
[ Upstream commit 0e68b5517d3767562889f1d83fdb828c26adb24f ] Running a rt-kernel base on 6.2.0-rc3-rt1 on an Ampere Altra outputs the following: BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:46 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 9, name: kworker/u320:0 preempt_count: 2, expected: 0 RCU nest depth: 0, expected: 0 3 locks held by kworker/u320:0/9: #0: ffff3fff8c27d128 ((wq_completion)efi_rts_wq){+.+.}-{0:0}, at: process_one_work (./include/linux/atomic/atomic-long.h:41) #1: ffff80000861bdd0 ((work_completion)(&efi_rts_work.work)){+.+.}-{0:0}, at: process_one_work (./include/linux/atomic/atomic-long.h:41) #2: ffffdf7e1ed3e460 (efi_rt_lock){+.+.}-{3:3}, at: efi_call_rts (drivers/firmware/efi/runtime-wrappers.c:101) Preemption disabled at: efi_virtmap_load (./arch/arm64/include/asm/mmu_context.h:248) CPU: 0 PID: 9 Comm: kworker/u320:0 Tainted: G W 6.2.0-rc3-rt1 Hardware name: WIWYNN Mt.Jade Server System B81.03001.0005/Mt.Jade Motherboard, BIOS 1.08.20220218 (SCP: 1.08.20220218) 2022/02/18 Workqueue: efi_rts_wq efi_call_rts Call trace: dump_backtrace (arch/arm64/kernel/stacktrace.c:158) show_stack (arch/arm64/kernel/stacktrace.c:165) dump_stack_lvl (lib/dump_stack.c:107 (discriminator 4)) dump_stack (lib/dump_stack.c:114) __might_resched (kernel/sched/core.c:10134) rt_spin_lock (kernel/locking/rtmutex.c:1769 (discriminator 4)) efi_call_rts (drivers/firmware/efi/runtime-wrappers.c:101) [...] This seems to come from commit ff7a167961d1 ("arm64: efi: Execute runtime services from a dedicated stack") which adds a spinlock. This spinlock is taken through: efi_call_rts() \-efi_call_virt() \-efi_call_virt_pointer() \-arch_efi_call_virt_setup() Make 'efi_rt_lock' a raw_spinlock to avoid being preempted. [ardb: The EFI runtime services are called with a different set of translation tables, and are permitted to use the SIMD registers. The context switch code preserves/restores neither, and so EFI calls must be made with preemption disabled, rather than only disabling migration.] Fixes: ff7a167961d1 ("arm64: efi: Execute runtime services from a dedicated stack") Signed-off-by: Pierre Gondois <pierre.gondois@arm.com> Cc: <stable@vger.kernel.org> # v6.1+ Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
148 lines
4.3 KiB
C
148 lines
4.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _ASM_EFI_H
|
|
#define _ASM_EFI_H
|
|
|
|
#include <asm/boot.h>
|
|
#include <asm/cpufeature.h>
|
|
#include <asm/fpsimd.h>
|
|
#include <asm/io.h>
|
|
#include <asm/memory.h>
|
|
#include <asm/mmu_context.h>
|
|
#include <asm/neon.h>
|
|
#include <asm/ptrace.h>
|
|
#include <asm/tlbflush.h>
|
|
|
|
#ifdef CONFIG_EFI
|
|
extern void efi_init(void);
|
|
#else
|
|
#define efi_init()
|
|
#endif
|
|
|
|
int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
|
|
int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
|
|
|
|
#define arch_efi_call_virt_setup() \
|
|
({ \
|
|
efi_virtmap_load(); \
|
|
__efi_fpsimd_begin(); \
|
|
raw_spin_lock(&efi_rt_lock); \
|
|
})
|
|
|
|
#define arch_efi_call_virt(p, f, args...) \
|
|
({ \
|
|
efi_##f##_t *__f; \
|
|
__f = p->f; \
|
|
__efi_rt_asm_wrapper(__f, #f, args); \
|
|
})
|
|
|
|
#define arch_efi_call_virt_teardown() \
|
|
({ \
|
|
raw_spin_unlock(&efi_rt_lock); \
|
|
__efi_fpsimd_end(); \
|
|
efi_virtmap_unload(); \
|
|
})
|
|
|
|
extern raw_spinlock_t efi_rt_lock;
|
|
efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...);
|
|
|
|
#define ARCH_EFI_IRQ_FLAGS_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
|
|
|
|
/*
|
|
* Even when Linux uses IRQ priorities for IRQ disabling, EFI does not.
|
|
* And EFI shouldn't really play around with priority masking as it is not aware
|
|
* which priorities the OS has assigned to its interrupts.
|
|
*/
|
|
#define arch_efi_save_flags(state_flags) \
|
|
((void)((state_flags) = read_sysreg(daif)))
|
|
|
|
#define arch_efi_restore_flags(state_flags) write_sysreg(state_flags, daif)
|
|
|
|
|
|
/* arch specific definitions used by the stub code */
|
|
|
|
/*
|
|
* In some configurations (e.g. VMAP_STACK && 64K pages), stacks built into the
|
|
* kernel need greater alignment than we require the segments to be padded to.
|
|
*/
|
|
#define EFI_KIMG_ALIGN \
|
|
(SEGMENT_ALIGN > THREAD_ALIGN ? SEGMENT_ALIGN : THREAD_ALIGN)
|
|
|
|
/* on arm64, the FDT may be located anywhere in system RAM */
|
|
static inline unsigned long efi_get_max_fdt_addr(unsigned long image_addr)
|
|
{
|
|
return ULONG_MAX;
|
|
}
|
|
|
|
/*
|
|
* On arm64, we have to ensure that the initrd ends up in the linear region,
|
|
* which is a 1 GB aligned region of size '1UL << (VA_BITS_MIN - 1)' that is
|
|
* guaranteed to cover the kernel Image.
|
|
*
|
|
* Since the EFI stub is part of the kernel Image, we can relax the
|
|
* usual requirements in Documentation/arm64/booting.rst, which still
|
|
* apply to other bootloaders, and are required for some kernel
|
|
* configurations.
|
|
*/
|
|
static inline unsigned long efi_get_max_initrd_addr(unsigned long image_addr)
|
|
{
|
|
return (image_addr & ~(SZ_1G - 1UL)) + (1UL << (VA_BITS_MIN - 1));
|
|
}
|
|
|
|
#define alloc_screen_info(x...) &screen_info
|
|
|
|
static inline void free_screen_info(struct screen_info *si)
|
|
{
|
|
}
|
|
|
|
static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
|
|
{
|
|
}
|
|
|
|
#define EFI_ALLOC_ALIGN SZ_64K
|
|
|
|
/*
|
|
* On ARM systems, virtually remapped UEFI runtime services are set up in two
|
|
* distinct stages:
|
|
* - The stub retrieves the final version of the memory map from UEFI, populates
|
|
* the virt_addr fields and calls the SetVirtualAddressMap() [SVAM] runtime
|
|
* service to communicate the new mapping to the firmware (Note that the new
|
|
* mapping is not live at this time)
|
|
* - During an early initcall(), the EFI system table is permanently remapped
|
|
* and the virtual remapping of the UEFI Runtime Services regions is loaded
|
|
* into a private set of page tables. If this all succeeds, the Runtime
|
|
* Services are enabled and the EFI_RUNTIME_SERVICES bit set.
|
|
*/
|
|
|
|
static inline void efi_set_pgd(struct mm_struct *mm)
|
|
{
|
|
__switch_mm(mm);
|
|
|
|
if (system_uses_ttbr0_pan()) {
|
|
if (mm != current->active_mm) {
|
|
/*
|
|
* Update the current thread's saved ttbr0 since it is
|
|
* restored as part of a return from exception. 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.
|
|
*/
|
|
update_saved_ttbr0(current, mm);
|
|
uaccess_ttbr0_enable();
|
|
post_ttbr_update_workaround();
|
|
} else {
|
|
/*
|
|
* Defer the switch to the current thread's TTBR0_EL1
|
|
* until uaccess_enable(). Restore the current
|
|
* thread's saved ttbr0 corresponding to its active_mm
|
|
*/
|
|
uaccess_ttbr0_disable();
|
|
update_saved_ttbr0(current, current->active_mm);
|
|
}
|
|
}
|
|
}
|
|
|
|
void efi_virtmap_load(void);
|
|
void efi_virtmap_unload(void);
|
|
|
|
#endif /* _ASM_EFI_H */
|