Resguardo inicial

linux-7.2.3/kernel/entry/Makefile

@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Prevent the noinstr section from being pestered by sanitizer and other goodies
+# as long as these things cannot be disabled per function.
+KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
+
+# Branch profiling isn't noinstr-safe
+ccflags-$(CONFIG_TRACE_BRANCH_PROFILING) += -DDISABLE_BRANCH_PROFILING
+
+CFLAGS_REMOVE_common.o	 = -fstack-protector -fstack-protector-strong
+CFLAGS_common.o		+= -fno-stack-protector
+
+obj-$(CONFIG_GENERIC_IRQ_ENTRY) 	+= common.o
+obj-$(CONFIG_GENERIC_SYSCALL) 		+= syscall-common.o syscall_user_dispatch.o
+obj-$(CONFIG_VIRT_XFER_TO_GUEST_WORK)	+= virt.o

linux-7.2.3/kernel/entry/common.c

@@ -0,0 +1,205 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/futex.h>
+#include <linux/highmem.h>
+#include <linux/irq-entry-common.h>
+#include <linux/jump_label.h>
+#include <linux/kmsan.h>
+#include <linux/livepatch.h>
+#include <linux/resume_user_mode.h>
+#include <linux/tick.h>
+
+/* Workaround to allow gradual conversion of architecture code */
+void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
+
+#ifdef CONFIG_HAVE_GENERIC_TIF_BITS
+#define EXIT_TO_USER_MODE_WORK_LOOP	(EXIT_TO_USER_MODE_WORK & ~_TIF_RSEQ)
+#else
+#define EXIT_TO_USER_MODE_WORK_LOOP	(EXIT_TO_USER_MODE_WORK)
+#endif
+
+/* TIF bits, which prevent a time slice extension. */
+#ifdef CONFIG_PREEMPT_RT
+/*
+ * Since rseq slice ext has a direct correlation to the worst case
+ * scheduling latency (schedule is delayed after all), only have it affect
+ * LAZY reschedules on PREEMPT_RT for now.
+ *
+ * However, since this delay is only applicable to userspace, a value
+ * for rseq_slice_extension_nsec that is strictly less than the worst case
+ * kernel space preempt_disable() region, should mean the scheduling latency
+ * is not affected, even for !LAZY.
+ *
+ * However, since this value depends on the hardware at hand, it cannot be
+ * pre-determined in any sensible way. Hence punt on this problem for now.
+ */
+# define TIF_SLICE_EXT_SCHED	(_TIF_NEED_RESCHED_LAZY)
+#else
+# define TIF_SLICE_EXT_SCHED	(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
+#endif
+#define TIF_SLICE_EXT_DENY	(EXIT_TO_USER_MODE_WORK & ~TIF_SLICE_EXT_SCHED)
+
+static __always_inline unsigned long __exit_to_user_mode_loop(struct pt_regs *regs,
+							      unsigned long ti_work)
+{
+	/*
+	 * Before returning to user space ensure that all pending work
+	 * items have been completed.
+	 */
+	while (ti_work & EXIT_TO_USER_MODE_WORK_LOOP) {
+
+		local_irq_enable();
+
+		if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) {
+			if (!rseq_grant_slice_extension(ti_work, TIF_SLICE_EXT_DENY))
+				schedule();
+		}
+
+		if (ti_work & _TIF_UPROBE)
+			uprobe_notify_resume(regs);
+
+		if (ti_work & _TIF_PATCH_PENDING)
+			klp_update_patch_state(current);
+
+		if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) {
+			futex_fixup_robust_unlock(regs);
+			arch_do_signal_or_restart(regs);
+		}
+
+		if (ti_work & _TIF_NOTIFY_RESUME)
+			resume_user_mode_work(regs);
+
+		/* Architecture specific TIF work */
+		arch_exit_to_user_mode_work(regs, ti_work);
+
+		/*
+		 * Disable interrupts and reevaluate the work flags as they
+		 * might have changed while interrupts and preemption was
+		 * enabled above.
+		 */
+		local_irq_disable();
+
+		/* Check if any of the above work has queued a deferred wakeup */
+		tick_nohz_user_enter_prepare();
+
+		ti_work = read_thread_flags();
+	}
+
+	/* Return the latest work state for arch_exit_to_user_mode() */
+	return ti_work;
+}
+
+/**
+ * exit_to_user_mode_loop - do any pending work before leaving to user space
+ * @regs:	Pointer to pt_regs on entry stack
+ * @ti_work:	TIF work flags as read by the caller
+ */
+__always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
+						     unsigned long ti_work)
+{
+	for (;;) {
+		ti_work = __exit_to_user_mode_loop(regs, ti_work);
+
+		if (likely(!rseq_exit_to_user_mode_restart(regs, ti_work)))
+			return ti_work;
+		ti_work = read_thread_flags();
+	}
+}
+
+noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
+{
+	if (user_mode(regs)) {
+		irqentry_state_t ret = {
+			.exit_rcu = false,
+		};
+
+		irqentry_enter_from_user_mode(regs);
+		return ret;
+	}
+
+	return irqentry_enter_from_kernel_mode(regs);
+}
+
+/**
+ * arch_irqentry_exit_need_resched - Architecture specific need resched function
+ *
+ * Invoked from raw_irqentry_exit_cond_resched() to check if resched is needed.
+ * Defaults return true.
+ *
+ * The main purpose is to permit arch to avoid preemption of a task from an IRQ.
+ */
+static inline bool arch_irqentry_exit_need_resched(void);
+
+#ifndef arch_irqentry_exit_need_resched
+static inline bool arch_irqentry_exit_need_resched(void) { return true; }
+#endif
+
+void raw_irqentry_exit_cond_resched(void)
+{
+	if (!preempt_count()) {
+		/* Sanity check RCU and thread stack */
+		rcu_irq_exit_check_preempt();
+		if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
+			WARN_ON_ONCE(!on_thread_stack());
+		if (need_resched() && arch_irqentry_exit_need_resched())
+			preempt_schedule_irq();
+	}
+}
+#ifdef CONFIG_PREEMPT_DYNAMIC
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+void dynamic_irqentry_exit_cond_resched(void)
+{
+	if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
+		return;
+	raw_irqentry_exit_cond_resched();
+}
+#endif
+#endif
+
+noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
+{
+	if (user_mode(regs))
+		irqentry_exit_to_user_mode(regs);
+	else
+		irqentry_exit_to_kernel_mode(regs, state);
+}
+
+irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs)
+{
+	irqentry_state_t irq_state;
+
+	irq_state.lockdep = lockdep_hardirqs_enabled();
+
+	__nmi_enter();
+	lockdep_hardirqs_off(CALLER_ADDR0);
+	lockdep_hardirq_enter();
+	ct_nmi_enter();
+
+	instrumentation_begin();
+	kmsan_unpoison_entry_regs(regs);
+	trace_hardirqs_off_finish();
+	ftrace_nmi_enter();
+	instrumentation_end();
+
+	return irq_state;
+}
+
+void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state)
+{
+	instrumentation_begin();
+	ftrace_nmi_exit();
+	if (irq_state.lockdep) {
+		trace_hardirqs_on_prepare();
+		lockdep_hardirqs_on_prepare();
+	}
+	instrumentation_end();
+
+	ct_nmi_exit();
+	lockdep_hardirq_exit();
+	if (irq_state.lockdep)
+		lockdep_hardirqs_on(CALLER_ADDR0);
+	__nmi_exit();
+}

linux-7.2.3/kernel/entry/syscall-common.c

@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/entry-common.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+/* Out of line to prevent tracepoint code duplication */
+
+long trace_syscall_enter(struct pt_regs *regs, long syscall)
+{
+	trace_sys_enter(regs, syscall);
+	/*
+	 * Probes or BPF hooks in the tracepoint may have changed the
+	 * system call number. Reread it.
+	 */
+	return syscall_get_nr(current, regs);
+}
+
+void trace_syscall_exit(struct pt_regs *regs, long ret)
+{
+	trace_sys_exit(regs, ret);
+}

linux-7.2.3/kernel/entry/syscall_user_dispatch.c

@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Collabora Ltd.
+ */
+
+#include <linux/entry-common.h>
+#include <linux/sched.h>
+#include <linux/prctl.h>
+#include <linux/ptrace.h>
+#include <linux/syscall_user_dispatch.h>
+#include <linux/uaccess.h>
+#include <linux/signal.h>
+#include <linux/elf.h>
+
+#include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/syscall.h>
+
+static void trigger_sigsys(struct pt_regs *regs)
+{
+	struct kernel_siginfo info;
+
+	clear_siginfo(&info);
+	info.si_signo = SIGSYS;
+	info.si_code = SYS_USER_DISPATCH;
+	info.si_call_addr = (void __user *)KSTK_EIP(current);
+	info.si_errno = 0;
+	info.si_arch = syscall_get_arch(current);
+	info.si_syscall = syscall_get_nr(current, regs);
+
+	force_sig_info(&info);
+}
+
+bool syscall_user_dispatch(struct pt_regs *regs)
+{
+	struct syscall_user_dispatch *sd = &current->syscall_dispatch;
+	char state;
+
+	if (likely(instruction_pointer(regs) - sd->offset < sd->len))
+		return false;
+
+	if (unlikely(arch_syscall_is_vdso_sigreturn(regs)))
+		return false;
+
+	if (likely(sd->selector)) {
+		/*
+		 * access_ok() is performed once, at prctl time, when
+		 * the selector is loaded by userspace.
+		 */
+		if (unlikely(__get_user(state, sd->selector))) {
+			force_exit_sig(SIGSEGV);
+			return true;
+		}
+
+		if (likely(state == SYSCALL_DISPATCH_FILTER_ALLOW))
+			return false;
+
+		if (state != SYSCALL_DISPATCH_FILTER_BLOCK) {
+			force_exit_sig(SIGSYS);
+			return true;
+		}
+	}
+
+	sd->on_dispatch = true;
+	syscall_rollback(current, regs);
+	trigger_sigsys(regs);
+
+	return true;
+}
+
+static int task_set_syscall_user_dispatch(struct task_struct *task, unsigned long mode,
+					  unsigned long offset, unsigned long len,
+					  char __user *selector)
+{
+	switch (mode) {
+	case PR_SYS_DISPATCH_OFF:
+		if (offset || len || selector)
+			return -EINVAL;
+		break;
+	case PR_SYS_DISPATCH_EXCLUSIVE_ON:
+		/*
+		 * Validate the direct dispatcher region just for basic
+		 * sanity against overflow and a 0-sized dispatcher
+		 * region.  If the user is able to submit a syscall from
+		 * an address, that address is obviously valid.
+		 */
+		if (offset && offset + len <= offset)
+			return -EINVAL;
+		break;
+	case PR_SYS_DISPATCH_INCLUSIVE_ON:
+		if (len == 0 || offset + len <= offset)
+			return -EINVAL;
+		/*
+		 * Invert the range, the check in syscall_user_dispatch()
+		 * supports wrap-around.
+		 */
+		offset = offset + len;
+		len = -len;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/*
+	 * access_ok() will clear memory tags for tagged addresses
+	 * if current has memory tagging enabled.
+	 *
+	 * To enable a tracer to set a tracees selector the
+	 * selector address must be untagged for access_ok(),
+	 * otherwise an untagged tracer will always fail to set a
+	 * tagged tracees selector.
+	 */
+	if (mode != PR_SYS_DISPATCH_OFF && selector &&
+		!access_ok(untagged_addr(selector), sizeof(*selector)))
+		return -EFAULT;
+
+	task->syscall_dispatch.selector = selector;
+	task->syscall_dispatch.offset = offset;
+	task->syscall_dispatch.len = len;
+	task->syscall_dispatch.on_dispatch = false;
+
+	if (mode != PR_SYS_DISPATCH_OFF)
+		set_task_syscall_work(task, SYSCALL_USER_DISPATCH);
+	else
+		clear_task_syscall_work(task, SYSCALL_USER_DISPATCH);
+
+	return 0;
+}
+
+int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
+			      unsigned long len, char __user *selector)
+{
+	return task_set_syscall_user_dispatch(current, mode, offset, len, selector);
+}
+
+int syscall_user_dispatch_get_config(struct task_struct *task, unsigned long size,
+				     void __user *data)
+{
+	struct syscall_user_dispatch *sd = &task->syscall_dispatch;
+	struct ptrace_sud_config cfg;
+
+	if (size != sizeof(cfg))
+		return -EINVAL;
+
+	if (test_task_syscall_work(task, SYSCALL_USER_DISPATCH))
+		cfg.mode = PR_SYS_DISPATCH_ON;
+	else
+		cfg.mode = PR_SYS_DISPATCH_OFF;
+
+	cfg.offset = sd->offset;
+	cfg.len = sd->len;
+	cfg.selector = (__u64)(uintptr_t)sd->selector;
+
+	if (copy_to_user(data, &cfg, sizeof(cfg)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long size,
+				     void __user *data)
+{
+	struct ptrace_sud_config cfg;
+
+	if (size != sizeof(cfg))
+		return -EINVAL;
+
+	if (copy_from_user(&cfg, data, sizeof(cfg)))
+		return -EFAULT;
+
+	return task_set_syscall_user_dispatch(task, cfg.mode, cfg.offset, cfg.len,
+					      (char __user *)(uintptr_t)cfg.selector);
+}

linux-7.2.3/kernel/entry/virt.c

@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/entry-virt.h>
+
+static int xfer_to_guest_mode_work(unsigned long ti_work)
+{
+	do {
+		int ret;
+
+		if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
+			return -EINTR;
+
+		if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY))
+			schedule();
+
+		if (ti_work & _TIF_NOTIFY_RESUME)
+			resume_user_mode_work(NULL);
+
+		ret = arch_xfer_to_guest_mode_handle_work(ti_work);
+		if (ret)
+			return ret;
+
+		ti_work = read_thread_flags();
+	} while (ti_work & XFER_TO_GUEST_MODE_WORK);
+	return 0;
+}
+
+int xfer_to_guest_mode_handle_work(void)
+{
+	unsigned long ti_work;
+
+	/*
+	 * This is invoked from the outer guest loop with interrupts and
+	 * preemption enabled.
+	 *
+	 * KVM invokes xfer_to_guest_mode_work_pending() with interrupts
+	 * disabled in the inner loop before going into guest mode. No need
+	 * to disable interrupts here.
+	 */
+	ti_work = read_thread_flags();
+	if (!(ti_work & XFER_TO_GUEST_MODE_WORK))
+		return 0;
+
+	return xfer_to_guest_mode_work(ti_work);
+}
+EXPORT_SYMBOL_GPL(xfer_to_guest_mode_handle_work);