linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: linux@arm.linux.org.uk (Russell King - ARM Linux)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH 20/19] ARM: LPAE: Invalidate the TLB before freeing the PMD
Date: Wed, 11 May 2011 11:54:19 +0100	[thread overview]
Message-ID: <20110511105419.GD5315@n2100.arm.linux.org.uk> (raw)
In-Reply-To: <1305109399-13156-1-git-send-email-catalin.marinas@arm.com>

On Wed, May 11, 2011 at 11:23:19AM +0100, Catalin Marinas wrote:
> +static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
> +				  unsigned long addr)
> +{
> +#ifdef CONFIG_ARM_LPAE
> +	tlb_add_flush(tlb, addr);
> +	tlb_flush(tlb);
> +	pmd_free((tlb)->mm, pmdp);
> +#endif
> +}

You're:

1. tlb_add_flush() - Adding the address which covers the PMD to the range
   of virtual addresses which need flushing - ok.
2. tlb_flush() - You're then forcing a flush.
3. pmd_free() - You're now freeing the page.

One of the points about the shootdown interface is that it batches things
up.  So what's wrong with:

static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
	unsigned long addr)
{
#ifdef CONFIG_ARM_LPAE
	tlb_add_flush(tlb, addr);
	tlb_remove_page(tlb, virt_to_page(pmdp));
#endif
}

and leave the tlb invalidate and actual page freeing to the batching code
to deal with?

  parent reply	other threads:[~2011-05-11 10:54 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-05-08 12:51 [PATCH v5 00/19] ARM: Add support for the Large Physical Address Extensions Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 01/19] ARM: LPAE: Use long long printk format for displaying the pud Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 02/19] ARM: LPAE: add ISBs around MMU enabling code Catalin Marinas
2011-05-08 21:41   ` Russell King - ARM Linux
2011-05-09 10:22     ` Catalin Marinas
2011-05-09 10:32       ` Russell King - ARM Linux
2011-05-09 10:59         ` Catalin Marinas
2011-05-09 12:05           ` Russell King - ARM Linux
2011-05-09 13:36             ` Catalin Marinas
2011-05-09 15:01             ` Catalin Marinas
2011-05-09 15:34               ` Russell King - ARM Linux
2011-05-09 15:38                 ` Catalin Marinas
2011-05-09 15:48                 ` Russell King - ARM Linux
2011-05-09 16:02                   ` Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 03/19] ARM: LPAE: Use unsigned long for __phys_to_virt and __virt_to_phys Catalin Marinas
2011-05-08 21:44   ` Russell King - ARM Linux
2011-05-16 17:28     ` Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 04/19] ARM: LPAE: Make TTBR1 always point to swapper_pg_dir on ARMv7 Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 05/19] ARM: LPAE: Use PMD_(SHIFT|SIZE|MASK) instead of PGDIR_* Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 06/19] ARM: LPAE: Factor out 2-level page table definitions into separate files Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 07/19] ARM: LPAE: Add (pte|pmd|pgd|pgprot)val_t type definitions as u32 Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 08/19] ARM: LPAE: Use a mask for physical addresses in page table entries Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 09/19] ARM: LPAE: Introduce the 3-level page table format definitions Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 10/19] ARM: LPAE: Page table maintenance for the 3-level format Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 11/19] ARM: LPAE: MMU setup for the 3-level page table format Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 12/19] ARM: LPAE: Add fault handling support Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 13/19] ARM: LPAE: Add context switching support Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 14/19] ARM: LPAE: Add identity mapping support for the 3-level page table format Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 15/19] ARM: LPAE: Add support for cpu_v7_do_(suspend|resume) Catalin Marinas
2011-05-18  7:27   ` Tony Lindgren
2011-05-20 13:21     ` Catalin Marinas
2011-05-20 15:17       ` Jean-Christophe PLAGNIOL-VILLARD
2011-05-20 18:09       ` Nicolas Pitre
2011-05-22 21:09         ` Catalin Marinas
2011-05-24  6:26           ` Tony Lindgren
2011-05-08 12:51 ` [PATCH v5 16/19] ARM: LPAE: Use generic dma_addr_t type definition Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 17/19] ARM: LPAE: mark memory banks with start > ULONG_MAX as highmem Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 18/19] ARM: LPAE: add support for ATAG_MEM64 Catalin Marinas
2011-05-08 12:51 ` [PATCH v5 19/19] ARM: LPAE: Add the Kconfig entries Catalin Marinas
2011-05-11 10:23 ` [PATCH 20/19] ARM: LPAE: Invalidate the TLB before freeing the PMD Catalin Marinas
2011-05-11 10:31   ` Sergei Shtylyov
2011-05-11 10:40     ` Catalin Marinas
2011-05-11 10:54   ` Russell King - ARM Linux [this message]
2011-05-11 13:40     ` Catalin Marinas
2011-05-11 14:00       ` Russell King - ARM Linux
2011-05-11 15:58         ` Catalin Marinas
2011-05-23 16:54 ` [PATCH v5 00/19] ARM: Add support for the Large Physical Address Extensions Russell King - ARM Linux
2011-05-23 17:22   ` Catalin Marinas
2011-05-24 10:04   ` Catalin Marinas
2011-05-26 21:15     ` Catalin Marinas
2011-05-26 21:44       ` Russell King - ARM Linux
2011-05-27  9:09         ` Catalin Marinas

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=20110511105419.GD5315@n2100.arm.linux.org.uk \
    --to=linux@arm.linux.org.uk \
    --cc=linux-arm-kernel@lists.infradead.org \
    /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;
as well as URLs for NNTP newsgroup(s).