linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: Alexey Kardashevskiy <aik@ozlabs.ru>
Cc: Paul Mackerras <paulus@samba.org>,
	linuxppc-dev@lists.ozlabs.org,
	Gavin Shan <gwshan@linux.vnet.ibm.com>
Subject: Re: [PATCH v3 03/18] KVM: PPC: Account TCE pages in locked_vm
Date: Mon, 28 Jul 2014 10:43:52 +1000	[thread overview]
Message-ID: <1406508232.4935.23.camel@pasglop> (raw)
In-Reply-To: <1406191691-31441-4-git-send-email-aik@ozlabs.ru>

On Thu, 2014-07-24 at 18:47 +1000, Alexey Kardashevskiy wrote:
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> ---

You need a description.

>  arch/powerpc/kvm/book3s_64_vio.c | 35 ++++++++++++++++++++++++++++++++++-
>  1 file changed, 34 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
> index 516f2ee..48b7ed4 100644
> --- a/arch/powerpc/kvm/book3s_64_vio.c
> +++ b/arch/powerpc/kvm/book3s_64_vio.c
> @@ -45,18 +45,48 @@ static long kvmppc_stt_npages(unsigned long window_size)
>  		     * sizeof(u64), PAGE_SIZE) / PAGE_SIZE;
>  }
>  
> +/*
> + * Checks ulimit in order not to let the user space to pin all
> + * available memory for TCE tables.
> + */
> +static long kvmppc_account_memlimit(long npages)
> +{
> +	unsigned long ret = 0, locked, lock_limit;
> +
> +	if (!current->mm)
> +		return -ESRCH; /* process exited */
> +
> +	down_write(&current->mm->mmap_sem);
> +	locked = current->mm->locked_vm + npages;
> +	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
> +	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
> +		pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n",
> +				rlimit(RLIMIT_MEMLOCK));
> +		ret = -ENOMEM;
> +	} else {
> +		current->mm->locked_vm += npages;
> +	}
> +	up_write(&current->mm->mmap_sem);
> +
> +	return ret;
> +}
> +
>  static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt)
>  {
>  	struct kvm *kvm = stt->kvm;
>  	int i;
> +	long npages = kvmppc_stt_npages(stt->window_size);
>  
>  	mutex_lock(&kvm->lock);
>  	list_del(&stt->list);
> -	for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
> +	for (i = 0; i < npages; i++)
>  		__free_page(stt->pages[i]);
> +
>  	kfree(stt);
>  	mutex_unlock(&kvm->lock);
>  
> +	kvmppc_account_memlimit(-(npages + 1));
> +
>  	kvm_put_kvm(kvm);
>  }
>  
> @@ -112,6 +142,9 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>  	}
>  
>  	npages = kvmppc_stt_npages(args->window_size);
> +	ret = kvmppc_account_memlimit(npages + 1);
> +	if (ret)
> +		goto fail;

This is called for VFIO only or is it also called when creating TCE
tables for emulated devices ? Because in the latter case, you don't
want to account the pages as locked, do you ?

Also, you need to explain what +1

Finally, do I correctly deduce that creating 10 TCE tables of 2G
each will end up accounting 20G as locked even if the guest for
example only has 4G of RAM ? 

>  	stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *),
>  		      GFP_KERNEL);

Ben.

  reply	other threads:[~2014-07-28  0:44 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-24  8:47 [PATCH v3 00/18] powernv: vfio: Add Dynamic DMA windows (DDW) Alexey Kardashevskiy
2014-07-24  8:47 ` [PATCH v3 01/18] powerpc/iommu: Fix comments with it_page_shift Alexey Kardashevskiy
2014-07-24  8:47 ` [PATCH v3 02/18] KVM: PPC: Use RCU when adding to arch.spapr_tce_tables Alexey Kardashevskiy
2014-07-28  0:40   ` Benjamin Herrenschmidt
2014-07-28  4:11     ` Alexey Kardashevskiy
2014-07-28  4:30       ` Benjamin Herrenschmidt
2014-07-24  8:47 ` [PATCH v3 03/18] KVM: PPC: Account TCE pages in locked_vm Alexey Kardashevskiy
2014-07-28  0:43   ` Benjamin Herrenschmidt [this message]
2014-07-28  4:23     ` Alexey Kardashevskiy
2014-07-28  4:34       ` Benjamin Herrenschmidt
2014-07-24  8:47 ` [PATCH v3 04/18] vfio: powerpc: Move locked_vm accounting to a helper Alexey Kardashevskiy
2014-07-28  0:46   ` Benjamin Herrenschmidt
2014-07-28  9:12     ` Alexey Kardashevskiy
2014-07-24  8:47 ` [PATCH v3 05/18] powerpc/powernv: Use it_page_shift for TCE invalidation Alexey Kardashevskiy
2014-07-24  8:47 ` [PATCH v3 06/18] powerpc/powernv: Use it_page_shift in TCE build Alexey Kardashevskiy
2014-07-24  8:48 ` [PATCH v3 07/18] powerpc/powernv: Add a page size parameter to pnv_pci_setup_iommu_table() Alexey Kardashevskiy
2014-07-24  8:48 ` [PATCH v3 08/18] powerpc/powernv: Make invalidate() a callback Alexey Kardashevskiy
2014-07-24  8:48 ` [PATCH v3 09/18] powerpc/spapr: vfio: Implement spapr_tce_iommu_ops Alexey Kardashevskiy
2014-07-24  8:48 ` [PATCH v3 10/18] powerpc/powernv: Convert/move set_bypass() callback to take_ownership() Alexey Kardashevskiy
2014-07-28  1:18   ` Benjamin Herrenschmidt
2014-07-28  3:55     ` Alexey Kardashevskiy
2014-07-28  4:19       ` Benjamin Herrenschmidt
2014-07-24  8:48 ` [PATCH v3 11/18] powerpc/iommu: Fix IOMMU ownership control functions Alexey Kardashevskiy
2014-07-24  8:48 ` [PATCH v3 12/18] powerpc/iommu: Fix missing permission bits in iommu_put_tce_user_mode() Alexey Kardashevskiy
2014-07-28  1:19   ` Benjamin Herrenschmidt
2014-07-28  4:32     ` Alexey Kardashevskiy
2014-07-28  4:35       ` Benjamin Herrenschmidt
2014-07-24  8:48 ` [PATCH v3 13/18] powerpc/iommu: Extend ppc_md.tce_build(_rm) to return old TCE values Alexey Kardashevskiy
2014-07-28  1:09   ` Benjamin Herrenschmidt
2014-07-28  1:16   ` Benjamin Herrenschmidt
2014-07-24  8:48 ` [PATCH v3 14/18] powerpc/powernv: Return non-zero TCE from pnv_tce_build Alexey Kardashevskiy
2014-07-24  8:48 ` [PATCH v3 15/18] powerpc/iommu: Implement put_page() if TCE had non-zero value Alexey Kardashevskiy
2014-07-24  8:48 ` [PATCH v3 16/18] powerpc/powernv: Implement Dynamic DMA windows (DDW) for IODA Alexey Kardashevskiy
2014-07-24  8:48 ` [PATCH v3 17/18] vfio: Use it_page_size Alexey Kardashevskiy
2014-07-24  8:48 ` [PATCH v3 18/18] vfio: powerpc: Enable Dynamic DMA windows Alexey Kardashevskiy

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=1406508232.4935.23.camel@pasglop \
    --to=benh@kernel.crashing.org \
    --cc=aik@ozlabs.ru \
    --cc=gwshan@linux.vnet.ibm.com \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=paulus@samba.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).