#include <asm/esr.h>
#include <asm/irq.h>
#include <asm/memory.h>
+#include <asm/mmu.h>
+#include <asm/processor.h>
#include <asm/ptrace.h>
#include <asm/thread_info.h>
#include <asm/asm-uaccess.h>
#define BAD_FIQ 2
#define BAD_ERROR 3
- .macro kernel_entry, el, regsize = 64
+ .macro kernel_ventry, el, label, regsize = 64
+ .align 7
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+alternative_if ARM64_UNMAP_KERNEL_AT_EL0
+ .if \el == 0
+ .if \regsize == 64
+ mrs x30, tpidrro_el0
+ msr tpidrro_el0, xzr
+ .else
+ mov x30, xzr
+ .endif
+ .endif
+alternative_else_nop_endif
+#endif
+
sub sp, sp, #S_FRAME_SIZE
+#ifdef CONFIG_VMAP_STACK
+ /*
+ * Test whether the SP has overflowed, without corrupting a GPR.
+ * Task and IRQ stacks are aligned to (1 << THREAD_SHIFT).
+ */
+ add sp, sp, x0 // sp' = sp + x0
+ sub x0, sp, x0 // x0' = sp' - x0 = (sp + x0) - x0 = sp
+ tbnz x0, #THREAD_SHIFT, 0f
+ sub x0, sp, x0 // x0'' = sp' - x0' = (sp + x0) - sp = x0
+ sub sp, sp, x0 // sp'' = sp' - x0 = (sp + x0) - x0 = sp
+ b el\()\el\()_\label
+
+0:
+ /*
+ * Either we've just detected an overflow, or we've taken an exception
+ * while on the overflow stack. Either way, we won't return to
+ * userspace, and can clobber EL0 registers to free up GPRs.
+ */
+
+ /* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */
+ msr tpidr_el0, x0
+
+ /* Recover the original x0 value and stash it in tpidrro_el0 */
+ sub x0, sp, x0
+ msr tpidrro_el0, x0
+
+ /* Switch to the overflow stack */
+ adr_this_cpu sp, overflow_stack + OVERFLOW_STACK_SIZE, x0
+
+ /*
+ * Check whether we were already on the overflow stack. This may happen
+ * after panic() re-enables interrupts.
+ */
+ mrs x0, tpidr_el0 // sp of interrupted context
+ sub x0, sp, x0 // delta with top of overflow stack
+ tst x0, #~(OVERFLOW_STACK_SIZE - 1) // within range?
+ b.ne __bad_stack // no? -> bad stack pointer
+
+ /* We were already on the overflow stack. Restore sp/x0 and carry on. */
+ sub sp, sp, x0
+ mrs x0, tpidrro_el0
+#endif
+ b el\()\el\()_\label
+ .endm
+
+ .macro tramp_alias, dst, sym
+ mov_q \dst, TRAMP_VALIAS
+ add \dst, \dst, #(\sym - .entry.tramp.text)
+ .endm
+
+ .macro kernel_entry, el, regsize = 64
.if \regsize == 32
mov w0, w0 // zero upper 32 bits of x0
.endif
.else
add x21, sp, #S_FRAME_SIZE
get_thread_info tsk
- /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+ /* Save the task's original addr_limit and set USER_DS */
ldr x20, [tsk, #TSK_TI_ADDR_LIMIT]
str x20, [sp, #S_ORIG_ADDR_LIMIT]
- mov x20, #TASK_SIZE_64
+ mov x20, #USER_DS
str x20, [tsk, #TSK_TI_ADDR_LIMIT]
/* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */
.endif /* \el == 0 */
mrs x23, spsr_el1
stp lr, x21, [sp, #S_LR]
+ /*
+ * In order to be able to dump the contents of struct pt_regs at the
+ * time the exception was taken (in case we attempt to walk the call
+ * stack later), chain it together with the stack frames.
+ */
+ .if \el == 0
+ stp xzr, xzr, [sp, #S_STACKFRAME]
+ .else
+ stp x29, x22, [sp, #S_STACKFRAME]
+ .endif
+ add x29, sp, #S_STACKFRAME
+
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
/*
* Set the TTBR0 PAN bit in SPSR. When the exception is taken from
.if \el != 0
mrs x21, ttbr0_el1
- tst x21, #0xffff << 48 // Check for the reserved ASID
+ tst x21, #TTBR_ASID_MASK // Check for the reserved ASID
orr x23, x23, #PSR_PAN_BIT // Set the emulated PAN in the saved SPSR
b.eq 1f // TTBR0 access already disabled
and x23, x23, #~PSR_PAN_BIT // Clear the emulated PAN in the saved SPSR
* Set syscallno to -1 by default (overridden later if real syscall).
*/
.if \el == 0
- mvn x21, xzr
- str x21, [sp, #S_SYSCALLNO]
+ mvn w21, wzr
+ str w21, [sp, #S_SYSCALLNO]
.endif
/*
tbnz x22, #22, 1f // Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set
.endif
- __uaccess_ttbr0_enable x0
+ __uaccess_ttbr0_enable x0, x1
.if \el == 0
/*
* Cavium erratum 27456 (broadcast TLBI instructions may cause I-cache
* corruption).
*/
- post_ttbr0_update_workaround
+ bl post_ttbr_update_workaround
.endif
1:
.if \el != 0
.if \el == 0
ldr x23, [sp, #S_SP] // load return stack pointer
msr sp_el0, x23
+ tst x22, #PSR_MODE32_BIT // native task?
+ b.eq 3f
+
#ifdef CONFIG_ARM64_ERRATUM_845719
alternative_if ARM64_WORKAROUND_845719
- tbz x22, #4, 1f
#ifdef CONFIG_PID_IN_CONTEXTIDR
mrs x29, contextidr_el1
msr contextidr_el1, x29
#else
msr contextidr_el1, xzr
#endif
-1:
alternative_else_nop_endif
#endif
+3:
.endif
msr elr_el1, x21 // set up the return data
ldp x28, x29, [sp, #16 * 14]
ldr lr, [sp, #S_LR]
add sp, sp, #S_FRAME_SIZE // restore sp
- eret // return to kernel
+
+ .if \el == 0
+alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ bne 4f
+ msr far_el1, x30
+ tramp_alias x30, tramp_exit_native
+ br x30
+4:
+ tramp_alias x30, tramp_exit_compat
+ br x30
+#endif
+ .else
+ eret
+ .endif
.endm
.macro irq_stack_entry
and x25, x25, #~(THREAD_SIZE - 1)
cbnz x25, 9998f
- adr_this_cpu x25, irq_stack, x26
- mov x26, #IRQ_STACK_START_SP
+ ldr_this_cpu x25, irq_stack_ptr, x26
+ mov x26, #IRQ_STACK_SIZE
add x26, x25, x26
/* switch to the irq stack */
mov sp, x26
-
- /*
- * Add a dummy stack frame, this non-standard format is fixed up
- * by unwind_frame()
- */
- stp x29, x19, [sp, #-16]!
- mov x29, sp
-
9998:
.endm
*
* x7 is reserved for the system call number in 32-bit mode.
*/
-sc_nr .req x25 // number of system calls
-scno .req x26 // syscall number
+wsc_nr .req w25 // number of system calls
+xsc_nr .req x25 // number of system calls (zero-extended)
+wscno .req w26 // syscall number
+xscno .req x26 // syscall number (zero-extended)
stbl .req x27 // syscall table pointer
tsk .req x28 // current thread_info
.align 11
ENTRY(vectors)
- ventry el1_sync_invalid // Synchronous EL1t
- ventry el1_irq_invalid // IRQ EL1t
- ventry el1_fiq_invalid // FIQ EL1t
- ventry el1_error_invalid // Error EL1t
+ kernel_ventry 1, sync_invalid // Synchronous EL1t
+ kernel_ventry 1, irq_invalid // IRQ EL1t
+ kernel_ventry 1, fiq_invalid // FIQ EL1t
+ kernel_ventry 1, error_invalid // Error EL1t
- ventry el1_sync // Synchronous EL1h
- ventry el1_irq // IRQ EL1h
- ventry el1_fiq_invalid // FIQ EL1h
- ventry el1_error_invalid // Error EL1h
+ kernel_ventry 1, sync // Synchronous EL1h
+ kernel_ventry 1, irq // IRQ EL1h
+ kernel_ventry 1, fiq_invalid // FIQ EL1h
+ kernel_ventry 1, error_invalid // Error EL1h
- ventry el0_sync // Synchronous 64-bit EL0
- ventry el0_irq // IRQ 64-bit EL0
- ventry el0_fiq_invalid // FIQ 64-bit EL0
- ventry el0_error_invalid // Error 64-bit EL0
+ kernel_ventry 0, sync // Synchronous 64-bit EL0
+ kernel_ventry 0, irq // IRQ 64-bit EL0
+ kernel_ventry 0, fiq_invalid // FIQ 64-bit EL0
+ kernel_ventry 0, error_invalid // Error 64-bit EL0
#ifdef CONFIG_COMPAT
- ventry el0_sync_compat // Synchronous 32-bit EL0
- ventry el0_irq_compat // IRQ 32-bit EL0
- ventry el0_fiq_invalid_compat // FIQ 32-bit EL0
- ventry el0_error_invalid_compat // Error 32-bit EL0
+ kernel_ventry 0, sync_compat, 32 // Synchronous 32-bit EL0
+ kernel_ventry 0, irq_compat, 32 // IRQ 32-bit EL0
+ kernel_ventry 0, fiq_invalid_compat, 32 // FIQ 32-bit EL0
+ kernel_ventry 0, error_invalid_compat, 32 // Error 32-bit EL0
#else
- ventry el0_sync_invalid // Synchronous 32-bit EL0
- ventry el0_irq_invalid // IRQ 32-bit EL0
- ventry el0_fiq_invalid // FIQ 32-bit EL0
- ventry el0_error_invalid // Error 32-bit EL0
+ kernel_ventry 0, sync_invalid, 32 // Synchronous 32-bit EL0
+ kernel_ventry 0, irq_invalid, 32 // IRQ 32-bit EL0
+ kernel_ventry 0, fiq_invalid, 32 // FIQ 32-bit EL0
+ kernel_ventry 0, error_invalid, 32 // Error 32-bit EL0
#endif
END(vectors)
+#ifdef CONFIG_VMAP_STACK
+ /*
+ * We detected an overflow in kernel_ventry, which switched to the
+ * overflow stack. Stash the exception regs, and head to our overflow
+ * handler.
+ */
+__bad_stack:
+ /* Restore the original x0 value */
+ mrs x0, tpidrro_el0
+
+ /*
+ * Store the original GPRs to the new stack. The orginal SP (minus
+ * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry.
+ */
+ sub sp, sp, #S_FRAME_SIZE
+ kernel_entry 1
+ mrs x0, tpidr_el0
+ add x0, x0, #S_FRAME_SIZE
+ str x0, [sp, #S_SP]
+
+ /* Stash the regs for handle_bad_stack */
+ mov x0, sp
+
+ /* Time to die */
+ bl handle_bad_stack
+ ASM_BUG()
+#endif /* CONFIG_VMAP_STACK */
+
/*
* Invalid mode handlers
*/
mov x0, sp
mov x1, #\reason
mrs x2, esr_el1
- b bad_mode
+ bl bad_mode
+ ASM_BUG()
.endm
el0_sync_invalid:
mrs x0, far_el1
enable_dbg
mov x2, sp
- b do_sp_pc_abort
+ bl do_sp_pc_abort
+ ASM_BUG()
el1_undef:
/*
* Undefined instruction
*/
enable_dbg
mov x0, sp
- b do_undefinstr
+ bl do_undefinstr
+ ASM_BUG()
el1_dbg:
/*
* Debug exception handling
mov x0, sp
mov x2, x1
mov x1, #BAD_SYNC
- b bad_mode
+ bl bad_mode
+ ASM_BUG()
ENDPROC(el1_sync)
.align 6
* AArch32 syscall handling
*/
adrp stbl, compat_sys_call_table // load compat syscall table pointer
- uxtw scno, w7 // syscall number in w7 (r7)
- mov sc_nr, #__NR_compat_syscalls
+ mov wscno, w7 // syscall number in w7 (r7)
+ mov wsc_nr, #__NR_compat_syscalls
b el0_svc_naked
.align 6
b ret_to_user
ENDPROC(el0_irq)
-/*
- * Register switch for AArch64. The callee-saved registers need to be saved
- * and restored. On entry:
- * x0 = previous task_struct (must be preserved across the switch)
- * x1 = next task_struct
- * Previous and next are guaranteed not to be the same.
- *
- */
-ENTRY(cpu_switch_to)
- mov x10, #THREAD_CPU_CONTEXT
- add x8, x0, x10
- mov x9, sp
- stp x19, x20, [x8], #16 // store callee-saved registers
- stp x21, x22, [x8], #16
- stp x23, x24, [x8], #16
- stp x25, x26, [x8], #16
- stp x27, x28, [x8], #16
- stp x29, x9, [x8], #16
- str lr, [x8]
- add x8, x1, x10
- ldp x19, x20, [x8], #16 // restore callee-saved registers
- ldp x21, x22, [x8], #16
- ldp x23, x24, [x8], #16
- ldp x25, x26, [x8], #16
- ldp x27, x28, [x8], #16
- ldp x29, x9, [x8], #16
- ldr lr, [x8]
- mov sp, x9
- msr sp_el0, x1
- ret
-ENDPROC(cpu_switch_to)
-
/*
* This is the fast syscall return path. We do as little as possible here,
* and this includes saving x0 back into the kernel stack.
kernel_exit 0
ENDPROC(ret_to_user)
-/*
- * This is how we return from a fork.
- */
-ENTRY(ret_from_fork)
- bl schedule_tail
- cbz x19, 1f // not a kernel thread
- mov x0, x20
- blr x19
-1: get_thread_info tsk
- b ret_to_user
-ENDPROC(ret_from_fork)
-
/*
* SVC handler.
*/
.align 6
el0_svc:
adrp stbl, sys_call_table // load syscall table pointer
- uxtw scno, w8 // syscall number in w8
- mov sc_nr, #__NR_syscalls
+ mov wscno, w8 // syscall number in w8
+ mov wsc_nr, #__NR_syscalls
el0_svc_naked: // compat entry point
- stp x0, scno, [sp, #S_ORIG_X0] // save the original x0 and syscall number
+ stp x0, xscno, [sp, #S_ORIG_X0] // save the original x0 and syscall number
enable_dbg_and_irq
ct_user_exit 1
ldr x16, [tsk, #TSK_TI_FLAGS] // check for syscall hooks
tst x16, #_TIF_SYSCALL_WORK
b.ne __sys_trace
- cmp scno, sc_nr // check upper syscall limit
+ cmp wscno, wsc_nr // check upper syscall limit
b.hs ni_sys
- ldr x16, [stbl, scno, lsl #3] // address in the syscall table
+ mask_nospec64 xscno, xsc_nr, x19 // enforce bounds for syscall number
+ ldr x16, [stbl, xscno, lsl #3] // address in the syscall table
blr x16 // call sys_* routine
b ret_fast_syscall
ni_sys:
* switches, and waiting for our parent to respond.
*/
__sys_trace:
- mov w0, #-1 // set default errno for
- cmp scno, x0 // user-issued syscall(-1)
+ cmp wscno, #-1 // user-issued syscall(-1)?
b.ne 1f
- mov x0, #-ENOSYS
+ mov x0, #-ENOSYS // set default errno if so
str x0, [sp, #S_X0]
1: mov x0, sp
bl syscall_trace_enter
cmp w0, #-1 // skip the syscall?
b.eq __sys_trace_return_skipped
- uxtw scno, w0 // syscall number (possibly new)
+ mov wscno, w0 // syscall number (possibly new)
mov x1, sp // pointer to regs
- cmp scno, sc_nr // check upper syscall limit
+ cmp wscno, wsc_nr // check upper syscall limit
b.hs __ni_sys_trace
ldp x0, x1, [sp] // restore the syscall args
ldp x2, x3, [sp, #S_X2]
ldp x4, x5, [sp, #S_X4]
ldp x6, x7, [sp, #S_X6]
- ldr x16, [stbl, scno, lsl #3] // address in the syscall table
+ ldr x16, [stbl, xscno, lsl #3] // address in the syscall table
blr x16 // call sys_* routine
__sys_trace_return:
.popsection // .entry.text
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+/*
+ * Exception vectors trampoline.
+ */
+ .pushsection ".entry.tramp.text", "ax"
+
+ .macro tramp_map_kernel, tmp
+ mrs \tmp, ttbr1_el1
+ sub \tmp, \tmp, #(SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
+ bic \tmp, \tmp, #USER_ASID_FLAG
+ msr ttbr1_el1, \tmp
+#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
+alternative_if ARM64_WORKAROUND_QCOM_FALKOR_E1003
+ /* ASID already in \tmp[63:48] */
+ movk \tmp, #:abs_g2_nc:(TRAMP_VALIAS >> 12)
+ movk \tmp, #:abs_g1_nc:(TRAMP_VALIAS >> 12)
+ /* 2MB boundary containing the vectors, so we nobble the walk cache */
+ movk \tmp, #:abs_g0_nc:((TRAMP_VALIAS & ~(SZ_2M - 1)) >> 12)
+ isb
+ tlbi vae1, \tmp
+ dsb nsh
+alternative_else_nop_endif
+#endif /* CONFIG_QCOM_FALKOR_ERRATUM_1003 */
+ .endm
+
+ .macro tramp_unmap_kernel, tmp
+ mrs \tmp, ttbr1_el1
+ add \tmp, \tmp, #(SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
+ orr \tmp, \tmp, #USER_ASID_FLAG
+ msr ttbr1_el1, \tmp
+ /*
+ * We avoid running the post_ttbr_update_workaround here because
+ * it's only needed by Cavium ThunderX, which requires KPTI to be
+ * disabled.
+ */
+ .endm
+
+ .macro tramp_ventry, regsize = 64
+ .align 7
+1:
+ .if \regsize == 64
+ msr tpidrro_el0, x30 // Restored in kernel_ventry
+ .endif
+ /*
+ * Defend against branch aliasing attacks by pushing a dummy
+ * entry onto the return stack and using a RET instruction to
+ * enter the full-fat kernel vectors.
+ */
+ bl 2f
+ b .
+2:
+ tramp_map_kernel x30
+#ifdef CONFIG_RANDOMIZE_BASE
+ adr x30, tramp_vectors + PAGE_SIZE
+alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003
+ ldr x30, [x30]
+#else
+ ldr x30, =vectors
+#endif
+ prfm plil1strm, [x30, #(1b - tramp_vectors)]
+ msr vbar_el1, x30
+ add x30, x30, #(1b - tramp_vectors)
+ isb
+ ret
+ .endm
+
+ .macro tramp_exit, regsize = 64
+ adr x30, tramp_vectors
+ msr vbar_el1, x30
+ tramp_unmap_kernel x30
+ .if \regsize == 64
+ mrs x30, far_el1
+ .endif
+ eret
+ .endm
+
+ .align 11
+ENTRY(tramp_vectors)
+ .space 0x400
+
+ tramp_ventry
+ tramp_ventry
+ tramp_ventry
+ tramp_ventry
+
+ tramp_ventry 32
+ tramp_ventry 32
+ tramp_ventry 32
+ tramp_ventry 32
+END(tramp_vectors)
+
+ENTRY(tramp_exit_native)
+ tramp_exit
+END(tramp_exit_native)
+
+ENTRY(tramp_exit_compat)
+ tramp_exit 32
+END(tramp_exit_compat)
+
+ .ltorg
+ .popsection // .entry.tramp.text
+#ifdef CONFIG_RANDOMIZE_BASE
+ .pushsection ".rodata", "a"
+ .align PAGE_SHIFT
+ .globl __entry_tramp_data_start
+__entry_tramp_data_start:
+ .quad vectors
+ .popsection // .rodata
+#endif /* CONFIG_RANDOMIZE_BASE */
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+
/*
* Special system call wrappers.
*/
mov x0, sp
b sys_rt_sigreturn
ENDPROC(sys_rt_sigreturn_wrapper)
+
+/*
+ * Register switch for AArch64. The callee-saved registers need to be saved
+ * and restored. On entry:
+ * x0 = previous task_struct (must be preserved across the switch)
+ * x1 = next task_struct
+ * Previous and next are guaranteed not to be the same.
+ *
+ */
+ENTRY(cpu_switch_to)
+ mov x10, #THREAD_CPU_CONTEXT
+ add x8, x0, x10
+ mov x9, sp
+ stp x19, x20, [x8], #16 // store callee-saved registers
+ stp x21, x22, [x8], #16
+ stp x23, x24, [x8], #16
+ stp x25, x26, [x8], #16
+ stp x27, x28, [x8], #16
+ stp x29, x9, [x8], #16
+ str lr, [x8]
+ add x8, x1, x10
+ ldp x19, x20, [x8], #16 // restore callee-saved registers
+ ldp x21, x22, [x8], #16
+ ldp x23, x24, [x8], #16
+ ldp x25, x26, [x8], #16
+ ldp x27, x28, [x8], #16
+ ldp x29, x9, [x8], #16
+ ldr lr, [x8]
+ mov sp, x9
+ msr sp_el0, x1
+ ret
+ENDPROC(cpu_switch_to)
+NOKPROBE(cpu_switch_to)
+
+/*
+ * This is how we return from a fork.
+ */
+ENTRY(ret_from_fork)
+ bl schedule_tail
+ cbz x19, 1f // not a kernel thread
+ mov x0, x20
+ blr x19
+1: get_thread_info tsk
+ b ret_to_user
+ENDPROC(ret_from_fork)
+NOKPROBE(ret_from_fork)