From 072de836f53be56a70cecf70b43ae43b7ce17376 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 11 Dec 2023 10:08:36 +0000
Subject: [PATCH] mk-rootfs.sh
---
kernel/arch/arm64/kernel/process.c | 360 ++++++++++++++++++++++++++++++++++++++++++-----------------
1 files changed, 254 insertions(+), 106 deletions(-)
diff --git a/kernel/arch/arm64/kernel/process.c b/kernel/arch/arm64/kernel/process.c
index 4338838..c38a5ab 100644
--- a/kernel/arch/arm64/kernel/process.c
+++ b/kernel/arch/arm64/kernel/process.c
@@ -1,34 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Based on arch/arm/kernel/process.c
*
* Original Copyright (C) 1995 Linus Torvalds
* Copyright (C) 1996-2000 Russell King - Converted to ARM.
* Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <stdarg.h>
#include <linux/compat.h>
#include <linux/efi.h>
+#include <linux/elf.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/kernel.h>
+#include <linux/lockdep.h>
+#include <linux/mman.h>
#include <linux/mm.h>
+#include <linux/nospec.h>
#include <linux/stddef.h>
#include <linux/sysctl.h>
#include <linux/unistd.h>
@@ -51,18 +44,22 @@
#include <linux/percpu.h>
#include <linux/thread_info.h>
#include <linux/prctl.h>
+#include <trace/hooks/fpsimd.h>
#include <asm/alternative.h>
+#include <asm/arch_gicv3.h>
#include <asm/compat.h>
+#include <asm/cpufeature.h>
#include <asm/cacheflush.h>
#include <asm/exec.h>
#include <asm/fpsimd.h>
#include <asm/mmu_context.h>
+#include <asm/mte.h>
#include <asm/processor.h>
-#include <asm/scs.h>
+#include <asm/pointer_auth.h>
#include <asm/stacktrace.h>
-#ifdef CONFIG_STACKPROTECTOR
+#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
#include <linux/stackprotector.h>
unsigned long __stack_chk_guard __ro_after_init;
EXPORT_SYMBOL(__stack_chk_guard);
@@ -74,22 +71,61 @@
void (*pm_power_off)(void);
EXPORT_SYMBOL_GPL(pm_power_off);
-void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
-EXPORT_SYMBOL_GPL(arm_pm_restart);
+static void noinstr __cpu_do_idle(void)
+{
+ dsb(sy);
+ wfi();
+}
+
+static void noinstr __cpu_do_idle_irqprio(void)
+{
+ unsigned long pmr;
+ unsigned long daif_bits;
+
+ daif_bits = read_sysreg(daif);
+ write_sysreg(daif_bits | PSR_I_BIT, daif);
+
+ /*
+ * Unmask PMR before going idle to make sure interrupts can
+ * be raised.
+ */
+ pmr = gic_read_pmr();
+ gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+ __cpu_do_idle();
+
+ gic_write_pmr(pmr);
+ write_sysreg(daif_bits, daif);
+}
+
+/*
+ * cpu_do_idle()
+ *
+ * Idle the processor (wait for interrupt).
+ *
+ * If the CPU supports priority masking we must do additional work to
+ * ensure that interrupts are not masked at the PMR (because the core will
+ * not wake up if we block the wake up signal in the interrupt controller).
+ */
+void noinstr cpu_do_idle(void)
+{
+ if (system_uses_irq_prio_masking())
+ __cpu_do_idle_irqprio();
+ else
+ __cpu_do_idle();
+}
/*
* This is our default idle handler.
*/
-void arch_cpu_idle(void)
+void noinstr arch_cpu_idle(void)
{
/*
* This should do all the clock switching and wait for interrupt
* tricks
*/
- trace_cpu_idle_rcuidle(1, smp_processor_id());
cpu_do_idle();
- local_irq_enable();
- trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
+ raw_local_irq_enable();
}
void arch_cpu_idle_enter(void)
@@ -116,11 +152,11 @@
* to execute e.g. a RAM-based pin loop is not sufficient. This allows the
* kexec'd kernel to use any and all RAM as it sees fit, without having to
* avoid any code or data used by any SW CPU pin loop. The CPU hotplug
- * functionality embodied in disable_nonboot_cpus() to achieve this.
+ * functionality embodied in smpt_shutdown_nonboot_cpus() to achieve this.
*/
void machine_shutdown(void)
{
- disable_nonboot_cpus();
+ smp_shutdown_nonboot_cpus(reboot_cpu);
}
/*
@@ -174,10 +210,7 @@
efi_reboot(reboot_mode, NULL);
/* Now call the architecture specific reboot code. */
- if (arm_pm_restart)
- arm_pm_restart(reboot_mode, cmd);
- else
- do_kernel_restart(cmd);
+ do_kernel_restart(cmd);
/*
* Whoops - the architecture was unable to reboot.
@@ -185,6 +218,15 @@
printk("Reboot failed -- System halted\n");
while (1);
}
+
+#define bstr(suffix, str) [PSR_BTYPE_ ## suffix >> PSR_BTYPE_SHIFT] = str
+static const char *const btypes[] = {
+ bstr(NONE, "--"),
+ bstr( JC, "jc"),
+ bstr( C, "-c"),
+ bstr( J , "j-")
+};
+#undef bstr
static void print_pstate(struct pt_regs *regs)
{
@@ -204,7 +246,10 @@
pstate & PSR_AA32_I_BIT ? 'I' : 'i',
pstate & PSR_AA32_F_BIT ? 'F' : 'f');
} else {
- printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO)\n",
+ const char *btype_str = btypes[(pstate & PSR_BTYPE_MASK) >>
+ PSR_BTYPE_SHIFT];
+
+ printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO %cTCO BTYPE=%s)\n",
pstate,
pstate & PSR_N_BIT ? 'N' : 'n',
pstate & PSR_Z_BIT ? 'Z' : 'z',
@@ -215,7 +260,9 @@
pstate & PSR_I_BIT ? 'I' : 'i',
pstate & PSR_F_BIT ? 'F' : 'f',
pstate & PSR_PAN_BIT ? '+' : '-',
- pstate & PSR_UAO_BIT ? '+' : '-');
+ pstate & PSR_UAO_BIT ? '+' : '-',
+ pstate & PSR_TCO_BIT ? '+' : '-',
+ btype_str);
}
}
@@ -232,7 +279,7 @@
* don't attempt to dump non-kernel addresses or
* values that are probably just small negative numbers
*/
- if (addr < VA_START || addr > -4096UL)
+ if (addr < PAGE_OFFSET || addr > -4096UL)
return;
printk("\n%s: %#lx:\n", name, addr + nbytes / 2);
@@ -258,7 +305,8 @@
for (j = 0; j < 8; j++) {
u32 data;
- if (probe_kernel_address(p, data)) {
+
+ if (aarch64_insn_read((void *)p, &data)) {
pr_cont(" ********");
} else {
pr_cont(" %08x", data);
@@ -307,13 +355,16 @@
if (!user_mode(regs)) {
printk("pc : %pS\n", (void *)regs->pc);
- printk("lr : %pS\n", (void *)lr);
+ printk("lr : %pS\n", (void *)ptrauth_strip_insn_pac(lr));
} else {
printk("pc : %016llx\n", regs->pc);
printk("lr : %016llx\n", lr);
}
printk("sp : %016llx\n", sp);
+
+ if (system_uses_irq_prio_masking())
+ printk("pmr_save: %08llx\n", regs->pmr_save);
i = top_reg;
@@ -333,11 +384,12 @@
void show_regs(struct pt_regs * regs)
{
__show_regs(regs);
- dump_backtrace(regs, NULL);
+ dump_backtrace(regs, NULL, KERN_DEFAULT);
if (!user_mode(regs))
show_extra_register_data(regs, 512);
}
+EXPORT_SYMBOL_GPL(show_regs);
static void tls_thread_flush(void)
{
@@ -400,13 +452,16 @@
dst->thread.sve_state = NULL;
clear_tsk_thread_flag(dst, TIF_SVE);
+ /* clear any pending asynchronous tag fault raised by the parent */
+ clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
+
return 0;
}
asmlinkage void ret_from_fork(void) asm("ret_from_fork");
int copy_thread(unsigned long clone_flags, unsigned long stack_start,
- unsigned long stk_sz, struct task_struct *p)
+ unsigned long stk_sz, struct task_struct *p, unsigned long tls)
{
struct pt_regs *childregs = task_pt_regs(p);
@@ -421,7 +476,9 @@
*/
fpsimd_flush_task_state(p);
- if (likely(!(p->flags & PF_KTHREAD))) {
+ ptrauth_thread_init_kernel(p);
+
+ if (likely(!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))) {
*childregs = *current_pt_regs();
childregs->regs[0] = 0;
@@ -439,20 +496,21 @@
}
/*
- * If a TLS pointer was passed to clone (4th argument), use it
- * for the new thread.
+ * If a TLS pointer was passed to clone, use it for the new
+ * thread.
*/
if (clone_flags & CLONE_SETTLS)
- p->thread.uw.tp_value = childregs->regs[3];
+ p->thread.uw.tp_value = tls;
} else {
+ /*
+ * A kthread has no context to ERET to, so ensure any buggy
+ * ERET is treated as an illegal exception return.
+ *
+ * When a user task is created from a kthread, childregs will
+ * be initialized by start_thread() or start_compat_thread().
+ */
memset(childregs, 0, sizeof(struct pt_regs));
- childregs->pstate = PSR_MODE_EL1h;
- if (IS_ENABLED(CONFIG_ARM64_UAO) &&
- cpus_have_const_cap(ARM64_HAS_UAO))
- childregs->pstate |= PSR_UAO_BIT;
-
- if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE)
- set_ssbs_bit(childregs);
+ childregs->pstate = PSR_MODE_EL1h | PSR_IL_BIT;
p->thread.cpu_context.x19 = stack_start;
p->thread.cpu_context.x20 = stk_sz;
@@ -499,8 +557,6 @@
*/
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.
@@ -512,18 +568,10 @@
* If all CPUs implement the SSBS extension, then we just need to
* context-switch the PSTATE field.
*/
- if (cpu_have_feature(cpu_feature(SSBS)))
+ if (cpus_have_const_cap(ARM64_SSBS))
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);
+ spectre_v4_enable_task_mitigation(next);
}
/*
@@ -541,6 +589,48 @@
}
/*
+ * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT.
+ * Ensure access is disabled when switching to a 32bit task, ensure
+ * access is enabled when switching to a 64bit task.
+ */
+static void erratum_1418040_thread_switch(struct task_struct *next)
+{
+ if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) ||
+ !this_cpu_has_cap(ARM64_WORKAROUND_1418040))
+ return;
+
+ if (is_compat_thread(task_thread_info(next)))
+ sysreg_clear_set(cntkctl_el1, ARCH_TIMER_USR_VCT_ACCESS_EN, 0);
+ else
+ sysreg_clear_set(cntkctl_el1, 0, ARCH_TIMER_USR_VCT_ACCESS_EN);
+}
+
+static void erratum_1418040_new_exec(void)
+{
+ preempt_disable();
+ erratum_1418040_thread_switch(current);
+ preempt_enable();
+}
+
+/*
+ * __switch_to() checks current->thread.sctlr_user as an optimisation. Therefore
+ * this function must be called with preemption disabled and the update to
+ * sctlr_user must be made in the same preemption disabled block so that
+ * __switch_to() does not see the variable update before the SCTLR_EL1 one.
+ */
+void update_sctlr_el1(u64 sctlr)
+{
+ /*
+ * EnIA must not be cleared while in the kernel as this is necessary for
+ * in-kernel PAC. It will be cleared on kernel exit if needed.
+ */
+ sysreg_clear_set(sctlr_el1, SCTLR_USER_MASK & ~SCTLR_ELx_ENIA, sctlr);
+
+ /* ISB required for the kernel uaccess routines when setting TCF0. */
+ isb();
+}
+
+/*
* Thread switching.
*/
__notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
@@ -555,7 +645,8 @@
entry_task_switch(next);
uao_thread_switch(next);
ssbs_thread_switch(next);
- scs_overflow_check(next);
+ erratum_1418040_thread_switch(next);
+ ptrauth_thread_switch_user(next);
/*
* Complete any pending TLB or cache maintenance on this CPU in case
@@ -564,6 +655,18 @@
* call.
*/
dsb(ish);
+
+ /*
+ * MTE thread switching must happen after the DSB above to ensure that
+ * any asynchronous tag check faults have been logged in the TFSR*_EL1
+ * registers.
+ */
+ mte_thread_switch(next);
+ /* avoid expensive SCTLR_EL1 accesses if no change */
+ if (prev->thread.sctlr_user != next->thread.sctlr_user)
+ update_sctlr_el1(next->thread.sctlr_user);
+
+ trace_android_vh_is_fpsimd_save(prev, next);
/* the actual thread switch */
last = cpu_switch_to(prev, next);
@@ -583,11 +686,8 @@
if (!stack_page)
return 0;
- frame.fp = thread_saved_fp(p);
- frame.pc = thread_saved_pc(p);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = p->curr_ret_stack;
-#endif
+ start_backtrace(&frame, thread_saved_fp(p), thread_saved_pc(p));
+
do {
if (unwind_frame(p, &frame))
goto out;
@@ -601,6 +701,7 @@
put_task_stack(p);
return ret;
}
+EXPORT_SYMBOL_GPL(get_wchan);
unsigned long arch_align_stack(unsigned long sp)
{
@@ -609,43 +710,39 @@
return sp & ~0xf;
}
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
- if (is_compat_task())
- return randomize_page(mm->brk, SZ_32M);
- else
- return randomize_page(mm->brk, SZ_1G);
-}
-
/*
* Called from setup_new_exec() after (COMPAT_)SET_PERSONALITY.
*/
void arch_setup_new_exec(void)
{
- current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0;
+ unsigned long mmflags = 0;
+
+ if (is_compat_task()) {
+ mmflags = MMCF_AARCH32;
+
+ /*
+ * Restrict the CPU affinity mask for a 32-bit task so that
+ * it contains only 32-bit-capable CPUs.
+ *
+ * From the perspective of the task, this looks similar to
+ * what would happen if the 64-bit-only CPUs were hot-unplugged
+ * at the point of execve(), although we try a bit harder to
+ * honour the cpuset hierarchy.
+ */
+ if (static_branch_unlikely(&arm64_mismatched_32bit_el0))
+ force_compatible_cpus_allowed_ptr(current);
+ }
+
+ current->mm->context.flags = mmflags;
+ ptrauth_thread_init_user();
+ mte_thread_init_user();
+ erratum_1418040_new_exec();
+
+ if (task_spec_ssb_noexec(current)) {
+ arch_prctl_spec_ctrl_set(current, PR_SPEC_STORE_BYPASS,
+ PR_SPEC_ENABLE);
+ }
}
-
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
-void __used stackleak_check_alloca(unsigned long size)
-{
- unsigned long stack_left;
- unsigned long current_sp = current_stack_pointer;
- struct stack_info info;
-
- BUG_ON(!on_accessible_stack(current, current_sp, &info));
-
- stack_left = current_sp - info.low;
-
- /*
- * There's a good chance we're almost out of stack space if this
- * is true. Using panic() over BUG() is more likely to give
- * reliable debugging output.
- */
- if (size >= stack_left)
- panic("alloca() over the kernel stack boundary\n");
-}
-EXPORT_SYMBOL(stackleak_check_alloca);
-#endif
#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
/*
@@ -653,11 +750,18 @@
*/
static unsigned int tagged_addr_disabled;
-long set_tagged_addr_ctrl(unsigned long arg)
+long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
{
- if (is_compat_task())
+ unsigned long valid_mask = PR_TAGGED_ADDR_ENABLE;
+ struct thread_info *ti = task_thread_info(task);
+
+ if (is_compat_thread(ti))
return -EINVAL;
- if (arg & ~PR_TAGGED_ADDR_ENABLE)
+
+ if (system_supports_mte())
+ valid_mask |= PR_MTE_TCF_MASK | PR_MTE_TAG_MASK;
+
+ if (arg & ~valid_mask)
return -EINVAL;
/*
@@ -667,20 +771,28 @@
if (arg & PR_TAGGED_ADDR_ENABLE && tagged_addr_disabled)
return -EINVAL;
- update_thread_flag(TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE);
+ if (set_mte_ctrl(task, arg) != 0)
+ return -EINVAL;
+
+ update_ti_thread_flag(ti, TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE);
return 0;
}
-long get_tagged_addr_ctrl(void)
+long get_tagged_addr_ctrl(struct task_struct *task)
{
- if (is_compat_task())
+ long ret = 0;
+ struct thread_info *ti = task_thread_info(task);
+
+ if (is_compat_thread(ti))
return -EINVAL;
- if (test_thread_flag(TIF_TAGGED_ADDR))
- return PR_TAGGED_ADDR_ENABLE;
+ if (test_ti_thread_flag(ti, TIF_TAGGED_ADDR))
+ ret = PR_TAGGED_ADDR_ENABLE;
- return 0;
+ ret |= get_mte_ctrl(task);
+
+ return ret;
}
/*
@@ -688,8 +800,6 @@
* only prevents the tagged address ABI enabling via prctl() and does not
* disable it for tasks that already opted in to the relaxed ABI.
*/
-static int zero;
-static int one = 1;
static struct ctl_table tagged_addr_sysctl_table[] = {
{
@@ -698,8 +808,8 @@
.data = &tagged_addr_disabled,
.maxlen = sizeof(int),
.proc_handler = proc_dointvec_minmax,
- .extra1 = &zero,
- .extra2 = &one,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
},
{ }
};
@@ -713,3 +823,41 @@
core_initcall(tagged_addr_init);
#endif /* CONFIG_ARM64_TAGGED_ADDR_ABI */
+
+asmlinkage void __sched arm64_preempt_schedule_irq(void)
+{
+ lockdep_assert_irqs_disabled();
+
+ /*
+ * Preempting a task from an IRQ means we leave copies of PSTATE
+ * on the stack. cpufeature's enable calls may modify PSTATE, but
+ * resuming one of these preempted tasks would undo those changes.
+ *
+ * Only allow a task to be preempted once cpufeatures have been
+ * enabled.
+ */
+ if (system_capabilities_finalized())
+ preempt_schedule_irq();
+}
+
+#ifdef CONFIG_BINFMT_ELF
+int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state,
+ bool has_interp, bool is_interp)
+{
+ /*
+ * For dynamically linked executables the interpreter is
+ * responsible for setting PROT_BTI on everything except
+ * itself.
+ */
+ if (is_interp != has_interp)
+ return prot;
+
+ if (!(state->flags & ARM64_ELF_BTI))
+ return prot;
+
+ if (prot & PROT_EXEC)
+ prot |= PROT_BTI;
+
+ return prot;
+}
+#endif
--
Gitblit v1.6.2