diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-27 01:32:39 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-27 01:32:39 +0300 |
commit | 2c96136a3f8dad6bfe35b003fb8b312f13a107e8 (patch) | |
tree | dcc5713059bf56cf70dfc4ec0d53ef7cbc88bcd1 /drivers | |
parent | 3e5822e0f99e429fa8b03c956dad890179b5b3b1 (diff) | |
parent | 84b9b44b99780d35fe72ac63c4724f158771e898 (diff) | |
download | linux-2c96136a3f8dad6bfe35b003fb8b312f13a107e8.tar.xz |
Merge tag 'x86_cc_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 confidential computing update from Borislav Petkov:
- Add support for unaccepted memory as specified in the UEFI spec v2.9.
The gist of it all is that Intel TDX and AMD SEV-SNP confidential
computing guests define the notion of accepting memory before using
it and thus preventing a whole set of attacks against such guests
like memory replay and the like.
There are a couple of strategies of how memory should be accepted -
the current implementation does an on-demand way of accepting.
* tag 'x86_cc_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
virt: sevguest: Add CONFIG_CRYPTO dependency
x86/efi: Safely enable unaccepted memory in UEFI
x86/sev: Add SNP-specific unaccepted memory support
x86/sev: Use large PSC requests if applicable
x86/sev: Allow for use of the early boot GHCB for PSC requests
x86/sev: Put PSC struct on the stack in prep for unaccepted memory support
x86/sev: Fix calculation of end address based on number of pages
x86/tdx: Add unaccepted memory support
x86/tdx: Refactor try_accept_one()
x86/tdx: Make _tdx_hypercall() and __tdx_module_call() available in boot stub
efi/unaccepted: Avoid load_unaligned_zeropad() stepping into unaccepted memory
efi: Add unaccepted memory support
x86/boot/compressed: Handle unaccepted memory
efi/libstub: Implement support for unaccepted memory
efi/x86: Get full memory map in allocate_e820()
mm: Add support for unaccepted memory
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/base/node.c | 7 | ||||
-rw-r--r-- | drivers/firmware/efi/Kconfig | 14 | ||||
-rw-r--r-- | drivers/firmware/efi/Makefile | 1 | ||||
-rw-r--r-- | drivers/firmware/efi/efi.c | 26 | ||||
-rw-r--r-- | drivers/firmware/efi/libstub/Makefile | 2 | ||||
-rw-r--r-- | drivers/firmware/efi/libstub/bitmap.c | 41 | ||||
-rw-r--r-- | drivers/firmware/efi/libstub/efistub.h | 6 | ||||
-rw-r--r-- | drivers/firmware/efi/libstub/find.c | 43 | ||||
-rw-r--r-- | drivers/firmware/efi/libstub/unaccepted_memory.c | 222 | ||||
-rw-r--r-- | drivers/firmware/efi/libstub/x86-stub.c | 75 | ||||
-rw-r--r-- | drivers/firmware/efi/unaccepted_memory.c | 147 | ||||
-rw-r--r-- | drivers/virt/coco/sev-guest/Kconfig | 1 |
12 files changed, 570 insertions, 15 deletions
diff --git a/drivers/base/node.c b/drivers/base/node.c index b46db17124f3..655975946ef6 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -449,6 +449,9 @@ static ssize_t node_read_meminfo(struct device *dev, "Node %d FileHugePages: %8lu kB\n" "Node %d FilePmdMapped: %8lu kB\n" #endif +#ifdef CONFIG_UNACCEPTED_MEMORY + "Node %d Unaccepted: %8lu kB\n" +#endif , nid, K(node_page_state(pgdat, NR_FILE_DIRTY)), nid, K(node_page_state(pgdat, NR_WRITEBACK)), @@ -478,6 +481,10 @@ static ssize_t node_read_meminfo(struct device *dev, nid, K(node_page_state(pgdat, NR_FILE_THPS)), nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED)) #endif +#ifdef CONFIG_UNACCEPTED_MEMORY + , + nid, K(sum_zone_node_page_state(nid, NR_UNACCEPTED)) +#endif ); len += hugetlb_report_node_meminfo(buf, len, nid); return len; diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index 043ca31c114e..231f1c70d1db 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -269,6 +269,20 @@ config EFI_COCO_SECRET virt/coco/efi_secret module to access the secrets, which in turn allows userspace programs to access the injected secrets. +config UNACCEPTED_MEMORY + bool + depends on EFI_STUB + help + Some Virtual Machine platforms, such as Intel TDX, require + some memory to be "accepted" by the guest before it can be used. + This mechanism helps prevent malicious hosts from making changes + to guest memory. + + UEFI specification v2.9 introduced EFI_UNACCEPTED_MEMORY memory type. + + This option adds support for unaccepted memory and makes such memory + usable by the kernel. + config EFI_EMBEDDED_FIRMWARE bool select CRYPTO_LIB_SHA256 diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile index b51f2a4c821e..e489fefd23da 100644 --- a/drivers/firmware/efi/Makefile +++ b/drivers/firmware/efi/Makefile @@ -41,3 +41,4 @@ obj-$(CONFIG_EFI_CAPSULE_LOADER) += capsule-loader.o obj-$(CONFIG_EFI_EARLYCON) += earlycon.o obj-$(CONFIG_UEFI_CPER_ARM) += cper-arm.o obj-$(CONFIG_UEFI_CPER_X86) += cper-x86.o +obj-$(CONFIG_UNACCEPTED_MEMORY) += unaccepted_memory.o diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 34b9e7876538..3a6ee7bb06f1 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -50,6 +50,9 @@ struct efi __read_mostly efi = { #ifdef CONFIG_EFI_COCO_SECRET .coco_secret = EFI_INVALID_TABLE_ADDR, #endif +#ifdef CONFIG_UNACCEPTED_MEMORY + .unaccepted = EFI_INVALID_TABLE_ADDR, +#endif }; EXPORT_SYMBOL(efi); @@ -584,6 +587,9 @@ static const efi_config_table_type_t common_tables[] __initconst = { #ifdef CONFIG_EFI_COCO_SECRET {LINUX_EFI_COCO_SECRET_AREA_GUID, &efi.coco_secret, "CocoSecret" }, #endif +#ifdef CONFIG_UNACCEPTED_MEMORY + {LINUX_EFI_UNACCEPTED_MEM_TABLE_GUID, &efi.unaccepted, "Unaccepted" }, +#endif #ifdef CONFIG_EFI_GENERIC_STUB {LINUX_EFI_SCREEN_INFO_TABLE_GUID, &screen_info_table }, #endif @@ -738,6 +744,25 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, } } + if (IS_ENABLED(CONFIG_UNACCEPTED_MEMORY) && + efi.unaccepted != EFI_INVALID_TABLE_ADDR) { + struct efi_unaccepted_memory *unaccepted; + + unaccepted = early_memremap(efi.unaccepted, sizeof(*unaccepted)); + if (unaccepted) { + unsigned long size; + + if (unaccepted->version == 1) { + size = sizeof(*unaccepted) + unaccepted->size; + memblock_reserve(efi.unaccepted, size); + } else { + efi.unaccepted = EFI_INVALID_TABLE_ADDR; + } + + early_memunmap(unaccepted, sizeof(*unaccepted)); + } + } + return 0; } @@ -822,6 +847,7 @@ static __initdata char memory_type_name[][13] = { "MMIO Port", "PAL Code", "Persistent", + "Unaccepted", }; char * __init efi_md_typeattr_format(char *buf, size_t size, diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index 3abb2b357482..16d64a34d1e1 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -96,6 +96,8 @@ CFLAGS_arm32-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET) zboot-obj-$(CONFIG_RISCV) := lib-clz_ctz.o lib-ashldi3.o lib-$(CONFIG_EFI_ZBOOT) += zboot.o $(zboot-obj-y) +lib-$(CONFIG_UNACCEPTED_MEMORY) += unaccepted_memory.o bitmap.o find.o + extra-y := $(lib-y) lib-y := $(patsubst %.o,%.stub.o,$(lib-y)) diff --git a/drivers/firmware/efi/libstub/bitmap.c b/drivers/firmware/efi/libstub/bitmap.c new file mode 100644 index 000000000000..5c9bba0d549b --- /dev/null +++ b/drivers/firmware/efi/libstub/bitmap.c @@ -0,0 +1,41 @@ +#include <linux/bitmap.h> + +void __bitmap_set(unsigned long *map, unsigned int start, int len) +{ + unsigned long *p = map + BIT_WORD(start); + const unsigned int size = start + len; + int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); + unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start); + + while (len - bits_to_set >= 0) { + *p |= mask_to_set; + len -= bits_to_set; + bits_to_set = BITS_PER_LONG; + mask_to_set = ~0UL; + p++; + } + if (len) { + mask_to_set &= BITMAP_LAST_WORD_MASK(size); + *p |= mask_to_set; + } +} + +void __bitmap_clear(unsigned long *map, unsigned int start, int len) +{ + unsigned long *p = map + BIT_WORD(start); + const unsigned int size = start + len; + int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); + unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); + + while (len - bits_to_clear >= 0) { + *p &= ~mask_to_clear; + len -= bits_to_clear; + bits_to_clear = BITS_PER_LONG; + mask_to_clear = ~0UL; + p++; + } + if (len) { + mask_to_clear &= BITMAP_LAST_WORD_MASK(size); + *p &= ~mask_to_clear; + } +} diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 54a2822cae77..6aa38a1bf126 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -1136,4 +1136,10 @@ void efi_remap_image(unsigned long image_base, unsigned alloc_size, asmlinkage efi_status_t __efiapi efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab); +efi_status_t allocate_unaccepted_bitmap(__u32 nr_desc, + struct efi_boot_memmap *map); +void process_unaccepted_memory(u64 start, u64 end); +void accept_memory(phys_addr_t start, phys_addr_t end); +void arch_accept_memory(phys_addr_t start, phys_addr_t end); + #endif diff --git a/drivers/firmware/efi/libstub/find.c b/drivers/firmware/efi/libstub/find.c new file mode 100644 index 000000000000..4e7740d28987 --- /dev/null +++ b/drivers/firmware/efi/libstub/find.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/bitmap.h> +#include <linux/math.h> +#include <linux/minmax.h> + +/* + * Common helper for find_next_bit() function family + * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) + * @MUNGE: The expression that post-processes a word containing found bit (may be empty) + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at + */ +#define FIND_NEXT_BIT(FETCH, MUNGE, size, start) \ +({ \ + unsigned long mask, idx, tmp, sz = (size), __start = (start); \ + \ + if (unlikely(__start >= sz)) \ + goto out; \ + \ + mask = MUNGE(BITMAP_FIRST_WORD_MASK(__start)); \ + idx = __start / BITS_PER_LONG; \ + \ + for (tmp = (FETCH) & mask; !tmp; tmp = (FETCH)) { \ + if ((idx + 1) * BITS_PER_LONG >= sz) \ + goto out; \ + idx++; \ + } \ + \ + sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(tmp)), sz); \ +out: \ + sz; \ +}) + +unsigned long _find_next_bit(const unsigned long *addr, unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr[idx], /* nop */, nbits, start); +} + +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start) +{ + return FIND_NEXT_BIT(~addr[idx], /* nop */, nbits, start); +} diff --git a/drivers/firmware/efi/libstub/unaccepted_memory.c b/drivers/firmware/efi/libstub/unaccepted_memory.c new file mode 100644 index 000000000000..ca61f4733ea5 --- /dev/null +++ b/drivers/firmware/efi/libstub/unaccepted_memory.c @@ -0,0 +1,222 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/efi.h> +#include <asm/efi.h> +#include "efistub.h" + +struct efi_unaccepted_memory *unaccepted_table; + +efi_status_t allocate_unaccepted_bitmap(__u32 nr_desc, + struct efi_boot_memmap *map) +{ + efi_guid_t unaccepted_table_guid = LINUX_EFI_UNACCEPTED_MEM_TABLE_GUID; + u64 unaccepted_start = ULLONG_MAX, unaccepted_end = 0, bitmap_size; + efi_status_t status; + int i; + + /* Check if the table is already installed */ + unaccepted_table = get_efi_config_table(unaccepted_table_guid); + if (unaccepted_table) { + if (unaccepted_table->version != 1) { + efi_err("Unknown version of unaccepted memory table\n"); + return EFI_UNSUPPORTED; + } + return EFI_SUCCESS; + } + + /* Check if there's any unaccepted memory and find the max address */ + for (i = 0; i < nr_desc; i++) { + efi_memory_desc_t *d; + unsigned long m = (unsigned long)map->map; + + d = efi_early_memdesc_ptr(m, map->desc_size, i); + if (d->type != EFI_UNACCEPTED_MEMORY) + continue; + + unaccepted_start = min(unaccepted_start, d->phys_addr); + unaccepted_end = max(unaccepted_end, + d->phys_addr + d->num_pages * PAGE_SIZE); + } + + if (unaccepted_start == ULLONG_MAX) + return EFI_SUCCESS; + + unaccepted_start = round_down(unaccepted_start, + EFI_UNACCEPTED_UNIT_SIZE); + unaccepted_end = round_up(unaccepted_end, EFI_UNACCEPTED_UNIT_SIZE); + + /* + * If unaccepted memory is present, allocate a bitmap to track what + * memory has to be accepted before access. + * + * One bit in the bitmap represents 2MiB in the address space: + * A 4k bitmap can track 64GiB of physical address space. + * + * In the worst case scenario -- a huge hole in the middle of the + * address space -- It needs 256MiB to handle 4PiB of the address + * space. + * + * The bitmap will be populated in setup_e820() according to the memory + * map after efi_exit_boot_services(). + */ + bitmap_size = DIV_ROUND_UP(unaccepted_end - unaccepted_start, + EFI_UNACCEPTED_UNIT_SIZE * BITS_PER_BYTE); + + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, + sizeof(*unaccepted_table) + bitmap_size, + (void **)&unaccepted_table); + if (status != EFI_SUCCESS) { + efi_err("Failed to allocate unaccepted memory config table\n"); + return status; + } + + unaccepted_table->version = 1; + unaccepted_table->unit_size = EFI_UNACCEPTED_UNIT_SIZE; + unaccepted_table->phys_base = unaccepted_start; + unaccepted_table->size = bitmap_size; + memset(unaccepted_table->bitmap, 0, bitmap_size); + + status = efi_bs_call(install_configuration_table, + &unaccepted_table_guid, unaccepted_table); + if (status != EFI_SUCCESS) { + efi_bs_call(free_pool, unaccepted_table); + efi_err("Failed to install unaccepted memory config table!\n"); + } + + return status; +} + +/* + * The accepted memory bitmap only works at unit_size granularity. Take + * unaligned start/end addresses and either: + * 1. Accepts the memory immediately and in its entirety + * 2. Accepts unaligned parts, and marks *some* aligned part unaccepted + * + * The function will never reach the bitmap_set() with zero bits to set. + */ +void process_unaccepted_memory(u64 start, u64 end) +{ + u64 unit_size = unaccepted_table->unit_size; + u64 unit_mask = unaccepted_table->unit_size - 1; + u64 bitmap_size = unaccepted_table->size; + + /* + * Ensure that at least one bit will be set in the bitmap by + * immediately accepting all regions under 2*unit_size. This is + * imprecise and may immediately accept some areas that could + * have been represented in the bitmap. But, results in simpler + * code below + * + * Consider case like this (assuming unit_size == 2MB): + * + * | 4k | 2044k | 2048k | + * ^ 0x0 ^ 2MB ^ 4MB + * + * Only the first 4k has been accepted. The 0MB->2MB region can not be + * represented in the bitmap. The 2MB->4MB region can be represented in + * the bitmap. But, the 0MB->4MB region is <2*unit_size and will be + * immediately accepted in its entirety. + */ + if (end - start < 2 * unit_size) { + arch_accept_memory(start, end); + return; + } + + /* + * No matter how the start and end are aligned, at least one unaccepted + * unit_size area will remain to be marked in the bitmap. + */ + + /* Immediately accept a <unit_size piece at the start: */ + if (start & unit_mask) { + arch_accept_memory(start, round_up(start, unit_size)); + start = round_up(start, unit_size); + } + + /* Immediately accept a <unit_size piece at the end: */ + if (end & unit_mask) { + arch_accept_memory(round_down(end, unit_size), end); + end = round_down(end, unit_size); + } + + /* + * Accept part of the range that before phys_base and cannot be recorded + * into the bitmap. + */ + if (start < unaccepted_table->phys_base) { + arch_accept_memory(start, + min(unaccepted_table->phys_base, end)); + start = unaccepted_table->phys_base; + } + + /* Nothing to record */ + if (end < unaccepted_table->phys_base) + return; + + /* Translate to offsets from the beginning of the bitmap */ + start -= unaccepted_table->phys_base; + end -= unaccepted_table->phys_base; + + /* Accept memory that doesn't fit into bitmap */ + if (end > bitmap_size * unit_size * BITS_PER_BYTE) { + unsigned long phys_start, phys_end; + + phys_start = bitmap_size * unit_size * BITS_PER_BYTE + + unaccepted_table->phys_base; + phys_end = end + unaccepted_table->phys_base; + + arch_accept_memory(phys_start, phys_end); + end = bitmap_size * unit_size * BITS_PER_BYTE; + } + + /* + * 'start' and 'end' are now both unit_size-aligned. + * Record the range as being unaccepted: + */ + bitmap_set(unaccepted_table->bitmap, + start / unit_size, (end - start) / unit_size); +} + +void accept_memory(phys_addr_t start, phys_addr_t end) +{ + unsigned long range_start, range_end; + unsigned long bitmap_size; + u64 unit_size; + + if (!unaccepted_table) + return; + + unit_size = unaccepted_table->unit_size; + + /* + * Only care for the part of the range that is represented + * in the bitmap. + */ + if (start < unaccepted_table->phys_base) + start = unaccepted_table->phys_base; + if (end < unaccepted_table->phys_base) + return; + + /* Translate to offsets from the beginning of the bitmap */ + start -= unaccepted_table->phys_base; + end -= unaccepted_table->phys_base; + + /* Make sure not to overrun the bitmap */ + if (end > unaccepted_table->size * unit_size * BITS_PER_BYTE) + end = unaccepted_table->size * unit_size * BITS_PER_BYTE; + + range_start = start / unit_size; + bitmap_size = DIV_ROUND_UP(end, unit_size); + + for_each_set_bitrange_from(range_start, range_end, + unaccepted_table->bitmap, bitmap_size) { + unsigned long phys_start, phys_end; + + phys_start = range_start * unit_size + unaccepted_table->phys_base; + phys_end = range_end * unit_size + unaccepted_table->phys_base; + + arch_accept_memory(phys_start, phys_end); + bitmap_clear(unaccepted_table->bitmap, + range_start, range_end - range_start); + } +} diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index a0bfd31358ba..220be75a5cdc 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -26,6 +26,17 @@ const efi_dxe_services_table_t *efi_dxe_table; u32 image_offset __section(".data"); static efi_loaded_image_t *image = NULL; +typedef union sev_memory_acceptance_protocol sev_memory_acceptance_protocol_t; +union sev_memory_acceptance_protocol { + struct { + efi_status_t (__efiapi * allow_unaccepted_memory)( + sev_memory_acceptance_protocol_t *); + }; + struct { + u32 allow_unaccepted_memory; + } mixed_mode; +}; + static efi_status_t preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) { @@ -310,6 +321,29 @@ setup_memory_protection(unsigned long image_base, unsigned long image_size) #endif } +static void setup_unaccepted_memory(void) +{ + efi_guid_t mem_acceptance_proto = OVMF_SEV_MEMORY_ACCEPTANCE_PROTOCOL_GUID; + sev_memory_acceptance_protocol_t *proto; + efi_status_t status; + + if (!IS_ENABLED(CONFIG_UNACCEPTED_MEMORY)) + return; + + /* + * Enable unaccepted memory before calling exit boot services in order + * for the UEFI to not accept all memory on EBS. + */ + status = efi_bs_call(locate_protocol, &mem_acceptance_proto, NULL, + (void **)&proto); + if (status != EFI_SUCCESS) + return; + + status = efi_call_proto(proto, allow_unaccepted_memory); + if (status != EFI_SUCCESS) + efi_err("Memory acceptance protocol failed\n"); +} + static const efi_char16_t apple[] = L"Apple"; static void setup_quirks(struct boot_params *boot_params, @@ -613,6 +647,16 @@ setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_s e820_type = E820_TYPE_PMEM; break; + case EFI_UNACCEPTED_MEMORY: + if (!IS_ENABLED(CONFIG_UNACCEPTED_MEMORY)) { + efi_warn_once( +"The system has unaccepted memory, but kernel does not support it\nConsider enabling CONFIG_UNACCEPTED_MEMORY\n"); + continue; + } + e820_type = E820_TYPE_RAM; + process_unaccepted_memory(d->phys_addr, + d->phys_addr + PAGE_SIZE * d->num_pages); + break; default: continue; } @@ -681,28 +725,27 @@ static efi_status_t allocate_e820(struct boot_params *params, struct setup_data **e820ext, u32 *e820ext_size) { - unsigned long map_size, desc_size, map_key; + struct efi_boot_memmap *map; efi_status_t status; - __u32 nr_desc, desc_version; - - /* Only need the size of the mem map and size of each mem descriptor */ - map_size = 0; - status = efi_bs_call(get_memory_map, &map_size, NULL, &map_key, - &desc_size, &desc_version); - if (status != EFI_BUFFER_TOO_SMALL) - return (status != EFI_SUCCESS) ? status : EFI_UNSUPPORTED; + __u32 nr_desc; - nr_desc = map_size / desc_size + EFI_MMAP_NR_SLACK_SLOTS; + status = efi_get_memory_map(&map, false); + if (status != EFI_SUCCESS) + return status; - if (nr_desc > ARRAY_SIZE(params->e820_table)) { - u32 nr_e820ext = nr_desc - ARRAY_SIZE(params->e820_table); + nr_desc = map->map_size / map->desc_size; + if (nr_desc > ARRAY_SIZE(params->e820_table) - EFI_MMAP_NR_SLACK_SLOTS) { + u32 nr_e820ext = nr_desc - ARRAY_SIZE(params->e820_table) + + EFI_MMAP_NR_SLACK_SLOTS; status = alloc_e820ext(nr_e820ext, e820ext, e820ext_size); - if (status != EFI_SUCCESS) - return status; } - return EFI_SUCCESS; + if (IS_ENABLED(CONFIG_UNACCEPTED_MEMORY) && status == EFI_SUCCESS) + status = allocate_unaccepted_bitmap(nr_desc, map); + + efi_bs_call(free_pool, map); + return status; } struct exit_boot_struct { @@ -899,6 +942,8 @@ asmlinkage unsigned long efi_main(efi_handle_t handle, setup_quirks(boot_params, bzimage_addr, buffer_end - buffer_start); + setup_unaccepted_memory(); + status = exit_boot(boot_params, handle); if (status != EFI_SUCCESS) { efi_err("exit_boot() failed!\n"); diff --git a/drivers/firmware/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c new file mode 100644 index 000000000000..853f7dc3c21d --- /dev/null +++ b/drivers/firmware/efi/unaccepted_memory.c @@ -0,0 +1,147 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/efi.h> +#include <linux/memblock.h> +#include <linux/spinlock.h> +#include <asm/unaccepted_memory.h> + +/* Protects unaccepted memory bitmap */ +static DEFINE_SPINLOCK(unaccepted_memory_lock); + +/* + * accept_memory() -- Consult bitmap and accept the memory if needed. + * + * Only memory that is explicitly marked as unaccepted in the bitmap requires + * an action. All the remaining memory is implicitly accepted and doesn't need + * acceptance. + * + * No need to accept: + * - anything if the system has no unaccepted table; + * - memory that is below phys_base; + * - memory that is above the memory that addressable by the bitmap; + */ +void accept_memory(phys_addr_t start, phys_addr_t end) +{ + struct efi_unaccepted_memory *unaccepted; + unsigned long range_start, range_end; + unsigned long flags; + u64 unit_size; + + unaccepted = efi_get_unaccepted_table(); + if (!unaccepted) + return; + + unit_size = unaccepted->unit_size; + + /* + * Only care for the part of the range that is represented + * in the bitmap. + */ + if (start < unaccepted->phys_base) + start = unaccepted->phys_base; + if (end < unaccepted->phys_base) + return; + + /* Translate to offsets from the beginning of the bitmap */ + start -= unaccepted->phys_base; + end -= unaccepted->phys_base; + + /* + * load_unaligned_zeropad() can lead to unwanted loads across page + * boundaries. The unwanted loads are typically harmless. But, they + * might be made to totally unrelated or even unmapped memory. + * load_unaligned_zeropad() relies on exception fixup (#PF, #GP and now + * #VE) to recover from these unwanted loads. + * + * But, this approach does not work for unaccepted memory. For TDX, a + * load from unaccepted memory will not lead to a recoverable exception + * within the guest. The guest will exit to the VMM where the only + * recourse is to terminate the guest. + * + * There are two parts to fix this issue and comprehensively avoid + * access to unaccepted memory. Together these ensure that an extra + * "guard" page is accepted in addition to the memory that needs to be + * used: + * + * 1. Implicitly extend the range_contains_unaccepted_memory(start, end) + * checks up to end+unit_size if 'end' is aligned on a unit_size + * boundary. + * + * 2. Implicitly extend accept_memory(start, end) to end+unit_size if + * 'end' is aligned on a unit_size boundary. (immediately following + * this comment) + */ + if (!(end % unit_size)) + end += unit_size; + + /* Make sure not to overrun the bitmap */ + if (end > unaccepted->size * unit_size * BITS_PER_BYTE) + end = unaccepted->size * unit_size * BITS_PER_BYTE; + + range_start = start / unit_size; + + spin_lock_irqsave(&unaccepted_memory_lock, flags); + for_each_set_bitrange_from(range_start, range_end, unaccepted->bitmap, + DIV_ROUND_UP(end, unit_size)) { + unsigned long phys_start, phys_end; + unsigned long len = range_end - range_start; + + phys_start = range_start * unit_size + unaccepted->phys_base; + phys_end = range_end * unit_size + unaccepted->phys_base; + + arch_accept_memory(phys_start, phys_end); + bitmap_clear(unaccepted->bitmap, range_start, len); + } + spin_unlock_irqrestore(&unaccepted_memory_lock, flags); +} + +bool range_contains_unaccepted_memory(phys_addr_t start, phys_addr_t end) +{ + struct efi_unaccepted_memory *unaccepted; + unsigned long flags; + bool ret = false; + u64 unit_size; + + unaccepted = efi_get_unaccepted_table(); + if (!unaccepted) + return false; + + unit_size = unaccepted->unit_size; + + /* + * Only care for the part of the range that is represented + * in the bitmap. + */ + if (start < unaccepted->phys_base) + start = unaccepted->phys_base; + if (end < unaccepted->phys_base) + return false; + + /* Translate to offsets from the beginning of the bitmap */ + start -= unaccepted->phys_base; + end -= unaccepted->phys_base; + + /* + * Also consider the unaccepted state of the *next* page. See fix #1 in + * the comment on load_unaligned_zeropad() in accept_memory(). + */ + if (!(end % unit_size)) + end += unit_size; + + /* Make sure not to overrun the bitmap */ + if (end > unaccepted->size * unit_size * BITS_PER_BYTE) + end = unaccepted->size * unit_size * BITS_PER_BYTE; + + spin_lock_irqsave(&unaccepted_memory_lock, flags); + while (start < end) { + if (test_bit(start / unit_size, unaccepted->bitmap)) { + ret = true; + break; + } + + start += unit_size; + } + spin_unlock_irqrestore(&unaccepted_memory_lock, flags); + + return ret; +} diff --git a/drivers/virt/coco/sev-guest/Kconfig b/drivers/virt/coco/sev-guest/Kconfig index f9db0799ae67..da2d7ca531f0 100644 --- a/drivers/virt/coco/sev-guest/Kconfig +++ b/drivers/virt/coco/sev-guest/Kconfig @@ -2,6 +2,7 @@ config SEV_GUEST tristate "AMD SEV Guest driver" default m depends on AMD_MEM_ENCRYPT + select CRYPTO select CRYPTO_AEAD2 select CRYPTO_GCM help |