Re: [PATCH v6] mm,kfence: decouple kfence from page granularity mapping judgement

[Kefeng Wang <wangkefeng.wang@huawei.com>]

On 2023/3/13 21:00, Marco Elver wrote:
> On Mon, 13 Mar 2023 at 12:57, Zhenhua Huang <quic_zhenhuah@quicinc.com> wrote:
>>
>> Kfence only needs its pool to be mapped as page granularity, if it is
>> inited early. Previous judgement was a bit over protected. From [1], Mark
>> suggested to "just map the KFENCE region a page granularity". So I
>> decouple it from judgement and do page granularity mapping for kfence
>> pool only. Need to be noticed that late init of kfence pool still requires
>> page granularity mapping.
>>
>> Page granularity mapping in theory cost more(2M per 1GB) memory on arm64
>> platform. Like what I've tested on QEMU(emulated 1GB RAM) with
>> gki_defconfig, also turning off rodata protection:
>> Before:
>> [root@liebao ]# cat /proc/meminfo
>> MemTotal:         999484 kB
>> After:
>> [root@liebao ]# cat /proc/meminfo
>> MemTotal:        1001480 kB
>>
>> To implement this, also relocate the kfence pool allocation before the
>> linear mapping setting up, arm64_kfence_alloc_pool is to allocate phys
>> addr, __kfence_pool is to be set after linear mapping set up.
>>
>> LINK: [1] https://lore.kernel.org/linux-arm-kernel/Y+IsdrvDNILA59UN@FVFF77S0Q05N/
>> Suggested-by: Mark Rutland <mark.rutland@arm.com>
>> Signed-off-by: Zhenhua Huang <quic_zhenhuah@quicinc.com>
>> ---
>>   arch/arm64/mm/mmu.c      | 42 ++++++++++++++++++++++++++++++++++++++++++
>>   arch/arm64/mm/pageattr.c |  8 ++++++--
>>   include/linux/kfence.h   | 10 ++++++++++
>>   mm/kfence/core.c         |  9 +++++++++
>>   4 files changed, 67 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
>> index 6f9d889..ca5c932 100644
>> --- a/arch/arm64/mm/mmu.c
>> +++ b/arch/arm64/mm/mmu.c
>> @@ -24,6 +24,7 @@
>>   #include <linux/mm.h>
>>   #include <linux/vmalloc.h>
>>   #include <linux/set_memory.h>
>> +#include <linux/kfence.h>
>>
>>   #include <asm/barrier.h>
>>   #include <asm/cputype.h>
>> @@ -525,6 +526,31 @@ static int __init enable_crash_mem_map(char *arg)
>>   }
>>   early_param("crashkernel", enable_crash_mem_map);
>>
>> +#ifdef CONFIG_KFENCE
>> +
>> +static phys_addr_t arm64_kfence_alloc_pool(void)
>> +{
>> +       phys_addr_t kfence_pool;
>> +
>> +       if (!kfence_sample_interval)
>> +               return 0;
>> +
>> +       kfence_pool = memblock_phys_alloc(KFENCE_POOL_SIZE, PAGE_SIZE);
>> +       if (!kfence_pool)
>> +               pr_err("failed to allocate kfence pool\n");
>> +
>> +       return kfence_pool;
>> +}
>> +
>> +#else
>> +
>> +static phys_addr_t arm64_kfence_alloc_pool(void)
>> +{
>> +       return 0;
>> +}
>> +
>> +#endif
>> +
>>   static void __init map_mem(pgd_t *pgdp)
>>   {
>>          static const u64 direct_map_end = _PAGE_END(VA_BITS_MIN);
>> @@ -532,6 +558,7 @@ static void __init map_mem(pgd_t *pgdp)
>>          phys_addr_t kernel_end = __pa_symbol(__init_begin);
>>          phys_addr_t start, end;
>>          int flags = NO_EXEC_MAPPINGS;
>> +       phys_addr_t kfence_pool;
>>          u64 i;
>>
>>          /*
>> @@ -564,6 +591,10 @@ static void __init map_mem(pgd_t *pgdp)
>>          }
>>   #endif
>>
>> +       kfence_pool = arm64_kfence_alloc_pool();
>> +       if (kfence_pool)
>> +               memblock_mark_nomap(kfence_pool, KFENCE_POOL_SIZE);
>> +
>>          /* map all the memory banks */
>>          for_each_mem_range(i, &start, &end) {
>>                  if (start >= end)
>> @@ -608,6 +639,17 @@ static void __init map_mem(pgd_t *pgdp)
>>                  }
>>          }
>>   #endif
>> +
>> +       /* Kfence pool needs page-level mapping */
>> +       if (kfence_pool) {
>> +               __map_memblock(pgdp, kfence_pool,
>> +                       kfence_pool + KFENCE_POOL_SIZE,
>> +                       pgprot_tagged(PAGE_KERNEL),
>> +                       NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
>> +               memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE);
>> +               /* kfence_pool really mapped now */
>> +               kfence_set_pool(kfence_pool);
>> +       }
>>   }
>>
>>   void mark_rodata_ro(void)
>> diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
>> index 79dd201..25e4a983 100644
>> --- a/arch/arm64/mm/pageattr.c
>> +++ b/arch/arm64/mm/pageattr.c
>> @@ -7,6 +7,7 @@
>>   #include <linux/module.h>
>>   #include <linux/sched.h>
>>   #include <linux/vmalloc.h>
>> +#include <linux/kfence.h>
>>
>>   #include <asm/cacheflush.h>
>>   #include <asm/set_memory.h>
>> @@ -22,12 +23,15 @@ bool rodata_full __ro_after_init = IS_ENABLED(CONFIG_RODATA_FULL_DEFAULT_ENABLED
>>   bool can_set_direct_map(void)
>>   {
>>          /*
>> -        * rodata_full, DEBUG_PAGEALLOC and KFENCE require linear map to be
>> +        * rodata_full and DEBUG_PAGEALLOC require linear map to be
>>           * mapped at page granularity, so that it is possible to
>>           * protect/unprotect single pages.
>> +        *
>> +        * Kfence pool requires page granularity mapping also if we init it
>> +        * late.
>>           */
>>          return (rodata_enabled && rodata_full) || debug_pagealloc_enabled() ||
>> -               IS_ENABLED(CONFIG_KFENCE);
>> +           (IS_ENABLED(CONFIG_KFENCE) && !kfence_sample_interval);
> 
> If you're struggling with kfence_sample_interval not existing if
> !CONFIG_KFENCE, this is one of the occasions where it'd be perfectly
> fine to write:
> 
> bool can_set_direct_map(void) {
> #ifdef CONFIG_KFENCE
>      /* ... your comment here ...*/
>      if (!kfence_sample_interval)
>          return true;
> }
> #endif
>       return .........
> }
> 
>>   }
>>
The can_set_direct_map() could be called anytime, eg, memory add,
vmalloc, and this will make different state of can_set_direct_map()
if kfence is re-enabled, I think that we need a new value to check 
whether or not the early kfence_pool is initialized.