Files
Will Deacon e98a9d0146 arm64/efi: Avoid voluntary preemption with efi_mm installed
Gus reports a bad kernel memory access when using software PAN
(CONFIG_ARM64_SW_TTBR0_PAN=y) on a machine with support for EFI runtime
services:

  Unable to handle kernel access to user memory outside uaccess routines
    at virtual address 00000000f322ff30
  Mem abort info:
    ESR = 0x0000000096000004
    FSC = 0x04: level 0 translation fault
  Internal error: Oops: 0000000096000004 [#1]  SMP
  Workqueue: efi_rts_wq efi_call_rts
  pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
  pc : efi_call_rts+0xd8/0x288
  Call trace:
   efi_call_rts+0xd8/0x288 (P)
   process_one_work+0x178/0x4f8
   worker_thread+0x194/0x328

This is because the fpsimd context management code called from
__efi_fpsimd_begin() can preempt voluntarily, returning later to the EFI
code with an incorrect value for TTBR0_EL1 thanks to the deferred mm
switching used by the software PAN implementation.

Since EFI runtime services cannot preempt voluntarily and because the
fpsimd switching code does not rely on the TTBR0_EL1 mappings, simply
reorder the fpsimd switch so that it occurs before we change the
page-table.

Cc: Ard Biesheuvel <[email protected]>
Reported-by: Gus Bourg <[email protected]>
Tested-by: Gus Bourg <[email protected]>
Fixes: a5baf582f4 ("arm64/efi: Call EFI runtime services without disabling preemption")
Link: https://lore.kernel.org/all/[email protected]/
Reviewed-by: Ard Biesheuvel <[email protected]>
Signed-off-by: Will Deacon <[email protected]>
2026-08-12 10:21:20 +00:00

264 lines
7.2 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Extensible Firmware Interface
*
* Based on Extensible Firmware Interface Specification version 2.4
*
* Copyright (C) 2013, 2014 Linaro Ltd.
*/
#include <linux/efi.h>
#include <linux/init.h>
#include <linux/kmemleak.h>
#include <linux/kthread.h>
#include <linux/screen_info.h>
#include <linux/vmalloc.h>
#include <asm/efi.h>
#include <asm/stacktrace.h>
#include <asm/vmap_stack.h>
static bool region_is_misaligned(const efi_memory_desc_t *md)
{
if (PAGE_SIZE == EFI_PAGE_SIZE)
return false;
return !PAGE_ALIGNED(md->phys_addr) ||
!PAGE_ALIGNED(md->num_pages << EFI_PAGE_SHIFT);
}
/*
* Only regions of type EFI_RUNTIME_SERVICES_CODE need to be
* executable, everything else can be mapped with the XN bits
* set. Also take the new (optional) RO/XP bits into account.
*/
static __init ptval_t create_mapping_protection(efi_memory_desc_t *md)
{
u64 attr = md->attribute;
u32 type = md->type;
if (type == EFI_MEMORY_MAPPED_IO) {
pgprot_t prot = __pgprot(PROT_DEVICE_nGnRE);
if (arm64_is_protected_mmio(md->phys_addr,
md->num_pages << EFI_PAGE_SHIFT))
prot = pgprot_encrypted(prot);
else
prot = pgprot_decrypted(prot);
return pgprot_val(prot);
}
if (region_is_misaligned(md)) {
static bool __initdata code_is_misaligned;
/*
* Regions that are not aligned to the OS page size cannot be
* mapped with strict permissions, as those might interfere
* with the permissions that are needed by the adjacent
* region's mapping. However, if we haven't encountered any
* misaligned runtime code regions so far, we can safely use
* non-executable permissions for non-code regions.
*/
code_is_misaligned |= (type == EFI_RUNTIME_SERVICES_CODE);
return code_is_misaligned ? pgprot_val(PAGE_KERNEL_EXEC)
: pgprot_val(PAGE_KERNEL);
}
/* R-- */
if ((attr & (EFI_MEMORY_XP | EFI_MEMORY_RO)) ==
(EFI_MEMORY_XP | EFI_MEMORY_RO))
return pgprot_val(PAGE_KERNEL_RO);
/* R-X */
if (attr & EFI_MEMORY_RO)
return pgprot_val(PAGE_KERNEL_ROX);
/* RW- */
if (((attr & (EFI_MEMORY_RP | EFI_MEMORY_WP | EFI_MEMORY_XP)) ==
EFI_MEMORY_XP) ||
type != EFI_RUNTIME_SERVICES_CODE)
return pgprot_val(PAGE_KERNEL);
/* RWX */
return pgprot_val(PAGE_KERNEL_EXEC);
}
int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
{
ptval_t prot_val = create_mapping_protection(md);
bool page_mappings_only = (md->type == EFI_RUNTIME_SERVICES_CODE ||
md->type == EFI_RUNTIME_SERVICES_DATA);
/*
* If this region is not aligned to the page size used by the OS, the
* mapping will be rounded outwards, and may end up sharing a page
* frame with an adjacent runtime memory region. Given that the page
* table descriptor covering the shared page will be rewritten when the
* adjacent region gets mapped, we must avoid block mappings here so we
* don't have to worry about splitting them when that happens.
*/
if (region_is_misaligned(md))
page_mappings_only = true;
create_pgd_mapping(mm, md->phys_addr, md->virt_addr,
md->num_pages << EFI_PAGE_SHIFT,
__pgprot(prot_val | PTE_NG), page_mappings_only);
return 0;
}
struct set_perm_data {
const efi_memory_desc_t *md;
bool has_bti;
};
static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
{
struct set_perm_data *spd = data;
const efi_memory_desc_t *md = spd->md;
pte_t pte = __ptep_get(ptep);
if (md->attribute & EFI_MEMORY_RO)
pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
if (md->attribute & EFI_MEMORY_XP)
pte = set_pte_bit(pte, __pgprot(PTE_PXN));
else if (system_supports_bti_kernel() && spd->has_bti)
pte = set_pte_bit(pte, __pgprot(PTE_GP));
__set_pte(ptep, pte);
return 0;
}
int __init efi_set_mapping_permissions(struct mm_struct *mm,
efi_memory_desc_t *md,
bool has_bti)
{
struct set_perm_data data = { md, has_bti };
BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE &&
md->type != EFI_RUNTIME_SERVICES_DATA);
if (region_is_misaligned(md))
return 0;
/*
* Calling apply_to_page_range() is only safe on regions that are
* guaranteed to be mapped down to pages. Since we are only called
* for regions that have been mapped using efi_create_mapping() above
* (and this is checked by the generic Memory Attributes table parsing
* routines), there is no need to check that again here.
*/
return apply_to_page_range(mm, md->virt_addr,
md->num_pages << EFI_PAGE_SHIFT,
set_permissions, &data);
}
/*
* UpdateCapsule() depends on the system being shutdown via
* ResetSystem().
*/
bool efi_poweroff_required(void)
{
return efi_enabled(EFI_RUNTIME_SERVICES);
}
asmlinkage efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f)
{
pr_err_ratelimited(FW_BUG "register x18 corrupted by EFI %s\n", f);
return s;
}
void arch_efi_call_virt_setup(void)
{
efi_runtime_assert_lock_held();
if (preemptible() && (current->flags & PF_KTHREAD)) {
/*
* Disable migration to ensure that a preempted EFI runtime
* service call will be resumed on the same CPU. This avoids
* potential issues with EFI runtime calls that are preempted
* while polling for an asynchronous completion of a secure
* firmware call, which may not permit the CPU to change.
*/
migrate_disable();
kthread_use_mm(&efi_mm);
} else {
efi_virtmap_load();
}
__efi_fpsimd_begin();
/*
* Enable access to the valid TTBR0_EL1 and invoke the errata
* workaround directly since there is no return from exception when
* invoking the EFI run-time services.
*/
uaccess_ttbr0_enable();
post_ttbr_update_workaround();
}
void arch_efi_call_virt_teardown(void)
{
__efi_fpsimd_end();
/*
* Defer the switch to the current thread's TTBR0_EL1 until
* uaccess_enable(). Do so before efi_virtmap_unload() updates the
* saved TTBR0 value, so the userland page tables are not activated
* inadvertently over the back of an exception.
*/
uaccess_ttbr0_disable();
if (preemptible() && (current->flags & PF_KTHREAD)) {
kthread_unuse_mm(&efi_mm);
migrate_enable();
} else {
efi_virtmap_unload();
}
}
asmlinkage u64 *efi_rt_stack_top __ro_after_init;
asmlinkage efi_status_t __efi_rt_asm_recover(void);
bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg)
{
/* Check whether the exception occurred while running the firmware */
if (!current_in_efi() || regs->pc >= TASK_SIZE_64)
return false;
pr_err(FW_BUG "Unable to handle %s in EFI runtime service\n", msg);
add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
regs->regs[0] = EFI_ABORTED;
regs->regs[30] = efi_rt_stack_top[-1];
regs->pc = (u64)__efi_rt_asm_recover;
if (IS_ENABLED(CONFIG_SHADOW_CALL_STACK))
regs->regs[18] = efi_rt_stack_top[-2];
return true;
}
/* EFI requires 8 KiB of stack space for runtime services */
static_assert(THREAD_SIZE >= SZ_8K);
static int __init arm64_efi_rt_init(void)
{
void *p;
if (!efi_enabled(EFI_RUNTIME_SERVICES))
return 0;
p = arch_alloc_vmap_stack(THREAD_SIZE, NUMA_NO_NODE);
if (!p) {
pr_warn("Failed to allocate EFI runtime stack\n");
clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
return -ENOMEM;
}
kmemleak_not_leak(p);
efi_rt_stack_top = p + THREAD_SIZE;
return 0;
}
core_initcall(arm64_efi_rt_init);