(_max, _min, _cbit) \
((((_max) & GHCB_MSR_VER_MAX_MASK) << GHCB_MSR_VER_MAX_POS) | \
(((_min) & GHCB_MSR_VER_MIN_MASK) << GHCB_MSR_VER_MIN_POS) | \
(((_cbit) & GHCB_MSR_CBIT_MASK) << GHCB_MSR_CBIT_POS) | \
#define GHCB_MSR_SEV_INFO(_max, _min, _cbit) \
/* GHCBData[63:48] */ \
((((_max) & 0xffff) << 48) | \
/* GHCBData[47:32] */ \
(((_min) & 0xffff) << 32) | \
/* GHCBData[31:24] */ \
(((_cbit) & 0xff) << 24) | \
GHCB_MSR_SEV_INFO_RESP)
#define GHCB_MSR_INFO(v) ((v) & 0xfffUL)
#define GHCB_MSR_PROTO_MAX(v) (((v) >> GHCB_MSR_VER_MAX_POS) & GHCB_MSR_VER_MAX_MASK)
#define GHCB_MSR_PROTO_MIN(v) (((v) >> GHCB_MSR_VER_MIN_POS) & GHCB_MSR_VER_MIN_MASK)
#define GHCB_MSR_PROTO_MAX(v) (((v) >> 48) & 0xffff)
#define GHCB_MSR_PROTO_MIN(v) (((v) >> 32) & 0xffff)
/* CPUID Request/Response */
#define GHCB_MSR_CPUID_REQ 0x004
......@@ -46,30 +45,36 @@
#define GHCB_CPUID_REQ_EBX 1
#define GHCB_CPUID_REQ_ECX 2
#define GHCB_CPUID_REQ_EDX 3
#define GHCB_CPUID_REQ(fn, reg) \
(GHCB_MSR_CPUID_REQ | \
(((unsigned long)reg & GHCB_MSR_CPUID_REG_MASK) << GHCB_MSR_CPUID_REG_POS) | \
(((unsigned long)fn) << GHCB_MSR_CPUID_FUNC_POS))
#define GHCB_CPUID_REQ(fn, reg) \
/* GHCBData[11:0] */ \
(GHCB_MSR_CPUID_REQ | \
/* GHCBData[31:12] */ \
(((unsigned long)(reg) & 0x3) << 30) | \
/* GHCBData[63:32] */ \
(((unsigned long)fn) << 32))
/* AP Reset Hold */
#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006
#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007
#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006
#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007
/* GHCB Hypervisor Feature Request/Response */
#define GHCB_MSR_HV_FT_REQ 0x080
#define GHCB_MSR_HV_FT_RESP 0x081
#define GHCB_MSR_HV_FT_REQ 0x080
#define GHCB_MSR_HV_FT_RESP 0x081
#define GHCB_MSR_TERM_REQ 0x100
#define GHCB_MSR_TERM_REASON_SET_POS 12
#define GHCB_MSR_TERM_REASON_SET_MASK 0xf
#define GHCB_MSR_TERM_REASON_POS 16
#define GHCB_MSR_TERM_REASON_MASK 0xff
#define GHCB_SEV_TERM_REASON(reason_set, reason_val) \
(((((u64)reason_set) & GHCB_MSR_TERM_REASON_SET_MASK) << GHCB_MSR_TERM_REASON_SET_POS) | \
((((u64)reason_val) & GHCB_MSR_TERM_REASON_MASK) << GHCB_MSR_TERM_REASON_POS))
#define GHCB_SEV_ES_REASON_GENERAL_REQUEST 0
#define GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED 1
#define GHCB_SEV_TERM_REASON(reason_set, reason_val) \
/* GHCBData[15:12] */ \
(((((u64)reason_set) & 0xf) << 12) | \
/* GHCBData[23:16] */ \
((((u64)reason_val) & 0xff) << 16))
#define GHCB_SEV_ES_GEN_REQ 0
#define GHCB_SEV_ES_PROT_UNSUPPORTED 1
#define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK)
......
arch/x86/kernel/cc_platform.c
View file @ 01d5e787
......@@ -50,6 +50,14 @@ static bool amd_cc_platform_has(enum cc_attr attr)
case CC_ATTR_GUEST_STATE_ENCRYPT:
return sev_status & MSR_AMD64_SEV_ES_ENABLED;
/*
* With SEV, the rep string I/O instructions need to be unrolled
* but SEV-ES supports them through the #VC handler.
*/
case CC_ATTR_GUEST_UNROLL_STRING_IO:
return (sev_status & MSR_AMD64_SEV_ENABLED) &&
!(sev_status & MSR_AMD64_SEV_ES_ENABLED);
default:
return false;
}
......
arch/x86/kernel/head64.c
View file @ 01d5e787
......@@ -126,6 +126,36 @@ static bool __head check_la57_support(unsigned long physaddr)
}
#endif
static unsigned long sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd)
{
unsigned long vaddr, vaddr_end;
int i;
/* Encrypt the kernel and related (if SME is active) */
sme_encrypt_kernel(bp);
/*
* Clear the memory encryption mask from the .bss..decrypted section.
* The bss section will be memset to zero later in the initialization so
* there is no need to zero it after changing the memory encryption
* attribute.
*/
if (sme_get_me_mask()) {
vaddr = (unsigned long)__start_bss_decrypted;
vaddr_end = (unsigned long)__end_bss_decrypted;
for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
i = pmd_index(vaddr);
pmd[i] -= sme_get_me_mask();
}
}
/*
* Return the SME encryption mask (if SME is active) to be used as a
* modifier for the initial pgdir entry programmed into CR3.
*/
return sme_get_me_mask();
}
/* Code in __startup_64() can be relocated during execution, but the compiler
* doesn't have to generate PC-relative relocations when accessing globals from
* that function. Clang actually does not generate them, which leads to
......@@ -135,7 +165,6 @@ static bool __head check_la57_support(unsigned long physaddr)
unsigned long __head __startup_64(unsigned long physaddr,
struct boot_params *bp)
{
unsigned long vaddr, vaddr_end;
unsigned long load_delta, *p;
unsigned long pgtable_flags;
pgdval_t *pgd;
......@@ -276,34 +305,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
*/
*fixup_long(&phys_base, physaddr) += load_delta - sme_get_me_mask();
/* Encrypt the kernel and related (if SME is active) */
sme_encrypt_kernel(bp);
/*
* Clear the memory encryption mask from the .bss..decrypted section.
* The bss section will be memset to zero later in the initialization so
* there is no need to zero it after changing the memory encryption
* attribute.
*
* This is early code, use an open coded check for SME instead of
* using cc_platform_has(). This eliminates worries about removing
* instrumentation or checking boot_cpu_data in the cc_platform_has()
* function.
*/
if (sme_get_me_mask()) {
vaddr = (unsigned long)__start_bss_decrypted;
vaddr_end = (unsigned long)__end_bss_decrypted;
for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
i = pmd_index(vaddr);
pmd[i] -= sme_get_me_mask();
}
}
/*
* Return the SME encryption mask (if SME is active) to be used as a
* modifier for the initial pgdir entry programmed into CR3.
*/
return sme_get_me_mask();
return sme_postprocess_startup(bp, pmd);
}
unsigned long __startup_secondary_64(void)
......
arch/x86/kernel/sev-shared.c
View file @ 01d5e787
......@@ -221,7 +221,7 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
fail:
/* Terminate the guest */
sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
}
static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
......
arch/x86/kernel/sev.c
View file @ 01d5e787
......@@ -26,6 +26,7 @@
#include <asm/fpu/xcr.h>
#include <asm/processor.h>
#include <asm/realmode.h>
#include <asm/setup.h>
#include <asm/traps.h>
#include <asm/svm.h>
#include <asm/smp.h>
......@@ -86,9 +87,6 @@ struct ghcb_state {
static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
DEFINE_STATIC_KEY_FALSE(sev_es_enable_key);
/* Needed in vc_early_forward_exception */
void do_early_exception(struct pt_regs *regs, int trapnr);
static __always_inline bool on_vc_stack(struct pt_regs *regs)
{
unsigned long sp = regs->sp;
......@@ -209,9 +207,6 @@ static noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
return ghcb;
}
/* Needed in vc_early_forward_exception */
void do_early_exception(struct pt_regs *regs, int trapnr);
static inline u64 sev_es_rd_ghcb_msr(void)
{
return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
......@@ -1432,7 +1427,7 @@ DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
show_regs(regs);
/* Ask hypervisor to sev_es_terminate */
sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
/* If that fails and we get here - just panic */
panic("Returned from Terminate-Request to Hypervisor\n");
......@@ -1480,7 +1475,7 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
/* Do initial setup or terminate the guest */
if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb()))
sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
vc_ghcb_invalidate(boot_ghcb);
......
arch/x86/mm/Makefile
View file @ 01d5e787
......@@ -2,9 +2,11 @@
# Kernel does not boot with instrumentation of tlb.c and mem_encrypt*.c
KCOV_INSTRUMENT_tlb.o := n
KCOV_INSTRUMENT_mem_encrypt.o := n
KCOV_INSTRUMENT_mem_encrypt_amd.o := n
KCOV_INSTRUMENT_mem_encrypt_identity.o := n
KASAN_SANITIZE_mem_encrypt.o := n
KASAN_SANITIZE_mem_encrypt_amd.o := n
KASAN_SANITIZE_mem_encrypt_identity.o := n
# Disable KCSAN entirely, because otherwise we get warnings that some functions
......@@ -13,6 +15,7 @@ KCSAN_SANITIZE := n
ifdef CONFIG_FUNCTION_TRACER
CFLAGS_REMOVE_mem_encrypt.o = -pg
CFLAGS_REMOVE_mem_encrypt_amd.o = -pg
CFLAGS_REMOVE_mem_encrypt_identity.o = -pg
endif
......@@ -52,6 +55,8 @@ obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o
obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o
obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt.o
obj-$(CONFIG_X86_MEM_ENCRYPT) += mem_encrypt.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_amd.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_identity.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_boot.o
arch/x86/mm/mem_encrypt.c
View file @ 01d5e787
// SPDX-License-Identifier: GPL-2.0-only
/*
* AMD Memory Encryption Support
* Memory Encryption Support Common Code
*
* Copyright (C) 2016 Advanced Micro Devices, Inc.
*
* Author: Tom Lendacky <thomas.lendacky@amd.com>
*/
#define DISABLE_BRANCH_PROFILING
#include <linux/linkage.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/dma-direct.h>
#include <linux/dma-mapping.h>
#include <linux/swiotlb.h>
#include <linux/cc_platform.h>
#include <linux/mem_encrypt.h>
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/bitops.h>
#include <linux/dma-mapping.h>
#include <linux/virtio_config.h>
#include <linux/cc_platform.h>
#include <asm/tlbflush.h>
#include <asm/fixmap.h>
#include <asm/setup.h>
#include <asm/bootparam.h>
#include <asm/set_memory.h>
#include <asm/cacheflush.h>
#include <asm/processor-flags.h>
#include <asm/msr.h>
#include <asm/cmdline.h>
#include "mm_internal.h"
/*
* Since SME related variables are set early in the boot process they must
* reside in the .data section so as not to be zeroed out when the .bss
* section is later cleared.
*/
u64 sme_me_mask __section(".data") = 0;
u64 sev_status __section(".data") = 0;
u64 sev_check_data __section(".data") = 0;
EXPORT_SYMBOL(sme_me_mask);
DEFINE_STATIC_KEY_FALSE(sev_enable_key);
EXPORT_SYMBOL_GPL(sev_enable_key);
/* Buffer used for early in-place encryption by BSP, no locking needed */
static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE);
/*
* This routine does not change the underlying encryption setting of the
* page(s) that map this memory. It assumes that eventually the memory is
* meant to be accessed as either encrypted or decrypted but the contents
* are currently not in the desired state.
*
* This routine follows the steps outlined in the AMD64 Architecture
* Programmer's Manual Volume 2, Section 7.10.8 Encrypt-in-Place.
*/
static void __init __sme_early_enc_dec(resource_size_t paddr,
unsigned long size, bool enc)
{
void *src, *dst;
size_t len;
if (!sme_me_mask)
return;
wbinvd();
/*
* There are limited number of early mapping slots, so map (at most)
* one page at time.
*/
while (size) {
len = min_t(size_t, sizeof(sme_early_buffer), size);
/*
* Create mappings for the current and desired format of
* the memory. Use a write-protected mapping for the source.
*/
src = enc ? early_memremap_decrypted_wp(paddr, len) :
early_memremap_encrypted_wp(paddr, len);
dst = enc ? early_memremap_encrypted(paddr, len) :
early_memremap_decrypted(paddr, len);
/*
* If a mapping can't be obtained to perform the operation,
* then eventual access of that area in the desired mode
* will cause a crash.
*/
BUG_ON(!src || !dst);
/*
* Use a temporary buffer, of cache-line multiple size, to
* avoid data corruption as documented in the APM.
*/
memcpy(sme_early_buffer, src, len);
memcpy(dst, sme_early_buffer, len);
early_memunmap(dst, len);
early_memunmap(src, len);
paddr += len;
size -= len;
}
}
void __init sme_early_encrypt(resource_size_t paddr, unsigned long size)
{
__sme_early_enc_dec(paddr, size, true);
}
void __init sme_early_decrypt(resource_size_t paddr, unsigned long size)
{
__sme_early_enc_dec(paddr, size, false);
}
static void __init __sme_early_map_unmap_mem(void *vaddr, unsigned long size,
bool map)
{
unsigned long paddr = (unsigned long)vaddr - __PAGE_OFFSET;
pmdval_t pmd_flags, pmd;
/* Use early_pmd_flags but remove the encryption mask */
pmd_flags = __sme_clr(early_pmd_flags);
do {
pmd = map ? (paddr & PMD_MASK) + pmd_flags : 0;
__early_make_pgtable((unsigned long)vaddr, pmd);
vaddr += PMD_SIZE;
paddr += PMD_SIZE;
size = (size <= PMD_SIZE) ? 0 : size - PMD_SIZE;
} while (size);
flush_tlb_local();
}
void __init sme_unmap_bootdata(char *real_mode_data)
{
struct boot_params *boot_data;
unsigned long cmdline_paddr;
if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
return;
/* Get the command line address before unmapping the real_mode_data */
boot_data = (struct boot_params *)real_mode_data;
cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32);
__sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), false);
if (!cmdline_paddr)
return;
__sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, false);
}
void __init sme_map_bootdata(char *real_mode_data)
{
struct boot_params *boot_data;
unsigned long cmdline_paddr;
if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
return;
__sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), true);
/* Get the command line address after mapping the real_mode_data */
boot_data = (struct boot_params *)real_mode_data;
cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32);
if (!cmdline_paddr)
return;
__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();
unsigned long size;
if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
return;
/*
* For SEV, all DMA has to occur via shared/unencrypted pages.
* SEV uses SWIOTLB to make this happen without changing device
* drivers. However, depending on the workload being run, the
* default 64MB of SWIOTLB may not be enough and SWIOTLB may
* run out of buffers for DMA, resulting in I/O errors and/or
* performance degradation especially with high I/O workloads.
*
* Adjust the default size of SWIOTLB for SEV guests using
* a percentage of guest memory for SWIOTLB buffers.
* Also, as the SWIOTLB bounce buffer memory is allocated
* from low memory, ensure that the adjusted size is within
* the limits of low available memory.
*
* The percentage of guest memory used here for SWIOTLB buffers
* is more of an approximation of the static adjustment which
* 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6%
*/
size = total_mem * 6 / 100;
size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G);
swiotlb_adjust_size(size);
}
static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot)
{
unsigned long pfn = 0;
pgprot_t prot;
switch (level) {
case PG_LEVEL_4K:
pfn = pte_pfn(*kpte);
prot = pte_pgprot(*kpte);
break;
case PG_LEVEL_2M:
pfn = pmd_pfn(*(pmd_t *)kpte);
prot = pmd_pgprot(*(pmd_t *)kpte);
break;
case PG_LEVEL_1G:
pfn = pud_pfn(*(pud_t *)kpte);
prot = pud_pgprot(*(pud_t *)kpte);
break;
default:
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;
else
pgprot_val(new_prot) &= ~_PAGE_ENC;
/* If prot is same then do nothing. */
if (pgprot_val(old_prot) == pgprot_val(new_prot))
return;
pa = pfn << PAGE_SHIFT;
size = page_level_size(level);
/*
* We are going to perform in-place en-/decryption and change the
* physical page attribute from C=1 to C=0 or vice versa. Flush the
* caches to ensure that data gets accessed with the correct C-bit.
*/
clflush_cache_range(__va(pa), size);
/* Encrypt/decrypt the contents in-place */
if (enc)
sme_early_encrypt(pa, size);
else
sme_early_decrypt(pa, size);
/* Change the page encryption mask. */
new_pte = pfn_pte(pfn, new_prot);
set_pte_atomic(kpte, new_pte);
}
static int __init early_set_memory_enc_dec(unsigned long vaddr,
unsigned long size, bool enc)
{
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;
for (; vaddr < vaddr_end; vaddr = vaddr_next) {
kpte = lookup_address(vaddr, &level);
if (!kpte || pte_none(*kpte)) {
ret = 1;
goto out;
}
if (level == PG_LEVEL_4K) {
__set_clr_pte_enc(kpte, level, enc);
vaddr_next = (vaddr & PAGE_MASK) + PAGE_SIZE;
continue;
}
psize = page_level_size(level);
pmask = page_level_mask(level);
/*
* Check whether we can change the large page in one go.
* We request a split when the address is not aligned and
* the number of pages to set/clear encryption bit is smaller
* than the number of pages in the large page.
*/
if (vaddr == (vaddr & pmask) &&
((vaddr_end - vaddr) >= psize)) {
__set_clr_pte_enc(kpte, level, enc);
vaddr_next = (vaddr & pmask) + psize;
continue;
}
/*
* The virtual address is part of a larger page, create the next
* level page table mapping (4K or 2M). If it is part of a 2M
* page then we request a split of the large page into 4K
* chunks. A 1GB large page is split into 2M pages, resp.
*/
if (level == PG_LEVEL_2M)
split_page_size_mask = 0;
else
split_page_size_mask = 1 << PG_LEVEL_2M;
/*
* kernel_physical_mapping_change() does not flush the TLBs, so
* a TLB flush is required after we exit from the for loop.
*/
kernel_physical_mapping_change(__pa(vaddr & pmask),
__pa((vaddr_end & pmask) + psize),
split_page_size_mask);
}
ret = 0;
notify_range_enc_status_changed(start, PAGE_ALIGN(size) >> PAGE_SHIFT, enc);
out:
__flush_tlb_all();
return ret;
}
int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size)
{
return early_set_memory_enc_dec(vaddr, size, false);
}
int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size)
{
return early_set_memory_enc_dec(vaddr, size, true);
}
void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc)
{
notify_range_enc_status_changed(vaddr, npages, enc);
}
/* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */
bool force_dma_unencrypted(struct device *dev)
......@@ -441,30 +40,6 @@ bool force_dma_unencrypted(struct device *dev)
return false;
}
void __init mem_encrypt_free_decrypted_mem(void)
{
unsigned long vaddr, vaddr_end, npages;
int r;
vaddr = (unsigned long)__start_bss_decrypted_unused;
vaddr_end = (unsigned long)__end_bss_decrypted;
npages = (vaddr_end - vaddr) >> PAGE_SHIFT;
/*
* The unused memory range was mapped decrypted, change the encryption
* attribute from decrypted to encrypted before freeing it.
*/
if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
r = set_memory_encrypted(vaddr, npages);
if (r) {
pr_warn("failed to free unused decrypted pages\n");
return;
}
}
free_init_pages("unused decrypted", vaddr, vaddr_end);
}
static void print_mem_encrypt_feature_info(void)
{
pr_info("AMD Memory Encryption Features active:");
......@@ -493,20 +68,12 @@ static void print_mem_encrypt_feature_info(void)
/* Architecture __weak replacement functions */
void __init mem_encrypt_init(void)
{
if (!sme_me_mask)
if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT))
return;
/* Call into SWIOTLB to update the SWIOTLB DMA buffers */
swiotlb_update_mem_attributes();
/*
* With SEV, we need to unroll the rep string I/O instructions,
* but SEV-ES supports them through the #VC handler.
*/
if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) &&
!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
static_branch_enable(&sev_enable_key);
print_mem_encrypt_feature_info();
}
......
arch/x86/mm/mem_encrypt_amd.c 0 → 100644
View file @ 01d5e787
// SPDX-License-Identifier: GPL-2.0-only
/*
* AMD Memory Encryption Support
*
* Copyright (C) 2016 Advanced Micro Devices, Inc.
*
* Author: Tom Lendacky <thomas.lendacky@amd.com>
*/
#define DISABLE_BRANCH_PROFILING
#include <linux/linkage.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/dma-direct.h>
#include <linux/swiotlb.h>
#include <linux/mem_encrypt.h>
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/bitops.h>
#include <linux/dma-mapping.h>
#include <linux/virtio_config.h>
#include <linux/cc_platform.h>
#include <asm/tlbflush.h>
#include <asm/fixmap.h>
#include <asm/setup.h>
#include <asm/bootparam.h>
#include <asm/set_memory.h>
#include <asm/cacheflush.h>
#include <asm/processor-flags.h>
#include <asm/msr.h>
#include <asm/cmdline.h>
#include "mm_internal.h"
/*
* Since SME related variables are set early in the boot process they must
* reside in the .data section so as not to be zeroed out when the .bss
* section is later cleared.
*/
u64 sme_me_mask __section(".data") = 0;
u64 sev_status __section(".data") = 0;
u64 sev_check_data __section(".data") = 0;
EXPORT_SYMBOL(sme_me_mask);
/* Buffer used for early in-place encryption by BSP, no locking needed */
static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE);
/*
* This routine does not change the underlying encryption setting of the
* page(s) that map this memory. It assumes that eventually the memory is
* meant to be accessed as either encrypted or decrypted but the contents
* are currently not in the desired state.
*
* This routine follows the steps outlined in the AMD64 Architecture
* Programmer's Manual Volume 2, Section 7.10.8 Encrypt-in-Place.
*/
static void __init __sme_early_enc_dec(resource_size_t paddr,
unsigned long size, bool enc)
{
void *src, *dst;
size_t len;
if (!sme_me_mask)
return;
wbinvd();
/*
* There are limited number of early mapping slots, so map (at most)
* one page at time.
*/
while (size) {
len = min_t(size_t, sizeof(sme_early_buffer), size);
/*
* Create mappings for the current and desired format of
* the memory. Use a write-protected mapping for the source.
*/
src = enc ? early_memremap_decrypted_wp(paddr, len) :
early_memremap_encrypted_wp(paddr, len);
dst = enc ? early_memremap_encrypted(paddr, len) :
early_memremap_decrypted(paddr, len);
/*
* If a mapping can't be obtained to perform the operation,
* then eventual access of that area in the desired mode
* will cause a crash.
*/
BUG_ON(!src || !dst);
/*
* Use a temporary buffer, of cache-line multiple size, to
* avoid data corruption as documented in the APM.
*/
memcpy(sme_early_buffer, src, len);
memcpy(dst, sme_early_buffer, len);
early_memunmap(dst, len);
early_memunmap(src, len);
paddr += len;
size -= len;
}
}
void __init sme_early_encrypt(resource_size_t paddr, unsigned long size)
{
__sme_early_enc_dec(paddr, size, true);
}
void __init sme_early_decrypt(resource_size_t paddr, unsigned long size)
{
__sme_early_enc_dec(paddr, size, false);
}
static void __init __sme_early_map_unmap_mem(void *vaddr, unsigned long size,
bool map)
{
unsigned long paddr = (unsigned long)vaddr - __PAGE_OFFSET;
pmdval_t pmd_flags, pmd;
/* Use early_pmd_flags but remove the encryption mask */
pmd_flags = __sme_clr(early_pmd_flags);
do {
pmd = map ? (paddr & PMD_MASK) + pmd_flags : 0;
__early_make_pgtable((unsigned long)vaddr, pmd);
vaddr += PMD_SIZE;
paddr += PMD_SIZE;
size = (size <= PMD_SIZE) ? 0 : size - PMD_SIZE;
} while (size);
flush_tlb_local();
}
void __init sme_unmap_bootdata(char *real_mode_data)
{
struct boot_params *boot_data;
unsigned long cmdline_paddr;
if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
return;
/* Get the command line address before unmapping the real_mode_data */
boot_data = (struct boot_params *)real_mode_data;
cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32);
__sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), false);
if (!cmdline_paddr)
return;
__sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, false);
}
void __init sme_map_bootdata(char *real_mode_data)
{
struct boot_params *boot_data;
unsigned long cmdline_paddr;
if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
return;
__sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), true);
/* Get the command line address after mapping the real_mode_data */
boot_data = (struct boot_params *)real_mode_data;
cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32);
if (!cmdline_paddr)
return;
__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();
unsigned long size;
if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
return;
/*
* For SEV, all DMA has to occur via shared/unencrypted pages.
* SEV uses SWIOTLB to make this happen without changing device
* drivers. However, depending on the workload being run, the
* default 64MB of SWIOTLB may not be enough and SWIOTLB may
* run out of buffers for DMA, resulting in I/O errors and/or
* performance degradation especially with high I/O workloads.
*
* Adjust the default size of SWIOTLB for SEV guests using
* a percentage of guest memory for SWIOTLB buffers.
* Also, as the SWIOTLB bounce buffer memory is allocated
* from low memory, ensure that the adjusted size is within
* the limits of low available memory.
*
* The percentage of guest memory used here for SWIOTLB buffers
* is more of an approximation of the static adjustment which
* 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6%
*/
size = total_mem * 6 / 100;
size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G);
swiotlb_adjust_size(size);
}
static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot)
{
unsigned long pfn = 0;
pgprot_t prot;
switch (level) {
case PG_LEVEL_4K:
pfn = pte_pfn(*kpte);
prot = pte_pgprot(*kpte);
break;
case PG_LEVEL_2M:
pfn = pmd_pfn(*(pmd_t *)kpte);
prot = pmd_pgprot(*(pmd_t *)kpte);
break;
case PG_LEVEL_1G:
pfn = pud_pfn(*(pud_t *)kpte);
prot = pud_pgprot(*(pud_t *)kpte);
break;
default:
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;
else
pgprot_val(new_prot) &= ~_PAGE_ENC;
/* If prot is same then do nothing. */
if (pgprot_val(old_prot) == pgprot_val(new_prot))
return;
pa = pfn << PAGE_SHIFT;
size = page_level_size(level);
/*
* We are going to perform in-place en-/decryption and change the
* physical page attribute from C=1 to C=0 or vice versa. Flush the
* caches to ensure that data gets accessed with the correct C-bit.
*/
clflush_cache_range(__va(pa), size);
/* Encrypt/decrypt the contents in-place */
if (enc)
sme_early_encrypt(pa, size);
else
sme_early_decrypt(pa, size);
/* Change the page encryption mask. */
new_pte = pfn_pte(pfn, new_prot);
set_pte_atomic(kpte, new_pte);
}
static int __init early_set_memory_enc_dec(unsigned long vaddr,
unsigned long size, bool enc)
{
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;
for (; vaddr < vaddr_end; vaddr = vaddr_next) {
kpte = lookup_address(vaddr, &level);
if (!kpte || pte_none(*kpte)) {
ret = 1;
goto out;
}
if (level == PG_LEVEL_4K) {
__set_clr_pte_enc(kpte, level, enc);
vaddr_next = (vaddr & PAGE_MASK) + PAGE_SIZE;
continue;
}
psize = page_level_size(level);
pmask = page_level_mask(level);
/*
* Check whether we can change the large page in one go.
* We request a split when the address is not aligned and
* the number of pages to set/clear encryption bit is smaller
* than the number of pages in the large page.
*/
if (vaddr == (vaddr & pmask) &&
((vaddr_end - vaddr) >= psize)) {
__set_clr_pte_enc(kpte, level, enc);
vaddr_next = (vaddr & pmask) + psize;
continue;
}
/*
* The virtual address is part of a larger page, create the next
* level page table mapping (4K or 2M). If it is part of a 2M
* page then we request a split of the large page into 4K
* chunks. A 1GB large page is split into 2M pages, resp.
*/
if (level == PG_LEVEL_2M)
split_page_size_mask = 0;
else
split_page_size_mask = 1 << PG_LEVEL_2M;
/*
* kernel_physical_mapping_change() does not flush the TLBs, so
* a TLB flush is required after we exit from the for loop.
*/
kernel_physical_mapping_change(__pa(vaddr & pmask),
__pa((vaddr_end & pmask) + psize),
split_page_size_mask);
}
ret = 0;
notify_range_enc_status_changed(start, PAGE_ALIGN(size) >> PAGE_SHIFT, enc);
out:
__flush_tlb_all();
return ret;
}
int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size)
{
return early_set_memory_enc_dec(vaddr, size, false);
}
int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size)
{
return early_set_memory_enc_dec(vaddr, size, true);
}
void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc)
{
notify_range_enc_status_changed(vaddr, npages, enc);
}
void __init mem_encrypt_free_decrypted_mem(void)
{
unsigned long vaddr, vaddr_end, npages;
int r;
vaddr = (unsigned long)__start_bss_decrypted_unused;
vaddr_end = (unsigned long)__end_bss_decrypted;
npages = (vaddr_end - vaddr) >> PAGE_SHIFT;
/*
* The unused memory range was mapped decrypted, change the encryption
* attribute from decrypted to encrypted before freeing it.
*/
if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
r = set_memory_encrypted(vaddr, npages);
if (r) {
pr_warn("failed to free unused decrypted pages\n");
return;
}
}
free_init_pages("unused decrypted", vaddr, vaddr_end);
}
include/linux/cc_platform.h
View file @ 01d5e787
......@@ -61,6 +61,17 @@ enum cc_attr {
* Examples include SEV-ES.
*/
CC_ATTR_GUEST_STATE_ENCRYPT,
/**
* @CC_ATTR_GUEST_UNROLL_STRING_IO: String I/O is implemented with
* IN/OUT instructions
*
* The platform/OS is running as a guest/virtual machine and uses
* IN/OUT instructions in place of string I/O.
*
* Examples include TDX guest & SEV.
*/
CC_ATTR_GUEST_UNROLL_STRING_IO,
};
#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7