[PATCH v2] arm64: fix the overlap between the kernel image and vmalloc address

[Tan Xiaojun]

Hi,
Mark, Ard,

Could you review this patch and give some suggestions? Or maybe you can give a better fix
for this problem. I care about this problem, but don't know how to do.

Very sorry to bother you or other people.
Thanks.
Xiaojun.

On 2017/4/25 23:09, zhongjiang wrote:
> Recently, xiaojun report the following issue.
> 
> [ 4544.984139] Unable to handle kernel paging request at virtual address ffff804392800000
> [ 4544.991995] pgd = ffff80096745f000
> [ 4544.995369] [ffff804392800000] *pgd=0000000000000000
> [ 4545.000297] Internal error: Oops: 96000005 [#1] PREEMPT SMP
> [ 4545.005815] Modules linked in:
> [ 4545.008843] CPU: 1 PID: 8976 Comm: cat Not tainted 4.11.0-rc6 #1
> [ 4545.014790] Hardware name: ARM Juno development board (r1) (DT)
> [ 4545.020653] task: ffff8009753fdb00 task.stack: ffff80097533c000
> [ 4545.026520] PC is at __memcpy+0x100/0x180
> [ 4545.030491] LR is at vread+0x144/0x280
> [ 4545.034202] pc : [<ffff0000083a1000>] lr : [<ffff0000081c126c>] pstate: 20000145
> [ 4545.041530] sp : ffff80097533fcb0
> [ 4545.044811] x29: ffff80097533fcb0 x28: ffff800962d24000
> [ 4545.050074] x27: 0000000000001000 x26: ffff8009753fdb00
> [ 4545.055337] x25: ffff000008200000 x24: ffff800977801380
> [ 4545.060600] x23: ffff8009753fdb00 x22: ffff800962d24000
> [ 4545.065863] x21: 0000000000001000 x20: ffff000008200000
> [ 4545.071125] x19: 0000000000001000 x18: 0000ffffefa323c0
> [ 4545.076387] x17: 0000ffffa9c87440 x16: ffff0000081fdfd0
> [ 4545.081649] x15: 0000ffffa9d01588 x14: 72a77346b2407be7
> [ 4545.086911] x13: 5299400690000000 x12: b0000001f9001a79
> [ 4545.092173] x11: 97fc098d91042260 x10: 0000000000000000
> [ 4545.097435] x9 : 0000000000000000 x8 : 9110626091260021
> [ 4545.102698] x7 : 0000000000001000 x6 : ffff800962d24000
> [ 4545.107960] x5 : ffff8009778013b0 x4 : 0000000000000000
> [ 4545.113222] x3 : 0400000000000001 x2 : 0000000000000f80
> [ 4545.118484] x1 : ffff804392800000 x0 : ffff800962d24000
> [ 4545.123745]
> [ 4545.125220] Process cat (pid: 8976, stack limit = 0xffff80097533c000)
> [ 4545.131598] Stack: (0xffff80097533fcb0 to 0xffff800975340000)
> [ 4545.137289] fca0:                                   ffff80097533fd30 ffff000008270f64
> [ 4545.145049] fcc0: 000000000000e000 000000003956f000 ffff000008f950d0 ffff80097533feb8
> [ 4545.152809] fce0: 0000000000002000 ffff8009753fdb00 ffff800962d24000 ffff000008e8d3d8
> [ 4545.160568] fd00: 0000000000001000 ffff000008200000 0000000000001000 ffff800962d24000
> [ 4545.168327] fd20: 0000000000001000 ffff000008e884a0 ffff80097533fdb0 ffff00000826340c
> [ 4545.176086] fd40: ffff800976bf2800 fffffffffffffffb 000000003956d000 ffff80097533feb8
> [ 4545.183846] fd60: 0000000060000000 0000000000000015 0000000000000124 000000000000003f
> [ 4545.191605] fd80: ffff000008962000 ffff8009753fdb00 ffff8009753fdb00 ffff8009753fdb00
> [ 4545.199364] fda0: 0000000300000124 0000000000002000 ffff80097533fdd0 ffff0000081fb83c
> [ 4545.207123] fdc0: 0000000000010000 ffff80097514f900 ffff80097533fe50 ffff0000081fcb28
> [ 4545.214883] fde0: 0000000000010000 ffff80097514f900 0000000000000000 0000000000000000
> [ 4545.222642] fe00: ffff80097533fe30 ffff0000081fca1c ffff80097514f900 0000000000000000
> [ 4545.230401] fe20: 000000003956d000 ffff80097533feb8 ffff80097533fe50 ffff0000081fcb04
> [ 4545.238160] fe40: 0000000000010000 ffff80097514f900 ffff80097533fe80 ffff0000081fe014
> [ 4545.245919] fe60: ffff80097514f900 ffff80097514f900 000000003956d000 0000000000010000
> [ 4545.253678] fe80: 0000000000000000 ffff000008082f30 0000000000000000 0000800977146000
> [ 4545.261438] fea0: ffffffffffffffff 0000ffffa9c8745c 0000000000000124 0000000008202000
> [ 4545.269197] fec0: 0000000000000003 000000003956d000 0000000000010000 0000000000000000
> [ 4545.276956] fee0: 0000000000011011 0000000000000001 0000000000000011 0000000000000002
> [ 4545.284715] ff00: 000000000000003f 1f3c201f7372686b 00000000ffffffff 0000000000000030
> [ 4545.292474] ff20: 0000000000000038 0000000000000000 0000ffffa9bcca94 0000ffffa9d01588
> [ 4545.300233] ff40: 0000000000000000 0000ffffa9c87440 0000ffffefa323c0 0000000000010000
> [ 4545.307993] ff60: 000000000041a310 000000003956d000 0000000000000003 000000007fffe000
> [ 4545.315751] ff80: 00000000004088d0 0000000000010000 0000000000000000 0000000000000000
> [ 4545.323511] ffa0: 0000000000010000 0000ffffefa32690 0000000000404dcc 0000ffffefa32690
> [ 4545.331270] ffc0: 0000ffffa9c8745c 0000000060000000 0000000000000003 000000000000003f
> [ 4545.339029] ffe0: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
> [ 4545.346786] Call trace:
> [ 4545.349207] Exception stack(0xffff80097533fae0 to 0xffff80097533fc10)
> [ 4545.355586] fae0: 0000000000001000 0001000000000000 ffff80097533fcb0 ffff0000083a1000
> [ 4545.363345] fb00: 000000003957c000 ffff80097533fc00 0000000020000145 0000000000000025
> [ 4545.371105] fb20: ffff800962d24000 ffff000008e8d3d8 0000000000001000 ffff8009753fdb00
> [ 4545.378864] fb40: 0000000000000000 0000000000000002 ffff80097533fd30 ffff000008082604
> [ 4545.386623] fb60: 0000000000001000 0001000000000000 ffff80097533fd30 ffff0000083a0a90
> [ 4545.394382] fb80: ffff800962d24000 ffff804392800000 0000000000000f80 0400000000000001
> [ 4545.402140] fba0: 0000000000000000 ffff8009778013b0 ffff800962d24000 0000000000001000
> [ 4545.409899] fbc0: 9110626091260021 0000000000000000 0000000000000000 97fc098d91042260
> [ 4545.417658] fbe0: b0000001f9001a79 5299400690000000 72a77346b2407be7 0000ffffa9d01588
> [ 4545.425416] fc00: ffff0000081fdfd0 0000ffffa9c87440
> [ 4545.430248] [<ffff0000083a1000>] __memcpy+0x100/0x180
> [ 4545.435253] [<ffff000008270f64>] read_kcore+0x21c/0x3b0
> [ 4545.440429] [<ffff00000826340c>] proc_reg_read+0x64/0x90
> [ 4545.445691] [<ffff0000081fb83c>] __vfs_read+0x1c/0x108
> [ 4545.450779] [<ffff0000081fcb28>] vfs_read+0x80/0x130
> [ 4545.455696] [<ffff0000081fe014>] SyS_read+0x44/0xa0
> [ 4545.460528] [<ffff000008082f30>] el0_svc_naked+0x24/0x28
> [ 4545.465790] Code: d503201f d503201f d503201f d503201f (a8c12027)
> [ 4545.471852] ---[ end trace 4d1897f94759f461 ]---
> [ 4545.476435] note: cat[8976] exited with preempt_count 2
> 
> I find the issue is introduced when applying commit f9040773b7bb
> ("arm64: move kernel image to base of vmalloc area"). This patch
> make the kernel image overlap with vmalloc area. It will result in
> vmalloc area have the huge page table. but the vmalloc_to_page is
> not realize the change. and the function is public to any arch.
> 
> I fix it by adding the another kernel image condition in vmalloc_to_page
> to make it keep the accordance with previous vmalloc mapping.
> 
> Fixes: f9040773b7bb ("arm64: move kernel image to base of vmalloc area")
> Reported-by: tan xiaojun <tanxiaojun at huawei.com>
> Suggested-by: Mark Rutland <mark.rutland at arm.com>
> Signed-off-by: zhongjiang <zhongjiang at huawei.com>
> ---
> v2
>  Reimplement the fix by adding the kernel_image_addr helper function.
>  instead by the previos fix by forcing the kernel image page table to
>  set up in page granularity. beacuse it will bring in TLB pressure.
> 
>  include/linux/mm.h |  8 ++++++++
>  mm/vmalloc.c       | 14 ++++++++++++++
>  2 files changed, 22 insertions(+)
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 6ad0ef6..1cc8156 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -509,6 +509,14 @@ static inline bool is_vmalloc_addr(const void *x)
>  	return false;
>  #endif
>  }
> +
> +static inline bool is_kernel_image_addr(const void *x)
> +{
> +	unsigned long addr = (unsigned long)x;
> +
> +	return addr >= (unsigned long)_stext && addr < (unsigned long)_end;
> +}
> +
>  #ifdef CONFIG_MMU
>  extern int is_vmalloc_or_module_addr(const void *x);
>  #else
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index 68eb002..19b9c6e 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -262,6 +262,11 @@ int is_vmalloc_or_module_addr(const void *x)
>  	return is_vmalloc_addr(x);
>  }
>  
> +static struct page *kernel_image_to_page(const void *addr)
> +{
> +	return virt_to_page(lm_alias(addr));
> +}
> +
>  /*
>   * Walk a vmap address to the struct page it maps.
>   */
> @@ -281,6 +286,15 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
>  	 */
>  	VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr));
>  
> +	/*
> +	 * kenrel image overlap with the vmalloc area in arm64, it will
> +	 * make the huge talbe page existence, if we walk the all page
> +	 * talbe, it may be result in the panic. Add the following code,
> +	 * it will keep consistent with previous behavior.
> +	 */
> +	if (is_kernel_image_addr(vmalloc_addr))
> +		return kernel_image_to_page(vmalloc_addr);
> +
>  	if (pgd_none(*pgd))
>  		return NULL;
>  	p4d = p4d_offset(pgd, addr);
>