diff mbox series

[v3,2/7] mm/swap: move no readahead swapin code to a stand-alone helper

Message ID 20240129175423.1987-3-ryncsn@gmail.com (mailing list archive)
State New
Headers show
Series swapin refactor for optimization and unified readahead | expand

Commit Message

Kairui Song Jan. 29, 2024, 5:54 p.m. UTC 
From: Kairui Song <kasong@tencent.com>

No feature change, simply move the routine to a standalone function to
be re-used later. The error path handling is copied from the "out_page"
label, to make the code change minimized for easier reviewing.

Signed-off-by: Kairui Song <kasong@tencent.com>
---
 mm/memory.c     | 32 ++++----------------------------
 mm/swap.h       |  8 ++++++++
 mm/swap_state.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 59 insertions(+), 28 deletions(-)

Comments

Huang, Ying Jan. 30, 2024, 5:38 a.m. UTC | #1 
Kairui Song <ryncsn@gmail.com> writes:

> From: Kairui Song <kasong@tencent.com>
>
> No feature change, simply move the routine to a standalone function to
> be re-used later. The error path handling is copied from the "out_page"
> label, to make the code change minimized for easier reviewing.

The error processing for mem_cgroup_swapin_charge_folio() failure is
changed a little.  That looks OK for me.  But you need to make it
explicit in change log.  Especially, it's not "no feature change"
strictly.

--
Best Regards,
Huang, Ying

> Signed-off-by: Kairui Song <kasong@tencent.com>
> ---
>  mm/memory.c     | 32 ++++----------------------------
>  mm/swap.h       |  8 ++++++++
>  mm/swap_state.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++
>  3 files changed, 59 insertions(+), 28 deletions(-)
>
> diff --git a/mm/memory.c b/mm/memory.c
> index 7e1f4849463a..81dc9d467f4e 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -3803,7 +3803,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
>  	swp_entry_t entry;
>  	pte_t pte;
>  	vm_fault_t ret = 0;
> -	void *shadow = NULL;
>  
>  	if (!pte_unmap_same(vmf))
>  		goto out;
> @@ -3867,33 +3866,10 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
>  	if (!folio) {
>  		if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
>  		    __swap_count(entry) == 1) {
> -			/* skip swapcache */
> -			folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0,
> -						vma, vmf->address, false);
> -			page = &folio->page;
> -			if (folio) {
> -				__folio_set_locked(folio);
> -				__folio_set_swapbacked(folio);
> -
> -				if (mem_cgroup_swapin_charge_folio(folio,
> -							vma->vm_mm, GFP_KERNEL,
> -							entry)) {
> -					ret = VM_FAULT_OOM;
> -					goto out_page;
> -				}
> -				mem_cgroup_swapin_uncharge_swap(entry);
> -
> -				shadow = get_shadow_from_swap_cache(entry);
> -				if (shadow)
> -					workingset_refault(folio, shadow);
> -
> -				folio_add_lru(folio);
> -
> -				/* To provide entry to swap_read_folio() */
> -				folio->swap = entry;
> -				swap_read_folio(folio, true, NULL);
> -				folio->private = NULL;
> -			}
> +			/* skip swapcache and readahead */
> +			folio = swapin_direct(entry, GFP_HIGHUSER_MOVABLE, vmf);
> +			if (folio)
> +				page = &folio->page;
>  		} else {
>  			page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
>  						vmf);
> diff --git a/mm/swap.h b/mm/swap.h
> index 758c46ca671e..83eab7b67e77 100644
> --- a/mm/swap.h
> +++ b/mm/swap.h
> @@ -56,6 +56,8 @@ struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
>  		struct mempolicy *mpol, pgoff_t ilx);
>  struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
>  			      struct vm_fault *vmf);
> +struct folio *swapin_direct(swp_entry_t entry, gfp_t flag,
> +			    struct vm_fault *vmf);
>  
>  static inline unsigned int folio_swap_flags(struct folio *folio)
>  {
> @@ -86,6 +88,12 @@ static inline struct folio *swap_cluster_readahead(swp_entry_t entry,
>  	return NULL;
>  }
>  
> +struct folio *swapin_direct(swp_entry_t entry, gfp_t flag,
> +			struct vm_fault *vmf)
> +{
> +	return NULL;
> +}
> +
>  static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
>  			struct vm_fault *vmf)
>  {
> diff --git a/mm/swap_state.c b/mm/swap_state.c
> index e671266ad772..645f5bcad123 100644
> --- a/mm/swap_state.c
> +++ b/mm/swap_state.c
> @@ -861,6 +861,53 @@ static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
>  	return folio;
>  }
>  
> +/**
> + * swapin_direct - swap in a folio skipping swap cache and readahead
> + * @entry: swap entry of this memory
> + * @gfp_mask: memory allocation flags
> + * @vmf: fault information
> + *
> + * Returns the struct folio for entry and addr after the swap entry is read
> + * in.
> + */
> +struct folio *swapin_direct(swp_entry_t entry, gfp_t gfp_mask,
> +			    struct vm_fault *vmf)
> +{
> +	struct vm_area_struct *vma = vmf->vma;
> +	struct folio *folio;
> +	void *shadow = NULL;
> +
> +	/* skip swapcache */
> +	folio = vma_alloc_folio(gfp_mask, 0,
> +				vma, vmf->address, false);
> +	if (folio) {
> +		__folio_set_locked(folio);
> +		__folio_set_swapbacked(folio);
> +
> +		if (mem_cgroup_swapin_charge_folio(folio,
> +					vma->vm_mm, GFP_KERNEL,
> +					entry)) {
> +			folio_unlock(folio);
> +			folio_put(folio);
> +			return NULL;
> +		}
> +		mem_cgroup_swapin_uncharge_swap(entry);
> +
> +		shadow = get_shadow_from_swap_cache(entry);
> +		if (shadow)
> +			workingset_refault(folio, shadow);
> +
> +		folio_add_lru(folio);
> +
> +		/* To provide entry to swap_read_folio() */
> +		folio->swap = entry;
> +		swap_read_folio(folio, true, NULL);
> +		folio->private = NULL;
> +	}
> +
> +	return folio;
> +}
> +
>  /**
>   * swapin_readahead - swap in pages in hope we need them soon
>   * @entry: swap entry of this memory
Kairui Song Jan. 30, 2024, 5:55 a.m. UTC | #2 
On Tue, Jan 30, 2024 at 1:40 PM Huang, Ying <ying.huang@intel.com> wrote:
>
> Kairui Song <ryncsn@gmail.com> writes:
>
> > From: Kairui Song <kasong@tencent.com>
> >
> > No feature change, simply move the routine to a standalone function to
> > be re-used later. The error path handling is copied from the "out_page"
> > label, to make the code change minimized for easier reviewing.
>
> The error processing for mem_cgroup_swapin_charge_folio() failure is
> changed a little.  That looks OK for me.  But you need to make it
> explicit in change log.  Especially, it's not "no feature change"
> strictly.

Yes, you are correct, I thought it was hardly observable for users, so
ignored that, let me fix the commit message then. Thanks for the
suggestion.

>
> --
> Best Regards,
> Huang, Ying
diff mbox series

Patch

diff --git a/mm/memory.c b/mm/memory.c
index 7e1f4849463a..81dc9d467f4e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3803,7 +3803,6 @@  vm_fault_t do_swap_page(struct vm_fault *vmf)
 	swp_entry_t entry;
 	pte_t pte;
 	vm_fault_t ret = 0;
-	void *shadow = NULL;
 
 	if (!pte_unmap_same(vmf))
 		goto out;
@@ -3867,33 +3866,10 @@  vm_fault_t do_swap_page(struct vm_fault *vmf)
 	if (!folio) {
 		if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
 		    __swap_count(entry) == 1) {
-			/* skip swapcache */
-			folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0,
-						vma, vmf->address, false);
-			page = &folio->page;
-			if (folio) {
-				__folio_set_locked(folio);
-				__folio_set_swapbacked(folio);
-
-				if (mem_cgroup_swapin_charge_folio(folio,
-							vma->vm_mm, GFP_KERNEL,
-							entry)) {
-					ret = VM_FAULT_OOM;
-					goto out_page;
-				}
-				mem_cgroup_swapin_uncharge_swap(entry);
-
-				shadow = get_shadow_from_swap_cache(entry);
-				if (shadow)
-					workingset_refault(folio, shadow);
-
-				folio_add_lru(folio);
-
-				/* To provide entry to swap_read_folio() */
-				folio->swap = entry;
-				swap_read_folio(folio, true, NULL);
-				folio->private = NULL;
-			}
+			/* skip swapcache and readahead */
+			folio = swapin_direct(entry, GFP_HIGHUSER_MOVABLE, vmf);
+			if (folio)
+				page = &folio->page;
 		} else {
 			page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
 						vmf);
diff --git a/mm/swap.h b/mm/swap.h
index 758c46ca671e..83eab7b67e77 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -56,6 +56,8 @@  struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
 		struct mempolicy *mpol, pgoff_t ilx);
 struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
 			      struct vm_fault *vmf);
+struct folio *swapin_direct(swp_entry_t entry, gfp_t flag,
+			    struct vm_fault *vmf);
 
 static inline unsigned int folio_swap_flags(struct folio *folio)
 {
@@ -86,6 +88,12 @@  static inline struct folio *swap_cluster_readahead(swp_entry_t entry,
 	return NULL;
 }
 
+struct folio *swapin_direct(swp_entry_t entry, gfp_t flag,
+			struct vm_fault *vmf)
+{
+	return NULL;
+}
+
 static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
 			struct vm_fault *vmf)
 {
diff --git a/mm/swap_state.c b/mm/swap_state.c
index e671266ad772..645f5bcad123 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -861,6 +861,53 @@  static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 	return folio;
 }
 
+/**
+ * swapin_direct - swap in a folio skipping swap cache and readahead
+ * @entry: swap entry of this memory
+ * @gfp_mask: memory allocation flags
+ * @vmf: fault information
+ *
+ * Returns the struct folio for entry and addr after the swap entry is read
+ * in.
+ */
+struct folio *swapin_direct(swp_entry_t entry, gfp_t gfp_mask,
+			    struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct folio *folio;
+	void *shadow = NULL;
+
+	/* skip swapcache */
+	folio = vma_alloc_folio(gfp_mask, 0,
+				vma, vmf->address, false);
+	if (folio) {
+		__folio_set_locked(folio);
+		__folio_set_swapbacked(folio);
+
+		if (mem_cgroup_swapin_charge_folio(folio,
+					vma->vm_mm, GFP_KERNEL,
+					entry)) {
+			folio_unlock(folio);
+			folio_put(folio);
+			return NULL;
+		}
+		mem_cgroup_swapin_uncharge_swap(entry);
+
+		shadow = get_shadow_from_swap_cache(entry);
+		if (shadow)
+			workingset_refault(folio, shadow);
+
+		folio_add_lru(folio);
+
+		/* To provide entry to swap_read_folio() */
+		folio->swap = entry;
+		swap_read_folio(folio, true, NULL);
+		folio->private = NULL;
+	}
+
+	return folio;
+}
+
 /**
  * swapin_readahead - swap in pages in hope we need them soon
  * @entry: swap entry of this memory