In do_notify_resume(), call task_isolation_before_pending_work_check()
first, to report isolation breaking, then after handling all pending
work, call task_isolation_start() for TIF_TASK_ISOLATION tasks.
Add _TIF_TASK_ISOLATION to _TIF_WORK_MASK, and _TIF_SYSCALL_WORK,
define local NOTIFY_RESUME_LOOP_FLAGS to check in the loop, since we
don't clear _TIF_TASK_ISOLATION in the loop.
Early kernel entry code calls task_isolation_kernel_enter(). In
particular:
Vectors:
el1_sync -> el1_sync_handler() -> task_isolation_kernel_enter()
el1_irq -> asm_nmi_enter(), handle_arch_irq()
el1_error -> do_serror()
el0_sync -> el0_sync_handler()
el0_irq -> handle_arch_irq()
el0_error -> do_serror()
el0_sync_compat -> el0_sync_compat_handler()
el0_irq_compat -> handle_arch_irq()
el0_error_compat -> do_serror()
SDEI entry:
__sdei_asm_handler -> __sdei_handler() -> nmi_enter()
Functions called from there:
asm_nmi_enter() -> nmi_enter() -> task_isolation_kernel_enter()
asm_nmi_exit() -> nmi_exit() -> task_isolation_kernel_return()
Handlers:
do_serror() -> nmi_enter() -> task_isolation_kernel_enter()
or task_isolation_kernel_enter()
el1_sync_handler() -> task_isolation_kernel_enter()
el0_sync_handler() -> task_isolation_kernel_enter()
el0_sync_compat_handler() -> task_isolation_kernel_enter()
handle_arch_irq() is irqchip-specific, most call handle_domain_irq()
There is a separate patch for irqchips that do not follow this rule.
handle_domain_irq() -> task_isolation_kernel_enter()
do_handle_IPI() -> task_isolation_kernel_enter() (may be redundant)
nmi_enter() -> task_isolation_kernel_enter()
Signed-off-by: Chris Metcalf <cmetcalf@xxxxxxxxxxxx>
[abelits@xxxxxxxxxxx: simplified to match kernel 5.10]
Signed-off-by: Alex Belits <abelits@xxxxxxxxxxx>
---
arch/arm64/Kconfig | 1 +
arch/arm64/include/asm/barrier.h | 1 +
arch/arm64/include/asm/thread_info.h | 7 +++++--
arch/arm64/kernel/entry-common.c | 7 +++++++
arch/arm64/kernel/ptrace.c | 10 ++++++++++
arch/arm64/kernel/signal.c | 13 ++++++++++++-
arch/arm64/kernel/smp.c | 3 +++
7 files changed, 39 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1515f6f153a0..fc958d8d8945 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -141,6 +141,7 @@ config ARM64
select HAVE_ARCH_PREL32_RELOCATIONS
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_STACKLEAK
+ select HAVE_ARCH_TASK_ISOLATION
select HAVE_ARCH_THREAD_STRUCT_WHITELIST
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index c3009b0e5239..ad5a6dd380cf 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -49,6 +49,7 @@
#define dma_rmb() dmb(oshld)
#define dma_wmb() dmb(oshst)
+#define instr_sync() isb()
/*
* Generate a mask for array_index__nospec() that is ~0UL when 0 <= idx < sz
* and 0 otherwise.
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 1fbab854a51b..3321c69c46fe 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -68,6 +68,7 @@ void arch_release_task_struct(struct task_struct *tsk);
#define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */
#define TIF_FSCHECK 5 /* Check FS is USER_DS on return */
#define TIF_MTE_ASYNC_FAULT 6 /* MTE Asynchronous Tag Check Fault */
+#define TIF_TASK_ISOLATION 7 /* task isolation enabled for task */
#define TIF_SYSCALL_TRACE 8 /* syscall trace active */
#define TIF_SYSCALL_AUDIT 9 /* syscall auditing */
#define TIF_SYSCALL_TRACEPOINT 10 /* syscall tracepoint for ftrace */
@@ -87,6 +88,7 @@ void arch_release_task_struct(struct task_struct *tsk);
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE)
+#define _TIF_TASK_ISOLATION (1 << TIF_TASK_ISOLATION)
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
@@ -101,11 +103,12 @@ void arch_release_task_struct(struct task_struct *tsk);
#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
_TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
- _TIF_UPROBE | _TIF_FSCHECK | _TIF_MTE_ASYNC_FAULT)
+ _TIF_UPROBE | _TIF_FSCHECK | \
+ _TIF_MTE_ASYNC_FAULT | _TIF_TASK_ISOLATION)
#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
_TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
- _TIF_SYSCALL_EMU)
+ _TIF_SYSCALL_EMU | _TIF_TASK_ISOLATION)
#ifdef CONFIG_SHADOW_CALL_STACK
#define INIT_SCS \
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 43d4c329775f..8152760de683 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -8,6 +8,7 @@
#include <linux/context_tracking.h>
#include <linux/ptrace.h>
#include <linux/thread_info.h>
+#include <linux/isolation.h>
#include <asm/cpufeature.h>
#include <asm/daifflags.h>
@@ -77,6 +78,8 @@ asmlinkage void notrace el1_sync_handler(struct pt_regs *regs)
{
unsigned long esr = read_sysreg(esr_el1);
+ task_isolation_kernel_enter();
+
switch (ESR_ELx_EC(esr)) {
case ESR_ELx_EC_DABT_CUR:
case ESR_ELx_EC_IABT_CUR:
@@ -249,6 +252,8 @@ asmlinkage void notrace el0_sync_handler(struct pt_regs *regs)
{
unsigned long esr = read_sysreg(esr_el1);
+ task_isolation_kernel_enter();
+
switch (ESR_ELx_EC(esr)) {
case ESR_ELx_EC_SVC64:
el0_svc(regs);
@@ -321,6 +326,8 @@ asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs)
{
unsigned long esr = read_sysreg(esr_el1);
+ task_isolation_kernel_enter();
+
switch (ESR_ELx_EC(esr)) {
case ESR_ELx_EC_SVC32:
el0_svc_compat(regs);
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index f49b349e16a3..2941f2b16796 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -29,6 +29,7 @@
#include <linux/regset.h>
#include <linux/tracehook.h>
#include <linux/elf.h>
+#include <linux/isolation.h>
#include <asm/compat.h>
#include <asm/cpufeature.h>
@@ -1803,6 +1804,15 @@ int syscall_trace_enter(struct pt_regs *regs)
return NO_SYSCALL;
}
+ /*
+ * In task isolation mode, we may prevent the syscall from
+ * running, and if so we also deliver a signal to the process.
+ */
+ if (test_thread_flag(TIF_TASK_ISOLATION)) {
+ if (task_isolation_syscall(regs->syscallno) == -1)
+ return NO_SYSCALL;
+ }
+
/* Do the secure computing after ptrace; failures should be fast. */
if (secure_computing() == -1)
return NO_SYSCALL;
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index a8184cad8890..e3a82b75e39d 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -20,6 +20,7 @@
#include <linux/tracehook.h>
#include <linux/ratelimit.h>
#include <linux/syscalls.h>
+#include <linux/isolation.h>
#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
@@ -911,6 +912,11 @@ static void do_signal(struct pt_regs *regs)
restore_saved_sigmask();
}
+#define NOTIFY_RESUME_LOOP_FLAGS \
+ (_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_RESUME | \
+ _TIF_FOREIGN_FPSTATE | _TIF_UPROBE | _TIF_FSCHECK | \
+ _TIF_MTE_ASYNC_FAULT)
+
asmlinkage void do_notify_resume(struct pt_regs *regs,
unsigned long thread_flags)
{
@@ -921,6 +927,8 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
*/
trace_hardirqs_off();
+ task_isolation_before_pending_work_check();
+
do {
/* Check valid user FS if needed */
addr_limit_user_check();
@@ -956,7 +964,10 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
local_daif_mask();
thread_flags = READ_ONCE(current_thread_info()->flags);
- } while (thread_flags & _TIF_WORK_MASK);
+ } while (thread_flags & NOTIFY_RESUME_LOOP_FLAGS);
+
+ if (thread_flags & _TIF_TASK_ISOLATION)
+ task_isolation_start();
}
unsigned long __ro_after_init signal_minsigstksz;
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 18e9727d3f64..4401eac4710c 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -33,6 +33,7 @@
#include <linux/kernel_stat.h>
#include <linux/kexec.h>
#include <linux/kvm_host.h>
+#include <linux/isolation.h>
#include <asm/alternative.h>
#include <asm/atomic.h>
@@ -890,6 +891,8 @@ static void do_handle_IPI(int ipinr)
{
unsigned int cpu = smp_processor_id();
+ task_isolation_kernel_enter();
+
if ((unsigned)ipinr < NR_IPI)
trace_ipi_entry_rcuidle(ipi_types[ipinr]);
--
2.20.1
