linux-stable/arch/arm64/kernel/suspend.c
Mark Rutland 25693f1771 arm64: Avoid cpus_have_const_cap() for ARM64_HAS_DIT
In __cpu_suspend_exit() we use cpus_have_const_cap() to check for
ARM64_HAS_DIT but this is not necessary and cpus_have_final_cap() of
alternative_has_cap_*() would be preferable.

For historical reasons, cpus_have_const_cap() is more complicated than
it needs to be. Before cpucaps are finalized, it will perform a bitmap
test of the system_cpucaps bitmap, and once cpucaps are finalized it
will use an alternative branch. This used to be necessary to handle some
race conditions in the window between cpucap detection and the
subsequent patching of alternatives and static branches, where different
branches could be out-of-sync with one another (or w.r.t. alternative
sequences). Now that we use alternative branches instead of static
branches, these are all patched atomically w.r.t. one another, and there
are only a handful of cases that need special care in the window between
cpucap detection and alternative patching.

Due to the above, it would be nice to remove cpus_have_const_cap(), and
migrate callers over to alternative_has_cap_*(), cpus_have_final_cap(),
or cpus_have_cap() depending on when their requirements. This will
remove redundant instructions and improve code generation, and will make
it easier to determine how each callsite will behave before, during, and
after alternative patching.

The ARM64_HAS_DIT cpucap is detected and patched (along with all other
cpucaps) before __cpu_suspend_exit() can run. We'll only use
__cpu_suspend_exit() as part of PSCI cpuidle or hibernation, and both of
these are intialized after system cpucaps are detected and patched: the
PSCI cpuidle driver is registered with a device_initcall, hibernation
restoration occurs in a late_initcall, and hibarnation saving is driven
by usrspace. Therefore it is not necessary to use cpus_have_const_cap(),
and using alternative_has_cap_*() or cpus_have_final_cap() is
sufficient.

This patch replaces the use of cpus_have_const_cap() with
alternative_has_cap_unlikely(), which will avoid generating code to test
the system_cpucaps bitmap and should be better for all subsequent calls
at runtime. To clearly document the ordering relationship between
suspend/resume and alternatives patching, an explicit check for
system_capabilities_finalized() is added to cpu_suspend() along with a
comment block, which will make it easier to spot issues if code is
changed in future to allow these functions to be reached earlier.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2023-10-16 14:17:04 +01:00

184 lines
5 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/ftrace.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/pgtable.h>
#include <linux/cpuidle.h>
#include <asm/alternative.h>
#include <asm/cacheflush.h>
#include <asm/cpufeature.h>
#include <asm/cpuidle.h>
#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
#include <asm/exec.h>
#include <asm/mte.h>
#include <asm/memory.h>
#include <asm/mmu_context.h>
#include <asm/smp_plat.h>
#include <asm/suspend.h>
/*
* This is allocated by cpu_suspend_init(), and used to store a pointer to
* the 'struct sleep_stack_data' the contains a particular CPUs state.
*/
unsigned long *sleep_save_stash;
/*
* This hook is provided so that cpu_suspend code can restore HW
* breakpoints as early as possible in the resume path, before reenabling
* debug exceptions. Code cannot be run from a CPU PM notifier since by the
* time the notifier runs debug exceptions might have been enabled already,
* with HW breakpoints registers content still in an unknown state.
*/
static int (*hw_breakpoint_restore)(unsigned int);
void __init cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int))
{
/* Prevent multiple restore hook initializations */
if (WARN_ON(hw_breakpoint_restore))
return;
hw_breakpoint_restore = hw_bp_restore;
}
void notrace __cpu_suspend_exit(void)
{
unsigned int cpu = smp_processor_id();
mte_suspend_exit();
/*
* We are resuming from reset with the idmap active in TTBR0_EL1.
* We must uninstall the idmap and restore the expected MMU
* state before we can possibly return to userspace.
*/
cpu_uninstall_idmap();
/* Restore CnP bit in TTBR1_EL1 */
if (system_supports_cnp())
cpu_enable_swapper_cnp();
/*
* PSTATE was not saved over suspend/resume, re-enable any detected
* features that might not have been set correctly.
*/
if (alternative_has_cap_unlikely(ARM64_HAS_DIT))
set_pstate_dit(1);
__uaccess_enable_hw_pan();
/*
* Restore HW breakpoint registers to sane values
* before debug exceptions are possibly reenabled
* by cpu_suspend()s local_daif_restore() call.
*/
if (hw_breakpoint_restore)
hw_breakpoint_restore(cpu);
/*
* On resume, firmware implementing dynamic mitigation will
* have turned the mitigation on. If the user has forcefully
* disabled it, make sure their wishes are obeyed.
*/
spectre_v4_enable_mitigation(NULL);
/* Restore additional feature-specific configuration */
ptrauth_suspend_exit();
}
/*
* cpu_suspend
*
* arg: argument to pass to the finisher function
* fn: finisher function pointer
*
*/
int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
{
int ret = 0;
unsigned long flags;
struct sleep_stack_data state;
struct arm_cpuidle_irq_context context;
/*
* Some portions of CPU state (e.g. PSTATE.{PAN,DIT}) are initialized
* before alternatives are patched, but are only restored by
* __cpu_suspend_exit() after alternatives are patched. To avoid
* accidentally losing these bits we must not attempt to suspend until
* after alternatives have been patched.
*/
WARN_ON(!system_capabilities_finalized());
/* Report any MTE async fault before going to suspend */
mte_suspend_enter();
/*
* From this point debug exceptions are disabled to prevent
* updates to mdscr register (saved and restored along with
* general purpose registers) from kernel debuggers.
*
* Strictly speaking the trace_hardirqs_off() here is superfluous,
* hardirqs should be firmly off by now. This really ought to use
* something like raw_local_daif_save().
*/
flags = local_daif_save();
/*
* Function graph tracer state gets inconsistent when the kernel
* calls functions that never return (aka suspend finishers) hence
* disable graph tracing during their execution.
*/
pause_graph_tracing();
/*
* Switch to using DAIF.IF instead of PMR in order to reliably
* resume if we're using pseudo-NMIs.
*/
arm_cpuidle_save_irq_context(&context);
ct_cpuidle_enter();
if (__cpu_suspend_enter(&state)) {
/* Call the suspend finisher */
ret = fn(arg);
/*
* Never gets here, unless the suspend finisher fails.
* Successful cpu_suspend() should return from cpu_resume(),
* returning through this code path is considered an error
* If the return value is set to 0 force ret = -EOPNOTSUPP
* to make sure a proper error condition is propagated
*/
if (!ret)
ret = -EOPNOTSUPP;
ct_cpuidle_exit();
} else {
ct_cpuidle_exit();
__cpu_suspend_exit();
}
arm_cpuidle_restore_irq_context(&context);
unpause_graph_tracing();
/*
* Restore pstate flags. OS lock and mdscr have been already
* restored, so from this point onwards, debugging is fully
* reenabled if it was enabled when core started shutdown.
*/
local_daif_restore(flags);
return ret;
}
static int __init cpu_suspend_init(void)
{
/* ctx_ptr is an array of physical addresses */
sleep_save_stash = kcalloc(mpidr_hash_size(), sizeof(*sleep_save_stash),
GFP_KERNEL);
if (WARN_ON(!sleep_save_stash))
return -ENOMEM;
return 0;
}
early_initcall(cpu_suspend_init);