From 1a1c130ab7575498eed5bcf7220037ae09cd1f8a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 23 Mar 2021 20:26:52 +0100 Subject: ACPI: tables: x86: Reserve memory occupied by ACPI tables The following problem has been reported by George Kennedy: Since commit 7fef431be9c9 ("mm/page_alloc: place pages to tail in __free_pages_core()") the following use after free occurs intermittently when ACPI tables are accessed. BUG: KASAN: use-after-free in ibft_init+0x134/0xc49 Read of size 4 at addr ffff8880be453004 by task swapper/0/1 CPU: 3 PID: 1 Comm: swapper/0 Not tainted 5.12.0-rc1-7a7fd0d #1 Call Trace: dump_stack+0xf6/0x158 print_address_description.constprop.9+0x41/0x60 kasan_report.cold.14+0x7b/0xd4 __asan_report_load_n_noabort+0xf/0x20 ibft_init+0x134/0xc49 do_one_initcall+0xc4/0x3e0 kernel_init_freeable+0x5af/0x66b kernel_init+0x16/0x1d0 ret_from_fork+0x22/0x30 ACPI tables mapped via kmap() do not have their mapped pages reserved and the pages can be "stolen" by the buddy allocator. Apparently, on the affected system, the ACPI table in question is not located in "reserved" memory, like ACPI NVS or ACPI Data, that will not be used by the buddy allocator, so the memory occupied by that table has to be explicitly reserved to prevent the buddy allocator from using it. In order to address this problem, rearrange the initialization of the ACPI tables on x86 to locate the initial tables earlier and reserve the memory occupied by them. The other architectures using ACPI should not be affected by this change. Link: https://lore.kernel.org/linux-acpi/1614802160-29362-1-git-send-email-george.kennedy@oracle.com/ Reported-by: George Kennedy Tested-by: George Kennedy Signed-off-by: Rafael J. Wysocki Reviewed-by: Mike Rapoport Cc: 5.10+ # 5.10+ --- arch/x86/kernel/acpi/boot.c | 25 ++++++++++++------------- arch/x86/kernel/setup.c | 8 +++----- 2 files changed, 15 insertions(+), 18 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 7bdc0239a943..14cd3186dc77 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1554,10 +1554,18 @@ void __init acpi_boot_table_init(void) /* * Initialize the ACPI boot-time table parser. */ - if (acpi_table_init()) { + if (acpi_locate_initial_tables()) disable_acpi(); - return; - } + else + acpi_reserve_initial_tables(); +} + +int __init early_acpi_boot_init(void) +{ + if (acpi_disabled) + return 1; + + acpi_table_init_complete(); acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf); @@ -1570,18 +1578,9 @@ void __init acpi_boot_table_init(void) } else { printk(KERN_WARNING PREFIX "Disabling ACPI support\n"); disable_acpi(); - return; + return 1; } } -} - -int __init early_acpi_boot_init(void) -{ - /* - * If acpi_disabled, bail out - */ - if (acpi_disabled) - return 1; /* * Process the Multiple APIC Description Table (MADT), if present diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d883176ef2ce..5ecd69a48393 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1045,6 +1045,9 @@ void __init setup_arch(char **cmdline_p) cleanup_highmap(); + /* Look for ACPI tables and reserve memory occupied by them. */ + acpi_boot_table_init(); + memblock_set_current_limit(ISA_END_ADDRESS); e820__memblock_setup(); @@ -1136,11 +1139,6 @@ void __init setup_arch(char **cmdline_p) early_platform_quirks(); - /* - * Parse the ACPI tables for possible boot-time SMP configuration. - */ - acpi_boot_table_init(); - early_acpi_boot_init(); initmem_init(); -- cgit v1.2.3-70-g09d2 From 8cdddd182bd7befae6af49c5fd612893f55d6ccb Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 24 Mar 2021 16:22:19 +0100 Subject: ACPI: processor: Fix CPU0 wakeup in acpi_idle_play_dead() Commit 496121c02127 ("ACPI: processor: idle: Allow probing on platforms with one ACPI C-state") broke CPU0 hotplug on certain systems, e.g. I'm observing the following on AWS Nitro (e.g r5b.xlarge but other instance types are affected as well): # echo 0 > /sys/devices/system/cpu/cpu0/online # echo 1 > /sys/devices/system/cpu/cpu0/online <10 seconds delay> -bash: echo: write error: Input/output error In fact, the above mentioned commit only revealed the problem and did not introduce it. On x86, to wakeup CPU an NMI is being used and hlt_play_dead()/mwait_play_dead() loops are prepared to handle it: /* * If NMI wants to wake up CPU0, start CPU0. */ if (wakeup_cpu0()) start_cpu0(); cpuidle_play_dead() -> acpi_idle_play_dead() (which is now being called on systems where it wasn't called before the above mentioned commit) serves the same purpose but it doesn't have a path for CPU0. What happens now on wakeup is: - NMI is sent to CPU0 - wakeup_cpu0_nmi() works as expected - we get back to while (1) loop in acpi_idle_play_dead() - safe_halt() puts CPU0 to sleep again. The straightforward/minimal fix is add the special handling for CPU0 on x86 and that's what the patch is doing. Fixes: 496121c02127 ("ACPI: processor: idle: Allow probing on platforms with one ACPI C-state") Signed-off-by: Vitaly Kuznetsov Cc: 5.10+ # 5.10+ Signed-off-by: Rafael J. Wysocki --- arch/x86/include/asm/smp.h | 1 + arch/x86/kernel/smpboot.c | 2 +- drivers/acpi/processor_idle.c | 7 +++++++ 3 files changed, 9 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index c0538f82c9a2..57ef2094af93 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -132,6 +132,7 @@ void native_play_dead(void); void play_dead_common(void); void wbinvd_on_cpu(int cpu); int wbinvd_on_all_cpus(void); +bool wakeup_cpu0(void); void native_smp_send_reschedule(int cpu); void native_send_call_func_ipi(const struct cpumask *mask); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 02813a7f3a7c..f877150a91da 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1659,7 +1659,7 @@ void play_dead_common(void) local_irq_disable(); } -static bool wakeup_cpu0(void) +bool wakeup_cpu0(void) { if (smp_processor_id() == 0 && enable_start_cpu0) return true; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index d93e400940a3..768a6b4d2368 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -29,6 +29,7 @@ */ #ifdef CONFIG_X86 #include +#include #endif #define _COMPONENT ACPI_PROCESSOR_COMPONENT @@ -541,6 +542,12 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) wait_for_freeze(); } else return -ENODEV; + +#if defined(CONFIG_X86) && defined(CONFIG_HOTPLUG_CPU) + /* If NMI wants to wake up CPU0, start CPU0. */ + if (wakeup_cpu0()) + start_cpu0(); +#endif } /* Never reached */ -- cgit v1.2.3-70-g09d2