From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp
---
kernel/arch/x86/kernel/machine_kexec_64.c | 186 +++++++++++++++++++++++++++++-----------------
1 files changed, 116 insertions(+), 70 deletions(-)
diff --git a/kernel/arch/x86/kernel/machine_kexec_64.c b/kernel/arch/x86/kernel/machine_kexec_64.c
index 4c8acdf..a29a44a 100644
--- a/kernel/arch/x86/kernel/machine_kexec_64.c
+++ b/kernel/arch/x86/kernel/machine_kexec_64.c
@@ -1,9 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* handle transition of Linux booting another kernel
* Copyright (C) 2002-2005 Eric Biederman <ebiederm@xmission.com>
- *
- * This source code is licensed under the GNU General Public License,
- * Version 2. See the file COPYING for more details.
*/
#define pr_fmt(fmt) "kexec: " fmt
@@ -18,9 +16,9 @@
#include <linux/io.h>
#include <linux/suspend.h>
#include <linux/vmalloc.h>
+#include <linux/efi.h>
#include <asm/init.h>
-#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/io_apic.h>
@@ -29,12 +27,86 @@
#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,
NULL
};
#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)
{
@@ -50,12 +122,13 @@
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 +165,11 @@
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 +206,11 @@
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;
@@ -158,6 +240,18 @@
if (result)
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);
}
@@ -203,48 +297,6 @@
);
}
-#ifdef CONFIG_KEXEC_FILE
-/* Update purgatory as needed after various image segments have been prepared */
-static int arch_update_purgatory(struct kimage *image)
-{
- int ret = 0;
-
- if (!image->file_mode)
- return 0;
-
- /* Setup copying of backup region */
- if (image->type == KEXEC_TYPE_CRASH) {
- ret = kexec_purgatory_get_set_symbol(image,
- "purgatory_backup_dest",
- &image->arch.backup_load_addr,
- sizeof(image->arch.backup_load_addr), 0);
- if (ret)
- return ret;
-
- ret = kexec_purgatory_get_set_symbol(image,
- "purgatory_backup_src",
- &image->arch.backup_src_start,
- sizeof(image->arch.backup_src_start), 0);
- if (ret)
- return ret;
-
- ret = kexec_purgatory_get_set_symbol(image,
- "purgatory_backup_sz",
- &image->arch.backup_src_sz,
- sizeof(image->arch.backup_src_sz), 0);
- if (ret)
- return ret;
- }
-
- return ret;
-}
-#else /* !CONFIG_KEXEC_FILE */
-static inline int arch_update_purgatory(struct kimage *image)
-{
- return 0;
-}
-#endif /* CONFIG_KEXEC_FILE */
-
int machine_kexec_prepare(struct kimage *image)
{
unsigned long start_pgtable;
@@ -255,11 +307,6 @@
/* Setup the identity mapped 64bit page table */
result = init_pgtable(image, start_pgtable);
- if (result)
- return result;
-
- /* update purgatory as needed */
- result = arch_update_purgatory(image);
if (result)
return result;
@@ -348,22 +395,6 @@
#endif
__ftrace_enabled_restore(save_ftrace_enabled);
-}
-
-void arch_crash_save_vmcoreinfo(void)
-{
- VMCOREINFO_NUMBER(phys_base);
- VMCOREINFO_SYMBOL(init_top_pgt);
- vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n",
- pgtable_l5_enabled());
-
-#ifdef CONFIG_NUMA
- VMCOREINFO_SYMBOL(node_data);
- VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
-#endif
- vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
- kaslr_offset());
- VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE);
}
/* arch-dependent functionality related to kexec file-based syscall */
@@ -556,8 +587,20 @@
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
@@ -568,6 +611,9 @@
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.
--
Gitblit v1.6.2