summaryrefslogtreecommitdiffstats
path: root/arch/arm64/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/kernel')
-rw-r--r--arch/arm64/kernel/cpufeature.c22
-rw-r--r--arch/arm64/kernel/debug-monitors.c14
-rw-r--r--arch/arm64/kernel/entry.S22
-rw-r--r--arch/arm64/kernel/fpsimd.c29
-rw-r--r--arch/arm64/kernel/ftrace.c22
-rw-r--r--arch/arm64/kernel/hw_breakpoint.c11
-rw-r--r--arch/arm64/kernel/module.c4
-rw-r--r--arch/arm64/kernel/perf_callchain.c7
-rw-r--r--arch/arm64/kernel/probes/kprobes.c40
-rw-r--r--arch/arm64/kernel/process.c36
-rw-r--r--arch/arm64/kernel/return_address.c12
-rw-r--r--arch/arm64/kernel/smp.c2
-rw-r--r--arch/arm64/kernel/stacktrace.c62
-rw-r--r--arch/arm64/kernel/time.c7
-rw-r--r--arch/arm64/kernel/traps.c13
-rw-r--r--arch/arm64/kernel/vdso/Makefile13
-rw-r--r--arch/arm64/kernel/vdso32/Makefile14
17 files changed, 192 insertions, 138 deletions
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index f29f36a65175..b1fdc486aed8 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -184,9 +184,17 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
};
static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
- S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
- S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
- ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
+ /*
+ * We already refuse to boot CPUs that don't support our configured
+ * page size, so we can only detect mismatches for a page size other
+ * than the one we're currently using. Unfortunately, SoCs like this
+ * exist in the wild so, even though we don't like it, we'll have to go
+ * along with it and treat them as non-strict.
+ */
+ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
+ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
+
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0),
/* Linux shouldn't care about secure memory */
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0),
@@ -225,8 +233,8 @@ static const struct arm64_ftr_bits ftr_ctr[] = {
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DIC_SHIFT, 1, 1),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_IDC_SHIFT, 1, 1),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_CWG_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_ERG_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_CWG_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_ERG_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DMINLINE_SHIFT, 4, 1),
/*
* Linux can handle differing I-cache policies. Userspace JITs will
@@ -468,6 +476,10 @@ static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new,
case FTR_LOWER_SAFE:
ret = new < cur ? new : cur;
break;
+ case FTR_HIGHER_OR_ZERO_SAFE:
+ if (!cur || !new)
+ break;
+ /* Fallthrough */
case FTR_HIGHER_SAFE:
ret = new > cur ? new : cur;
break;
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index f8719bd30850..48222a4760c2 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -207,16 +207,16 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr)
list = user_mode(regs) ? &user_step_hook : &kernel_step_hook;
- rcu_read_lock();
-
+ /*
+ * Since single-step exception disables interrupt, this function is
+ * entirely not preemptible, and we can use rcu list safely here.
+ */
list_for_each_entry_rcu(hook, list, node) {
retval = hook->fn(regs, esr);
if (retval == DBG_HOOK_HANDLED)
break;
}
- rcu_read_unlock();
-
return retval;
}
NOKPROBE_SYMBOL(call_step_hook);
@@ -305,14 +305,16 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
list = user_mode(regs) ? &user_break_hook : &kernel_break_hook;
- rcu_read_lock();
+ /*
+ * Since brk exception disables interrupt, this function is
+ * entirely not preemptible, and we can use rcu list safely here.
+ */
list_for_each_entry_rcu(hook, list, node) {
unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
if ((comment & ~hook->mask) == hook->imm)
fn = hook->fn;
}
- rcu_read_unlock();
return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
}
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 9cdc4592da3e..320a30dbe35e 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -586,10 +586,8 @@ el1_sync:
b.eq el1_ia
cmp x24, #ESR_ELx_EC_SYS64 // configurable trap
b.eq el1_undef
- cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception
- b.eq el1_sp_pc
cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception
- b.eq el1_sp_pc
+ b.eq el1_pc
cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL1
b.eq el1_undef
cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1
@@ -611,9 +609,11 @@ el1_da:
bl do_mem_abort
kernel_exit 1
-el1_sp_pc:
+el1_pc:
/*
- * Stack or PC alignment exception handling
+ * PC alignment exception handling. We don't handle SP alignment faults,
+ * since we will have hit a recursive exception when trying to push the
+ * initial pt_regs.
*/
mrs x0, far_el1
inherit_daif pstate=x23, tmp=x2
@@ -732,9 +732,9 @@ el0_sync:
ccmp x24, #ESR_ELx_EC_WFx, #4, ne
b.eq el0_sys
cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception
- b.eq el0_sp_pc
+ b.eq el0_sp
cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception
- b.eq el0_sp_pc
+ b.eq el0_pc
cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0
b.eq el0_undef
cmp x24, #ESR_ELx_EC_BREAKPT_LOW // debug exception in EL0
@@ -758,7 +758,7 @@ el0_sync_compat:
cmp x24, #ESR_ELx_EC_FP_EXC32 // FP/ASIMD exception
b.eq el0_fpsimd_exc
cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception
- b.eq el0_sp_pc
+ b.eq el0_pc
cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0
b.eq el0_undef
cmp x24, #ESR_ELx_EC_CP15_32 // CP15 MRC/MCR trap
@@ -858,11 +858,15 @@ el0_fpsimd_exc:
mov x1, sp
bl do_fpsimd_exc
b ret_to_user
+el0_sp:
+ ldr x26, [sp, #S_SP]
+ b el0_sp_pc
+el0_pc:
+ mrs x26, far_el1
el0_sp_pc:
/*
* Stack or PC alignment exception handling
*/
- mrs x26, far_el1
gic_prio_kentry_setup tmp=x0
enable_da_f
#ifdef CONFIG_TRACE_IRQFLAGS
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index eec4776ae5f0..37d3912cfe06 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -406,6 +406,18 @@ static __uint128_t arm64_cpu_to_le128(__uint128_t x)
#define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x)
+static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst,
+ unsigned int vq)
+{
+ unsigned int i;
+ __uint128_t *p;
+
+ for (i = 0; i < SVE_NUM_ZREGS; ++i) {
+ p = (__uint128_t *)ZREG(sst, vq, i);
+ *p = arm64_cpu_to_le128(fst->vregs[i]);
+ }
+}
+
/*
* Transfer the FPSIMD state in task->thread.uw.fpsimd_state to
* task->thread.sve_state.
@@ -423,17 +435,12 @@ static void fpsimd_to_sve(struct task_struct *task)
unsigned int vq;
void *sst = task->thread.sve_state;
struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
- unsigned int i;
- __uint128_t *p;
if (!system_supports_sve())
return;
vq = sve_vq_from_vl(task->thread.sve_vl);
- for (i = 0; i < 32; ++i) {
- p = (__uint128_t *)ZREG(sst, vq, i);
- *p = arm64_cpu_to_le128(fst->vregs[i]);
- }
+ __fpsimd_to_sve(sst, fst, vq);
}
/*
@@ -459,7 +466,7 @@ static void sve_to_fpsimd(struct task_struct *task)
return;
vq = sve_vq_from_vl(task->thread.sve_vl);
- for (i = 0; i < 32; ++i) {
+ for (i = 0; i < SVE_NUM_ZREGS; ++i) {
p = (__uint128_t const *)ZREG(sst, vq, i);
fst->vregs[i] = arm64_le128_to_cpu(*p);
}
@@ -550,8 +557,6 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
unsigned int vq;
void *sst = task->thread.sve_state;
struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
- unsigned int i;
- __uint128_t *p;
if (!test_tsk_thread_flag(task, TIF_SVE))
return;
@@ -559,11 +564,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
vq = sve_vq_from_vl(task->thread.sve_vl);
memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
-
- for (i = 0; i < 32; ++i) {
- p = (__uint128_t *)ZREG(sst, vq, i);
- *p = arm64_cpu_to_le128(fst->vregs[i]);
- }
+ __fpsimd_to_sve(sst, fst, vq);
}
int sve_set_vector_length(struct task_struct *task,
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 1285c7b2947f..171773257974 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -73,7 +73,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
if (offset < -SZ_128M || offset >= SZ_128M) {
#ifdef CONFIG_ARM64_MODULE_PLTS
- struct plt_entry trampoline;
+ struct plt_entry trampoline, *dst;
struct module *mod;
/*
@@ -106,23 +106,27 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
* to check if the actual opcodes are in fact identical,
* regardless of the offset in memory so use memcmp() instead.
*/
- trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline);
- if (memcmp(mod->arch.ftrace_trampoline, &trampoline,
- sizeof(trampoline))) {
- if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) {
+ dst = mod->arch.ftrace_trampoline;
+ trampoline = get_plt_entry(addr, dst);
+ if (memcmp(dst, &trampoline, sizeof(trampoline))) {
+ if (plt_entry_is_initialized(dst)) {
pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
return -EINVAL;
}
/* point the trampoline to our ftrace entry point */
module_disable_ro(mod);
- *mod->arch.ftrace_trampoline = trampoline;
+ *dst = trampoline;
module_enable_ro(mod, true);
- /* update trampoline before patching in the branch */
- smp_wmb();
+ /*
+ * Ensure updated trampoline is visible to instruction
+ * fetch before we patch in the branch.
+ */
+ __flush_icache_range((unsigned long)&dst[0],
+ (unsigned long)&dst[1]);
}
- addr = (unsigned long)(void *)mod->arch.ftrace_trampoline;
+ addr = (unsigned long)dst;
#else /* CONFIG_ARM64_MODULE_PLTS */
return -EINVAL;
#endif /* CONFIG_ARM64_MODULE_PLTS */
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index dceb84520948..38ee1514cd9c 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -536,13 +536,18 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
/* Aligned */
break;
case 1:
- /* Allow single byte watchpoint. */
- if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
- break;
case 2:
/* Allow halfword watchpoints and breakpoints. */
if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
break;
+
+ /* Fallthrough */
+ case 3:
+ /* Allow single byte watchpoint. */
+ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
+ break;
+
+ /* Fallthrough */
default:
return -EINVAL;
}
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 46e643e30708..03ff15bffbb6 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -314,18 +314,21 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
/* MOVW instruction relocations. */
case R_AARCH64_MOVW_UABS_G0_NC:
overflow_check = false;
+ /* Fall through */
case R_AARCH64_MOVW_UABS_G0:
ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
AARCH64_INSN_IMM_MOVKZ);
break;
case R_AARCH64_MOVW_UABS_G1_NC:
overflow_check = false;
+ /* Fall through */
case R_AARCH64_MOVW_UABS_G1:
ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
AARCH64_INSN_IMM_MOVKZ);
break;
case R_AARCH64_MOVW_UABS_G2_NC:
overflow_check = false;
+ /* Fall through */
case R_AARCH64_MOVW_UABS_G2:
ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
AARCH64_INSN_IMM_MOVKZ);
@@ -393,6 +396,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
break;
case R_AARCH64_ADR_PREL_PG_HI21_NC:
overflow_check = false;
+ /* Fall through */
case R_AARCH64_ADR_PREL_PG_HI21:
ovf = reloc_insn_adrp(me, sechdrs, loc, val);
if (ovf && ovf != -ERANGE)
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index 9d63514b9836..b0e03e052dd1 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -154,12 +154,7 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
return;
}
- frame.fp = regs->regs[29];
- frame.pc = regs->pc;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
-
+ start_backtrace(&frame, regs->regs[29], regs->pc);
walk_stackframe(current, &frame, callchain_trace, entry);
}
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index bd5dfffca272..c4452827419b 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -21,6 +21,7 @@
#include <asm/ptrace.h>
#include <asm/cacheflush.h>
#include <asm/debug-monitors.h>
+#include <asm/daifflags.h>
#include <asm/system_misc.h>
#include <asm/insn.h>
#include <linux/uaccess.h>
@@ -168,33 +169,6 @@ static void __kprobes set_current_kprobe(struct kprobe *p)
}
/*
- * When PSTATE.D is set (masked), then software step exceptions can not be
- * generated.
- * SPSR's D bit shows the value of PSTATE.D immediately before the
- * exception was taken. PSTATE.D is set while entering into any exception
- * mode, however software clears it for any normal (none-debug-exception)
- * mode in the exception entry. Therefore, when we are entering into kprobe
- * breakpoint handler from any normal mode then SPSR.D bit is already
- * cleared, however it is set when we are entering from any debug exception
- * mode.
- * Since we always need to generate single step exception after a kprobe
- * breakpoint exception therefore we need to clear it unconditionally, when
- * we become sure that the current breakpoint exception is for kprobe.
- */
-static void __kprobes
-spsr_set_debug_flag(struct pt_regs *regs, int mask)
-{
- unsigned long spsr = regs->pstate;
-
- if (mask)
- spsr |= PSR_D_BIT;
- else
- spsr &= ~PSR_D_BIT;
-
- regs->pstate = spsr;
-}
-
-/*
* Interrupts need to be disabled before single-step mode is set, and not
* reenabled until after single-step mode ends.
* Without disabling interrupt on local CPU, there is a chance of
@@ -205,17 +179,17 @@ spsr_set_debug_flag(struct pt_regs *regs, int mask)
static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
struct pt_regs *regs)
{
- kcb->saved_irqflag = regs->pstate;
+ kcb->saved_irqflag = regs->pstate & DAIF_MASK;
regs->pstate |= PSR_I_BIT;
+ /* Unmask PSTATE.D for enabling software step exceptions. */
+ regs->pstate &= ~PSR_D_BIT;
}
static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
struct pt_regs *regs)
{
- if (kcb->saved_irqflag & PSR_I_BIT)
- regs->pstate |= PSR_I_BIT;
- else
- regs->pstate &= ~PSR_I_BIT;
+ regs->pstate &= ~DAIF_MASK;
+ regs->pstate |= kcb->saved_irqflag;
}
static void __kprobes
@@ -252,8 +226,6 @@ static void __kprobes setup_singlestep(struct kprobe *p,
set_ss_context(kcb, slot); /* mark pending ss */
- spsr_set_debug_flag(regs, 0);
-
/* IRQs and single stepping do not mix well. */
kprobes_save_local_irqflag(kcb, regs);
kernel_enable_single_step(regs);
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 6a869d9f304f..f674f28df663 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -398,7 +398,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
childregs->pstate |= PSR_UAO_BIT;
if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE)
- childregs->pstate |= PSR_SSBS_BIT;
+ set_ssbs_bit(childregs);
if (system_uses_irq_prio_masking())
childregs->pmr_save = GIC_PRIO_IRQON;
@@ -443,6 +443,32 @@ void uao_thread_switch(struct task_struct *next)
}
/*
+ * Force SSBS state on context-switch, since it may be lost after migrating
+ * from a CPU which treats the bit as RES0 in a heterogeneous system.
+ */
+static void ssbs_thread_switch(struct task_struct *next)
+{
+ struct pt_regs *regs = task_pt_regs(next);
+
+ /*
+ * Nothing to do for kernel threads, but 'regs' may be junk
+ * (e.g. idle task) so check the flags and bail early.
+ */
+ if (unlikely(next->flags & PF_KTHREAD))
+ return;
+
+ /* If the mitigation is enabled, then we leave SSBS clear. */
+ if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) ||
+ test_tsk_thread_flag(next, TIF_SSBD))
+ return;
+
+ if (compat_user_mode(regs))
+ set_compat_ssbs_bit(regs);
+ else if (user_mode(regs))
+ set_ssbs_bit(regs);
+}
+
+/*
* We store our current task in sp_el0, which is clobbered by userspace. Keep a
* shadow copy so that we can restore this upon entry from userspace.
*
@@ -471,6 +497,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
entry_task_switch(next);
uao_thread_switch(next);
ptrauth_thread_switch(next);
+ ssbs_thread_switch(next);
/*
* Complete any pending TLB or cache maintenance on this CPU in case
@@ -498,11 +525,8 @@ unsigned long get_wchan(struct task_struct *p)
if (!stack_page)
return 0;
- frame.fp = thread_saved_fp(p);
- frame.pc = thread_saved_pc(p);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
+ start_backtrace(&frame, thread_saved_fp(p), thread_saved_pc(p));
+
do {
if (unwind_frame(p, &frame))
goto out;
diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c
index b21cba90f82d..a5e8b3b9d798 100644
--- a/arch/arm64/kernel/return_address.c
+++ b/arch/arm64/kernel/return_address.c
@@ -8,6 +8,7 @@
#include <linux/export.h>
#include <linux/ftrace.h>
+#include <linux/kprobes.h>
#include <asm/stack_pointer.h>
#include <asm/stacktrace.h>
@@ -29,6 +30,7 @@ static int save_return_addr(struct stackframe *frame, void *d)
return 0;
}
}
+NOKPROBE_SYMBOL(save_return_addr);
void *return_address(unsigned int level)
{
@@ -38,12 +40,9 @@ void *return_address(unsigned int level)
data.level = level + 2;
data.addr = NULL;
- frame.fp = (unsigned long)__builtin_frame_address(0);
- frame.pc = (unsigned long)return_address; /* dummy */
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
-
+ start_backtrace(&frame,
+ (unsigned long)__builtin_frame_address(0),
+ (unsigned long)return_address);
walk_stackframe(current, &frame, save_return_addr, &data);
if (!data.level)
@@ -52,3 +51,4 @@ void *return_address(unsigned int level)
return NULL;
}
EXPORT_SYMBOL_GPL(return_address);
+NOKPROBE_SYMBOL(return_address);
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index ea90d3bd9253..018a33e01b0e 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -152,8 +152,8 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
pr_crit("CPU%u: died during early boot\n", cpu);
break;
}
- /* Fall through */
pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
+ /* Fall through */
case CPU_STUCK_IN_KERNEL:
pr_crit("CPU%u: is stuck in kernel\n", cpu);
if (status & CPU_STUCK_REASON_52_BIT_VA)
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 62d395151abe..a336cb124320 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -7,6 +7,7 @@
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/ftrace.h>
+#include <linux/kprobes.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
@@ -29,9 +30,18 @@
* ldp x29, x30, [sp]
* add sp, sp, #0x10
*/
+
+/*
+ * Unwind from one frame record (A) to the next frame record (B).
+ *
+ * We terminate early if the location of B indicates a malformed chain of frame
+ * records (e.g. a cycle), determined based on the location and fp value of A
+ * and the location (but not the fp value) of B.
+ */
int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
{
unsigned long fp = frame->fp;
+ struct stack_info info;
if (fp & 0xf)
return -EINVAL;
@@ -39,11 +49,40 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
if (!tsk)
tsk = current;
- if (!on_accessible_stack(tsk, fp, NULL))
+ if (!on_accessible_stack(tsk, fp, &info))
+ return -EINVAL;
+
+ if (test_bit(info.type, frame->stacks_done))
return -EINVAL;
+ /*
+ * As stacks grow downward, any valid record on the same stack must be
+ * at a strictly higher address than the prior record.
+ *
+ * Stacks can nest in several valid orders, e.g.
+ *
+ * TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL
+ * TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW
+ *
+ * ... but the nesting itself is strict. Once we transition from one
+ * stack to another, it's never valid to unwind back to that first
+ * stack.
+ */
+ if (info.type == frame->prev_type) {
+ if (fp <= frame->prev_fp)
+ return -EINVAL;
+ } else {
+ set_bit(frame->prev_type, frame->stacks_done);
+ }
+
+ /*
+ * Record this frame record's values and location. The prev_fp and
+ * prev_type are only meaningful to the next unwind_frame() invocation.
+ */
frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
+ frame->prev_fp = fp;
+ frame->prev_type = info.type;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
if (tsk->ret_stack &&
@@ -73,6 +112,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
return 0;
}
+NOKPROBE_SYMBOL(unwind_frame);
void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
int (*fn)(struct stackframe *, void *), void *data)
@@ -87,6 +127,7 @@ void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
break;
}
}
+NOKPROBE_SYMBOL(walk_stackframe);
#ifdef CONFIG_STACKTRACE
struct stack_trace_data {
@@ -122,12 +163,7 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
data.skip = trace->skip;
data.no_sched_functions = 0;
- frame.fp = regs->regs[29];
- frame.pc = regs->pc;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
-
+ start_backtrace(&frame, regs->regs[29], regs->pc);
walk_stackframe(current, &frame, save_trace, &data);
}
EXPORT_SYMBOL_GPL(save_stack_trace_regs);
@@ -146,17 +182,15 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
data.no_sched_functions = nosched;
if (tsk != current) {
- frame.fp = thread_saved_fp(tsk);
- frame.pc = thread_saved_pc(tsk);
+ start_backtrace(&frame, thread_saved_fp(tsk),
+ thread_saved_pc(tsk));
} else {
/* We don't want this function nor the caller */
data.skip += 2;
- frame.fp = (unsigned long)__builtin_frame_address(0);
- frame.pc = (unsigned long)__save_stack_trace;
+ start_backtrace(&frame,
+ (unsigned long)__builtin_frame_address(0),
+ (unsigned long)__save_stack_trace);
}
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
walk_stackframe(tsk, &frame, save_trace, &data);
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index 9f25aedeac9d..0b2946414dc9 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -38,11 +38,8 @@ unsigned long profile_pc(struct pt_regs *regs)
if (!in_lock_functions(regs->pc))
return regs->pc;
- frame.fp = regs->regs[29];
- frame.pc = regs->pc;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
+ start_backtrace(&frame, regs->regs[29], regs->pc);
+
do {
int ret = unwind_frame(NULL, &frame);
if (ret < 0)
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 969e1565152b..32893b3d9164 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -100,18 +100,17 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
return;
if (tsk == current) {
- frame.fp = (unsigned long)__builtin_frame_address(0);
- frame.pc = (unsigned long)dump_backtrace;
+ start_backtrace(&frame,
+ (unsigned long)__builtin_frame_address(0),
+ (unsigned long)dump_backtrace);
} else {
/*
* task blocked in __switch_to
*/
- frame.fp = thread_saved_fp(tsk);
- frame.pc = thread_saved_pc(tsk);
+ start_backtrace(&frame,
+ thread_saved_fp(tsk),
+ thread_saved_pc(tsk));
}
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
printk("Call trace:\n");
do {
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 4ab863045188..dd2514bb1511 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -32,10 +32,10 @@ UBSAN_SANITIZE := n
OBJECT_FILES_NON_STANDARD := y
KCOV_INSTRUMENT := n
-ifeq ($(c-gettimeofday-y),)
CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny
-else
-CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny -include $(c-gettimeofday-y)
+
+ifneq ($(c-gettimeofday-y),)
+ CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
endif
# Clang versions less than 8 do not support -mcmodel=tiny
@@ -57,8 +57,7 @@ $(obj)/vdso.o : $(obj)/vdso.so
# Link rule for the .so file, .lds has to be first
$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
- $(call if_changed,ld)
- $(call if_changed,vdso_check)
+ $(call if_changed,vdsold_and_vdso_check)
# Strip rule for the .so file
$(obj)/%.so: OBJCOPYFLAGS := -S
@@ -74,8 +73,8 @@ include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
$(call if_changed,vdsosym)
# Actual build commands
-quiet_cmd_vdsocc = VDSOCC $@
- cmd_vdsocc = $(CC) $(a_flags) $(c_flags) -c -o $@ $<
+quiet_cmd_vdsold_and_vdso_check = LD $@
+ cmd_vdsold_and_vdso_check = $(cmd_ld); $(cmd_vdso_check)
# Install commands for the unstripped file
quiet_cmd_vdso_install = INSTALL $@
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 60a4c6239712..1fba0776ed40 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -144,8 +144,7 @@ $(obj)/vdso.so.dbg: $(obj)/vdso.so.raw $(obj)/$(munge) FORCE
# Link rule for the .so file, .lds has to be first
$(obj)/vdso.so.raw: $(src)/vdso.lds $(obj-vdso) FORCE
- $(call if_changed,vdsold)
- $(call if_changed,vdso_check)
+ $(call if_changed,vdsold_and_vdso_check)
# Compilation rules for the vDSO sources
$(c-obj-vdso): %.o: %.c FORCE
@@ -156,14 +155,17 @@ $(asm-obj-vdso): %.o: %.S FORCE
$(call if_changed_dep,vdsoas)
# Actual build commands
-quiet_cmd_vdsold = VDSOL $@
+quiet_cmd_vdsold_and_vdso_check = LD32 $@
+ cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check)
+
+quiet_cmd_vdsold = LD32 $@
cmd_vdsold = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \
-Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@
-quiet_cmd_vdsocc = VDSOC $@
+quiet_cmd_vdsocc = CC32 $@
cmd_vdsocc = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $<
-quiet_cmd_vdsocc_gettimeofday = VDSOC_GTD $@
+quiet_cmd_vdsocc_gettimeofday = CC32 $@
cmd_vdsocc_gettimeofday = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $<
-quiet_cmd_vdsoas = VDSOA $@
+quiet_cmd_vdsoas = AS32 $@
cmd_vdsoas = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $<
quiet_cmd_vdsomunge = MUNGE $@
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2024-06-10 17:43:55 +0200