diff options
| -rw-r--r-- | arch/x86/include/asm/xen/page.h | 20 | ||||
| -rw-r--r-- | arch/x86/xen/mmu.c | 34 | ||||
| -rw-r--r-- | arch/x86/xen/p2m.c | 735 | ||||
| -rw-r--r-- | arch/x86/xen/xen-ops.h | 2 |
4 files changed, 347 insertions, 444 deletions
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 57aba6ba6f92..b54a3d20d6b2 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -65,13 +65,25 @@ extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn) * bits (identity or foreign) are set. * - __pfn_to_mfn() returns the found entry of the p2m table. A possibly set * identity or foreign indicator will be still set. __pfn_to_mfn() is - * encapsulating get_phys_to_machine(). - * - get_phys_to_machine() is to be called by __pfn_to_mfn() only to allow - * for future optimizations. + * encapsulating get_phys_to_machine() which is called in special cases only. + * - get_phys_to_machine() is to be called by __pfn_to_mfn() only in special + * cases needing an extended handling. */ static inline unsigned long __pfn_to_mfn(unsigned long pfn) { - return get_phys_to_machine(pfn); + unsigned long mfn; + + if (pfn < xen_p2m_size) + mfn = xen_p2m_addr[pfn]; + else if (unlikely(pfn < xen_max_p2m_pfn)) + return get_phys_to_machine(pfn); + else + return IDENTITY_FRAME(pfn); + + if (unlikely(mfn == INVALID_P2M_ENTRY)) + return get_phys_to_machine(pfn); + + return mfn; } static inline unsigned long pfn_to_mfn(unsigned long pfn) diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 3e3f8f8c3a30..6ab6150c8560 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1158,20 +1158,16 @@ static void __init xen_cleanhighmap(unsigned long vaddr, * instead of somewhere later and be confusing. */ xen_mc_flush(); } -static void __init xen_pagetable_p2m_copy(void) + +static void __init xen_pagetable_p2m_free(void) { unsigned long size; unsigned long addr; - unsigned long new_mfn_list; - - if (xen_feature(XENFEAT_auto_translated_physmap)) - return; size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); - new_mfn_list = xen_revector_p2m_tree(); /* No memory or already called. */ - if (!new_mfn_list || new_mfn_list == xen_start_info->mfn_list) + if ((unsigned long)xen_p2m_addr == xen_start_info->mfn_list) return; /* using __ka address and sticking INVALID_P2M_ENTRY! */ @@ -1189,8 +1185,6 @@ static void __init xen_pagetable_p2m_copy(void) size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); memblock_free(__pa(xen_start_info->mfn_list), size); - /* And revector! Bye bye old array */ - xen_start_info->mfn_list = new_mfn_list; /* At this stage, cleanup_highmap has already cleaned __ka space * from _brk_limit way up to the max_pfn_mapped (which is the end of @@ -1214,14 +1208,26 @@ static void __init xen_pagetable_p2m_copy(void) } #endif -static void __init xen_pagetable_init(void) +static void __init xen_pagetable_p2m_setup(void) { - paging_init(); + if (xen_feature(XENFEAT_auto_translated_physmap)) + return; + + xen_vmalloc_p2m_tree(); + #ifdef CONFIG_X86_64 - xen_pagetable_p2m_copy(); -#else - xen_revector_p2m_tree(); + xen_pagetable_p2m_free(); #endif + /* And revector! Bye bye old array */ + xen_start_info->mfn_list = (unsigned long)xen_p2m_addr; +} + +static void __init xen_pagetable_init(void) +{ + paging_init(); + + xen_pagetable_p2m_setup(); + /* Allocate and initialize top and mid mfn levels for p2m structure */ xen_build_mfn_list_list(); diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 8c3d8fbbba93..7d844739e513 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -3,21 +3,22 @@ * guests themselves, but it must also access and update the p2m array * during suspend/resume when all the pages are reallocated. * - * The p2m table is logically a flat array, but we implement it as a - * three-level tree to allow the address space to be sparse. + * The logical flat p2m table is mapped to a linear kernel memory area. + * For accesses by Xen a three-level tree linked via mfns only is set up to + * allow the address space to be sparse. * - * Xen - * | - * p2m_top p2m_top_mfn - * / \ / \ - * p2m_mid p2m_mid p2m_mid_mfn p2m_mid_mfn - * / \ / \ / / - * p2m p2m p2m p2m p2m p2m p2m ... + * Xen + * | + * p2m_top_mfn + * / \ + * p2m_mid_mfn p2m_mid_mfn + * / / + * p2m p2m p2m ... * * The p2m_mid_mfn pages are mapped by p2m_top_mfn_p. * - * The p2m_top and p2m_top_mfn levels are limited to 1 page, so the - * maximum representable pseudo-physical address space is: + * The p2m_top_mfn level is limited to 1 page, so the maximum representable + * pseudo-physical address space is: * P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE pages * * P2M_PER_PAGE depends on the architecture, as a mfn is always @@ -30,6 +31,9 @@ * leaf entries, or for the top root, or middle one, for which there is a void * entry, we assume it is "missing". So (for example) * pfn_to_mfn(0x90909090)=INVALID_P2M_ENTRY. + * We have a dedicated page p2m_missing with all entries being + * INVALID_P2M_ENTRY. This page may be referenced multiple times in the p2m + * list/tree in case there are multiple areas with P2M_PER_PAGE invalid pfns. * * We also have the possibility of setting 1-1 mappings on certain regions, so * that: @@ -39,122 +43,20 @@ * PCI BARs, or ACPI spaces), we can create mappings easily because we * get the PFN value to match the MFN. * - * For this to work efficiently we have one new page p2m_identity and - * allocate (via reserved_brk) any other pages we need to cover the sides - * (1GB or 4MB boundary violations). All entries in p2m_identity are set to - * INVALID_P2M_ENTRY type (Xen toolstack only recognizes that and MFNs, - * no other fancy value). + * For this to work efficiently we have one new page p2m_identity. All entries + * in p2m_identity are set to INVALID_P2M_ENTRY type (Xen toolstack only + * recognizes that and MFNs, no other fancy value). * * On lookup we spot that the entry points to p2m_identity and return the * identity value instead of dereferencing and returning INVALID_P2M_ENTRY. * If the entry points to an allocated page, we just proceed as before and - * return the PFN. If the PFN has IDENTITY_FRAME_BIT set we unmask that in + * return the PFN. If the PFN has IDENTITY_FRAME_BIT set we unmask that in * appropriate functions (pfn_to_mfn). * * The reason for having the IDENTITY_FRAME_BIT instead of just returning the * PFN is that we could find ourselves where pfn_to_mfn(pfn)==pfn for a * non-identity pfn. To protect ourselves against we elect to set (and get) the * IDENTITY_FRAME_BIT on all identity mapped PFNs. - * - * This simplistic diagram is used to explain the more subtle piece of code. - * There is also a digram of the P2M at the end that can help. - * Imagine your E820 looking as so: - * - * 1GB 2GB 4GB - * /-------------------+---------\/----\ /----------\ /---+-----\ - * | System RAM | Sys RAM ||ACPI| | reserved | | Sys RAM | - * \-------------------+---------/\----/ \----------/ \---+-----/ - * ^- 1029MB ^- 2001MB - * - * [1029MB = 263424 (0x40500), 2001MB = 512256 (0x7D100), - * 2048MB = 524288 (0x80000)] - * - * And dom0_mem=max:3GB,1GB is passed in to the guest, meaning memory past 1GB - * is actually not present (would have to kick the balloon driver to put it in). - * - * When we are told to set the PFNs for identity mapping (see patch: "xen/setup: - * Set identity mapping for non-RAM E820 and E820 gaps.") we pass in the start - * of the PFN and the end PFN (263424 and 512256 respectively). The first step - * is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page - * covers 512^2 of page estate (1GB) and in case the start or end PFN is not - * aligned on 512^2*PAGE_SIZE (1GB) we reserve_brk new middle and leaf pages as - * required to split any existing p2m_mid_missing middle pages. - * - * With the E820 example above, 263424 is not 1GB aligned so we allocate a - * reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000. - * Each entry in the allocate page is "missing" (points to p2m_missing). - * - * Next stage is to determine if we need to do a more granular boundary check - * on the 4MB (or 2MB depending on architecture) off the start and end pfn's. - * We check if the start pfn and end pfn violate that boundary check, and if - * so reserve_brk a (p2m[x][y]) leaf page. This way we have a much finer - * granularity of setting which PFNs are missing and which ones are identity. - * In our example 263424 and 512256 both fail the check so we reserve_brk two - * pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing" - * values) and assign them to p2m[1][2] and p2m[1][488] respectively. - * - * At this point we would at minimum reserve_brk one page, but could be up to - * three. Each call to set_phys_range_identity has at maximum a three page - * cost. If we were to query the P2M at this stage, all those entries from - * start PFN through end PFN (so 1029MB -> 2001MB) would return - * INVALID_P2M_ENTRY ("missing"). - * - * The next step is to walk from the start pfn to the end pfn setting - * the IDENTITY_FRAME_BIT on each PFN. This is done in set_phys_range_identity. - * If we find that the middle entry is pointing to p2m_missing we can swap it - * over to p2m_identity - this way covering 4MB (or 2MB) PFN space (and - * similarly swapping p2m_mid_missing for p2m_mid_identity for larger regions). - * At this point we do not need to worry about boundary aligment (so no need to - * reserve_brk a middle page, figure out which PFNs are "missing" and which - * ones are identity), as that has been done earlier. If we find that the - * middle leaf is not occupied by p2m_identity or p2m_missing, we dereference - * that page (which covers 512 PFNs) and set the appropriate PFN with - * IDENTITY_FRAME_BIT. In our example 263424 and 512256 end up there, and we - * set from p2m[1][2][256->511] and p2m[1][488][0->256] with - * IDENTITY_FRAME_BIT set. - * - * All other regions that are void (or not filled) either point to p2m_missing - * (considered missing) or have the default value of INVALID_P2M_ENTRY (also - * considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511] - * contain the INVALID_P2M_ENTRY value and are considered "missing." - * - * Finally, the region beyond the end of of the E820 (4 GB in this example) - * is set to be identity (in case there are MMIO regions placed here). - * - * This is what the p2m ends up looking (for the E820 above) with this - * fabulous drawing: - * - * p2m /--------------\ - * /-----\ | &mfn_list[0],| /-----------------\ - * | 0 |------>| &mfn_list[1],| /---------------\ | ~0, ~0, .. | - * |-----| | ..., ~0, ~0 | | ~0, ~0, [x]---+----->| IDENTITY [@256] | - * | 1 |---\ \--------------/ | [p2m_identity]+\ | IDENTITY [@257] | - * |-----| \ | [p2m_identity]+\\ | .... | - * | 2 |--\ \-------------------->| ... | \\ \----------------/ - * |-----| \ \---------------/ \\ - * | 3 |-\ \ \\ p2m_identity [1] - * |-----| \ \-------------------->/---------------\ /-----------------\ - * | .. |\ | | [p2m_identity]+-->| ~0, ~0, ~0, ... | - * \-----/ | | | [p2m_identity]+-->| ..., ~0 | - * | | | .... | \-----------------/ - * | | +-[x], ~0, ~0.. +\ - * | | \---------------/ \ - * | | \-> /---------------\ - * | V p2m_mid_missing p2m_missing | IDENTITY[@0] | - * | /-----------------\ /------------\ | IDENTITY[@256]| - * | | [p2m_missing] +---->| ~0, ~0, ...| | ~0, ~0, .... | - * | | [p2m_missing] +---->| ..., ~0 | \---------------/ - * | | ... | \------------/ - * | \-----------------/ - * | - * | p2m_mid_identity - * | /-----------------\ - * \-->| [p2m_identity] +---->[1] - * | [p2m_identity] +---->[1] - * | ... | - * \-----------------/ - * - * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT) */ #include <linux/init.h> @@ -179,6 +81,8 @@ #include "multicalls.h" #include "xen-ops.h" +#define PMDS_PER_MID_PAGE (P2M_MID_PER_PAGE / PTRS_PER_PTE) + static void __init m2p_override_init(void); unsigned long *xen_p2m_addr __read_mostly; @@ -188,22 +92,15 @@ EXPORT_SYMBOL_GPL(xen_p2m_size); unsigned long xen_max_p2m_pfn __read_mostly; EXPORT_SYMBOL_GPL(xen_max_p2m_pfn); +static DEFINE_SPINLOCK(p2m_update_lock); + static unsigned long *p2m_mid_missing_mfn; static unsigned long *p2m_top_mfn; static unsigned long **p2m_top_mfn_p; - -/* Placeholders for holes in the address space */ -static RESERVE_BRK_ARRAY(unsigned long, p2m_missing, P2M_PER_PAGE); -static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_missing, P2M_MID_PER_PAGE); - -static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE); - -static RESERVE_BRK_ARRAY(unsigned long, p2m_identity, P2M_PER_PAGE); -static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_identity, P2M_MID_PER_PAGE); - -RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); - -static int use_brk = 1; +static unsigned long *p2m_missing; +static unsigned long *p2m_identity; +static pte_t *p2m_missing_pte; +static pte_t *p2m_identity_pte; static inline unsigned p2m_top_index(unsigned long pfn) { @@ -221,14 +118,6 @@ static inline unsigned p2m_index(unsigned long pfn) return pfn % P2M_PER_PAGE; } -static void p2m_top_init(unsigned long ***top) -{ - unsigned i; - - for (i = 0; i < P2M_TOP_PER_PAGE; i++) - top[i] = p2m_mid_missing; -} - static void p2m_top_mfn_init(unsigned long *top) { unsigned i; @@ -245,35 +134,32 @@ static void p2m_top_mfn_p_init(unsigned long **top) top[i] = p2m_mid_missing_mfn; } -static void p2m_mid_init(unsigned long **mid, unsigned long *leaf) +static void p2m_mid_mfn_init(unsigned long *mid, unsigned long *leaf) { unsigned i; for (i = 0; i < P2M_MID_PER_PAGE; i++) - mid[i] = leaf; + mid[i] = virt_to_mfn(leaf); } -static void p2m_mid_mfn_init(unsigned long *mid, unsigned long *leaf) +static void p2m_init(unsigned long *p2m) { unsigned i; - for (i = 0; i < P2M_MID_PER_PAGE; i++) - mid[i] = virt_to_mfn(leaf); + for (i = 0; i < P2M_PER_PAGE; i++) + p2m[i] = INVALID_P2M_ENTRY; } -static void p2m_init(unsigned long *p2m) +static void p2m_init_identity(unsigned long *p2m, unsigned long pfn) { unsigned i; - for (i = 0; i < P2M_MID_PER_PAGE; i++) - p2m[i] = INVALID_P2M_ENTRY; + for (i = 0; i < P2M_PER_PAGE; i++) + p2m[i] = IDENTITY_FRAME(pfn + i); } static void * __ref alloc_p2m_page(void) { - if (unlikely(use_brk)) - return extend_brk(PAGE_SIZE, PAGE_SIZE); - if (unlikely(!slab_is_available())) return alloc_bootmem_align(PAGE_SIZE, PAGE_SIZE); @@ -299,7 +185,10 @@ static void free_p2m_page(void *p) */ void __ref xen_build_mfn_list_list(void) { - unsigned long pfn; + unsigned long pfn, mfn; + pte_t *ptep; + unsigned int level, topidx, mididx; + unsigned long *mid_mfn_p; if (xen_feature(XENFEAT_auto_translated_physmap)) return; @@ -319,20 +208,23 @@ void __ref xen_build_mfn_list_list(void) p2m_mid_mfn_init(p2m_mid_missing_mfn, p2m_missing); } - for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += P2M_PER_PAGE) { - unsigned topidx = p2m_top_index(pfn); - unsigned mididx = p2m_mid_index(pfn); - unsigned long **mid; - unsigned long *mid_mfn_p; + for (pfn = 0; pfn < xen_max_p2m_pfn && pfn < MAX_P2M_PFN; + pfn += P2M_PER_PAGE) { + topidx = p2m_top_index(pfn); + mididx = p2m_mid_index(pfn); - mid = p2m_top[topidx]; mid_mfn_p = p2m_top_mfn_p[topidx]; + ptep = lookup_address((unsigned long)(xen_p2m_addr + pfn), + &level); + BUG_ON(!ptep || level != PG_LEVEL_4K); + mfn = pte_mfn(*ptep); + ptep = (pte_t *)((unsigned long)ptep & ~(PAGE_SIZE - 1)); /* Don't bother allocating any mfn mid levels if * they're just missing, just update the stored mfn, * since all could have changed over a migrate. */ - if (mid == p2m_mid_missing) { + if (ptep == p2m_missing_pte || ptep == p2m_identity_pte) { BUG_ON(mididx); BUG_ON(mid_mfn_p != p2m_mid_missing_mfn); p2m_top_mfn[topidx] = virt_to_mfn(p2m_mid_missing_mfn); @@ -341,11 +233,6 @@ void __ref xen_build_mfn_list_list(void) } if (mid_mfn_p == p2m_mid_missing_mfn) { - /* - * XXX boot-time only! We should never find - * missing parts of the mfn tree after - * runtime. - */ mid_mfn_p = alloc_p2m_page(); p2m_mid_mfn_init(mid_mfn_p, p2m_missing); @@ -353,7 +240,7 @@ void __ref xen_build_mfn_list_list(void) } p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p); - mid_mfn_p[mididx] = virt_to_mfn(mid[mididx]); + mid_mfn_p[mididx] = mfn; } } @@ -372,154 +259,153 @@ void xen_setup_mfn_list_list(void) /* Set up p2m_top to point to the domain-builder provided p2m pages */ void __init xen_build_dynamic_phys_to_machine(void) { - unsigned long *mfn_list; - unsigned long max_pfn; unsigned long pfn; if (xen_feature(XENFEAT_auto_translated_physmap)) return; xen_p2m_addr = (unsigned long *)xen_start_info->mfn_list; - mfn_list = (unsigned long *)xen_start_info->mfn_list; - max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages); - xen_max_p2m_pfn = max_pfn; - xen_p2m_size = max_pfn; + xen_p2m_size = ALIGN(xen_start_info->nr_pages, P2M_PER_PAGE); - p2m_missing = alloc_p2m_page(); - p2m_init(p2m_missing); - p2m_identity = alloc_p2m_page(); - p2m_init(p2m_identity); + for (pfn = xen_start_info->nr_pages; pfn < xen_p2m_size; pfn++) + xen_p2m_addr[pfn] = INVALID_P2M_ENTRY; - p2m_mid_missing = alloc_p2m_page(); - p2m_mid_init(p2m_mid_missing, p2m_missing); - p2m_mid_identity = alloc_p2m_page(); - p2m_mid_init(p2m_mid_identity, p2m_identity); + xen_max_p2m_pfn = xen_p2m_size; +} - p2m_top = alloc_p2m_page(); - p2m_top_init(p2m_top); +#define P2M_TYPE_IDENTITY 0 +#define P2M_TYPE_MISSING 1 +#define P2M_TYPE_PFN 2 +#define P2M_TYPE_UNKNOWN 3 - /* - * The domain builder gives us a pre-constructed p2m array in - * mfn_list for all the pages initially given to us, so we just - * need to graft that into our tree structure. - */ - for (pfn = 0; pfn < max_pfn; pfn += P2M_PER_PAGE) { - unsigned topidx = p2m_top_index(pfn); - unsigned mididx = p2m_mid_index(pfn); +static int xen_p2m_elem_type(unsigned long pfn) +{ + unsigned long mfn; - if (p2m_top[topidx] == p2m_mid_missing) { - unsigned long **mid = alloc_p2m_page(); - p2m_mid_init(mid, p2m_missing); + if (pfn >= xen_p2m_size) + return P2M_TYPE_IDENTITY; - p2m_top[topidx] = mid; - } + mfn = xen_p2m_addr[pfn]; - /* - * As long as the mfn_list has enough entries to completely - * fill a p2m page, pointing into the array is ok. But if - * not the entries beyond the last pfn will be undefined. - */ - if (unlikely(pfn + P2M_PER_PAGE > max_pfn)) { - unsigned long p2midx; + if (mfn == INVALID_P2M_ENTRY) + return P2M_TYPE_MISSING; - p2midx = max_pfn % P2M_PER_PAGE; - for ( ; p2midx < P2M_PER_PAGE; p2midx++) - mfn_list[pfn + p2midx] = INVALID_P2M_ENTRY; - } - p2m_top[topidx][mididx] = &mfn_list[pfn]; - } + if (mfn & IDENTITY_FRAME_BIT) + return P2M_TYPE_IDENTITY; + + return P2M_TYPE_PFN; } -#ifdef CONFIG_X86_64 -unsigned long __init xen_revector_p2m_tree(void) + +static void __init xen_rebuild_p2m_list(unsigned long *p2m) { - unsigned long va_start; - unsigned long va_end; + unsigned int i, chunk; unsigned long pfn; - unsigned long pfn_free = 0; - unsigned long *mfn_list = NULL; - unsigned long size; - - use_brk = 0; - va_start = xen_start_info->mfn_list; - /*We copy in increments of P2M_PER_PAGE * sizeof(unsigned long), - * so make sure it is rounded up to that */ - size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); - va_end = va_start + size; - - /* If we were revectored already, don't do it again. */ - if (va_start <= __START_KERNEL_map && va_start >= __PAGE_OFFSET) - return 0; - - mfn_list = alloc_bootmem_align(size, PAGE_SIZE); - if (!mfn_list) { - pr_warn("Could not allocate space for a new P2M tree!\n"); - return xen_start_info->mfn_list; - } - /* Fill it out with INVALID_P2M_ENTRY value */ - memset(mfn_list, 0xFF, size); + unsigned long *mfns; + pte_t *ptep; + pmd_t *pmdp; + int type; - for (pfn = 0; pfn < ALIGN(MAX_DOMAIN_PAGES, P2M_PER_PAGE); pfn += P2M_PER_PAGE) { - unsigned topidx = p2m_top_index(pfn); - unsigned mididx; - unsigned long *mid_p; - - if (!p2m_top[topidx]) - continue; + p2m_missing = alloc_p2m_page(); + p2m_init(p2m_missing); + p2m_identity = alloc_p2m_page(); + p2m_init(p2m_identity); - if (p2m_top[topidx] == p2m_mid_missing) - continue; + p2m_missing_pte = alloc_p2m_page(); + paravirt_alloc_pte(&init_mm, __pa(p2m_missing_pte) >> PAGE_SHIFT); + p2m_identity_pte = alloc_p2m_page(); + paravirt_alloc_pte(&init_mm, __pa(p2m_identity_pte) >> PAGE_SHIFT); + for (i = 0; i < PTRS_PER_PTE; i++) { + set_pte(p2m_missing_pte + i, + pfn_pte(PFN_DOWN(__pa(p2m_missing)), PAGE_KERNEL)); + set_pte(p2m_identity_pte + i, + pfn_pte(PFN_DOWN(__pa(p2m_identity)), PAGE_KERNEL)); + } - mididx = p2m_mid_index(pfn); - mid_p = p2m_top[topidx][mididx]; - if (!mid_p) - continue; - if ((mid_p == p2m_missing) || (mid_p == p2m_identity)) + for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += chunk) { + /* + * Try to map missing/identity PMDs or p2m-pages if possible. + * We have to respect the structure of the mfn_list_list + * which will be built just afterwards. + * Chunk size to test is one p2m page if we are in the middle + * of a mfn_list_list mid page and the complete mid page area + * if we are at index 0 of the mid page. Please note that a + * mid page might cover more than one PMD, e.g. on 32 bit PAE + * kernels. + */ + chunk = (pfn & (P2M_PER_PAGE * P2M_MID_PER_PAGE - 1)) ? + P2M_PER_PAGE : P2M_PER_PAGE * P2M_MID_PER_PAGE; + + type = xen_p2m_elem_type(pfn); + i = 0; + if (type != P2M_TYPE_PFN) + for (i = 1; i < chunk; i++) + if (xen_p2m_elem_type(pfn + i) != type) + break; + if (i < chunk) + /* Reset to minimal chunk size. */ + chunk = P2M_PER_PAGE; + + if (type == P2M_TYPE_PFN || i < chunk) { + /* Use initial p2m page contents. */ +#ifdef CONFIG_X86_64 + mfns = alloc_p2m_page(); + copy_page(mfns, xen_p2m_addr + pfn); +#else + mfns = xen_p2m_addr + pfn; +#endif + ptep = populate_extra_pte((unsigned long)(p2m + pfn)); + set_pte(ptep, + pfn_pte(PFN_DOWN(__pa(mfns)), PAGE_KERNEL)); continue; + } - if ((unsigned long)mid_p == INVALID_P2M_ENTRY) + if (chunk == P2M_PER_PAGE) { + /* Map complete missing or identity p2m-page. */ + mfns = (type == P2M_TYPE_MISSING) ? + p2m_missing : p2m_identity; + ptep = populate_extra_pte((unsigned long)(p2m + pfn)); + set_pte(ptep, + pfn_pte(PFN_DOWN(__pa(mfns)), PAGE_KERNEL)); continue; + } - /* The old va. Rebase it on mfn_list */ - if (mid_p >= (unsigned long *)va_start && mid_p <= (unsigned long *)va_end) { - unsigned long *new; + /* Complete missing or identity PMD(s) can be mapped. */ + ptep = (type == P2M_TYPE_MISSING) ? + p2m_missing_pte : p2m_identity_pte; + for (i = 0; i < PMDS_PER_MID_PAGE; i++) { + pmdp = populate_extra_pmd( + (unsigned long)(p2m + pfn + i * PTRS_PER_PTE)); + set_pmd(pmdp, __pmd(__pa(ptep) | _KERNPG_TABLE)); + } + } +} - if (pfn_free > (size / sizeof(unsigned long))) { - WARN(1, "Only allocated for %ld pages, but we want %ld!\n", - size / sizeof(unsigned long), pfn_free); - return 0; - } - new = &mfn_list[pfn_free]; +void __init xen_vmalloc_p2m_tree(void) +{ + static struct vm_struct vm; - copy_page(new, mid_p); - p2m_top[topidx][mididx] = &mfn_list[pfn_free]; + vm.flags = VM_ALLOC; + vm.size = ALIGN(sizeof(unsigned long) * xen_max_p2m_pfn, + PMD_SIZE * PMDS_PER_MID_PAGE); + vm_area_register_early(&vm, PMD_SIZE * PMDS_PER_MID_PAGE); + pr_notice("p2m virtual area at %p, size is %lx\n", vm.addr, vm.size); - pfn_free += P2M_PER_PAGE; + xen_max_p2m_pfn = vm.size / sizeof(unsigned long); - } - /* This should be the leafs allocated for identity from _brk. */ - } + xen_rebuild_p2m_list(vm.addr); + xen_p2m_addr = vm.addr; xen_p2m_size = xen_max_p2m_pfn; - xen_p2m_addr = mfn_list; xen_inv_extra_mem(); m2p_override_init(); - return (unsigned long)mfn_list; } -#else -unsigned long __init xen_revector_p2m_tree(void) -{ - use_brk = 0; - xen_p2m_size = xen_max_p2m_pfn; - xen_inv_extra_mem(); - m2p_override_init(); - return 0; -} -#endif + unsigned long get_phys_to_machine(unsigned long pfn) { - unsigned topidx, mididx, idx; + pte_t *ptep; + unsigned int level; if (unlikely(pfn >= xen_p2m_size)) { if (pfn < xen_max_p2m_pfn) @@ -528,23 +414,83 @@ unsigned long get_phys_to_machine(unsigned long pfn) return IDENTITY_FRAME(pfn); } - topidx = p2m_top_index(pfn); - mididx = p2m_mid_index(pfn); - idx = p2m_index(pfn); + ptep = lookup_address((unsigned long)(xen_p2m_addr + pfn), &level); + BUG_ON(!ptep || level != PG_LEVEL_4K); /* * The INVALID_P2M_ENTRY is filled in both p2m_*identity * and in p2m_*missing, so returning the INVALID_P2M_ENTRY * would be wrong. */ - if (p2m_top[topidx][mididx] == p2m_identity) + if (pte_pfn(*ptep) == PFN_DOWN(__pa(p2m_identity))) return IDENTITY_FRAME(pfn); - return p2m_top[topidx][mididx][idx]; + return xen_p2m_addr[pfn]; } EXPORT_SYMBOL_GPL(get_phys_to_machine); /* + * Allocate new pmd(s). It is checked whether the old pmd is still in place. + * If not, nothing is changed. This is okay as the only reason for allocating + * a new pmd is to replace p2m_missing_pte or p2m_identity_pte by a individual + * pmd. In case of PAE/x86-32 there are multiple pmds to allocate! + */ +static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg) +{ + pte_t *ptechk; + pte_t *pteret = ptep; + pte_t *pte_newpg[PMDS_PER_MID_PAGE]; + pmd_t *pmdp; + unsigned int level; + unsigned long flags; + unsigned long vaddr; + int i; + + /* Do all allocations first to bail out in error case. */ + for (i = 0; i < PMDS_PER_MID_PAGE; i++) { + pte_newpg[i] = alloc_p2m_page(); + if (!pte_newpg[i]) { + for (i--; i >= 0; i--) + free_p2m_page(pte_newpg[i]); + + return NULL; + } + } + + vaddr = addr & ~(PMD_SIZE * PMDS_PER_MID_PAGE - 1); + + for (i = 0; i < PMDS_PER_MID_PAGE; i++) { + copy_page(pte_newpg[i], pte_pg); + paravirt_alloc_pte(&init_mm, __pa(pte_newpg[i]) >> PAGE_SHIFT); + + pmdp = lookup_pmd_address(vaddr); + BUG_ON(!pmdp); + + spin_lock_irqsave(&p2m_update_lock, flags); + + ptechk = lookup_address(vaddr, &level); + if (ptechk == pte_pg) { + set_pmd(pmdp, + __pmd(__pa(pte_newpg[i]) | _KERNPG_TABLE)); + if (vaddr == (addr & ~(PMD_SIZE - 1))) + pteret = pte_offset_kernel(pmdp, addr); + pte_newpg[i] = NULL; + } + + spin_unlock_irqrestore(&p2m_update_lock, flags); + + if (pte_newpg[i]) { + paravirt_release_pte(__pa(pte_newpg[i]) >> PAGE_SHIFT); + free_p2m_page(pte_newpg[i]); + } + + vaddr += PMD_SIZE; + } + + return pteret; +} + +/* * Fully allocate the p2m structure for a given pfn. We need to check * that both the top and mid levels are allocated, and make sure the * parallel mfn tree is kept in sync. We may race with other cpus, so @@ -554,58 +500,62 @@ EXPORT_SYMBOL_GPL(get_phys_to_machine); static bool alloc_p2m(unsigned long pfn) { unsigned topidx, mididx; - unsigned long ***top_p, **mid; unsigned long *top_mfn_p, *mid_mfn; - unsigned long *p2m_orig; + pte_t *ptep, *pte_pg; + unsigned int level; + unsigned long flags; + unsigned long addr = (unsigned long)(xen_p2m_addr + pfn); + unsigned long p2m_pfn; topidx = p2m_top_index(pfn); mididx = p2m_mid_index(pfn); - top_p = &p2m_top[topidx]; - mid = ACCESS_ONCE(*top_p); + ptep = lookup_address(addr, &level); + BUG_ON(!ptep || level != PG_LEVEL_4K); + pte_pg = (pte_t *)((unsigned long)ptep & ~(PAGE_SIZE - 1)); - if (mid == p2m_mid_missing) { - /* Mid level is missing, allocate a new one */ - mid = alloc_p2m_page(); - if (!mid) + if (pte_pg == p2m_missing_pte || pte_pg == p2m_identity_pte) { + /* PMD level is missing, allocate a new one */ + ptep = alloc_p2m_pmd(addr, ptep, pte_pg); + if (!ptep) return false; - - p2m_mid_init(mid, p2m_missing); - - if (cmpxchg(top_p, p2m_mid_missing, mid) != p2m_mid_missing) - free_p2m_page(mid); } - top_mfn_p = &p2m_top_mfn[topidx]; - mid_mfn = ACCESS_ONCE(p2m_top_mfn_p[topidx]); + if (p2m_top_mfn) { + top_mfn_p = &p2m_top_mfn[topidx]; + mid_mfn = ACCESS_ONCE(p2m_top_mfn_p[topidx]); - BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p); + BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p); - if (mid_mfn == p2m_mid_missing_mfn) { - /* Separately check the mid mfn level */ - unsigned long missing_mfn; - unsigned long mid_mfn_mfn; - unsigned long old_mfn; + if (mid_mfn == p2m_mid_missing_mfn) { + /* Separately check the mid mfn level */ + unsigned long missing_mfn; + unsigned long mid_mfn_mfn; + unsigned long old_mfn; - mid_mfn = alloc_p2m_page(); - if (!mid_mfn) - return false; + mid_mfn = alloc_p2m_page(); + if (!mid_mfn) + return false; - p2m_mid_mfn_init(mid_mfn, p2m_missing); + p2m_mid_mfn_init(mid_mfn, p2m_missing); - missing_mfn = virt_to_mfn(p2m_mid_missing_mfn); - mid_mfn_mfn = virt_to_mfn(mid_mfn); - old_mfn = cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn); - if (old_mfn != missing_mfn) { - free_p2m_page(mid_mfn); - mid_mfn = mfn_to_virt(old_mfn); - } else { - p2m_top_mfn_p[topidx] = mid_mfn; + missing_mfn = virt_to_mfn(p2m_mid_missing_mfn); + mid_mfn_mfn = virt_to_mfn(mid_mfn); + old_mfn = cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn); + if (old_mfn != missing_mfn) { + free_p2m_page(mid_mfn); + mid_mfn = mfn_to_virt(old_mfn); + } else { + p2m_top_mfn_p[topidx] = mid_mfn; + } } + } else { + mid_mfn = NULL; } - p2m_orig = ACCESS_ONCE(p2m_top[topidx][mididx]); - if (p2m_orig == p2m_identity || p2m_orig == p2m_missing) { + p2m_pfn = pte_pfn(ACCESS_ONCE(*ptep)); + if (p2m_pfn == PFN_DOWN(__pa(p2m_identity)) || + p2m_pfn == PFN_DOWN(__pa(p2m_missing))) { /* p2m leaf page is missing */ unsigned long *p2m; @@ -613,12 +563,25 @@ static bool alloc_p2m(unsigned long pfn) if (!p2m) return false; - p2m_init(p2m); + if (p2m_pfn == PFN_DOWN(__pa(p2m_missing))) + p2m_init(p2m); + else + p2m_init_identity(p2m, pfn); + + spin_lock_irqsave(&p2m_update_lock, flags); + + if (pte_pfn(*ptep) == p2m_pfn) { + set_pte(ptep, + pfn_pte(PFN_DOWN(__pa(p2m)), PAGE_KERNEL)); + if (mid_mfn) + mid_mfn[mididx] = virt_to_mfn(p2m); + p2m = NULL; + } + + spin_unlock_irqrestore(&p2m_update_lock, flags); - if (cmpxchg(&mid[mididx], p2m_orig, p2m) != p2m_orig) + if (p2m) free_p2m_page(p2m); - else - mid_mfn[mididx] = virt_to_mfn(p2m); } return true; @@ -647,10 +610,10 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s, return pfn - pfn_s; } -/* Try to install p2m mapping; fail if intermediate bits missing */ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) { - unsigned topidx, mididx, idx; + pte_t *ptep; + unsigned int level; /* don't track P2M changes in autotranslate guests */ if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) @@ -661,55 +624,27 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) return true; } - topidx = p2m_top_index(pfn); - mididx = p2m_mid_index(pfn); - idx = p2m_index(pfn); - - /* For sparse holes were the p2m leaf has real PFN along with - * PCI holes, stick in the PFN as the MFN value. - * - * set_phys_range_identity() will have allocated new middle - * and leaf pages as required so an existing p2m_mid_missing - * or p2m_missing mean that whole range will be identity so - * these can be switched to p2m_mid_identity or p2m_identity. - */ - if (mfn != INVALID_P2M_ENTRY && (mfn & IDENTITY_FRAME_BIT)) { - if (p2m_top[topidx] == p2m_mid_identity) - return true; - - if (p2m_top[topidx] == p2m_mid_missing) { - WARN_ON(cmpxchg(&p2m_top[topidx], p2m_mid_missing, - p2m_mid_identity) != p2m_mid_missing); - return true; - } - - if (p2m_top[topidx][mididx] == p2m_identity) - return true; - - /* Swap over from MISSING to IDENTITY if needed. */ - if (p2m_top[topidx][mididx] == p2m_missing) { - WARN_ON(cmpxchg(&p2m_top[topidx][mididx], p2m_missing, - p2m_identity) != p2m_missing); - return true; - } - } + ptep = lookup_address((unsigned long)(xen_p2m_addr + pfn), &level); + BUG_ON(!ptep || level != PG_LEVEL_4K); - if (p2m_top[topidx][mididx] == p2m_missing) + if (pte_pfn(*ptep) == PFN_DOWN(__pa(p2m_missing))) return mfn == INVALID_P2M_ENTRY; - p2m_top[topidx][mididx][idx] = mfn; + if (pte_pfn(*ptep) == PFN_DOWN(__pa(p2m_identity))) + return mfn == IDENTITY_FRAME(pfn); + + xen_p2m_addr[pfn] = mfn; return true; } bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) { - if (unlikely(!__set_phys_to_machine(pfn, mfn))) { + if (unlikely(!__set_phys_to_machine(pfn, mfn))) { if (!alloc_p2m(pfn)) return false; - if (!__set_phys_to_machine(pfn, mfn)) - return false; + return __set_phys_to_machine(pfn, mfn); } return true; @@ -1035,79 +970,29 @@ EXPORT_SYMBOL_GPL(m2p_find_override_pfn); #include "debugfs.h" static int p2m_dump_show(struct seq_file *m, void *v) { - static const char * const level_name[] = { "top", "middle", - "entry", "abnormal", "error"}; -#define TYPE_IDENTITY 0 -#define TYPE_MISSING 1 -#define TYPE_PFN 2 -#define TYPE_UNKNOWN 3 static const char * const type_name[] = { - [TYPE_IDENTITY] = "identity", - [TYPE_MISSING] = "missing", - [TYPE_PFN] = "pfn", - [TYPE_UNKNOWN] = "abnormal"}; - unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0; - unsigned int uninitialized_var(prev_level); - unsigned int uninitialized_var(prev_type); - - if (!p2m_top) - return 0; - - for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn++) { - unsigned topidx = p2m_top_index(pfn); - unsigned mididx = p2m_mid_index(pfn); - unsigned idx = p2m_index(pfn); - unsigned lvl, type; - - lvl = 4; - type = TYPE_UNKNOWN; - if (p2m_top[topidx] == p2m_mid_missing) { - lvl = 0; type = TYPE_MISSING; - } else if (p2m_top[topidx] == NULL) { - lvl = 0; type = TYPE_UNKNOWN; - } else if (p2m_top[topidx][mididx] == NULL) { - lvl = 1; type = TYPE_UNKNOWN; - } else if (p2m_top[topidx][mididx] == p2m_identity) { - lvl = 1; type = TYPE_IDENTITY; - } else if (p2m_top[topidx][mididx] == p2m_missing) { - lvl = 1; type = TYPE_MISSING; - } else if (p2m_top[topidx][mididx][idx] == 0) { - lvl = 2; type = TYPE_UNKNOWN; - } else if (p2m_top[topidx][mididx][idx] == IDENTITY_FRAME(pfn)) { - lvl = 2; type = TYPE_IDENTITY; - } else if (p2m_top[topidx][mididx][idx] == INVALID_P2M_ENTRY) { - lvl = 2; type = TYPE_MISSING; - } else if (p2m_top[topidx][mididx][idx] == pfn) { - lvl = 2; type = TYPE_PFN; - } else if (p2m_top[topidx][mididx][idx] != pfn) { - lvl = 2; type = TYPE_PFN; - } - if (pfn == 0) { - prev_level = lvl; + [P2M_TYPE_IDENTITY] = "identity", + [P2M_TYPE_MISSING] = "missing", + [P2M_TYPE_PFN] = "pfn", + [P2M_TYPE_UNKNOWN] = "abnormal"}; + unsigned long pfn, first_pfn; + int type, prev_type; + + prev_type = xen_p2m_elem_type(0); + first_pfn = 0; + + for (pfn = 0; pfn < xen_p2m_size; pfn++) { + type = xen_p2m_elem_type(pfn); + if (type != prev_type) { + seq_printf(m, " [0x%lx->0x%lx] %s\n", first_pfn, pfn, + type_name[prev_type]); prev_type = type; - } - if (pfn == MAX_DOMAIN_PAGES-1) { - lvl = 3; - type = TYPE_UNKNOWN; - } - if (prev_type != type) { - seq_printf(m, " [0x%lx->0x%lx] %s\n", - prev_pfn_type, pfn, type_name[prev_type]); - prev_pfn_type = pfn; - prev_type = type; - } - if (prev_level != lvl) { - seq_printf(m, " [0x%lx->0x%lx] level %s\n", - prev_pfn_level, pfn, level_name[prev_level]); - prev_pfn_level = pfn; - prev_level = lvl; + first_pfn = pfn; } } + seq_printf(m, " [0x%lx->0x%lx] %s\n", first_pfn, pfn, + type_name[prev_type]); return 0; -#undef TYPE_IDENTITY -#undef TYPE_MISSING -#undef TYPE_PFN -#undef TYPE_UNKNOWN } static int p2m_dump_open(struct inode *inode, struct file *filp) diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 02b0b0fba041..f92921fa54f9 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -49,7 +49,7 @@ void xen_hvm_init_shared_info(void); void xen_unplug_emulated_devices(void); void __init xen_build_dynamic_phys_to_machine(void); -unsigned long __init xen_revector_p2m_tree(void); +void __init xen_vmalloc_p2m_tree(void); void xen_init_irq_ops(void); void xen_setup_timer(int cpu); |