On Sun, Nov 19, 2023 at 11:48 AM Kairui Song <ryncsn@xxxxxxxxx> wrote:
>
> From: Kairui Song <kasong@xxxxxxxxxxx>
>
> No feature change, just prepare for later commits.
You need to have a proper commit message why this change needs to happen.
Preparing is too generic, it does not give any real information.
For example, it seems you want to reduce one swap cache lookup because
swap_readahead already has it?
I am a bit puzzled at this patch. It shuffles a lot of sensitive code.
However I do not get the value.
It seems like this patch should be merged with the later patch that
depends on it to be judged together.
>
> Signed-off-by: Kairui Song <kasong@xxxxxxxxxxx>
> ---
> mm/memory.c | 61 +++++++++++++++++++++++--------------------------
> mm/swap.h | 10 ++++++--
> mm/swap_state.c | 26 +++++++++++++--------
> mm/swapfile.c | 30 +++++++++++-------------
> 4 files changed, 66 insertions(+), 61 deletions(-)
>
> diff --git a/mm/memory.c b/mm/memory.c
> index f4237a2e3b93..22af9f3e8c75 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -3786,13 +3786,13 @@ static vm_fault_t handle_pte_marker(struct vm_fault *vmf)
> vm_fault_t do_swap_page(struct vm_fault *vmf)
> {
> struct vm_area_struct *vma = vmf->vma;
> - struct folio *swapcache, *folio = NULL;
> + struct folio *swapcache = NULL, *folio = NULL;
> + enum swap_cache_result cache_result;
> struct page *page;
> struct swap_info_struct *si = NULL;
> rmap_t rmap_flags = RMAP_NONE;
> bool exclusive = false;
> swp_entry_t entry;
> - bool swapcached;
> pte_t pte;
> vm_fault_t ret = 0;
>
> @@ -3850,42 +3850,37 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
> if (unlikely(!si))
> goto out;
>
> - folio = swap_cache_get_folio(entry, vma, vmf->address);
> - if (folio)
> - page = folio_file_page(folio, swp_offset(entry));
> - swapcache = folio;
Is the motivation that swap_readahead() already has a swap cache look up so you
remove this look up here?
> -
> - if (!folio) {
> - page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
> - vmf, &swapcached);
> - if (page) {
> - folio = page_folio(page);
> - if (swapcached)
> - swapcache = folio;
> - } else {
> + page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
> + vmf, &cache_result);
> + if (page) {
> + folio = page_folio(page);
> + if (cache_result != SWAP_CACHE_HIT) {
> + /* Had to read the page from swap area: Major fault */
> + ret = VM_FAULT_MAJOR;
> + count_vm_event(PGMAJFAULT);
> + count_memcg_event_mm(vma->vm_mm, PGMAJFAULT);
> + }
> + if (cache_result != SWAP_CACHE_BYPASS)
> + swapcache = folio;
> + if (PageHWPoison(page)) {
There is a lot of code shuffle here. From the diff it is hard to tell
if they are doing the same thing as before.
> /*
> - * Back out if somebody else faulted in this pte
> - * while we released the pte lock.
> + * hwpoisoned dirty swapcache pages are kept for killing
> + * owner processes (which may be unknown at hwpoison time)
> */
> - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
> - vmf->address, &vmf->ptl);
> - if (likely(vmf->pte &&
> - pte_same(ptep_get(vmf->pte), vmf->orig_pte)))
> - ret = VM_FAULT_OOM;
> - goto unlock;
> + ret = VM_FAULT_HWPOISON;
> + goto out_release;
> }
> -
> - /* Had to read the page from swap area: Major fault */
> - ret = VM_FAULT_MAJOR;
> - count_vm_event(PGMAJFAULT);
> - count_memcg_event_mm(vma->vm_mm, PGMAJFAULT);
> - } else if (PageHWPoison(page)) {
> + } else {
> /*
> - * hwpoisoned dirty swapcache pages are kept for killing
> - * owner processes (which may be unknown at hwpoison time)
> + * Back out if somebody else faulted in this pte
> + * while we released the pte lock.
> */
> - ret = VM_FAULT_HWPOISON;
> - goto out_release;
> + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
> + vmf->address, &vmf->ptl);
> + if (likely(vmf->pte &&
> + pte_same(ptep_get(vmf->pte), vmf->orig_pte)))
> + ret = VM_FAULT_OOM;
> + goto unlock;
> }
>
> ret |= folio_lock_or_retry(folio, vmf);
> diff --git a/mm/swap.h b/mm/swap.h
> index a9a654af791e..ac9136eee690 100644
> --- a/mm/swap.h
> +++ b/mm/swap.h
> @@ -30,6 +30,12 @@ extern struct address_space *swapper_spaces[];
> (&swapper_spaces[swp_type(entry)][swp_offset(entry) \
> >> SWAP_ADDRESS_SPACE_SHIFT])
>
> +enum swap_cache_result {
> + SWAP_CACHE_HIT,
> + SWAP_CACHE_MISS,
> + SWAP_CACHE_BYPASS,
> +};
Does any function later care about CACHE_BYPASS?
Again, better introduce it with the function that uses it. Don't
introduce it for "just in case I might use it later".
> +
> void show_swap_cache_info(void);
> bool add_to_swap(struct folio *folio);
> void *get_shadow_from_swap_cache(swp_entry_t entry);
> @@ -55,7 +61,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
> struct page *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, bool *swapcached);
> + struct vm_fault *vmf, enum swap_cache_result *result);
>
> static inline unsigned int folio_swap_flags(struct folio *folio)
> {
> @@ -92,7 +98,7 @@ static inline struct page *swap_cluster_readahead(swp_entry_t entry,
> }
>
> static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
> - struct vm_fault *vmf, bool *swapcached)
> + struct vm_fault *vmf, enum swap_cache_result *result)
> {
> return NULL;
> }
> diff --git a/mm/swap_state.c b/mm/swap_state.c
> index d87c20f9f7ec..e96d63bf8a22 100644
> --- a/mm/swap_state.c
> +++ b/mm/swap_state.c
> @@ -908,8 +908,7 @@ static struct page *swapin_no_readahead(swp_entry_t entry, gfp_t gfp_mask,
> * @entry: swap entry of this memory
> * @gfp_mask: memory allocation flags
> * @vmf: fault information
> - * @swapcached: pointer to a bool used as indicator if the
> - * page is swapped in through swapcache.
> + * @result: a return value to indicate swap cache usage.
> *
> * Returns the struct page for entry and addr, after queueing swapin.
> *
> @@ -918,30 +917,39 @@ static struct page *swapin_no_readahead(swp_entry_t entry, gfp_t gfp_mask,
> * or vma-based(ie, virtual address based on faulty address) readahead.
> */
> struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
> - struct vm_fault *vmf, bool *swapcached)
> + struct vm_fault *vmf, enum swap_cache_result *result)
> {
> + enum swap_cache_result cache_result;
> struct swap_info_struct *si;
> struct mempolicy *mpol;
> + struct folio *folio;
> struct page *page;
> pgoff_t ilx;
> - bool cached;
> +
> + folio = swap_cache_get_folio(entry, vmf->vma, vmf->address);
> + if (folio) {
> + page = folio_file_page(folio, swp_offset(entry));
> + cache_result = SWAP_CACHE_HIT;
> + goto done;
> + }
>
> si = swp_swap_info(entry);
> mpol = get_vma_policy(vmf->vma, vmf->address, 0, &ilx);
> if (swap_use_no_readahead(si, swp_offset(entry))) {
> page = swapin_no_readahead(entry, gfp_mask, mpol, ilx, vmf->vma->vm_mm);
> - cached = false;
> + cache_result = SWAP_CACHE_BYPASS;
> } else if (swap_use_vma_readahead(si)) {
> page = swap_vma_readahead(entry, gfp_mask, mpol, ilx, vmf);
> - cached = true;
> + cache_result = SWAP_CACHE_MISS;
> } else {
> page = swap_cluster_readahead(entry, gfp_mask, mpol, ilx);
> - cached = true;
> + cache_result = SWAP_CACHE_MISS;
> }
> mpol_cond_put(mpol);
>
> - if (swapcached)
> - *swapcached = cached;
> +done:
> + if (result)
> + *result = cache_result;
>
> return page;
> }
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 01c3f53b6521..b6d57fff5e21 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -1822,13 +1822,21 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
>
> si = swap_info[type];
> do {
> - struct folio *folio;
> + struct page *page;
> unsigned long offset;
> unsigned char swp_count;
> + struct folio *folio = NULL;
> swp_entry_t entry;
> int ret;
> pte_t ptent;
>
> + struct vm_fault vmf = {
> + .vma = vma,
> + .address = addr,
> + .real_address = addr,
> + .pmd = pmd,
> + };
Is this code move caused by skipping the swap cache look up here?
This is very sensitive code related to swap cache racing. It needs
very careful reviewing. Better not shuffle it for no good reason.
Chris
> +
> if (!pte++) {
> pte = pte_offset_map(pmd, addr);
> if (!pte)
> @@ -1847,22 +1855,10 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
> offset = swp_offset(entry);
> pte_unmap(pte);
> pte = NULL;
> -
> - folio = swap_cache_get_folio(entry, vma, addr);
> - if (!folio) {
> - struct page *page;
> - struct vm_fault vmf = {
> - .vma = vma,
> - .address = addr,
> - .real_address = addr,
> - .pmd = pmd,
> - };
> -
> - page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
> - &vmf, NULL);
> - if (page)
> - folio = page_folio(page);
> - }
> + page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
> + &vmf, NULL);
> + if (page)
> + folio = page_folio(page);
> if (!folio) {
> /*
> * The entry could have been freed, and will not
> --
> 2.42.0
>
>
