Linux MIPS Architecture development
 help / color / mirror / Atom feed
From: Joshua Kinard <kumba@gentoo.org>
To: Huacai Chen <chenhc@lemote.com>, Ralf Baechle <ralf@linux-mips.org>
Cc: Aurelien Jarno <aurelien@aurel32.net>,
	"Steven J. Hill" <Steven.Hill@imgtec.com>,
	linux-mips@linux-mips.org, Fuxin Zhang <zhangfx@lemote.com>,
	Zhangjin Wu <wuzhangjin@gmail.com>
Subject: Re: [PATCH 4/6] MIPS: tlbex: Fix bugs in tlbchange handler
Date: Wed, 27 Jan 2016 00:50:50 -0500	[thread overview]
Message-ID: <56A85ABA.7000903@gentoo.org> (raw)
In-Reply-To: <1453814784-14230-5-git-send-email-chenhc@lemote.com>

On 01/26/2016 08:26, Huacai Chen wrote:
> If a tlb miss triggered when EXL=1, tlb refill exception is treated as
> tlb invalid exception, so tlbp may fails. In this situation, CP0_Index
> register doesn't contain a valid value. This may not be a problem for
> VTLB since it is fully-associative. However, FTLB is set-associative so
> not every tlb entry is valid for a specific address. Thus, we should
> use tlbwr instead of tlbwi when tlbp fails.
> 
> There is a similar case for huge page, so build_huge_tlb_write_entry()
> is also modified. If wmode != tlb_random, that means the caller is tlb
> invalid handler, we should select tlbr/tlbi depend on the tlbp result.

This patch triggered instruction bus errors on my Octane (R14000) once it
switched to userland, using PAGE_SIZE_64KB, MAX_ORDER=14, and THP.  Without the
patch, that same configuration boots fine, so I suspect this change isn't
appropriate for all systems.

--J


> Signed-off-by: Huacai Chen <chenhc@lemote.com>
> ---
>  arch/mips/mm/tlbex.c | 31 ++++++++++++++++++++++++++++++-
>  1 file changed, 30 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
> index d0975cd..da68ffb 100644
> --- a/arch/mips/mm/tlbex.c
> +++ b/arch/mips/mm/tlbex.c
> @@ -173,7 +173,10 @@ enum label_id {
>  	label_large_segbits_fault,
>  #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
>  	label_tlb_huge_update,
> +	label_tail_huge_miss,
> +	label_tail_huge_done,
>  #endif
> +	label_tail_miss,
>  };
>  
>  UASM_L_LA(_second_part)
> @@ -192,7 +195,10 @@ UASM_L_LA(_r3000_write_probe_fail)
>  UASM_L_LA(_large_segbits_fault)
>  #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
>  UASM_L_LA(_tlb_huge_update)
> +UASM_L_LA(_tail_huge_miss)
> +UASM_L_LA(_tail_huge_done)
>  #endif
> +UASM_L_LA(_tail_miss)
>  
>  static int hazard_instance;
>  
> @@ -706,8 +712,24 @@ static void build_huge_tlb_write_entry(u32 **p, struct uasm_label **l,
>  	uasm_i_ori(p, tmp, tmp, PM_HUGE_MASK & 0xffff);
>  	uasm_i_mtc0(p, tmp, C0_PAGEMASK);
>  
> -	build_tlb_write_entry(p, l, r, wmode);
> +	if (wmode == tlb_random) { /* Caller is TLB Refill Handler */
> +		build_tlb_write_entry(p, l, r, wmode);
> +		build_restore_pagemask(p, r, tmp, label_leave, restore_scratch);
> +		return;
> +	}
> +
> +	/* Caller is TLB Load/Store/Modify Handler */
> +	uasm_i_mfc0(p, tmp, C0_INDEX);
> +	uasm_il_bltz(p, r, tmp, label_tail_huge_miss);
> +	uasm_i_nop(p);
> +	build_tlb_write_entry(p, l, r, tlb_indexed);
> +	uasm_il_b(p, r, label_tail_huge_done);
> +	uasm_i_nop(p);
> +
> +	uasm_l_tail_huge_miss(l, *p);
> +	build_tlb_write_entry(p, l, r, tlb_random);
>  
> +	uasm_l_tail_huge_done(l, *p);
>  	build_restore_pagemask(p, r, tmp, label_leave, restore_scratch);
>  }
>  
> @@ -2026,7 +2048,14 @@ build_r4000_tlbchange_handler_tail(u32 **p, struct uasm_label **l,
>  	uasm_i_ori(p, ptr, ptr, sizeof(pte_t));
>  	uasm_i_xori(p, ptr, ptr, sizeof(pte_t));
>  	build_update_entries(p, tmp, ptr);
> +	uasm_i_mfc0(p, ptr, C0_INDEX);
> +	uasm_il_bltz(p, r, ptr, label_tail_miss);
> +	uasm_i_nop(p);
>  	build_tlb_write_entry(p, l, r, tlb_indexed);
> +	uasm_il_b(p, r, label_leave);
> +	uasm_i_nop(p);
> +	uasm_l_tail_miss(l, *p);
> +	build_tlb_write_entry(p, l, r, tlb_random);
>  	uasm_l_leave(l, *p);
>  	build_restore_work_registers(p);
>  	uasm_i_eret(p); /* return from trap */
> 

  parent reply	other threads:[~2016-01-27  5:51 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-01-26 13:26 [PATCH 0/6] MIPS: Loongson: Add Loongson-3A R2 support Huacai Chen
2016-01-26 13:26 ` [PATCH 1/6] MIPS: Loongson: Add Loongson-3A R2 basic support Huacai Chen
2016-01-26 13:26 ` [PATCH 2/6] MIPS: Loongson: Invalidate special TLBs when needed Huacai Chen
2016-01-26 13:26 ` [PATCH 3/6] MIPS: Loongson-3: Fast TLB refill handler Huacai Chen
2016-01-26 13:26 ` [PATCH 4/6] MIPS: tlbex: Fix bugs in tlbchange handler Huacai Chen
2016-01-26 21:15   ` David Daney
2016-01-27  4:53     ` Huacai Chen
2016-01-27  5:50   ` Joshua Kinard [this message]
2016-01-27 10:22     ` Joshua Kinard
2016-01-26 13:26 ` [PATCH 5/6] MIPS: Loongson: Introduce and use cpu_has_coherent_cache feature Huacai Chen
2016-01-26 13:42   ` James Hogan
2016-01-26 13:42     ` James Hogan
2016-01-27  4:58     ` Huacai Chen
2016-01-27 11:15       ` James Hogan
2016-01-28  7:38         ` Huacai Chen
2016-01-26 13:26 ` [PATCH 6/6] MIPS: Loongson-3: Introduce CONFIG_LOONGSON3_ENHANCEMENT Huacai Chen
2016-01-26 14:19   ` James Hogan
2016-01-26 14:19     ` James Hogan
2016-01-27  5:02     ` Huacai Chen
2016-01-27 11:18       ` James Hogan
2016-01-28  7:48         ` Huacai Chen

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=56A85ABA.7000903@gentoo.org \
    --to=kumba@gentoo.org \
    --cc=Steven.Hill@imgtec.com \
    --cc=aurelien@aurel32.net \
    --cc=chenhc@lemote.com \
    --cc=linux-mips@linux-mips.org \
    --cc=ralf@linux-mips.org \
    --cc=wuzhangjin@gmail.com \
    --cc=zhangfx@lemote.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox