* [GIT pull] x86/boot for 5.3-rc1
@ 2019-07-09 12:33 Thomas Gleixner
2019-07-09 12:33 ` [GIT pull] x86/kdump " Thomas Gleixner
2019-07-09 19:55 ` [GIT pull] x86/boot " pr-tracker-bot
0 siblings, 2 replies; 4+ messages in thread
From: Thomas Gleixner @ 2019-07-09 12:33 UTC (permalink / raw)
To: Linus Torvalds; +Cc: linux-kernel, x86
Linus,
please pull the latest x86-boot-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-boot-for-linus
up to: 8ff80fbe7e98: x86/kdump/64: Restrict kdump kernel reservation to <64TB
Assorted updates to kexec/kdump:
- Proper kexec support for 4/5-level paging and jumping from a 5-level to
a 4-level paging kernel.
- Make the EFI support for kexec/kdump more robust
- Enforce that the GDT is properly aligned instead of getting the
alignment by chance.
Thanks,
tglx
------------------>
Baoquan He (3):
x86/boot: Add xloadflags bits to check for 5-level paging support
x86/kexec/64: Prevent kexec from 5-level paging to a 4-level only kernel
x86/kdump/64: Restrict kdump kernel reservation to <64TB
Borislav Petkov (2):
Revert "x86/boot: Disable RSDP parsing temporarily"
x86/boot: Call get_rsdp_addr() after console_init()
Junichi Nomura (1):
x86/boot: Use efi_setup_data for searching RSDP on kexec-ed kernels
Kairui Song (2):
x86/kexec: Add the EFI system tables and ACPI tables to the ident map
x86/kexec: Add the ACPI NVS region to the ident map
Xiaoyao Li (1):
x86/boot: Make the GDT 8-byte aligned
arch/x86/boot/compressed/acpi.c | 143 +++++++++++++++++++++++++---------
arch/x86/boot/compressed/head_64.S | 1 +
arch/x86/boot/compressed/misc.c | 11 ++-
| 12 ++-
arch/x86/include/uapi/asm/bootparam.h | 2 +
arch/x86/kernel/kexec-bzimage64.c | 5 ++
arch/x86/kernel/machine_kexec_64.c | 87 +++++++++++++++++++++
arch/x86/kernel/setup.c | 15 +++-
include/linux/sizes.h | 1 +
9 files changed, 234 insertions(+), 43 deletions(-)
diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c
index ad84239e595e..15255f388a85 100644
--- a/arch/x86/boot/compressed/acpi.c
+++ b/arch/x86/boot/compressed/acpi.c
@@ -44,17 +44,109 @@ static acpi_physical_address get_acpi_rsdp(void)
return addr;
}
-/* Search EFI system tables for RSDP. */
-static acpi_physical_address efi_get_rsdp_addr(void)
+/*
+ * Search EFI system tables for RSDP. If both ACPI_20_TABLE_GUID and
+ * ACPI_TABLE_GUID are found, take the former, which has more features.
+ */
+static acpi_physical_address
+__efi_get_rsdp_addr(unsigned long config_tables, unsigned int nr_tables,
+ bool efi_64)
{
acpi_physical_address rsdp_addr = 0;
#ifdef CONFIG_EFI
- unsigned long systab, systab_tables, config_tables;
+ int i;
+
+ /* Get EFI tables from systab. */
+ for (i = 0; i < nr_tables; i++) {
+ acpi_physical_address table;
+ efi_guid_t guid;
+
+ if (efi_64) {
+ efi_config_table_64_t *tbl = (efi_config_table_64_t *)config_tables + i;
+
+ guid = tbl->guid;
+ table = tbl->table;
+
+ if (!IS_ENABLED(CONFIG_X86_64) && table >> 32) {
+ debug_putstr("Error getting RSDP address: EFI config table located above 4GB.\n");
+ return 0;
+ }
+ } else {
+ efi_config_table_32_t *tbl = (efi_config_table_32_t *)config_tables + i;
+
+ guid = tbl->guid;
+ table = tbl->table;
+ }
+
+ if (!(efi_guidcmp(guid, ACPI_TABLE_GUID)))
+ rsdp_addr = table;
+ else if (!(efi_guidcmp(guid, ACPI_20_TABLE_GUID)))
+ return table;
+ }
+#endif
+ return rsdp_addr;
+}
+
+/* EFI/kexec support is 64-bit only. */
+#ifdef CONFIG_X86_64
+static struct efi_setup_data *get_kexec_setup_data_addr(void)
+{
+ struct setup_data *data;
+ u64 pa_data;
+
+ pa_data = boot_params->hdr.setup_data;
+ while (pa_data) {
+ data = (struct setup_data *)pa_data;
+ if (data->type == SETUP_EFI)
+ return (struct efi_setup_data *)(pa_data + sizeof(struct setup_data));
+
+ pa_data = data->next;
+ }
+ return NULL;
+}
+
+static acpi_physical_address kexec_get_rsdp_addr(void)
+{
+ efi_system_table_64_t *systab;
+ struct efi_setup_data *esd;
+ struct efi_info *ei;
+ char *sig;
+
+ esd = (struct efi_setup_data *)get_kexec_setup_data_addr();
+ if (!esd)
+ return 0;
+
+ if (!esd->tables) {
+ debug_putstr("Wrong kexec SETUP_EFI data.\n");
+ return 0;
+ }
+
+ ei = &boot_params->efi_info;
+ sig = (char *)&ei->efi_loader_signature;
+ if (strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) {
+ debug_putstr("Wrong kexec EFI loader signature.\n");
+ return 0;
+ }
+
+ /* Get systab from boot params. */
+ systab = (efi_system_table_64_t *) (ei->efi_systab | ((__u64)ei->efi_systab_hi << 32));
+ if (!systab)
+ error("EFI system table not found in kexec boot_params.");
+
+ return __efi_get_rsdp_addr((unsigned long)esd->tables, systab->nr_tables, true);
+}
+#else
+static acpi_physical_address kexec_get_rsdp_addr(void) { return 0; }
+#endif /* CONFIG_X86_64 */
+
+static acpi_physical_address efi_get_rsdp_addr(void)
+{
+#ifdef CONFIG_EFI
+ unsigned long systab, config_tables;
unsigned int nr_tables;
struct efi_info *ei;
bool efi_64;
- int size, i;
char *sig;
ei = &boot_params->efi_info;
@@ -88,49 +180,20 @@ static acpi_physical_address efi_get_rsdp_addr(void)
config_tables = stbl->tables;
nr_tables = stbl->nr_tables;
- size = sizeof(efi_config_table_64_t);
} else {
efi_system_table_32_t *stbl = (efi_system_table_32_t *)systab;
config_tables = stbl->tables;
nr_tables = stbl->nr_tables;
- size = sizeof(efi_config_table_32_t);
}
if (!config_tables)
error("EFI config tables not found.");
- /* Get EFI tables from systab. */
- for (i = 0; i < nr_tables; i++) {
- acpi_physical_address table;
- efi_guid_t guid;
-
- config_tables += size;
-
- if (efi_64) {
- efi_config_table_64_t *tbl = (efi_config_table_64_t *)config_tables;
-
- guid = tbl->guid;
- table = tbl->table;
-
- if (!IS_ENABLED(CONFIG_X86_64) && table >> 32) {
- debug_putstr("Error getting RSDP address: EFI config table located above 4GB.\n");
- return 0;
- }
- } else {
- efi_config_table_32_t *tbl = (efi_config_table_32_t *)config_tables;
-
- guid = tbl->guid;
- table = tbl->table;
- }
-
- if (!(efi_guidcmp(guid, ACPI_TABLE_GUID)))
- rsdp_addr = table;
- else if (!(efi_guidcmp(guid, ACPI_20_TABLE_GUID)))
- return table;
- }
+ return __efi_get_rsdp_addr(config_tables, nr_tables, efi_64);
+#else
+ return 0;
#endif
- return rsdp_addr;
}
static u8 compute_checksum(u8 *buffer, u32 length)
@@ -220,6 +283,14 @@ acpi_physical_address get_rsdp_addr(void)
if (!pa)
pa = boot_params->acpi_rsdp_addr;
+ /*
+ * Try to get EFI data from setup_data. This can happen when we're a
+ * kexec'ed kernel and kexec(1) has passed all the required EFI info to
+ * us.
+ */
+ if (!pa)
+ pa = kexec_get_rsdp_addr();
+
if (!pa)
pa = efi_get_rsdp_addr();
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index fafb75c6c592..6233ae35d0d9 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -659,6 +659,7 @@ no_longmode:
gdt64:
.word gdt_end - gdt
.quad 0
+ .balign 8
gdt:
.word gdt_end - gdt
.long gdt
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 5a237e8dbf8d..24e65a0f756d 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -351,9 +351,6 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
/* Clear flags intended for solely in-kernel use. */
boot_params->hdr.loadflags &= ~KASLR_FLAG;
- /* Save RSDP address for later use. */
- /* boot_params->acpi_rsdp_addr = get_rsdp_addr(); */
-
sanitize_boot_params(boot_params);
if (boot_params->screen_info.orig_video_mode == 7) {
@@ -368,6 +365,14 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
cols = boot_params->screen_info.orig_video_cols;
console_init();
+
+ /*
+ * Save RSDP address for later use. Have this after console_init()
+ * so that early debugging output from the RSDP parsing code can be
+ * collected.
+ */
+ boot_params->acpi_rsdp_addr = get_rsdp_addr();
+
debug_putstr("early console in extract_kernel\n");
free_mem_ptr = heap; /* Heap */
--git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 850b8762e889..be19f4199727 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -419,7 +419,17 @@ xloadflags:
# define XLF4 0
#endif
- .word XLF0 | XLF1 | XLF23 | XLF4
+#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_5LEVEL
+#define XLF56 (XLF_5LEVEL|XLF_5LEVEL_ENABLED)
+#else
+#define XLF56 XLF_5LEVEL
+#endif
+#else
+#define XLF56 0
+#endif
+
+ .word XLF0 | XLF1 | XLF23 | XLF4 | XLF56
cmdline_size: .long COMMAND_LINE_SIZE-1 #length of the command line,
#added with boot protocol
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 60733f137e9a..c895df5482c5 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -29,6 +29,8 @@
#define XLF_EFI_HANDOVER_32 (1<<2)
#define XLF_EFI_HANDOVER_64 (1<<3)
#define XLF_EFI_KEXEC (1<<4)
+#define XLF_5LEVEL (1<<5)
+#define XLF_5LEVEL_ENABLED (1<<6)
#ifndef __ASSEMBLY__
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 22f60dd26460..7f439739ea3d 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -321,6 +321,11 @@ static int bzImage64_probe(const char *buf, unsigned long len)
return ret;
}
+ if (!(header->xloadflags & XLF_5LEVEL) && pgtable_l5_enabled()) {
+ pr_err("bzImage cannot handle 5-level paging mode.\n");
+ return ret;
+ }
+
/* I've got a bzImage */
pr_debug("It's a relocatable bzImage64\n");
ret = 0;
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index ceba408ea982..b2b88dcaaf88 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -18,6 +18,7 @@
#include <linux/io.h>
#include <linux/suspend.h>
#include <linux/vmalloc.h>
+#include <linux/efi.h>
#include <asm/init.h>
#include <asm/pgtable.h>
@@ -29,6 +30,55 @@
#include <asm/setup.h>
#include <asm/set_memory.h>
+#ifdef CONFIG_ACPI
+/*
+ * Used while adding mapping for ACPI tables.
+ * Can be reused when other iomem regions need be mapped
+ */
+struct init_pgtable_data {
+ struct x86_mapping_info *info;
+ pgd_t *level4p;
+};
+
+static int mem_region_callback(struct resource *res, void *arg)
+{
+ struct init_pgtable_data *data = arg;
+ unsigned long mstart, mend;
+
+ mstart = res->start;
+ mend = mstart + resource_size(res) - 1;
+
+ return kernel_ident_mapping_init(data->info, data->level4p, mstart, mend);
+}
+
+static int
+map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p)
+{
+ struct init_pgtable_data data;
+ unsigned long flags;
+ int ret;
+
+ data.info = info;
+ data.level4p = level4p;
+ flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+
+ ret = walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1,
+ &data, mem_region_callback);
+ if (ret && ret != -EINVAL)
+ return ret;
+
+ /* ACPI tables could be located in ACPI Non-volatile Storage region */
+ ret = walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1,
+ &data, mem_region_callback);
+ if (ret && ret != -EINVAL)
+ return ret;
+
+ return 0;
+}
+#else
+static int map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p) { return 0; }
+#endif
+
#ifdef CONFIG_KEXEC_FILE
const struct kexec_file_ops * const kexec_file_loaders[] = {
&kexec_bzImage64_ops,
@@ -36,6 +86,31 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
};
#endif
+static int
+map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
+{
+#ifdef CONFIG_EFI
+ unsigned long mstart, mend;
+
+ if (!efi_enabled(EFI_BOOT))
+ return 0;
+
+ mstart = (boot_params.efi_info.efi_systab |
+ ((u64)boot_params.efi_info.efi_systab_hi<<32));
+
+ if (efi_enabled(EFI_64BIT))
+ mend = mstart + sizeof(efi_system_table_64_t);
+ else
+ mend = mstart + sizeof(efi_system_table_32_t);
+
+ if (!mstart)
+ return 0;
+
+ return kernel_ident_mapping_init(info, level4p, mstart, mend);
+#endif
+ return 0;
+}
+
static void free_transition_pgtable(struct kimage *image)
{
free_page((unsigned long)image->arch.p4d);
@@ -159,6 +234,18 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
return result;
}
+ /*
+ * Prepare EFI systab and ACPI tables for kexec kernel since they are
+ * not covered by pfn_mapped.
+ */
+ result = map_efi_systab(&info, level4p);
+ if (result)
+ return result;
+
+ result = map_acpi_tables(&info, level4p);
+ if (result)
+ return result;
+
return init_transition_pgtable(image, level4p);
}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 08a5f4a131f5..dcbdf54fb5c1 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -453,15 +453,24 @@ static void __init memblock_x86_reserve_range_setup_data(void)
#define CRASH_ALIGN SZ_16M
/*
- * Keep the crash kernel below this limit. On 32 bits earlier kernels
- * would limit the kernel to the low 512 MiB due to mapping restrictions.
+ * Keep the crash kernel below this limit.
+ *
+ * On 32 bits earlier kernels would limit the kernel to the low 512 MiB
+ * due to mapping restrictions.
+ *
+ * On 64bit, kdump kernel need be restricted to be under 64TB, which is
+ * the upper limit of system RAM in 4-level paing mode. Since the kdump
+ * jumping could be from 5-level to 4-level, the jumping will fail if
+ * kernel is put above 64TB, and there's no way to detect the paging mode
+ * of the kernel which will be loaded for dumping during the 1st kernel
+ * bootup.
*/
#ifdef CONFIG_X86_32
# define CRASH_ADDR_LOW_MAX SZ_512M
# define CRASH_ADDR_HIGH_MAX SZ_512M
#else
# define CRASH_ADDR_LOW_MAX SZ_4G
-# define CRASH_ADDR_HIGH_MAX MAXMEM
+# define CRASH_ADDR_HIGH_MAX SZ_64T
#endif
static int __init reserve_crashkernel_low(void)
diff --git a/include/linux/sizes.h b/include/linux/sizes.h
index fbde0bc7e882..8651269cb46c 100644
--- a/include/linux/sizes.h
+++ b/include/linux/sizes.h
@@ -47,5 +47,6 @@
#define SZ_2G 0x80000000
#define SZ_4G _AC(0x100000000, ULL)
+#define SZ_64T _AC(0x400000000000, ULL)
#endif /* __LINUX_SIZES_H__ */
^ permalink raw reply related [flat|nested] 4+ messages in thread
* [GIT pull] x86/kdump for 5.3-rc1
2019-07-09 12:33 [GIT pull] x86/boot for 5.3-rc1 Thomas Gleixner
@ 2019-07-09 12:33 ` Thomas Gleixner
2019-07-09 19:55 ` pr-tracker-bot
2019-07-09 19:55 ` [GIT pull] x86/boot " pr-tracker-bot
1 sibling, 1 reply; 4+ messages in thread
From: Thomas Gleixner @ 2019-07-09 12:33 UTC (permalink / raw)
To: Linus Torvalds; +Cc: linux-kernel, x86
Linus,
please pull the latest x86-kdump-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-kdump-for-linus
up to: 4eb5fec31e61: fs/proc/vmcore: Enable dumping of encrypted memory when SEV was active
Yet more kexec/kdump updates:
- Properly support kexec when AMD's memory encryption (SME) is enabled
- Pass reserved e820 ranges to the kexec kernel so both PCI and SME can
work.
Thanks,
tglx
------------------>
Lianbo Jiang (6):
x86/e820, ioport: Add a new I/O resource descriptor IORES_DESC_RESERVED
x86/mm: Rework ioremap resource mapping determination
x86/crash: Add e820 reserved ranges to kdump kernel's e820 table
x86/kexec: Do not map kexec area as decrypted when SEV is active
x86/kexec: Set the C-bit in the identity map page table when SEV is active
fs/proc/vmcore: Enable dumping of encrypted memory when SEV was active
Thomas Lendacky (2):
x86/mm: Identify the end of the kernel area to be reserved
x86/mm: Create a workarea in the kernel for SME early encryption
arch/x86/include/asm/sections.h | 2 ++
arch/x86/kernel/crash.c | 6 ++++
arch/x86/kernel/e820.c | 2 +-
arch/x86/kernel/machine_kexec_64.c | 31 +++++++++++++++--
arch/x86/kernel/setup.c | 8 ++++-
arch/x86/kernel/vmlinux.lds.S | 34 +++++++++++++++++-
arch/x86/mm/ioremap.c | 71 ++++++++++++++++++++++++--------------
arch/x86/mm/mem_encrypt_identity.c | 22 ++++++++++--
fs/proc/vmcore.c | 6 ++--
include/linux/ioport.h | 10 ++++++
10 files changed, 155 insertions(+), 37 deletions(-)
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index 8ea1cfdbeabc..71b32f2570ab 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -13,4 +13,6 @@ extern char __end_rodata_aligned[];
extern char __end_rodata_hpage_align[];
#endif
+extern char __end_of_kernel_reserve[];
+
#endif /* _ASM_X86_SECTIONS_H */
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 576b2e1bfc12..32c956705b8e 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -381,6 +381,12 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd,
memmap_entry_callback);
+ /* Add e820 reserved ranges */
+ cmd.type = E820_TYPE_RESERVED;
+ flags = IORESOURCE_MEM;
+ walk_iomem_res_desc(IORES_DESC_RESERVED, flags, 0, -1, &cmd,
+ memmap_entry_callback);
+
/* Add crashk_low_res region */
if (crashk_low_res.end) {
ei.addr = crashk_low_res.start;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 8f32e705a980..e69408bf664b 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1063,10 +1063,10 @@ static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry)
case E820_TYPE_NVS: return IORES_DESC_ACPI_NV_STORAGE;
case E820_TYPE_PMEM: return IORES_DESC_PERSISTENT_MEMORY;
case E820_TYPE_PRAM: return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
+ case E820_TYPE_RESERVED: return IORES_DESC_RESERVED;
case E820_TYPE_RESERVED_KERN: /* Fall-through: */
case E820_TYPE_RAM: /* Fall-through: */
case E820_TYPE_UNUSABLE: /* Fall-through: */
- case E820_TYPE_RESERVED: /* Fall-through: */
default: return IORES_DESC_NONE;
}
}
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index ceba408ea982..16c37fe489bc 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -50,12 +50,13 @@ static void free_transition_pgtable(struct kimage *image)
static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
{
+ pgprot_t prot = PAGE_KERNEL_EXEC_NOENC;
+ unsigned long vaddr, paddr;
+ int result = -ENOMEM;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
- unsigned long vaddr, paddr;
- int result = -ENOMEM;
vaddr = (unsigned long)relocate_kernel;
paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE);
@@ -92,7 +93,11 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
}
pte = pte_offset_kernel(pmd, vaddr);
- set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC));
+
+ if (sev_active())
+ prot = PAGE_KERNEL_EXEC;
+
+ set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot));
return 0;
err:
return result;
@@ -129,6 +134,11 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
level4p = (pgd_t *)__va(start_pgtable);
clear_page(level4p);
+ if (sev_active()) {
+ info.page_flag |= _PAGE_ENC;
+ info.kernpg_flag |= _PAGE_ENC;
+ }
+
if (direct_gbpages)
info.direct_gbpages = true;
@@ -559,8 +569,20 @@ void arch_kexec_unprotect_crashkres(void)
kexec_mark_crashkres(false);
}
+/*
+ * During a traditional boot under SME, SME will encrypt the kernel,
+ * so the SME kexec kernel also needs to be un-encrypted in order to
+ * replicate a normal SME boot.
+ *
+ * During a traditional boot under SEV, the kernel has already been
+ * loaded encrypted, so the SEV kexec kernel needs to be encrypted in
+ * order to replicate a normal SEV boot.
+ */
int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp)
{
+ if (sev_active())
+ return 0;
+
/*
* If SME is active we need to be sure that kexec pages are
* not encrypted because when we boot to the new kernel the
@@ -571,6 +593,9 @@ int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp)
void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages)
{
+ if (sev_active())
+ return;
+
/*
* If SME is active we need to reset the pages back to being
* an encrypted mapping before freeing them.
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 08a5f4a131f5..dac60ad37e5e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -827,8 +827,14 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
void __init setup_arch(char **cmdline_p)
{
+ /*
+ * Reserve the memory occupied by the kernel between _text and
+ * __end_of_kernel_reserve symbols. Any kernel sections after the
+ * __end_of_kernel_reserve symbol must be explicitly reserved with a
+ * separate memblock_reserve() or they will be discarded.
+ */
memblock_reserve(__pa_symbol(_text),
- (unsigned long)__bss_stop - (unsigned long)_text);
+ (unsigned long)__end_of_kernel_reserve - (unsigned long)_text);
/*
* Make sure page 0 is always reserved because on systems with
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 0850b5149345..147cd020516a 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -368,6 +368,14 @@ SECTIONS
__bss_stop = .;
}
+ /*
+ * The memory occupied from _text to here, __end_of_kernel_reserve, is
+ * automatically reserved in setup_arch(). Anything after here must be
+ * explicitly reserved using memblock_reserve() or it will be discarded
+ * and treated as available memory.
+ */
+ __end_of_kernel_reserve = .;
+
. = ALIGN(PAGE_SIZE);
.brk : AT(ADDR(.brk) - LOAD_OFFSET) {
__brk_base = .;
@@ -379,10 +387,34 @@ SECTIONS
. = ALIGN(PAGE_SIZE); /* keep VO_INIT_SIZE page aligned */
_end = .;
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ /*
+ * Early scratch/workarea section: Lives outside of the kernel proper
+ * (_text - _end).
+ *
+ * Resides after _end because even though the .brk section is after
+ * __end_of_kernel_reserve, the .brk section is later reserved as a
+ * part of the kernel. Since it is located after __end_of_kernel_reserve
+ * it will be discarded and become part of the available memory. As
+ * such, it can only be used by very early boot code and must not be
+ * needed afterwards.
+ *
+ * Currently used by SME for performing in-place encryption of the
+ * kernel during boot. Resides on a 2MB boundary to simplify the
+ * pagetable setup used for SME in-place encryption.
+ */
+ . = ALIGN(HPAGE_SIZE);
+ .init.scratch : AT(ADDR(.init.scratch) - LOAD_OFFSET) {
+ __init_scratch_begin = .;
+ *(.init.scratch)
+ . = ALIGN(HPAGE_SIZE);
+ __init_scratch_end = .;
+ }
+#endif
+
STABS_DEBUG
DWARF_DEBUG
- /* Sections to be discarded */
DISCARDS
/DISCARD/ : {
*(.eh_frame)
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 4b6423e7bd21..e500f1df1140 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -28,9 +28,11 @@
#include "physaddr.h"
-struct ioremap_mem_flags {
- bool system_ram;
- bool desc_other;
+/*
+ * Descriptor controlling ioremap() behavior.
+ */
+struct ioremap_desc {
+ unsigned int flags;
};
/*
@@ -62,13 +64,14 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size,
return err;
}
-static bool __ioremap_check_ram(struct resource *res)
+/* Does the range (or a subset of) contain normal RAM? */
+static unsigned int __ioremap_check_ram(struct resource *res)
{
unsigned long start_pfn, stop_pfn;
unsigned long i;
if ((res->flags & IORESOURCE_SYSTEM_RAM) != IORESOURCE_SYSTEM_RAM)
- return false;
+ return 0;
start_pfn = (res->start + PAGE_SIZE - 1) >> PAGE_SHIFT;
stop_pfn = (res->end + 1) >> PAGE_SHIFT;
@@ -76,28 +79,44 @@ static bool __ioremap_check_ram(struct resource *res)
for (i = 0; i < (stop_pfn - start_pfn); ++i)
if (pfn_valid(start_pfn + i) &&
!PageReserved(pfn_to_page(start_pfn + i)))
- return true;
+ return IORES_MAP_SYSTEM_RAM;
}
- return false;
+ return 0;
}
-static int __ioremap_check_desc_other(struct resource *res)
+/*
+ * In a SEV guest, NONE and RESERVED should not be mapped encrypted because
+ * there the whole memory is already encrypted.
+ */
+static unsigned int __ioremap_check_encrypted(struct resource *res)
{
- return (res->desc != IORES_DESC_NONE);
+ if (!sev_active())
+ return 0;
+
+ switch (res->desc) {
+ case IORES_DESC_NONE:
+ case IORES_DESC_RESERVED:
+ break;
+ default:
+ return IORES_MAP_ENCRYPTED;
+ }
+
+ return 0;
}
-static int __ioremap_res_check(struct resource *res, void *arg)
+static int __ioremap_collect_map_flags(struct resource *res, void *arg)
{
- struct ioremap_mem_flags *flags = arg;
+ struct ioremap_desc *desc = arg;
- if (!flags->system_ram)
- flags->system_ram = __ioremap_check_ram(res);
+ if (!(desc->flags & IORES_MAP_SYSTEM_RAM))
+ desc->flags |= __ioremap_check_ram(res);
- if (!flags->desc_other)
- flags->desc_other = __ioremap_check_desc_other(res);
+ if (!(desc->flags & IORES_MAP_ENCRYPTED))
+ desc->flags |= __ioremap_check_encrypted(res);
- return flags->system_ram && flags->desc_other;
+ return ((desc->flags & (IORES_MAP_SYSTEM_RAM | IORES_MAP_ENCRYPTED)) ==
+ (IORES_MAP_SYSTEM_RAM | IORES_MAP_ENCRYPTED));
}
/*
@@ -106,15 +125,15 @@ static int __ioremap_res_check(struct resource *res, void *arg)
* resource described not as IORES_DESC_NONE (e.g. IORES_DESC_ACPI_TABLES).
*/
static void __ioremap_check_mem(resource_size_t addr, unsigned long size,
- struct ioremap_mem_flags *flags)
+ struct ioremap_desc *desc)
{
u64 start, end;
start = (u64)addr;
end = start + size - 1;
- memset(flags, 0, sizeof(*flags));
+ memset(desc, 0, sizeof(struct ioremap_desc));
- walk_mem_res(start, end, flags, __ioremap_res_check);
+ walk_mem_res(start, end, desc, __ioremap_collect_map_flags);
}
/*
@@ -131,15 +150,15 @@ static void __ioremap_check_mem(resource_size_t addr, unsigned long size,
* have to convert them into an offset in a page-aligned mapping, but the
* caller shouldn't need to know that small detail.
*/
-static void __iomem *__ioremap_caller(resource_size_t phys_addr,
- unsigned long size, enum page_cache_mode pcm,
- void *caller, bool encrypted)
+static void __iomem *
+__ioremap_caller(resource_size_t phys_addr, unsigned long size,
+ enum page_cache_mode pcm, void *caller, bool encrypted)
{
unsigned long offset, vaddr;
resource_size_t last_addr;
const resource_size_t unaligned_phys_addr = phys_addr;
const unsigned long unaligned_size = size;
- struct ioremap_mem_flags mem_flags;
+ struct ioremap_desc io_desc;
struct vm_struct *area;
enum page_cache_mode new_pcm;
pgprot_t prot;
@@ -158,12 +177,12 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
return NULL;
}
- __ioremap_check_mem(phys_addr, size, &mem_flags);
+ __ioremap_check_mem(phys_addr, size, &io_desc);
/*
* Don't allow anybody to remap normal RAM that we're using..
*/
- if (mem_flags.system_ram) {
+ if (io_desc.flags & IORES_MAP_SYSTEM_RAM) {
WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n",
&phys_addr, &last_addr);
return NULL;
@@ -201,7 +220,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
* resulting mapping.
*/
prot = PAGE_KERNEL_IO;
- if ((sev_active() && mem_flags.desc_other) || encrypted)
+ if ((io_desc.flags & IORES_MAP_ENCRYPTED) || encrypted)
prot = pgprot_encrypted(prot);
switch (pcm) {
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 4aa9b1480866..6a8dd483f7d9 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -73,6 +73,19 @@ struct sme_populate_pgd_data {
unsigned long vaddr_end;
};
+/*
+ * This work area lives in the .init.scratch section, which lives outside of
+ * the kernel proper. It is sized to hold the intermediate copy buffer and
+ * more than enough pagetable pages.
+ *
+ * By using this section, the kernel can be encrypted in place and it
+ * avoids any possibility of boot parameters or initramfs images being
+ * placed such that the in-place encryption logic overwrites them. This
+ * section is 2MB aligned to allow for simple pagetable setup using only
+ * PMD entries (see vmlinux.lds.S).
+ */
+static char sme_workarea[2 * PMD_PAGE_SIZE] __section(.init.scratch);
+
static char sme_cmdline_arg[] __initdata = "mem_encrypt";
static char sme_cmdline_on[] __initdata = "on";
static char sme_cmdline_off[] __initdata = "off";
@@ -314,8 +327,13 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
}
#endif
- /* Set the encryption workarea to be immediately after the kernel */
- workarea_start = kernel_end;
+ /*
+ * We're running identity mapped, so we must obtain the address to the
+ * SME encryption workarea using rip-relative addressing.
+ */
+ asm ("lea sme_workarea(%%rip), %0"
+ : "=r" (workarea_start)
+ : "p" (sme_workarea));
/*
* Calculate required number of workarea bytes needed:
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 7bb96fdd38ad..57957c91c6df 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -166,7 +166,7 @@ void __weak elfcorehdr_free(unsigned long long addr)
*/
ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos)
{
- return read_from_oldmem(buf, count, ppos, 0, false);
+ return read_from_oldmem(buf, count, ppos, 0, sev_active());
}
/*
@@ -174,7 +174,7 @@ ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos)
*/
ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
{
- return read_from_oldmem(buf, count, ppos, 0, sme_active());
+ return read_from_oldmem(buf, count, ppos, 0, mem_encrypt_active());
}
/*
@@ -374,7 +374,7 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
buflen);
start = m->paddr + *fpos - m->offset;
tmp = read_from_oldmem(buffer, tsz, &start,
- userbuf, sme_active());
+ userbuf, mem_encrypt_active());
if (tmp < 0)
return tmp;
buflen -= tsz;
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index da0ebaec25f0..5db386cfc2d4 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -12,6 +12,7 @@
#ifndef __ASSEMBLY__
#include <linux/compiler.h>
#include <linux/types.h>
+#include <linux/bits.h>
/*
* Resources are tree-like, allowing
* nesting etc..
@@ -133,6 +134,15 @@ enum {
IORES_DESC_PERSISTENT_MEMORY_LEGACY = 5,
IORES_DESC_DEVICE_PRIVATE_MEMORY = 6,
IORES_DESC_DEVICE_PUBLIC_MEMORY = 7,
+ IORES_DESC_RESERVED = 8,
+};
+
+/*
+ * Flags controlling ioremap() behavior.
+ */
+enum {
+ IORES_MAP_SYSTEM_RAM = BIT(0),
+ IORES_MAP_ENCRYPTED = BIT(1),
};
/* helpers to define resources */
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [GIT pull] x86/kdump for 5.3-rc1
2019-07-09 12:33 ` [GIT pull] x86/kdump " Thomas Gleixner
@ 2019-07-09 19:55 ` pr-tracker-bot
0 siblings, 0 replies; 4+ messages in thread
From: pr-tracker-bot @ 2019-07-09 19:55 UTC (permalink / raw)
To: Thomas Gleixner; +Cc: Linus Torvalds, linux-kernel, x86
The pull request you sent on Tue, 09 Jul 2019 12:33:14 -0000:
> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-kdump-for-linus
has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/565eb5f8c5d379b6a6a3134c76b2fcfecdd007d3
Thank you!
--
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [GIT pull] x86/boot for 5.3-rc1
2019-07-09 12:33 [GIT pull] x86/boot for 5.3-rc1 Thomas Gleixner
2019-07-09 12:33 ` [GIT pull] x86/kdump " Thomas Gleixner
@ 2019-07-09 19:55 ` pr-tracker-bot
1 sibling, 0 replies; 4+ messages in thread
From: pr-tracker-bot @ 2019-07-09 19:55 UTC (permalink / raw)
To: Thomas Gleixner; +Cc: Linus Torvalds, linux-kernel, x86
The pull request you sent on Tue, 09 Jul 2019 12:33:14 -0000:
> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-boot-for-linus
has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/b7d5c9239855f99762e8a547bea03a436e8a12e8
Thank you!
--
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2019-07-09 19:55 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-07-09 12:33 [GIT pull] x86/boot for 5.3-rc1 Thomas Gleixner
2019-07-09 12:33 ` [GIT pull] x86/kdump " Thomas Gleixner
2019-07-09 19:55 ` pr-tracker-bot
2019-07-09 19:55 ` [GIT pull] x86/boot " pr-tracker-bot
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).