@@ -88,6 +88,7 @@ lib-$(CONFIG_EFI_GENERIC_STUB) += efi-stub.o string.o intrinsics.o systable.o \
lib-$(CONFIG_ARM) += arm32-stub.o
lib-$(CONFIG_ARM64) += arm64.o arm64-stub.o smbios.o
lib-$(CONFIG_X86) += x86-stub.o
+lib-$(CONFIG_X86_64) += x86-5lvl.o
lib-$(CONFIG_RISCV) += riscv.o riscv-stub.o
lib-$(CONFIG_LOONGARCH) += loongarch.o loongarch-stub.o
@@ -73,6 +73,8 @@ efi_status_t efi_parse_options(char const *cmdline)
efi_loglevel = CONSOLE_LOGLEVEL_QUIET;
} else if (!strcmp(param, "noinitrd")) {
efi_noinitrd = true;
+ } else if (IS_ENABLED(CONFIG_X86_64) && !strcmp(param, "no5lvl")) {
+ efi_no5lvl = true;
} else if (!strcmp(param, "efi") && val) {
efi_nochunk = parse_option_str(val, "nochunk");
efi_novamap |= parse_option_str(val, "novamap");
@@ -33,6 +33,7 @@
#define EFI_ALLOC_LIMIT ULONG_MAX
#endif
+extern bool efi_no5lvl;
extern bool efi_nochunk;
extern bool efi_nokaslr;
extern int efi_loglevel;
new file mode 100644
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/efi.h>
+
+#include <asm/boot.h>
+#include <asm/desc.h>
+#include <asm/efi.h>
+
+#include "efistub.h"
+#include "x86-stub.h"
+
+bool efi_no5lvl;
+
+static void (*la57_toggle)(void *trampoline, bool enable_5lvl);
+
+static const struct desc_struct gdt[] = {
+ [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff),
+ [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff),
+};
+
+/*
+ * Enabling (or disabling) 5 level paging is tricky, because it can only be
+ * done from 32-bit mode with paging disabled. This means not only that the
+ * code itself must be running from 32-bit addressable physical memory, but
+ * also that the root page table must be 32-bit addressable, as we cannot
+ * program a 64-bit value into CR3 when running in 32-bit mode.
+ */
+efi_status_t efi_setup_5level_paging(void)
+{
+ u8 tmpl_size = (u8 *)&trampoline_ljmp_imm_offset - (u8 *)&trampoline_32bit_src;
+ efi_status_t status;
+ u8 *la57_code;
+
+ if (!efi_is_64bit())
+ return EFI_SUCCESS;
+
+ /* check for 5 level paging support */
+ if (native_cpuid_eax(0) < 7 ||
+ !(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31))))
+ return EFI_SUCCESS;
+
+ /* allocate some 32-bit addressable memory for code and a page table */
+ status = efi_allocate_pages(2 * PAGE_SIZE, (unsigned long *)&la57_code,
+ U32_MAX);
+ if (status != EFI_SUCCESS)
+ return status;
+
+ la57_toggle = memcpy(la57_code, trampoline_32bit_src, tmpl_size);
+ memset(la57_code + tmpl_size, 0x90, PAGE_SIZE - tmpl_size);
+
+ /*
+ * To avoid having to allocate a 32-bit addressable stack, we use a
+ * ljmp to switch back to long mode. However, this takes an absolute
+ * address, so we have to poke it in at runtime.
+ */
+ *(u32 *)&la57_code[trampoline_ljmp_imm_offset] += (unsigned long)la57_code;
+
+ efi_adjust_memory_range_protection((unsigned long)la57_toggle, PAGE_SIZE);
+
+ return EFI_SUCCESS;
+}
+
+void efi_5level_switch(void)
+{
+ bool want_la57 = IS_ENABLED(CONFIG_X86_5LEVEL) && !efi_no5lvl;
+ bool have_la57 = native_read_cr4() & X86_CR4_LA57;
+ bool need_toggle = want_la57 ^ have_la57;
+ u64 *pgt = (void *)la57_toggle + PAGE_SIZE;
+ u64 *cr3 = (u64 *)__native_read_cr3();
+ u64 *new_cr3;
+
+ if (!la57_toggle || !need_toggle)
+ return;
+
+ if (!have_la57) {
+ /*
+ * We are going to enable 5 level paging, so we need to
+ * allocate a root level page from the 32-bit addressable
+ * physical region, and plug the existing hierarchy into it.
+ */
+ new_cr3 = memset(pgt, 0, PAGE_SIZE);
+ new_cr3[0] = (u64)cr3 | _PAGE_TABLE_NOENC;
+ } else {
+ // take the new root table pointer from the current entry #0
+ new_cr3 = (u64 *)(cr3[0] & PAGE_MASK);
+
+ // copy the new root level table if it is not 32-bit addressable
+ if ((u64)new_cr3 > U32_MAX)
+ new_cr3 = memcpy(pgt, new_cr3, PAGE_SIZE);
+ }
+
+ native_load_gdt(&(struct desc_ptr){ sizeof(gdt) - 1, (u64)gdt });
+
+ la57_toggle(new_cr3, want_la57);
+}
@@ -17,6 +17,7 @@
#include <asm/boot.h>
#include "efistub.h"
+#include "x86-stub.h"
/* Maximum physical address for 64-bit kernel with 4-level paging */
#define MAXMEM_X86_64_4LEVEL (1ull << 46)
@@ -212,8 +213,8 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
}
}
-static void
-adjust_memory_range_protection(unsigned long start, unsigned long size)
+void efi_adjust_memory_range_protection(unsigned long start,
+ unsigned long size)
{
efi_status_t status;
efi_gcd_memory_space_desc_t desc;
@@ -267,35 +268,14 @@ adjust_memory_range_protection(unsigned long start, unsigned long size)
}
}
-/*
- * Trampoline takes 2 pages and can be loaded in first megabyte of memory
- * with its end placed between 128k and 640k where BIOS might start.
- * (see arch/x86/boot/compressed/pgtable_64.c)
- *
- * We cannot find exact trampoline placement since memory map
- * can be modified by UEFI, and it can alter the computed address.
- */
-
-#define TRAMPOLINE_PLACEMENT_BASE ((128 - 8)*1024)
-#define TRAMPOLINE_PLACEMENT_SIZE (640*1024 - (128 - 8)*1024)
-
void startup_32(struct boot_params *boot_params);
static void
setup_memory_protection(unsigned long image_base, unsigned long image_size)
{
- /*
- * Allow execution of possible trampoline used
- * for switching between 4- and 5-level page tables
- * and relocated kernel image.
- */
-
- adjust_memory_range_protection(TRAMPOLINE_PLACEMENT_BASE,
- TRAMPOLINE_PLACEMENT_SIZE);
-
#ifdef CONFIG_64BIT
if (image_base != (unsigned long)startup_32)
- adjust_memory_range_protection(image_base, image_size);
+ efi_adjust_memory_range_protection(image_base, image_size);
#else
/*
* Clear protection flags on a whole range of possible
@@ -305,8 +285,8 @@ setup_memory_protection(unsigned long image_base, unsigned long image_size)
* need to remove possible protection on relocated image
* itself disregarding further relocations.
*/
- adjust_memory_range_protection(LOAD_PHYSICAL_ADDR,
- KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR);
+ efi_adjust_memory_range_protection(LOAD_PHYSICAL_ADDR,
+ KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR);
#endif
}
@@ -804,6 +784,12 @@ void __noreturn efi_stub_entry(efi_handle_t handle,
efi_dxe_table = NULL;
}
+ status = efi_setup_5level_paging();
+ if (status != EFI_SUCCESS) {
+ efi_err("efi_setup_5level_paging() failed!\n");
+ goto fail;
+ }
+
/*
* If the kernel isn't already loaded at a suitable address,
* relocate it.
@@ -922,6 +908,8 @@ void __noreturn efi_stub_entry(efi_handle_t handle,
goto fail;
}
+ efi_5level_switch();
+
if (IS_ENABLED(CONFIG_X86_64))
/* add offset of startup_64() */
bzimage_addr += 0x200;
new file mode 100644
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/efi.h>
+
+extern void trampoline_32bit_src(void *, bool);
+extern const u16 trampoline_ljmp_imm_offset;
+
+void efi_adjust_memory_range_protection(unsigned long start,
+ unsigned long size);
+
+#ifdef CONFIG_X86_64
+efi_status_t efi_setup_5level_paging(void);
+void efi_5level_switch(void);
+#else
+static inline efi_status_t efi_setup_5level_paging(void) { return EFI_SUCCESS; }
+static inline void efi_5level_switch(void) {}
+#endif