Re: [PATCH v1 05/11] KVM: s390: pv: refactor s390_reset_acc

From: Janosch Frank <frankja@linux.ibm.com>
To: Claudio Imbrenda <imbrenda@linux.ibm.com>, kvm@vger.kernel.org
Cc: cohuck@redhat.com, borntraeger@de.ibm.com, thuth@redhat.com,
	pasic@linux.ibm.com, david@redhat.com,
	linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v1 05/11] KVM: s390: pv: refactor s390_reset_acc
Date: Wed, 26 May 2021 14:11:26 +0200	[thread overview]
Message-ID: <fb23fc95-50ed-284c-041a-c21f1753c101@linux.ibm.com> (raw)
In-Reply-To: <20210517200758.22593-6-imbrenda@linux.ibm.com>

On 5/17/21 10:07 PM, Claudio Imbrenda wrote:
> Refactor s390_reset_acc so that its pieces can be reused in upcoming
> patches. The users parameter for s390_destroy_range will be needed in
> upcoming patches.
> 
> We don't want to hold all the locks used in a walk_page_range for too
> long, and the destroy page UVC does take some time to complete.
> Therefore we quickly gather the pages to destroy, and then destroy them
> without holding all the locks.
> 

Acked-by: Janosch Frank <frankja@linux.ibm.com>

> Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
> ---
>  arch/s390/include/asm/gmap.h |  5 +-
>  arch/s390/kvm/pv.c           | 12 ++++-
>  arch/s390/mm/gmap.c          | 88 ++++++++++++++++++++++++------------
>  3 files changed, 73 insertions(+), 32 deletions(-)
> 
> diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
> index 40264f60b0da..618ddc455867 100644
> --- a/arch/s390/include/asm/gmap.h
> +++ b/arch/s390/include/asm/gmap.h
> @@ -147,5 +147,8 @@ int gmap_mprotect_notify(struct gmap *, unsigned long start,
>  void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
>  			     unsigned long gaddr, unsigned long vmaddr);
>  int gmap_mark_unmergeable(void);
> -void s390_reset_acc(struct mm_struct *mm);
> +void s390_uv_destroy_range(struct mm_struct *mm, unsigned int users,
> +			   unsigned long start, unsigned long end);
> +void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns);
> +
>  #endif /* _ASM_S390_GMAP_H */
> diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
> index e0532ab725bf..c3f9f30d2ed4 100644
> --- a/arch/s390/kvm/pv.c
> +++ b/arch/s390/kvm/pv.c
> @@ -12,6 +12,8 @@
>  #include <asm/gmap.h>
>  #include <asm/uv.h>
>  #include <asm/mman.h>
> +#include <linux/pagewalk.h>
> +#include <linux/sched/mm.h>
>  #include "kvm-s390.h"
>  
>  int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
> @@ -204,8 +206,14 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
>  {
>  	int cc;
>  
> -	/* make all pages accessible before destroying the guest */
> -	s390_reset_acc(kvm->mm);
> +	/*
> +	 * if the mm still has a mapping, make all its pages accessible
> +	 * before destroying the guest
> +	 */
> +	if (mmget_not_zero(kvm->mm)) {
> +		s390_uv_destroy_range(kvm->mm, 0, 0, TASK_SIZE);
> +		mmput(kvm->mm);
> +	}
>  
>  	cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm),
>  			   UVC_CMD_DESTROY_SEC_CONF, rc, rrc);
> diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
> index de679facc720..ad210a6e2c41 100644
> --- a/arch/s390/mm/gmap.c
> +++ b/arch/s390/mm/gmap.c
> @@ -2670,41 +2670,71 @@ void s390_reset_cmma(struct mm_struct *mm)
>  }
>  EXPORT_SYMBOL_GPL(s390_reset_cmma);
>  
> -/*
> - * make inaccessible pages accessible again
> - */
> -static int __s390_reset_acc(pte_t *ptep, unsigned long addr,
> -			    unsigned long next, struct mm_walk *walk)
> +#define DESTROY_LOOP_THRESHOLD 32
> +
> +struct reset_walk_state {
> +	unsigned long next;
> +	unsigned long count;
> +	unsigned long pfns[DESTROY_LOOP_THRESHOLD];

Candidate for a module parameter and extensive performance testing?

> +};
> +
> +static int s390_gather_pages(pte_t *ptep, unsigned long addr,
> +			     unsigned long next, struct mm_walk *walk)

A "pv" somewhere in that function name would be helpful to me.
Also the "__" prefix applies here I think. We never call the function
directly and it's static. And I assume that's what the "__" prefix is
trying to tell us. :)

>  {
> +	struct reset_walk_state *p = walk->private;
>  	pte_t pte = READ_ONCE(*ptep);
>  
> -	/* There is a reference through the mapping */
> -	if (pte_present(pte))
> -		WARN_ON_ONCE(uv_destroy_owned_page(pte_val(pte) & PAGE_MASK));
> -
> -	return 0;
> +	if (pte_present(pte)) {
> +		/* we have a reference from the mapping, take an extra one */
> +		get_page(phys_to_page(pte_val(pte)));
> +		p->pfns[p->count] = phys_to_pfn(pte_val(pte));
> +		p->next = next;
> +		p->count++;
> +	}
> +	return p->count >= DESTROY_LOOP_THRESHOLD;
>  }
>  
> -static const struct mm_walk_ops reset_acc_walk_ops = {
> -	.pte_entry		= __s390_reset_acc,
> +static const struct mm_walk_ops gather_pages_ops = {
> +	.pte_entry = s390_gather_pages,
>  };
>  
> -#include <linux/sched/mm.h>
> -void s390_reset_acc(struct mm_struct *mm)
> +/*
> + * Call the Destroy secure page UVC on each page in the given array of PFNs.
> + * Each page needs to have an extra reference, which will be released here.
> + */
> +void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns)
>  {
> -	if (!mm_is_protected(mm))
> -		return;
> -	/*
> -	 * we might be called during
> -	 * reset:                             we walk the pages and clear
> -	 * close of all kvm file descriptors: we walk the pages and clear
> -	 * exit of process on fd closure:     vma already gone, do nothing
> -	 */
> -	if (!mmget_not_zero(mm))
> -		return;
> -	mmap_read_lock(mm);
> -	walk_page_range(mm, 0, TASK_SIZE, &reset_acc_walk_ops, NULL);
> -	mmap_read_unlock(mm);
> -	mmput(mm);
> +	unsigned long i;
> +
> +	for (i = 0; i < count; i++) {
> +		/* we always have an extra reference */
> +		uv_destroy_owned_page(pfn_to_phys(pfns[i]));
> +		/* get rid of the extra reference */
> +		put_page(pfn_to_page(pfns[i]));
> +		cond_resched();
> +	}
> +}
> +EXPORT_SYMBOL_GPL(s390_uv_destroy_pfns);
> +
> +/*
> + * Walk the given range of the given address space, and call the destroy
> + * secure page UVC on each page.
> + * Exit early if the number of users of the mm drops to (or below) the given
> + * value.
> + */
> +void s390_uv_destroy_range(struct mm_struct *mm, unsigned int users,
> +			   unsigned long start, unsigned long end)
> +{
> +	struct reset_walk_state state = { .next = start };
> +	int r = 1;
> +
> +	while ((r > 0) && (atomic_read(&mm->mm_users) > users)) {
> +		state.count = 0;
> +		mmap_read_lock(mm);
> +		r = walk_page_range(mm, state.next, end, &gather_pages_ops, &state);
> +		mmap_read_unlock(mm);
> +		cond_resched();
> +		s390_uv_destroy_pfns(state.count, state.pfns);
> +	}
>  }
> -EXPORT_SYMBOL_GPL(s390_reset_acc);
> +EXPORT_SYMBOL_GPL(s390_uv_destroy_range);
> 