arm64: errata: Fix exec handling in erratum 1418040 workaround
PATCH 1/1 arm64: errata: Fix exec handling in erratum 1418040 workaround
From: D Scott Phillips <[email protected]>
commit 38e0257e0e6f4fef2aa2966b089b56a8b1cfb75c upstream.
The erratum 1418040 workaround enables CNTVCT_EL1 access trapping in EL0 when executing compat threads. The workaround is applied when switching between tasks, but the need for the workaround could also change at an exec(), when a non-compat task execs a compat binary or vice versa. Apply the workaround in arch_setup_new_exec().
This leaves a small window of time between SET_PERSONALITY and arch_setup_new_exec where preemption could occur and confuse the old workaround logic that compares TIF_32BIT between prev and next. Instead, we can just read cntkctl to make sure it's in the state that the next task needs. I measured cntkctl read time to be about the same as a mov from a general-purpose register on N1. Update the workaround logic to examine the current value of cntkctl instead of the previous task's compat state.
--- arch/arm64/kernel/process.c | 39 +++++++++++++++---------------------- 1 file changed, 16 insertions(+), 23 deletions(-)
arch/arm64/kernel/process.c +16 -23
@@ -515,34 +515,26 @@ static void entry_task_switch(struct task_struct *next)/* * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT. -* Assuming the virtual counter is enabled at the beginning of times: -* -* - disable access when switching from a 64bit task to a 32bit task -* - enable access when switching from a 32bit task to a 64bit task +* 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 *prev, -struct task_struct *next) +static void erratum_1418040_thread_switch (struct task_struct *next) { -bool prev32, next32; -u64 val; - -if (!IS_ENABLED (CONFIG_ARM64_ERRATUM_1418040 )) -return ; - - prev32 =is_compat_thread (task_thread_info (prev)); - next32 =is_compat_thread (task_thread_info (next)); - -if (prev32 == next32 || !this_cpu_has_cap (ARM64_WORKAROUND_1418040 )) +if (!IS_ENABLED (CONFIG_ARM64_ERRATUM_1418040 ) || + !this_cpu_has_cap (ARM64_WORKAROUND_1418040 ))return ; - val =read_sysreg (cntkctl_el1); - -if (!next32) - val |=ARCH_TIMER_USR_VCT_ACCESS_EN ; +if (is_compat_thread (task_thread_info (next))) +sysreg_clear_set (cntkctl_el1,ARCH_TIMER_USR_VCT_ACCESS_EN ,0 );else - val &= ~ARCH_TIMER_USR_VCT_ACCESS_EN ; +sysreg_clear_set (cntkctl_el1,0 ,ARCH_TIMER_USR_VCT_ACCESS_EN ); +} -write_sysreg (val, cntkctl_el1); +static void erratum_1418040_new_exec (void ) +{ +preempt_disable (); +erratum_1418040_thread_switch (current); +preempt_enable (); }/*
@@ -560,7 +552,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,entry_task_switch (next);uao_thread_switch (next);ssbs_thread_switch (next); -erratum_1418040_thread_switch (prev, next); +erratum_1418040_thread_switch (next);/* * Complete any pending TLB or cache maintenance on this CPU in case
@@ -619,6 +611,7 @@ void arch_setup_new_exec(void) current->mm->context.flags =is_compat_task () ?MMCF_AARCH32 :0 ;ptrauth_thread_init_user (current); +erratum_1418040_new_exec (); }#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
Greg Kroah-Hartman
maintainerQuoted 18 lines · Catalin Marinas
From: D Scott Phillips <[email protected]>
commit
38e0257e0e6f4fef2aa2966b089b56a8b1cfb75cupstream.The erratum 1418040 workaround enables
CNTVCT_EL1access trapping in EL0 when executing compat threads. The workaround is applied when switching between tasks, but the need for the workaround could also change at anexec(), when a non-compat task execs a compat binary or vice versa. Apply the workaround inarch_setup_new_exec().This leaves a small window of time between
SET_PERSONALITYandarch_setup_new_execwhere preemption could occur and confuse the old workaround logic that comparesTIF_32BITbetween prev and next. Instead, we can just read cntkctl to make sure it's in the state that the next task needs. I measured cntkctl read time to be about the same as a mov from a general-purpose register on N1. Update the workaround logic to examine the current value of cntkctl instead of the previous task's compat state.
Quoted 2 lines
Fixes d49f7d7376d0 ("arm64: Move handling of erratum 1418040 into C code")Cc <[email protected]> # 5.9.x
5.9.x is long end-of-life, did you mean to do this for 5.10.y?
If so, it does not apply cleanly there :(
thanks,
greg k-h
Quoted 19 lines · Greg Kroah-Hartman
Quoted 18 lines · Catalin Marinas
From: D Scott Phillips <[email protected]>
commit
38e0257e0e6f4fef2aa2966b089b56a8b1cfb75cupstream.The erratum 1418040 workaround enables
CNTVCT_EL1access trapping in EL0 when executing compat threads. The workaround is applied when switching between tasks, but the need for the workaround could also change at anexec(), when a non-compat task execs a compat binary or vice versa. Apply the workaround inarch_setup_new_exec().This leaves a small window of time between
SET_PERSONALITYandarch_setup_new_execwhere preemption could occur and confuse the old workaround logic that comparesTIF_32BITbetween prev and next. Instead, we can just read cntkctl to make sure it's in the state that the next task needs. I measured cntkctl read time to be about the same as a mov from a general-purpose register on N1. Update the workaround logic to examine the current value of cntkctl instead of the previous task's compat state.
Quoted 4 lines
Quoted 2 lines
Fixes d49f7d7376d0 ("arm64: Move handling of erratum 1418040 into C code")Cc <[email protected]> # 5.9.x5.9.x is long end-of-life, did you mean to do this for 5.10.y?
Ah, true, not sure how I ended up checking out the 5.9 stable branch (maybe I had 4.9 in mind for an unrelated thing and just thought of something .9).
I'll send you a backport to 5.10.
Signature · 1 line
Catalin