diff options
Diffstat (limited to 'arch/s390/mm/gmap.c')
| -rw-r--r-- | arch/s390/mm/gmap.c | 841 |
1 files changed, 287 insertions, 554 deletions
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 6f96b5a71c63..a94bd4870c65 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -8,6 +8,7 @@ * Janosch Frank <frankja@linux.vnet.ibm.com> */ +#include <linux/cpufeature.h> #include <linux/kernel.h> #include <linux/pagewalk.h> #include <linux/swap.h> @@ -20,10 +21,21 @@ #include <linux/pgtable.h> #include <asm/page-states.h> #include <asm/pgalloc.h> +#include <asm/machine.h> #include <asm/gmap.h> #include <asm/page.h> #include <asm/tlb.h> +/* + * The address is saved in a radix tree directly; NULL would be ambiguous, + * since 0 is a valid address, and NULL is returned when nothing was found. + * The lower bits are ignored by all users of the macro, so it can be used + * to distinguish a valid address 0 from a NULL. + */ +#define VALID_GADDR_FLAG 1 +#define IS_GADDR_VALID(gaddr) ((gaddr) & VALID_GADDR_FLAG) +#define MAKE_VALID_GADDR(gaddr) (((gaddr) & HPAGE_MASK) | VALID_GADDR_FLAG) + #define GMAP_SHADOW_FAKE_TABLE 1ULL static struct page *gmap_alloc_crst(void) @@ -43,7 +55,7 @@ static struct page *gmap_alloc_crst(void) * * Returns a guest address space structure. */ -static struct gmap *gmap_alloc(unsigned long limit) +struct gmap *gmap_alloc(unsigned long limit) { struct gmap *gmap; struct page *page; @@ -70,9 +82,7 @@ static struct gmap *gmap_alloc(unsigned long limit) gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL_ACCOUNT); if (!gmap) goto out; - INIT_LIST_HEAD(&gmap->crst_list); INIT_LIST_HEAD(&gmap->children); - INIT_LIST_HEAD(&gmap->pt_list); INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL_ACCOUNT); INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC | __GFP_ACCOUNT); INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC | __GFP_ACCOUNT); @@ -82,8 +92,6 @@ static struct gmap *gmap_alloc(unsigned long limit) page = gmap_alloc_crst(); if (!page) goto out_free; - page->index = 0; - list_add(&page->lru, &gmap->crst_list); table = page_to_virt(page); crst_table_init(table, etype); gmap->table = table; @@ -97,6 +105,7 @@ out_free: out: return NULL; } +EXPORT_SYMBOL_GPL(gmap_alloc); /** * gmap_create - create a guest address space @@ -128,7 +137,7 @@ EXPORT_SYMBOL_GPL(gmap_create); static void gmap_flush_tlb(struct gmap *gmap) { - if (MACHINE_HAS_IDTE) + if (cpu_has_idte()) __tlb_flush_idte(gmap->asce); else __tlb_flush_global(); @@ -185,30 +194,46 @@ static void gmap_rmap_radix_tree_free(struct radix_tree_root *root) } while (nr > 0); } +static void gmap_free_crst(unsigned long *table, bool free_ptes) +{ + bool is_segment = (table[0] & _SEGMENT_ENTRY_TYPE_MASK) == 0; + int i; + + if (is_segment) { + if (!free_ptes) + goto out; + for (i = 0; i < _CRST_ENTRIES; i++) + if (!(table[i] & _SEGMENT_ENTRY_INVALID)) + page_table_free_pgste(page_ptdesc(phys_to_page(table[i]))); + } else { + for (i = 0; i < _CRST_ENTRIES; i++) + if (!(table[i] & _REGION_ENTRY_INVALID)) + gmap_free_crst(__va(table[i] & PAGE_MASK), free_ptes); + } + +out: + free_pages((unsigned long)table, CRST_ALLOC_ORDER); +} + /** * gmap_free - free a guest address space * @gmap: pointer to the guest address space structure * * No locks required. There are no references to this gmap anymore. */ -static void gmap_free(struct gmap *gmap) +void gmap_free(struct gmap *gmap) { - struct page *page, *next; - /* Flush tlb of all gmaps (if not already done for shadows) */ if (!(gmap_is_shadow(gmap) && gmap->removed)) gmap_flush_tlb(gmap); /* Free all segment & region tables. */ - list_for_each_entry_safe(page, next, &gmap->crst_list, lru) - __free_pages(page, CRST_ALLOC_ORDER); + gmap_free_crst(gmap->table, gmap_is_shadow(gmap)); + gmap_radix_tree_free(&gmap->guest_to_host); gmap_radix_tree_free(&gmap->host_to_guest); /* Free additional data for a shadow gmap */ if (gmap_is_shadow(gmap)) { - /* Free all page tables. */ - list_for_each_entry_safe(page, next, &gmap->pt_list, lru) - page_table_free_pgste(page); gmap_rmap_radix_tree_free(&gmap->host_to_rmap); /* Release reference to the parent */ gmap_put(gmap->parent); @@ -216,6 +241,7 @@ static void gmap_free(struct gmap *gmap) kfree(gmap); } +EXPORT_SYMBOL_GPL(gmap_free); /** * gmap_get - increase reference counter for guest address space @@ -279,37 +305,6 @@ void gmap_remove(struct gmap *gmap) } EXPORT_SYMBOL_GPL(gmap_remove); -/** - * gmap_enable - switch primary space to the guest address space - * @gmap: pointer to the guest address space structure - */ -void gmap_enable(struct gmap *gmap) -{ - S390_lowcore.gmap = (unsigned long) gmap; -} -EXPORT_SYMBOL_GPL(gmap_enable); - -/** - * gmap_disable - switch back to the standard primary address space - * @gmap: pointer to the guest address space structure - */ -void gmap_disable(struct gmap *gmap) -{ - S390_lowcore.gmap = 0UL; -} -EXPORT_SYMBOL_GPL(gmap_disable); - -/** - * gmap_get_enabled - get a pointer to the currently enabled gmap - * - * Returns a pointer to the currently enabled gmap. 0 if none is enabled. - */ -struct gmap *gmap_get_enabled(void) -{ - return (struct gmap *) S390_lowcore.gmap; -} -EXPORT_SYMBOL_GPL(gmap_get_enabled); - /* * gmap_alloc_table is assumed to be called with mmap_lock held */ @@ -327,10 +322,8 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table, crst_table_init(new, init); spin_lock(&gmap->guest_table_lock); if (*table & _REGION_ENTRY_INVALID) { - list_add(&page->lru, &gmap->crst_list); *table = __pa(new) | _REGION_ENTRY_LENGTH | (*table & _REGION_ENTRY_TYPE_MASK); - page->index = gaddr; page = NULL; } spin_unlock(&gmap->guest_table_lock); @@ -339,21 +332,23 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table, return 0; } -/** - * __gmap_segment_gaddr - find virtual address from segment pointer - * @entry: pointer to a segment table entry in the guest address space - * - * Returns the virtual address in the guest address space for the segment - */ -static unsigned long __gmap_segment_gaddr(unsigned long *entry) +static unsigned long host_to_guest_lookup(struct gmap *gmap, unsigned long vmaddr) { - struct page *page; - unsigned long offset; + return (unsigned long)radix_tree_lookup(&gmap->host_to_guest, vmaddr >> PMD_SHIFT); +} - offset = (unsigned long) entry / sizeof(unsigned long); - offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE; - page = pmd_pgtable_page((pmd_t *) entry); - return page->index + offset; +static unsigned long host_to_guest_delete(struct gmap *gmap, unsigned long vmaddr) +{ + return (unsigned long)radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT); +} + +static pmd_t *host_to_guest_pmd_delete(struct gmap *gmap, unsigned long vmaddr, + unsigned long *gaddr) +{ + *gaddr = host_to_guest_delete(gmap, vmaddr); + if (IS_GADDR_VALID(*gaddr)) + return (pmd_t *)gmap_table_walk(gmap, *gaddr, 1); + return NULL; } /** @@ -365,16 +360,19 @@ static unsigned long __gmap_segment_gaddr(unsigned long *entry) */ static int __gmap_unlink_by_vmaddr(struct gmap *gmap, unsigned long vmaddr) { - unsigned long *entry; + unsigned long gaddr; int flush = 0; + pmd_t *pmdp; BUG_ON(gmap_is_shadow(gmap)); spin_lock(&gmap->guest_table_lock); - entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT); - if (entry) { - flush = (*entry != _SEGMENT_ENTRY_EMPTY); - *entry = _SEGMENT_ENTRY_EMPTY; + + pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr); + if (pmdp) { + flush = (pmd_val(*pmdp) != _SEGMENT_ENTRY_EMPTY); + *pmdp = __pmd(_SEGMENT_ENTRY_EMPTY); } + spin_unlock(&gmap->guest_table_lock); return flush; } @@ -493,26 +491,6 @@ unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr) EXPORT_SYMBOL_GPL(__gmap_translate); /** - * gmap_translate - translate a guest address to a user space address - * @gmap: pointer to guest mapping meta data structure - * @gaddr: guest address - * - * Returns user space address which corresponds to the guest address or - * -EFAULT if no such mapping exists. - * This function does not establish potentially missing page table entries. - */ -unsigned long gmap_translate(struct gmap *gmap, unsigned long gaddr) -{ - unsigned long rc; - - mmap_read_lock(gmap->mm); - rc = __gmap_translate(gmap, gaddr); - mmap_read_unlock(gmap->mm); - return rc; -} -EXPORT_SYMBOL_GPL(gmap_translate); - -/** * gmap_unlink - disconnect a page table from the gmap shadow tables * @mm: pointer to the parent mm_struct * @table: pointer to the host page table @@ -596,12 +574,12 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) pud = pud_offset(p4d, vmaddr); VM_BUG_ON(pud_none(*pud)); /* large puds cannot yet be handled */ - if (pud_large(*pud)) + if (pud_leaf(*pud)) return -EFAULT; pmd = pmd_offset(pud, vmaddr); VM_BUG_ON(pmd_none(*pmd)); /* Are we allowed to use huge pages? */ - if (pmd_large(*pmd) && !gmap->mm->context.allow_gmap_hpage_1m) + if (pmd_leaf(*pmd) && !gmap->mm->context.allow_gmap_hpage_1m) return -EFAULT; /* Link gmap segment table entry location to page table. */ rc = radix_tree_preload(GFP_KERNEL_ACCOUNT); @@ -611,12 +589,14 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) spin_lock(&gmap->guest_table_lock); if (*table == _SEGMENT_ENTRY_EMPTY) { rc = radix_tree_insert(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT, table); + vmaddr >> PMD_SHIFT, + (void *)MAKE_VALID_GADDR(gaddr)); if (!rc) { - if (pmd_large(*pmd)) { + if (pmd_leaf(*pmd)) { *table = (pmd_val(*pmd) & _SEGMENT_ENTRY_HARDWARE_BITS_LARGE) - | _SEGMENT_ENTRY_GMAP_UC; + | _SEGMENT_ENTRY_GMAP_UC + | _SEGMENT_ENTRY; } else *table = pmd_val(*pmd) & _SEGMENT_ENTRY_HARDWARE_BITS; @@ -633,50 +613,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) radix_tree_preload_end(); return rc; } - -/** - * gmap_fault - resolve a fault on a guest address - * @gmap: pointer to guest mapping meta data structure - * @gaddr: guest address - * @fault_flags: flags to pass down to handle_mm_fault() - * - * Returns 0 on success, -ENOMEM for out of memory conditions, and -EFAULT - * if the vm address is already mapped to a different guest segment. - */ -int gmap_fault(struct gmap *gmap, unsigned long gaddr, - unsigned int fault_flags) -{ - unsigned long vmaddr; - int rc; - bool unlocked; - - mmap_read_lock(gmap->mm); - -retry: - unlocked = false; - vmaddr = __gmap_translate(gmap, gaddr); - if (IS_ERR_VALUE(vmaddr)) { - rc = vmaddr; - goto out_up; - } - if (fixup_user_fault(gmap->mm, vmaddr, fault_flags, - &unlocked)) { - rc = -EFAULT; - goto out_up; - } - /* - * In the case that fixup_user_fault unlocked the mmap_lock during - * faultin redo __gmap_translate to not race with a map/unmap_segment. - */ - if (unlocked) - goto retry; - - rc = __gmap_link(gmap, gaddr, vmaddr); -out_up: - mmap_read_unlock(gmap->mm); - return rc; -} -EXPORT_SYMBOL_GPL(gmap_fault); +EXPORT_SYMBOL(__gmap_link); /* * this function is assumed to be called with mmap_lock held @@ -801,8 +738,7 @@ static void gmap_call_notifier(struct gmap *gmap, unsigned long start, * * Note: Can also be called for shadow gmaps. */ -static inline unsigned long *gmap_table_walk(struct gmap *gmap, - unsigned long gaddr, int level) +unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level) { const int asce_type = gmap->asce & _ASCE_TYPE_MASK; unsigned long *table = gmap->table; @@ -849,10 +785,11 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap, if (*table & _REGION_ENTRY_INVALID) return NULL; table = __va(*table & _SEGMENT_ENTRY_ORIGIN); - table += (gaddr & _PAGE_INDEX) >> _PAGE_SHIFT; + table += (gaddr & _PAGE_INDEX) >> PAGE_SHIFT; } return table; } +EXPORT_SYMBOL(gmap_table_walk); /** * gmap_pte_op_walk - walk the gmap page table, get the page table lock @@ -943,7 +880,7 @@ static inline pmd_t *gmap_pmd_op_walk(struct gmap *gmap, unsigned long gaddr) } /* 4k page table entries are locked via the pte (pte_alloc_map_lock). */ - if (!pmd_large(*pmdp)) + if (!pmd_leaf(*pmdp)) spin_unlock(&gmap->guest_table_lock); return pmdp; } @@ -955,7 +892,7 @@ static inline pmd_t *gmap_pmd_op_walk(struct gmap *gmap, unsigned long gaddr) */ static inline void gmap_pmd_op_end(struct gmap *gmap, pmd_t *pmdp) { - if (pmd_large(*pmdp)) + if (pmd_leaf(*pmdp)) spin_unlock(&gmap->guest_table_lock); } @@ -1049,86 +986,40 @@ static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr, * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE * @bits: pgste notification bits to set * - * Returns 0 if successfully protected, -ENOMEM if out of memory and - * -EFAULT if gaddr is invalid (or mapping for shadows is missing). + * Returns: + * PAGE_SIZE if a small page was successfully protected; + * HPAGE_SIZE if a large page was successfully protected; + * -ENOMEM if out of memory; + * -EFAULT if gaddr is invalid (or mapping for shadows is missing); + * -EAGAIN if the guest mapping is missing and should be fixed by the caller. * - * Called with sg->mm->mmap_lock in read. + * Context: Called with sg->mm->mmap_lock in read. */ -static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr, - unsigned long len, int prot, unsigned long bits) +int gmap_protect_one(struct gmap *gmap, unsigned long gaddr, int prot, unsigned long bits) { - unsigned long vmaddr, dist; pmd_t *pmdp; - int rc; + int rc = 0; BUG_ON(gmap_is_shadow(gmap)); - while (len) { - rc = -EAGAIN; - pmdp = gmap_pmd_op_walk(gmap, gaddr); - if (pmdp) { - if (!pmd_large(*pmdp)) { - rc = gmap_protect_pte(gmap, gaddr, pmdp, prot, - bits); - if (!rc) { - len -= PAGE_SIZE; - gaddr += PAGE_SIZE; - } - } else { - rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot, - bits); - if (!rc) { - dist = HPAGE_SIZE - (gaddr & ~HPAGE_MASK); - len = len < dist ? 0 : len - dist; - gaddr = (gaddr & HPAGE_MASK) + HPAGE_SIZE; - } - } - gmap_pmd_op_end(gmap, pmdp); - } - if (rc) { - if (rc == -EINVAL) - return rc; - /* -EAGAIN, fixup of userspace mm and gmap */ - vmaddr = __gmap_translate(gmap, gaddr); - if (IS_ERR_VALUE(vmaddr)) - return vmaddr; - rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, prot); - if (rc) - return rc; - } - } - return 0; -} + pmdp = gmap_pmd_op_walk(gmap, gaddr); + if (!pmdp) + return -EAGAIN; -/** - * gmap_mprotect_notify - change access rights for a range of ptes and - * call the notifier if any pte changes again - * @gmap: pointer to guest mapping meta data structure - * @gaddr: virtual address in the guest address space - * @len: size of area - * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE - * - * Returns 0 if for each page in the given range a gmap mapping exists, - * the new access rights could be set and the notifier could be armed. - * If the gmap mapping is missing for one or more pages -EFAULT is - * returned. If no memory could be allocated -ENOMEM is returned. - * This function establishes missing page table entries. - */ -int gmap_mprotect_notify(struct gmap *gmap, unsigned long gaddr, - unsigned long len, int prot) -{ - int rc; + if (!pmd_leaf(*pmdp)) { + rc = gmap_protect_pte(gmap, gaddr, pmdp, prot, bits); + if (!rc) + rc = PAGE_SIZE; + } else { + rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot, bits); + if (!rc) + rc = HPAGE_SIZE; + } + gmap_pmd_op_end(gmap, pmdp); - if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK) || gmap_is_shadow(gmap)) - return -EINVAL; - if (!MACHINE_HAS_ESOP && prot == PROT_READ) - return -EINVAL; - mmap_read_lock(gmap->mm); - rc = gmap_protect_range(gmap, gaddr, len, prot, GMAP_NOTIFY_MPROT); - mmap_read_unlock(gmap->mm); return rc; } -EXPORT_SYMBOL_GPL(gmap_mprotect_notify); +EXPORT_SYMBOL_GPL(gmap_protect_one); /** * gmap_read_table - get an unsigned long value from a guest page table using @@ -1315,7 +1206,7 @@ static void gmap_unshadow_page(struct gmap *sg, unsigned long raddr) table = gmap_table_walk(sg, raddr, 0); /* get page table pointer */ if (!table || *table & _PAGE_INVALID) return; - gmap_call_notifier(sg, raddr, raddr + _PAGE_SIZE - 1); + gmap_call_notifier(sg, raddr, raddr + PAGE_SIZE - 1); ptep_unshadow_pte(sg->mm, raddr, (pte_t *) table); } @@ -1333,7 +1224,7 @@ static void __gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr, int i; BUG_ON(!gmap_is_shadow(sg)); - for (i = 0; i < _PAGE_ENTRIES; i++, raddr += _PAGE_SIZE) + for (i = 0; i < _PAGE_ENTRIES; i++, raddr += PAGE_SIZE) pgt[i] = _PAGE_INVALID; } @@ -1348,7 +1239,7 @@ static void gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr) { unsigned long *ste; phys_addr_t sto, pgt; - struct page *page; + struct ptdesc *ptdesc; BUG_ON(!gmap_is_shadow(sg)); ste = gmap_table_walk(sg, raddr, 1); /* get segment pointer */ @@ -1361,9 +1252,8 @@ static void gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr) *ste = _SEGMENT_ENTRY_EMPTY; __gmap_unshadow_pgt(sg, raddr, __va(pgt)); /* Free page table */ - page = phys_to_page(pgt); - list_del(&page->lru); - page_table_free_pgste(page); + ptdesc = page_ptdesc(phys_to_page(pgt)); + page_table_free_pgste(ptdesc); } /** @@ -1377,7 +1267,7 @@ static void gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr) static void __gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr, unsigned long *sgt) { - struct page *page; + struct ptdesc *ptdesc; phys_addr_t pgt; int i; @@ -1389,9 +1279,8 @@ static void __gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr, sgt[i] = _SEGMENT_ENTRY_EMPTY; __gmap_unshadow_pgt(sg, raddr, __va(pgt)); /* Free page table */ - page = phys_to_page(pgt); - list_del(&page->lru); - page_table_free_pgste(page); + ptdesc = page_ptdesc(phys_to_page(pgt)); + page_table_free_pgste(ptdesc); } } @@ -1420,7 +1309,6 @@ static void gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr) __gmap_unshadow_sgt(sg, raddr, __va(sgt)); /* Free segment table */ page = phys_to_page(sgt); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } @@ -1448,7 +1336,6 @@ static void __gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr, __gmap_unshadow_sgt(sg, raddr, __va(sgt)); /* Free segment table */ page = phys_to_page(sgt); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } } @@ -1478,7 +1365,6 @@ static void gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr) __gmap_unshadow_r3t(sg, raddr, __va(r3t)); /* Free region 3 table */ page = phys_to_page(r3t); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } @@ -1506,7 +1392,6 @@ static void __gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr, __gmap_unshadow_r3t(sg, raddr, __va(r3t)); /* Free region 3 table */ page = phys_to_page(r3t); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } } @@ -1536,7 +1421,6 @@ static void gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr) __gmap_unshadow_r2t(sg, raddr, __va(r2t)); /* Free region 2 table */ page = phys_to_page(r2t); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } @@ -1568,7 +1452,6 @@ static void __gmap_unshadow_r1t(struct gmap *sg, unsigned long raddr, r1t[i] = _REGION1_ENTRY_EMPTY; /* Free region 2 table */ page = phys_to_page(r2t); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } } @@ -1579,7 +1462,7 @@ static void __gmap_unshadow_r1t(struct gmap *sg, unsigned long raddr, * * Called with sg->guest_table_lock */ -static void gmap_unshadow(struct gmap *sg) +void gmap_unshadow(struct gmap *sg) { unsigned long *table; @@ -1605,142 +1488,7 @@ static void gmap_unshadow(struct gmap *sg) break; } } - -/** - * gmap_find_shadow - find a specific asce in the list of shadow tables - * @parent: pointer to the parent gmap - * @asce: ASCE for which the shadow table is created - * @edat_level: edat level to be used for the shadow translation - * - * Returns the pointer to a gmap if a shadow table with the given asce is - * already available, ERR_PTR(-EAGAIN) if another one is just being created, - * otherwise NULL - */ -static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce, - int edat_level) -{ - struct gmap *sg; - - list_for_each_entry(sg, &parent->children, list) { - if (sg->orig_asce != asce || sg->edat_level != edat_level || - sg->removed) - continue; - if (!sg->initialized) - return ERR_PTR(-EAGAIN); - refcount_inc(&sg->ref_count); - return sg; - } - return NULL; -} - -/** - * gmap_shadow_valid - check if a shadow guest address space matches the - * given properties and is still valid - * @sg: pointer to the shadow guest address space structure - * @asce: ASCE for which the shadow table is requested - * @edat_level: edat level to be used for the shadow translation - * - * Returns 1 if the gmap shadow is still valid and matches the given - * properties, the caller can continue using it. Returns 0 otherwise, the - * caller has to request a new shadow gmap in this case. - * - */ -int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level) -{ - if (sg->removed) - return 0; - return sg->orig_asce == asce && sg->edat_level == edat_level; -} -EXPORT_SYMBOL_GPL(gmap_shadow_valid); - -/** - * gmap_shadow - create/find a shadow guest address space - * @parent: pointer to the parent gmap - * @asce: ASCE for which the shadow table is created - * @edat_level: edat level to be used for the shadow translation - * - * The pages of the top level page table referred by the asce parameter - * will be set to read-only and marked in the PGSTEs of the kvm process. - * The shadow table will be removed automatically on any change to the - * PTE mapping for the source table. - * - * Returns a guest address space structure, ERR_PTR(-ENOMEM) if out of memory, - * ERR_PTR(-EAGAIN) if the caller has to retry and ERR_PTR(-EFAULT) if the - * parent gmap table could not be protected. - */ -struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, - int edat_level) -{ - struct gmap *sg, *new; - unsigned long limit; - int rc; - - BUG_ON(parent->mm->context.allow_gmap_hpage_1m); - BUG_ON(gmap_is_shadow(parent)); - spin_lock(&parent->shadow_lock); - sg = gmap_find_shadow(parent, asce, edat_level); - spin_unlock(&parent->shadow_lock); - if (sg) - return sg; - /* Create a new shadow gmap */ - limit = -1UL >> (33 - (((asce & _ASCE_TYPE_MASK) >> 2) * 11)); - if (asce & _ASCE_REAL_SPACE) - limit = -1UL; - new = gmap_alloc(limit); - if (!new) - return ERR_PTR(-ENOMEM); - new->mm = parent->mm; - new->parent = gmap_get(parent); - new->orig_asce = asce; - new->edat_level = edat_level; - new->initialized = false; - spin_lock(&parent->shadow_lock); - /* Recheck if another CPU created the same shadow */ - sg = gmap_find_shadow(parent, asce, edat_level); - if (sg) { - spin_unlock(&parent->shadow_lock); - gmap_free(new); - return sg; - } - if (asce & _ASCE_REAL_SPACE) { - /* only allow one real-space gmap shadow */ - list_for_each_entry(sg, &parent->children, list) { - if (sg->orig_asce & _ASCE_REAL_SPACE) { - spin_lock(&sg->guest_table_lock); - gmap_unshadow(sg); - spin_unlock(&sg->guest_table_lock); - list_del(&sg->list); - gmap_put(sg); - break; - } - } - } - refcount_set(&new->ref_count, 2); - list_add(&new->list, &parent->children); - if (asce & _ASCE_REAL_SPACE) { - /* nothing to protect, return right away */ - new->initialized = true; - spin_unlock(&parent->shadow_lock); - return new; - } - spin_unlock(&parent->shadow_lock); - /* protect after insertion, so it will get properly invalidated */ - mmap_read_lock(parent->mm); - rc = gmap_protect_range(parent, asce & _ASCE_ORIGIN, - ((asce & _ASCE_TABLE_LENGTH) + 1) * PAGE_SIZE, - PROT_READ, GMAP_NOTIFY_SHADOW); - mmap_read_unlock(parent->mm); - spin_lock(&parent->shadow_lock); - new->initialized = true; - if (rc) { - list_del(&new->list); - gmap_free(new); - new = ERR_PTR(rc); - } - spin_unlock(&parent->shadow_lock); - return new; -} -EXPORT_SYMBOL_GPL(gmap_shadow); +EXPORT_SYMBOL(gmap_unshadow); /** * gmap_shadow_r2t - create an empty shadow region 2 table @@ -1774,9 +1522,6 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t, page = gmap_alloc_crst(); if (!page) return -ENOMEM; - page->index = r2t & _REGION_ENTRY_ORIGIN; - if (fake) - page->index |= GMAP_SHADOW_FAKE_TABLE; s_r2t = page_to_phys(page); /* Install shadow region second table */ spin_lock(&sg->guest_table_lock); @@ -1798,7 +1543,6 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t, _REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INVALID; if (sg->edat_level >= 1) *table |= (r2t & _REGION_ENTRY_PROTECT); - list_add(&page->lru, &sg->crst_list); if (fake) { /* nothing to protect for fake tables */ *table &= ~_REGION_ENTRY_INVALID; @@ -1858,9 +1602,6 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, page = gmap_alloc_crst(); if (!page) return -ENOMEM; - page->index = r3t & _REGION_ENTRY_ORIGIN; - if (fake) - page->index |= GMAP_SHADOW_FAKE_TABLE; s_r3t = page_to_phys(page); /* Install shadow region second table */ spin_lock(&sg->guest_table_lock); @@ -1882,7 +1623,6 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, _REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INVALID; if (sg->edat_level >= 1) *table |= (r3t & _REGION_ENTRY_PROTECT); - list_add(&page->lru, &sg->crst_list); if (fake) { /* nothing to protect for fake tables */ *table &= ~_REGION_ENTRY_INVALID; @@ -1942,9 +1682,6 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt, page = gmap_alloc_crst(); if (!page) return -ENOMEM; - page->index = sgt & _REGION_ENTRY_ORIGIN; - if (fake) - page->index |= GMAP_SHADOW_FAKE_TABLE; s_sgt = page_to_phys(page); /* Install shadow region second table */ spin_lock(&sg->guest_table_lock); @@ -1966,7 +1703,6 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt, _REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID; if (sg->edat_level >= 1) *table |= sgt & _REGION_ENTRY_PROTECT; - list_add(&page->lru, &sg->crst_list); if (fake) { /* nothing to protect for fake tables */ *table &= ~_REGION_ENTRY_INVALID; @@ -1999,45 +1735,22 @@ out_free: } EXPORT_SYMBOL_GPL(gmap_shadow_sgt); -/** - * gmap_shadow_pgt_lookup - find a shadow page table - * @sg: pointer to the shadow guest address space structure - * @saddr: the address in the shadow aguest address space - * @pgt: parent gmap address of the page table to get shadowed - * @dat_protection: if the pgtable is marked as protected by dat - * @fake: pgt references contiguous guest memory block, not a pgtable - * - * Returns 0 if the shadow page table was found and -EAGAIN if the page - * table was not found. - * - * Called with sg->mm->mmap_lock in read. - */ -int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr, - unsigned long *pgt, int *dat_protection, - int *fake) +static void gmap_pgste_set_pgt_addr(struct ptdesc *ptdesc, unsigned long pgt_addr) { - unsigned long *table; - struct page *page; - int rc; + unsigned long *pgstes = page_to_virt(ptdesc_page(ptdesc)); - BUG_ON(!gmap_is_shadow(sg)); - spin_lock(&sg->guest_table_lock); - table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */ - if (table && !(*table & _SEGMENT_ENTRY_INVALID)) { - /* Shadow page tables are full pages (pte+pgste) */ - page = pfn_to_page(*table >> PAGE_SHIFT); - *pgt = page->index & ~GMAP_SHADOW_FAKE_TABLE; - *dat_protection = !!(*table & _SEGMENT_ENTRY_PROTECT); - *fake = !!(page->index & GMAP_SHADOW_FAKE_TABLE); - rc = 0; - } else { - rc = -EAGAIN; - } - spin_unlock(&sg->guest_table_lock); - return rc; + pgstes += _PAGE_ENTRIES; + + pgstes[0] &= ~PGSTE_ST2_MASK; + pgstes[1] &= ~PGSTE_ST2_MASK; + pgstes[2] &= ~PGSTE_ST2_MASK; + pgstes[3] &= ~PGSTE_ST2_MASK; + pgstes[0] |= (pgt_addr >> 16) & PGSTE_ST2_MASK; + pgstes[1] |= pgt_addr & PGSTE_ST2_MASK; + pgstes[2] |= (pgt_addr << 16) & PGSTE_ST2_MASK; + pgstes[3] |= (pgt_addr << 32) & PGSTE_ST2_MASK; } -EXPORT_SYMBOL_GPL(gmap_shadow_pgt_lookup); /** * gmap_shadow_pgt - instantiate a shadow page table @@ -2057,19 +1770,20 @@ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt, { unsigned long raddr, origin; unsigned long *table; - struct page *page; + struct ptdesc *ptdesc; phys_addr_t s_pgt; int rc; BUG_ON(!gmap_is_shadow(sg) || (pgt & _SEGMENT_ENTRY_LARGE)); /* Allocate a shadow page table */ - page = page_table_alloc_pgste(sg->mm); - if (!page) + ptdesc = page_table_alloc_pgste(sg->mm); + if (!ptdesc) return -ENOMEM; - page->index = pgt & _SEGMENT_ENTRY_ORIGIN; + origin = pgt & _SEGMENT_ENTRY_ORIGIN; if (fake) - page->index |= GMAP_SHADOW_FAKE_TABLE; - s_pgt = page_to_phys(page); + origin |= GMAP_SHADOW_FAKE_TABLE; + gmap_pgste_set_pgt_addr(ptdesc, origin); + s_pgt = page_to_phys(ptdesc_page(ptdesc)); /* Install shadow page table */ spin_lock(&sg->guest_table_lock); table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */ @@ -2087,7 +1801,6 @@ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt, /* mark as invalid as long as the parent table is not protected */ *table = (unsigned long) s_pgt | _SEGMENT_ENTRY | (pgt & _SEGMENT_ENTRY_PROTECT) | _SEGMENT_ENTRY_INVALID; - list_add(&page->lru, &sg->pt_list); if (fake) { /* nothing to protect for fake tables */ *table &= ~_SEGMENT_ENTRY_INVALID; @@ -2113,7 +1826,7 @@ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt, return rc; out_free: spin_unlock(&sg->guest_table_lock); - page_table_free_pgste(page); + page_table_free_pgste(ptdesc); return rc; } @@ -2265,7 +1978,6 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr, pte_t *pte, unsigned long bits) { unsigned long offset, gaddr = 0; - unsigned long *table; struct gmap *gmap, *sg, *next; offset = ((unsigned long) pte) & (255 * sizeof(pte_t)); @@ -2273,12 +1985,9 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr, rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); - table = radix_tree_lookup(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT); - if (table) - gaddr = __gmap_segment_gaddr(table) + offset; + gaddr = host_to_guest_lookup(gmap, vmaddr) + offset; spin_unlock(&gmap->guest_table_lock); - if (!table) + if (!IS_GADDR_VALID(gaddr)) continue; if (!list_empty(&gmap->children) && (bits & PGSTE_VSIE_BIT)) { @@ -2318,10 +2027,10 @@ static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *pmdp, pmd_t new, gaddr &= HPAGE_MASK; pmdp_notify_gmap(gmap, pmdp, gaddr); new = clear_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_GMAP_IN)); - if (MACHINE_HAS_TLB_GUEST) + if (machine_has_tlb_guest()) __pmdp_idte(gaddr, (pmd_t *)pmdp, IDTE_GUEST_ASCE, gmap->asce, IDTE_GLOBAL); - else if (MACHINE_HAS_IDTE) + else if (cpu_has_idte()) __pmdp_idte(gaddr, (pmd_t *)pmdp, 0, 0, IDTE_GLOBAL); else __pmdp_csp(pmdp); @@ -2338,13 +2047,12 @@ static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr, rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); - pmdp = (pmd_t *)radix_tree_delete(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT); + pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr); if (pmdp) { - gaddr = __gmap_segment_gaddr((unsigned long *)pmdp); pmdp_notify_gmap(gmap, pmdp, gaddr); WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | - _SEGMENT_ENTRY_GMAP_UC)); + _SEGMENT_ENTRY_GMAP_UC | + _SEGMENT_ENTRY)); if (purge) __pmdp_csp(pmdp); set_pmd(pmdp, __pmd(_SEGMENT_ENTRY_EMPTY)); @@ -2384,27 +2092,25 @@ EXPORT_SYMBOL_GPL(gmap_pmdp_csp); */ void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr) { - unsigned long *entry, gaddr; + unsigned long gaddr; struct gmap *gmap; pmd_t *pmdp; rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); - entry = radix_tree_delete(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT); - if (entry) { - pmdp = (pmd_t *)entry; - gaddr = __gmap_segment_gaddr(entry); + pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr); + if (pmdp) { pmdp_notify_gmap(gmap, pmdp, gaddr); - WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | - _SEGMENT_ENTRY_GMAP_UC)); - if (MACHINE_HAS_TLB_GUEST) + WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | + _SEGMENT_ENTRY_GMAP_UC | + _SEGMENT_ENTRY)); + if (machine_has_tlb_guest()) __pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE, gmap->asce, IDTE_LOCAL); - else if (MACHINE_HAS_IDTE) + else if (cpu_has_idte()) __pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL); - *entry = _SEGMENT_ENTRY_EMPTY; + *pmdp = __pmd(_SEGMENT_ENTRY_EMPTY); } spin_unlock(&gmap->guest_table_lock); } @@ -2419,29 +2125,27 @@ EXPORT_SYMBOL_GPL(gmap_pmdp_idte_local); */ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr) { - unsigned long *entry, gaddr; + unsigned long gaddr; struct gmap *gmap; pmd_t *pmdp; rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); - entry = radix_tree_delete(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT); - if (entry) { - pmdp = (pmd_t *)entry; - gaddr = __gmap_segment_gaddr(entry); + pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr); + if (pmdp) { pmdp_notify_gmap(gmap, pmdp, gaddr); - WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | - _SEGMENT_ENTRY_GMAP_UC)); - if (MACHINE_HAS_TLB_GUEST) + WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | + _SEGMENT_ENTRY_GMAP_UC | + _SEGMENT_ENTRY)); + if (machine_has_tlb_guest()) __pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE, gmap->asce, IDTE_GLOBAL); - else if (MACHINE_HAS_IDTE) + else if (cpu_has_idte()) __pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL); else __pmdp_csp(pmdp); - *entry = _SEGMENT_ENTRY_EMPTY; + *pmdp = __pmd(_SEGMENT_ENTRY_EMPTY); } spin_unlock(&gmap->guest_table_lock); } @@ -2497,7 +2201,7 @@ void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4], if (!pmdp) return; - if (pmd_large(*pmdp)) { + if (pmd_leaf(*pmdp)) { if (gmap_test_and_clear_dirty_pmd(gmap, pmdp, gaddr)) bitmap_fill(bitmap, _PAGE_ENTRIES); } else { @@ -2547,41 +2251,6 @@ static inline void thp_split_mm(struct mm_struct *mm) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* - * Remove all empty zero pages from the mapping for lazy refaulting - * - This must be called after mm->context.has_pgste is set, to avoid - * future creation of zero pages - * - This must be called after THP was disabled. - * - * mm contracts with s390, that even if mm were to remove a page table, - * racing with the loop below and so causing pte_offset_map_lock() to fail, - * it will never insert a page table containing empty zero pages once - * mm_forbids_zeropage(mm) i.e. mm->context.has_pgste is set. - */ -static int __zap_zero_pages(pmd_t *pmd, unsigned long start, - unsigned long end, struct mm_walk *walk) -{ - unsigned long addr; - - for (addr = start; addr != end; addr += PAGE_SIZE) { - pte_t *ptep; - spinlock_t *ptl; - - ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); - if (!ptep) - break; - if (is_zero_pfn(pte_pfn(*ptep))) - ptep_xchg_direct(walk->mm, addr, ptep, __pte(_PAGE_INVALID)); - pte_unmap_unlock(ptep, ptl); - } - return 0; -} - -static const struct mm_walk_ops zap_zero_walk_ops = { - .pmd_entry = __zap_zero_pages, - .walk_lock = PGWALK_WRLOCK, -}; - -/* * switch on pgstes for its userspace process (for kvm) */ int s390_enable_sie(void) @@ -2591,29 +2260,146 @@ int s390_enable_sie(void) /* Do we have pgstes? if yes, we are done */ if (mm_has_pgste(mm)) return 0; - /* Fail if the page tables are 2K */ - if (!mm_alloc_pgste(mm)) - return -EINVAL; mmap_write_lock(mm); mm->context.has_pgste = 1; /* split thp mappings and disable thp for future mappings */ thp_split_mm(mm); - walk_page_range(mm, 0, TASK_SIZE, &zap_zero_walk_ops, NULL); mmap_write_unlock(mm); return 0; } EXPORT_SYMBOL_GPL(s390_enable_sie); -int gmap_mark_unmergeable(void) +static int find_zeropage_pte_entry(pte_t *pte, unsigned long addr, + unsigned long end, struct mm_walk *walk) { + unsigned long *found_addr = walk->private; + + /* Return 1 of the page is a zeropage. */ + if (is_zero_pfn(pte_pfn(*pte))) { + /* + * Shared zeropage in e.g., a FS DAX mapping? We cannot do the + * right thing and likely don't care: FAULT_FLAG_UNSHARE + * currently only works in COW mappings, which is also where + * mm_forbids_zeropage() is checked. + */ + if (!is_cow_mapping(walk->vma->vm_flags)) + return -EFAULT; + + *found_addr = addr; + return 1; + } + return 0; +} + +static const struct mm_walk_ops find_zeropage_ops = { + .pte_entry = find_zeropage_pte_entry, + .walk_lock = PGWALK_WRLOCK, +}; + +/* + * Unshare all shared zeropages, replacing them by anonymous pages. Note that + * we cannot simply zap all shared zeropages, because this could later + * trigger unexpected userfaultfd missing events. + * + * This must be called after mm->context.allow_cow_sharing was + * set to 0, to avoid future mappings of shared zeropages. + * + * mm contracts with s390, that even if mm were to remove a page table, + * and racing with walk_page_range_vma() calling pte_offset_map_lock() + * would fail, it will never insert a page table containing empty zero + * pages once mm_forbids_zeropage(mm) i.e. + * mm->context.allow_cow_sharing is set to 0. + */ +static int __s390_unshare_zeropages(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, 0); + unsigned long addr; + vm_fault_t fault; + int rc; + + for_each_vma(vmi, vma) { + /* + * We could only look at COW mappings, but it's more future + * proof to catch unexpected zeropages in other mappings and + * fail. + */ + if ((vma->vm_flags & VM_PFNMAP) || is_vm_hugetlb_page(vma)) + continue; + addr = vma->vm_start; + +retry: + rc = walk_page_range_vma(vma, addr, vma->vm_end, + &find_zeropage_ops, &addr); + if (rc < 0) + return rc; + else if (!rc) + continue; + + /* addr was updated by find_zeropage_pte_entry() */ + fault = handle_mm_fault(vma, addr, + FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE, + NULL); + if (fault & VM_FAULT_OOM) + return -ENOMEM; + /* + * See break_ksm(): even after handle_mm_fault() returned 0, we + * must start the lookup from the current address, because + * handle_mm_fault() may back out if there's any difficulty. + * + * VM_FAULT_SIGBUS and VM_FAULT_SIGSEGV are unexpected but + * maybe they could trigger in the future on concurrent + * truncation. In that case, the shared zeropage would be gone + * and we can simply retry and make progress. + */ + cond_resched(); + goto retry; + } + + return 0; +} + +static int __s390_disable_cow_sharing(struct mm_struct *mm) +{ + int rc; + + if (!mm->context.allow_cow_sharing) + return 0; + + mm->context.allow_cow_sharing = 0; + + /* Replace all shared zeropages by anonymous pages. */ + rc = __s390_unshare_zeropages(mm); /* * Make sure to disable KSM (if enabled for the whole process or * individual VMAs). Note that nothing currently hinders user space * from re-enabling it. */ - return ksm_disable(current->mm); + if (!rc) + rc = ksm_disable(mm); + if (rc) + mm->context.allow_cow_sharing = 1; + return rc; +} + +/* + * Disable most COW-sharing of memory pages for the whole process: + * (1) Disable KSM and unmerge/unshare any KSM pages. + * (2) Disallow shared zeropages and unshare any zerpages that are mapped. + * + * Not that we currently don't bother with COW-shared pages that are shared + * with parent/child processes due to fork(). + */ +int s390_disable_cow_sharing(void) +{ + int rc; + + mmap_write_lock(current->mm); + rc = __s390_disable_cow_sharing(current->mm); + mmap_write_unlock(current->mm); + return rc; } -EXPORT_SYMBOL_GPL(gmap_mark_unmergeable); +EXPORT_SYMBOL_GPL(s390_disable_cow_sharing); /* * Enable storage key handling from now on and initialize the storage @@ -2645,7 +2431,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr, { pmd_t *pmd = (pmd_t *)pte; unsigned long start, end; - struct page *page = pmd_page(*pmd); + struct folio *folio = page_folio(pmd_page(*pmd)); /* * The write check makes sure we do not set a key on shared @@ -2658,9 +2444,9 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr, return 0; start = pmd_val(*pmd) & HPAGE_MASK; - end = start + HPAGE_SIZE - 1; + end = start + HPAGE_SIZE; __storage_key_init_range(start, end); - set_bit(PG_arch_1, &page->flags); + set_bit(PG_arch_1, &folio->flags); cond_resched(); return 0; } @@ -2682,7 +2468,7 @@ int s390_enable_skey(void) goto out_up; mm->context.uses_skeys = 1; - rc = gmap_mark_unmergeable(); + rc = __s390_disable_cow_sharing(mm); if (rc) { mm->context.uses_skeys = 0; goto out_up; @@ -2753,13 +2539,15 @@ static const struct mm_walk_ops gather_pages_ops = { */ void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns) { + struct folio *folio; unsigned long i; for (i = 0; i < count; i++) { + folio = pfn_folio(pfns[i]); /* we always have an extra reference */ - uv_destroy_owned_page(pfn_to_phys(pfns[i])); + uv_destroy_folio(folio); /* get rid of the extra reference */ - put_page(pfn_to_page(pfns[i])); + folio_put(folio); cond_resched(); } } @@ -2800,49 +2588,6 @@ int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start, EXPORT_SYMBOL_GPL(__s390_uv_destroy_range); /** - * s390_unlist_old_asce - Remove the topmost level of page tables from the - * list of page tables of the gmap. - * @gmap: the gmap whose table is to be removed - * - * On s390x, KVM keeps a list of all pages containing the page tables of the - * gmap (the CRST list). This list is used at tear down time to free all - * pages that are now not needed anymore. - * - * This function removes the topmost page of the tree (the one pointed to by - * the ASCE) from the CRST list. - * - * This means that it will not be freed when the VM is torn down, and needs - * to be handled separately by the caller, unless a leak is actually - * intended. Notice that this function will only remove the page from the - * list, the page will still be used as a top level page table (and ASCE). - */ -void s390_unlist_old_asce(struct gmap *gmap) -{ - struct page *old; - - old = virt_to_page(gmap->table); - spin_lock(&gmap->guest_table_lock); - list_del(&old->lru); - /* - * Sometimes the topmost page might need to be "removed" multiple - * times, for example if the VM is rebooted into secure mode several - * times concurrently, or if s390_replace_asce fails after calling - * s390_remove_old_asce and is attempted again later. In that case - * the old asce has been removed from the list, and therefore it - * will not be freed when the VM terminates, but the ASCE is still - * in use and still pointed to. - * A subsequent call to replace_asce will follow the pointer and try - * to remove the same page from the list again. - * Therefore it's necessary that the page of the ASCE has valid - * pointers, so list_del can work (and do nothing) without - * dereferencing stale or invalid pointers. - */ - INIT_LIST_HEAD(&old->lru); - spin_unlock(&gmap->guest_table_lock); -} -EXPORT_SYMBOL_GPL(s390_unlist_old_asce); - -/** * s390_replace_asce - Try to replace the current ASCE of a gmap with a copy * @gmap: the gmap whose ASCE needs to be replaced * @@ -2861,8 +2606,6 @@ int s390_replace_asce(struct gmap *gmap) struct page *page; void *table; - s390_unlist_old_asce(gmap); - /* Replacing segment type ASCEs would cause serious issues */ if ((gmap->asce & _ASCE_TYPE_MASK) == _ASCE_TYPE_SEGMENT) return -EINVAL; @@ -2870,19 +2613,9 @@ int s390_replace_asce(struct gmap *gmap) page = gmap_alloc_crst(); if (!page) return -ENOMEM; - page->index = 0; table = page_to_virt(page); memcpy(table, gmap->table, 1UL << (CRST_ALLOC_ORDER + PAGE_SHIFT)); - /* - * The caller has to deal with the old ASCE, but here we make sure - * the new one is properly added to the CRST list, so that - * it will be freed when the VM is torn down. - */ - spin_lock(&gmap->guest_table_lock); - list_add(&page->lru, &gmap->crst_list); - spin_unlock(&gmap->guest_table_lock); - /* Set new table origin while preserving existing ASCE control bits */ asce = (gmap->asce & ~_ASCE_ORIGIN) | __pa(table); WRITE_ONCE(gmap->asce, asce); |