The dcssblk driver has long needed special case supoprt to enable limited dax operation, so called CONFIG_FS_DAX_LIMITED. This mode works around the incomplete support for ZONE_DEVICE on s390 by forgoing the ability of dax-mapped pages to support GUP. Now, pending cleanups to fsdax that fix its reference counting [1] depend on the ability of all dax drivers to supply ZONE_DEVICE pages. To allow that work to move forward, dax support needs to be paused for dcssblk until ZONE_DEVICE support arrives. That work has been known for a few years [2], and the removal of "pte_devmap" requirements [3] makes the conversion easier. For now, place the support behind CONFIG_BROKEN, and remove PFN_SPECIAL (dcssblk was the only user). Link: http://lore.kernel.org/cover.9f0e45d52f5cff58807831b6b867084d0b14b61c.1725941415.git-series.apopple@xxxxxxxxxx [1] Link: http://lore.kernel.org/20210820210318.187742e8@thinkpad/ [2] Link: http://lore.kernel.org/4511465a4f8429f45e2ac70d2e65dc5e1df1eb47.1725941415.git-series.apopple@xxxxxxxxxx [3] Cc: Gerald Schaefer <gerald.schaefer@xxxxxxxxxxxxx> Cc: Heiko Carstens <hca@xxxxxxxxxxxxx> Cc: Vasily Gorbik <gor@xxxxxxxxxxxxx> Cc: Alexander Gordeev <agordeev@xxxxxxxxxxxxx> Cc: Christian Borntraeger <borntraeger@xxxxxxxxxxxxx> Cc: Sven Schnelle <svens@xxxxxxxxxxxxx> Cc: Jan Kara <jack@xxxxxxx> Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx> Cc: Christoph Hellwig <hch@xxxxxx> Cc: Alistair Popple <apopple@xxxxxxxxxx> Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx> --- drivers/s390/block/Kconfig | 12 ++++++++++-- drivers/s390/block/dcssblk.c | 26 +++++++++++++++++--------- fs/Kconfig | 9 +-------- fs/dax.c | 12 ------------ include/linux/pfn_t.h | 15 --------------- mm/memory.c | 2 -- mm/memremap.c | 4 ---- 7 files changed, 28 insertions(+), 52 deletions(-) diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig index e3710a762aba..4bfe469c04aa 100644 --- a/drivers/s390/block/Kconfig +++ b/drivers/s390/block/Kconfig @@ -4,13 +4,21 @@ comment "S/390 block device drivers" config DCSSBLK def_tristate m - select FS_DAX_LIMITED - select DAX prompt "DCSSBLK support" depends on S390 && BLOCK help Support for dcss block device +config DCSSBLK_DAX + def_bool y + depends on DCSSBLK + # requires S390 ZONE_DEVICE support + depends on BROKEN + select DAX + prompt "DCSSBLK DAX support" + help + Enable DAX operation for the dcss block device + config DASD def_tristate y prompt "Support for DASD devices" diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 02a4a51da1b7..d1bc79cf56bd 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -540,6 +540,21 @@ static const struct attribute_group *dcssblk_dev_attr_groups[] = { NULL, }; +static int dcssblk_setup_dax(struct dcssblk_dev_info *dev_info) +{ + struct dax_device *dax_dev; + + if (!IS_ENABLED(CONFIG_DCSSBLK_DAX)) + return 0; + + dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops); + if (IS_ERR(dax_dev)) + return PTR_ERR(dax_dev); + set_dax_synchronous(dax_dev); + dev_info->dax_dev = dax_dev; + return dax_add_host(dev_info->dax_dev, dev_info->gd); +} + /* * device attribute for adding devices */ @@ -680,14 +695,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char if (rc) goto put_dev; - dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops); - if (IS_ERR(dax_dev)) { - rc = PTR_ERR(dax_dev); - goto put_dev; - } - set_dax_synchronous(dax_dev); - dev_info->dax_dev = dax_dev; - rc = dax_add_host(dev_info->dax_dev, dev_info->gd); + rc = dcssblk_setup_dax(dev_info); if (rc) goto out_dax; @@ -923,7 +931,7 @@ __dcssblk_direct_access(struct dcssblk_dev_info *dev_info, pgoff_t pgoff, *kaddr = __va(dev_info->start + offset); if (pfn) *pfn = __pfn_to_pfn_t(PFN_DOWN(dev_info->start + offset), - PFN_DEV|PFN_SPECIAL); + PFN_DEV); return (dev_sz - offset) / PAGE_SIZE; } diff --git a/fs/Kconfig b/fs/Kconfig index 0e4efec1d92e..a6f4f28fa09e 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -60,7 +60,7 @@ endif # BLOCK config FS_DAX bool "File system based Direct Access (DAX) support" depends on MMU - depends on ZONE_DEVICE || FS_DAX_LIMITED + depends on ZONE_DEVICE select FS_IOMAP select DAX help @@ -96,13 +96,6 @@ config FS_DAX_PMD depends on ZONE_DEVICE depends on TRANSPARENT_HUGEPAGE -# Selected by DAX drivers that do not expect filesystem DAX to support -# get_user_pages() of DAX mappings. I.e. "limited" indicates no support -# for fork() of processes with MAP_SHARED mappings or support for -# direct-I/O to a DAX mapping. -config FS_DAX_LIMITED - bool - # Posix ACL utility routines # # Note: Posix ACLs can be implemented without these helpers. Never use diff --git a/fs/dax.c b/fs/dax.c index becb4a6920c6..6257d3fdf8f8 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -359,9 +359,6 @@ static void dax_associate_entry(void *entry, struct address_space *mapping, unsigned long size = dax_entry_size(entry), pfn, index; int i = 0; - if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) - return; - index = linear_page_index(vma, address & ~(size - 1)); for_each_mapped_pfn(entry, pfn) { struct page *page = pfn_to_page(pfn); @@ -381,9 +378,6 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping, { unsigned long pfn; - if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) - return; - for_each_mapped_pfn(entry, pfn) { struct page *page = pfn_to_page(pfn); @@ -684,12 +678,6 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping, pgoff_t end_idx; XA_STATE(xas, &mapping->i_pages, start_idx); - /* - * In the 'limited' case get_user_pages() for dax is disabled. - */ - if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) - return NULL; - if (!dax_mapping(mapping) || !mapping_mapped(mapping)) return NULL; diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 2d9148221e9a..eb8da94d1d19 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -9,18 +9,14 @@ * PFN_SG_LAST - pfn references a page and is the last scatterlist entry * PFN_DEV - pfn is not covered by system memmap by default * PFN_MAP - pfn has a dynamic page mapping established by a device driver - * PFN_SPECIAL - for CONFIG_FS_DAX_LIMITED builds to allow XIP, but not - * get_user_pages */ #define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) #define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1)) #define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2)) #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3)) #define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4)) -#define PFN_SPECIAL (1ULL << (BITS_PER_LONG_LONG - 5)) #define PFN_FLAGS_TRACE \ - { PFN_SPECIAL, "SPECIAL" }, \ { PFN_SG_CHAIN, "SG_CHAIN" }, \ { PFN_SG_LAST, "SG_LAST" }, \ { PFN_DEV, "DEV" }, \ @@ -117,15 +113,4 @@ pud_t pud_mkdevmap(pud_t pud); #endif #endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */ -#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL -static inline bool pfn_t_special(pfn_t pfn) -{ - return (pfn.val & PFN_SPECIAL) == PFN_SPECIAL; -} -#else -static inline bool pfn_t_special(pfn_t pfn) -{ - return false; -} -#endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */ #endif /* _LINUX_PFN_T_H_ */ diff --git a/mm/memory.c b/mm/memory.c index c31ea300cdf6..676f5cda992a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2462,8 +2462,6 @@ static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn, bool mkwrite) return true; if (pfn_t_devmap(pfn)) return true; - if (pfn_t_special(pfn)) - return true; if (is_zero_pfn(pfn_t_to_pfn(pfn))) return true; return false; diff --git a/mm/memremap.c b/mm/memremap.c index 40d4547ce514..a6bbbe180eab 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -332,10 +332,6 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) } break; case MEMORY_DEVICE_FS_DAX: - if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) { - WARN(1, "File system DAX not supported\n"); - return ERR_PTR(-EINVAL); - } params.pgprot = pgprot_decrypted(params.pgprot); break; case MEMORY_DEVICE_GENERIC:
