#include <linux/module.h>
#include <linux/gfp.h>
#include <linux/memblock.h>
+#include <linux/seq_file.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
/*
* Protects atomic reservation decrease/increase against concurrent increases.
- * Also protects non-atomic updates of current_pages and driver_pages, and
- * balloon lists.
+ * Also protects non-atomic updates of current_pages and balloon lists.
*/
DEFINE_SPINLOCK(xen_reservation_lock);
if (val & _PAGE_PRESENT) {
unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
pteval_t flags = val & PTE_FLAGS_MASK;
- unsigned long mfn = pfn_to_mfn(pfn);
+ unsigned long mfn;
+ if (!xen_feature(XENFEAT_auto_translated_physmap))
+ mfn = get_phys_to_machine(pfn);
+ else
+ mfn = pfn;
/*
* If there's no mfn for the pfn, then just create an
* empty non-present pte. Unfortunately this loses
if (unlikely(mfn == INVALID_P2M_ENTRY)) {
mfn = 0;
flags = 0;
+ } else {
+ /*
+ * Paramount to do this test _after_ the
+ * INVALID_P2M_ENTRY as INVALID_P2M_ENTRY &
+ * IDENTITY_FRAME_BIT resolves to true.
+ */
+ mfn &= ~FOREIGN_FRAME_BIT;
+ if (mfn & IDENTITY_FRAME_BIT) {
+ mfn &= ~IDENTITY_FRAME_BIT;
+ flags |= _PAGE_IOMAP;
+ }
}
-
val = ((pteval_t)mfn << PAGE_SHIFT) | flags;
}
}
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
- WARN(addr != other_addr,
+#ifdef CONFIG_XEN_DEBUG
+pte_t xen_make_pte_debug(pteval_t pte)
+{
+ phys_addr_t addr = (pte & PTE_PFN_MASK);
+ phys_addr_t other_addr;
+ bool io_page = false;
+ pte_t _pte;
+
+ if (pte & _PAGE_IOMAP)
+ io_page = true;
+
+ _pte = xen_make_pte(pte);
+
+ if (!addr)
+ return _pte;
+
+ if (io_page &&
+ (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
+ other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT;
- WARN((addr == other_addr) && (!io_page) && (!iomap_set),
+ + WARN_ONCE(addr != other_addr,
+ "0x%lx is using VM_IO, but it is 0x%lx!\n",
+ (unsigned long)addr, (unsigned long)other_addr);
+ } else {
+ pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP;
+ other_addr = (_pte.pte & PTE_PFN_MASK);
+ + WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set),
+ "0x%lx is missing VM_IO (and wasn't fixed)!\n",
+ (unsigned long)addr);
+ }
+
+ return _pte;
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug);
+#endif
+
pgd_t xen_make_pgd(pgdval_t pgd)
{
pgd = pte_pfn_to_mfn(pgd);
*/
void xen_mm_pin_all(void)
{
- unsigned long flags;
struct page *page;
- spin_lock_irqsave(&pgd_lock, flags);
+ spin_lock(&pgd_lock);
list_for_each_entry(page, &pgd_list, lru) {
if (!PagePinned(page)) {
}
}
- spin_unlock_irqrestore(&pgd_lock, flags);
+ spin_unlock(&pgd_lock);
}
/*
* that's before we have page structures to store the bits. So do all
* the book-keeping now.
*/
----static __init int xen_mark_pinned(struct mm_struct *mm, struct page *page,
++++static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
enum pt_level level)
{
SetPagePinned(page);
*/
void xen_mm_unpin_all(void)
{
- unsigned long flags;
struct page *page;
- spin_lock_irqsave(&pgd_lock, flags);
+ spin_lock(&pgd_lock);
list_for_each_entry(page, &pgd_list, lru) {
if (PageSavePinned(page)) {
}
}
- spin_unlock_irqrestore(&pgd_lock, flags);
+ spin_unlock(&pgd_lock);
}
void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
active_mm = percpu_read(cpu_tlbstate.active_mm);
---- if (active_mm == mm)
++++ if (active_mm == mm && percpu_read(cpu_tlbstate.state) != TLBSTATE_OK)
leave_mm(smp_processor_id());
/* If this cpu still has a stale cr3 reference, then make sure
spin_unlock(&mm->page_table_lock);
}
----static __init void xen_pagetable_setup_start(pgd_t *base)
++++static void __init xen_pagetable_setup_start(pgd_t *base)
{
}
++++static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
++++{
++++ /* reserve the range used */
++++ native_pagetable_reserve(start, end);
++++
++++ /* set as RW the rest */
++++ printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n", end,
++++ PFN_PHYS(pgt_buf_top));
++++ while (end < PFN_PHYS(pgt_buf_top)) {
++++ make_lowmem_page_readwrite(__va(end));
++++ end += PAGE_SIZE;
++++ }
++++}
++++
static void xen_post_allocator_init(void);
----static __init void xen_pagetable_setup_done(pgd_t *base)
++++static void __init xen_pagetable_setup_done(pgd_t *base)
{
xen_setup_shared_info();
xen_post_allocator_init();
return ret;
}
- - #ifdef CONFIG_X86_64
- - static __initdata u64 __last_pgt_set_rw = 0;
- - static __initdata u64 __pgt_buf_start = 0;
- - static __initdata u64 __pgt_buf_end = 0;
- - static __initdata u64 __pgt_buf_top = 0;
- - /*
- - * As a consequence of the commit:
- - *
- - * commit 4b239f458c229de044d6905c2b0f9fe16ed9e01e
- - * Date: Fri Dec 17 16:58:28 2010 -0800
- - *
- - * x86-64, mm: Put early page table high
- - *
- - * at some point init_memory_mapping is going to reach the pagetable pages
- - * area and map those pages too (mapping them as normal memory that falls
- - * in the range of addresses passed to init_memory_mapping as argument).
- - * Some of those pages are already pagetable pages (they are in the range
- - * pgt_buf_start-pgt_buf_end) therefore they are going to be mapped RO and
- - * everything is fine.
- - * Some of these pages are not pagetable pages yet (they fall in the range
- - * pgt_buf_end-pgt_buf_top; for example the page at pgt_buf_end) so they
- - * are going to be mapped RW. When these pages become pagetable pages and
- - * are hooked into the pagetable, xen will find that the guest has already
- - * a RW mapping of them somewhere and fail the operation.
- - * The reason Xen requires pagetables to be RO is that the hypervisor needs
- - * to verify that the pagetables are valid before using them. The validation
- - * operations are called "pinning".
- - *
- - * In order to fix the issue we mark all the pages in the entire range
- - * pgt_buf_start-pgt_buf_top as RO, however when the pagetable allocation
- - * is completed only the range pgt_buf_start-pgt_buf_end is reserved by
- - * init_memory_mapping. Hence the kernel is going to crash as soon as one
- - * of the pages in the range pgt_buf_end-pgt_buf_top is reused (b/c those
- - * ranges are RO).
- - *
- - * For this reason, 'mark_rw_past_pgt' is introduced which is called _after_
- - * the init_memory_mapping has completed (in a perfect world we would
- - * call this function from init_memory_mapping, but lets ignore that).
- - *
- - * Because we are called _after_ init_memory_mapping the pgt_buf_[start,
- - * end,top] have all changed to new values (b/c init_memory_mapping
- - * is called and setting up another new page-table). Hence, the first time
- - * we enter this function, we save away the pgt_buf_start value and update
- - * the pgt_buf_[end,top].
- - *
- - * When we detect that the "old" pgt_buf_start through pgt_buf_end
- - * PFNs have been reserved (so memblock_x86_reserve_range has been called),
- - * we immediately set out to RW the "old" pgt_buf_end through pgt_buf_top.
- - *
- - * And then we update those "old" pgt_buf_[end|top] with the new ones
- - * so that we can redo this on the next pagetable.
- - */
- - static __init void mark_rw_past_pgt(void) {
- -
- - if (pgt_buf_end > pgt_buf_start) {
- - u64 addr, size;
- -
- - /* Save it away. */
- - if (!__pgt_buf_start) {
- - __pgt_buf_start = pgt_buf_start;
- - __pgt_buf_end = pgt_buf_end;
- - __pgt_buf_top = pgt_buf_top;
- - return;
- - }
- - /* If we get the range that starts at __pgt_buf_end that means
- - * the range is reserved, and that in 'init_memory_mapping'
- - * the 'memblock_x86_reserve_range' has been called with the
- - * outdated __pgt_buf_start, __pgt_buf_end (the "new"
- - * pgt_buf_[start|end|top] refer now to a new pagetable.
- - * Note: we are called _after_ the pgt_buf_[..] have been
- - * updated.*/
- -
- - addr = memblock_x86_find_in_range_size(PFN_PHYS(__pgt_buf_start),
- - &size, PAGE_SIZE);
- -
- - /* Still not reserved, meaning 'memblock_x86_reserve_range'
- - * hasn't been called yet. Update the _end and _top.*/
- - if (addr == PFN_PHYS(__pgt_buf_start)) {
- - __pgt_buf_end = pgt_buf_end;
- - __pgt_buf_top = pgt_buf_top;
- - return;
- - }
- -
- - /* OK, the area is reserved, meaning it is time for us to
- - * set RW for the old end->top PFNs. */
- -
- - /* ..unless we had already done this. */
- - if (__pgt_buf_end == __last_pgt_set_rw)
- - return;
- -
- - addr = PFN_PHYS(__pgt_buf_end);
- -
- - /* set as RW the rest */
- - printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n",
- - PFN_PHYS(__pgt_buf_end), PFN_PHYS(__pgt_buf_top));
- -
- - while (addr < PFN_PHYS(__pgt_buf_top)) {
- - make_lowmem_page_readwrite(__va(addr));
- - addr += PAGE_SIZE;
- - }
- - /* And update everything so that we are ready for the next
- - * pagetable (the one created for regions past 4GB) */
- - __last_pgt_set_rw = __pgt_buf_end;
- - __pgt_buf_start = pgt_buf_start;
- - __pgt_buf_end = pgt_buf_end;
- - __pgt_buf_top = pgt_buf_top;
- - }
- - return;
- - }
- - #else
- - static __init void mark_rw_past_pgt(void) { }
- - #endif
static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
#ifdef CONFIG_X86_64
#endif
}
- -static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
- -{
- - unsigned long pfn = pte_pfn(pte);
- -
#ifdef CONFIG_X86_32
- - static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
++++static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
+ +{
/* If there's an existing pte, then don't allow _PAGE_RW to be set */
if (pte_val_ma(*ptep) & _PAGE_PRESENT)
pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
pte_val_ma(pte));
- -#endif
+ +
+ + return pte;
+ +}
+ +#else /* CONFIG_X86_64 */
- - static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
++++static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
+ +{
+ + unsigned long pfn = pte_pfn(pte);
- - /*
- - * A bit of optimization. We do not need to call the workaround
- - * when xen_set_pte_init is called with a PTE with 0 as PFN.
- - * That is b/c the pagetable at that point are just being populated
- - * with empty values and we can save some cycles by not calling
- - * the 'memblock' code.*/
- - if (pfn)
- - mark_rw_past_pgt();
/*
* If the new pfn is within the range of the newly allocated
* kernel pagetable, and it isn't being mapped into an
- * early_ioremap fixmap slot, make sure it is RO.
+ * early_ioremap fixmap slot as a freshly allocated page, make sure
+ * it is RO.
*/
- if (!is_early_ioremap_ptep(ptep) &&
- pfn >= e820_table_start && pfn < e820_table_end)
+ if (((!is_early_ioremap_ptep(ptep) &&
- pfn >= pgt_buf_start && pfn < pgt_buf_end)) ||
+ + pfn >= pgt_buf_start && pfn < pgt_buf_top)) ||
+ (is_early_ioremap_ptep(ptep) && pfn != (pgt_buf_end - 1)))
pte = pte_wrprotect(pte);
return pte;
}
+ +#endif /* CONFIG_X86_64 */
/* Init-time set_pte while constructing initial pagetables, which
doesn't allow RO pagetable pages to be remapped RW */
----static __init void xen_set_pte_init(pte_t *ptep, pte_t pte)
++++static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
{
pte = mask_rw_pte(ptep, pte);
/* Early in boot, while setting up the initial pagetable, assume
everything is pinned. */
----static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
++++static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
{
#ifdef CONFIG_FLATMEM
BUG_ON(mem_map); /* should only be used early */
}
/* Used for pmd and pud */
----static __init void xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
++++static void __init xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
{
#ifdef CONFIG_FLATMEM
BUG_ON(mem_map); /* should only be used early */
/* Early release_pte assumes that all pts are pinned, since there's
only init_mm and anything attached to that is pinned. */
----static __init void xen_release_pte_init(unsigned long pfn)
++++static void __init xen_release_pte_init(unsigned long pfn)
{
pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
}
----static __init void xen_release_pmd_init(unsigned long pfn)
++++static void __init xen_release_pmd_init(unsigned long pfn)
{
make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
}
BUG();
}
----static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
++++static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
{
unsigned pmdidx, pteidx;
unsigned ident_pte;
for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
pte_t pte;
- if (pfn > max_pfn_mapped)
- max_pfn_mapped = pfn;
-
if (!pte_none(pte_page[pteidx]))
continue;
}
/*
- * Set up the inital kernel pagetable.
+ * Set up the initial kernel pagetable.
*
* We can construct this by grafting the Xen provided pagetable into
* head_64.S's preconstructed pagetables. We copy the Xen L2's into
* of the physical mapping once some sort of allocator has been set
* up.
*/
----__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
++++pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
unsigned long max_pfn)
{
pud_t *l3;
pmd_t *l2;
+ /* max_pfn_mapped is the last pfn mapped in the initial memory
+ * mappings. Considering that on Xen after the kernel mappings we
+ * have the mappings of some pages that don't exist in pfn space, we
+ * set max_pfn_mapped to the last real pfn mapped. */
+ max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
+
/* Zap identity mapping */
init_level4_pgt[0] = __pgd(0);
static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
----static __init void xen_write_cr3_init(unsigned long cr3)
++++static void __init xen_write_cr3_init(unsigned long cr3)
{
unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir));
pv_mmu_ops.write_cr3 = &xen_write_cr3;
}
----__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
++++pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
unsigned long max_pfn)
{
pmd_t *kernel_pmd;
initial_kernel_pmd =
extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
- max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
- xen_start_info->nr_pt_frames * PAGE_SIZE +
- 512*1024);
+ max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
#endif
}
----__init void xen_ident_map_ISA(void)
++++void __init xen_ident_map_ISA(void)
{
unsigned long pa;
xen_flush_tlb();
}
----static __init void xen_post_allocator_init(void)
++++static void __init xen_post_allocator_init(void)
{
- - mark_rw_past_pgt();
- -
+#ifdef CONFIG_XEN_DEBUG
+ pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
+#endif
pv_mmu_ops.set_pte = xen_set_pte;
pv_mmu_ops.set_pmd = xen_set_pmd;
pv_mmu_ops.set_pud = xen_set_pud;
preempt_enable();
}
----static const struct pv_mmu_ops xen_mmu_ops __initdata = {
++++static const struct pv_mmu_ops xen_mmu_ops __initconst = {
.read_cr2 = xen_read_cr2,
.write_cr2 = xen_write_cr2,
void __init xen_init_mmu_ops(void)
{
++++ x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve;
x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
pv_mmu_ops = xen_mmu_ops;
in_frames[i] = virt_to_mfn(vaddr);
MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0);
- set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
+ __set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
if (out_frames)
out_frames[i] = virt_to_pfn(vaddr);
#ifdef CONFIG_XEN_DEBUG_FS
+static int p2m_dump_open(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, p2m_dump_show, NULL);
+}
+
+static const struct file_operations p2m_dump_fops = {
+ .open = p2m_dump_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
static struct dentry *d_mmu_debug;
static int __init xen_mmu_debugfs(void)
debugfs_create_u32("prot_commit_batched", 0444, d_mmu_debug,
&mmu_stats.prot_commit_batched);
+ debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops);
return 0;
}
fs_initcall(xen_mmu_debugfs);
* P2M_PER_PAGE depends on the architecture, as a mfn is always
* unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to
* 512 and 1024 entries respectively.
+ *
+ * In short, these structures contain the Machine Frame Number (MFN) of the PFN.
+ *
+ * However not all entries are filled with MFNs. Specifically for all other
+ * 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 also have the possibility of setting 1-1 mappings on certain regions, so
+ * that:
+ * pfn_to_mfn(0xc0000)=0xc0000
+ *
+ * The benefit of this is, that we can assume for non-RAM regions (think
+ * PCI BARs, or ACPI spaces), we can create mappings easily b/c 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).
+ *
+ * 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
+ * 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
+ * /-------------------+---------\/----\ /----------\ /---+-----\
+ * | 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 loop on aligned 1GB PFNs from start pfn
+ * to end pfn. We reserve_brk top leaf pages if they are missing (means they
+ * point to p2m_mid_missing).
+ *
+ * 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 middle (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 leaf is pointing to p2m_missing we can swap it
+ * over to p2m_identity - this way covering 4MB (or 2MB) PFN space. 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."
+ *
+ * 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
+ * |-----| \ \-------------------->/---------------\ /-----------------\
+ * | .. +->+ | [p2m_identity]+-->| ~0, ~0, ~0, ... |
+ * \-----/ / | [p2m_identity]+-->| ..., ~0 |
+ * / /---------------\ | .... | \-----------------/
+ * / | IDENTITY[@0] | /-+-[x], ~0, ~0.. |
+ * / | IDENTITY[@256]|<----/ \---------------/
+ * / | ~0, ~0, .... |
+ * | \---------------/
+ * |
+ * p2m_missing p2m_missing
+ * /------------------\ /------------\
+ * | [p2m_mid_missing]+---->| ~0, ~0, ~0 |
+ * | [p2m_mid_missing]+---->| ..., ~0 |
+ * \------------------/ \------------/
+ *
+ * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT)
*/
#include <linux/init.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/sched.h>
+#include <linux/seq_file.h>
#include <asm/cache.h>
#include <asm/setup.h>
static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE);
+static RESERVE_BRK_ARRAY(unsigned long, p2m_identity, P2M_PER_PAGE);
+
RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
+/* We might hit two boundary violations at the start and end, at max each
+ * boundary violation will require three middle nodes. */
+RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3);
+
static inline unsigned p2m_top_index(unsigned long pfn)
{
BUG_ON(pfn >= MAX_P2M_PFN);
* - After resume we're called from within stop_machine, but the mfn
* tree should alreay be completely allocated.
*/
-void xen_build_mfn_list_list(void)
+void __ref xen_build_mfn_list_list(void)
{
unsigned long pfn;
p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_top_init(p2m_top);
+ p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_init(p2m_identity);
+
/*
* The domain builder gives us a pre-constructed p2m array in
* mfn_list for all the pages initially given to us, so we just
mididx = p2m_mid_index(pfn);
idx = p2m_index(pfn);
+ /*
+ * 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)
+ return IDENTITY_FRAME(pfn);
+
return p2m_top[topidx][mididx][idx];
}
EXPORT_SYMBOL_GPL(get_phys_to_machine);
p2m_top_mfn_p[topidx] = mid_mfn;
}
- if (p2m_top[topidx][mididx] == p2m_missing) {
+ if (p2m_top[topidx][mididx] == p2m_identity ||
+ p2m_top[topidx][mididx] == p2m_missing) {
/* p2m leaf page is missing */
unsigned long *p2m;
+ unsigned long *p2m_orig = p2m_top[topidx][mididx];
p2m = alloc_p2m_page();
if (!p2m)
p2m_init(p2m);
- if (cmpxchg(&mid[mididx], p2m_missing, p2m) != p2m_missing)
+ if (cmpxchg(&mid[mididx], p2m_orig, p2m) != p2m_orig)
free_p2m_page(p2m);
else
mid_mfn[mididx] = virt_to_mfn(p2m);
return true;
}
-- - if (p2m_top[topidx] == p2m_mid_missing) {
-- - unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
+static bool __init __early_alloc_p2m(unsigned long pfn)
+{
+ unsigned topidx, mididx, idx;
+
+ topidx = p2m_top_index(pfn);
+ mididx = p2m_mid_index(pfn);
+ idx = p2m_index(pfn);
+
+ /* Pfff.. No boundary cross-over, lets get out. */
+ if (!idx)
+ return false;
+
+ WARN(p2m_top[topidx][mididx] == p2m_identity,
+ "P2M[%d][%d] == IDENTITY, should be MISSING (or alloced)!\n",
+ topidx, mididx);
+
+ /*
+ * Could be done by xen_build_dynamic_phys_to_machine..
+ */
+ if (p2m_top[topidx][mididx] != p2m_missing)
+ return false;
+
+ /* Boundary cross-over for the edges: */
+ if (idx) {
+ unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
++ ++ unsigned long *mid_mfn_p;
+
+ p2m_init(p2m);
+
+ p2m_top[topidx][mididx] = p2m;
+
++ ++ /* For save/restore we need to MFN of the P2M saved */
++ ++
++ ++ mid_mfn_p = p2m_top_mfn_p[topidx];
++ ++ WARN(mid_mfn_p[mididx] != virt_to_mfn(p2m_missing),
++ ++ "P2M_TOP_P[%d][%d] != MFN of p2m_missing!\n",
++ ++ topidx, mididx);
++ ++ mid_mfn_p[mididx] = virt_to_mfn(p2m);
++ ++
+ }
+ return idx != 0;
+}
+unsigned long __init set_phys_range_identity(unsigned long pfn_s,
+ unsigned long pfn_e)
+{
+ unsigned long pfn;
+
+ if (unlikely(pfn_s >= MAX_P2M_PFN || pfn_e >= MAX_P2M_PFN))
+ return 0;
+
+ if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
+ return pfn_e - pfn_s;
+
+ if (pfn_s > pfn_e)
+ return 0;
+
+ for (pfn = (pfn_s & ~(P2M_MID_PER_PAGE * P2M_PER_PAGE - 1));
+ pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE));
+ pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
+ {
+ unsigned topidx = p2m_top_index(pfn);
++ ++ unsigned long *mid_mfn_p;
++ ++ unsigned long **mid;
++ ++
++ ++ mid = p2m_top[topidx];
++ ++ mid_mfn_p = p2m_top_mfn_p[topidx];
++ ++ if (mid == p2m_mid_missing) {
++ ++ mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
+
+ p2m_mid_init(mid);
+
+ p2m_top[topidx] = mid;
++ ++
++ ++ BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
++ ++ }
++ ++ /* And the save/restore P2M tables.. */
++ ++ if (mid_mfn_p == p2m_mid_missing_mfn) {
++ ++ mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
++ ++ p2m_mid_mfn_init(mid_mfn_p);
++ ++
++ ++ p2m_top_mfn_p[topidx] = mid_mfn_p;
++ ++ p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
++ ++ /* Note: we don't set mid_mfn_p[midix] here,
++ ++ * look in __early_alloc_p2m */
+ }
+ }
+
+ __early_alloc_p2m(pfn_s);
+ __early_alloc_p2m(pfn_e);
+
+ for (pfn = pfn_s; pfn < pfn_e; pfn++)
+ if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn)))
+ break;
+
+ if (!WARN((pfn - pfn_s) != (pfn_e - pfn_s),
+ "Identity mapping failed. We are %ld short of 1-1 mappings!\n",
+ (pfn_e - pfn_s) - (pfn - pfn_s)))
+ printk(KERN_DEBUG "1-1 mapping on %lx->%lx\n", pfn_s, pfn);
+
+ 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;
+ if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
+ BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
+ return true;
+ }
if (unlikely(pfn >= MAX_P2M_PFN)) {
BUG_ON(mfn != INVALID_P2M_ENTRY);
return true;
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.
+ */
+ if (mfn != INVALID_P2M_ENTRY && (mfn & IDENTITY_FRAME_BIT)) {
+ 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;
+ }
+ }
+
if (p2m_top[topidx][mididx] == p2m_missing)
return mfn == INVALID_P2M_ENTRY;
bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
- if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
- BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
- return true;
- }
-
if (unlikely(!__set_phys_to_machine(pfn, mfn))) {
if (!alloc_p2m(pfn))
return false;
}
/* Add an MFN override for a particular page */
----int m2p_add_override(unsigned long mfn, struct page *page)
++++int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte)
{
unsigned long flags;
unsigned long pfn;
- unsigned long address;
+ unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
if (!PageHighMem(page)) {
address = (unsigned long)__va(pfn << PAGE_SHIFT);
ptep = lookup_address(address, &level);
----
if (WARN(ptep == NULL || level != PG_LEVEL_4K,
"m2p_add_override: pfn %lx not mapped", pfn))
return -EINVAL;
page->private = mfn;
page->index = pfn_to_mfn(pfn);
- __set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
- if (!PageHighMem(page))
+ if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn))))
+ return -ENOMEM;
+
--- if (!PageHighMem(page))
++++ if (clear_pte && !PageHighMem(page))
/* Just zap old mapping for now */
pte_clear(&init_mm, address, ptep);
----
spin_lock_irqsave(&m2p_override_lock, flags);
list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]);
spin_unlock_irqrestore(&m2p_override_lock, flags);
return 0;
}
----
----int m2p_remove_override(struct page *page)
++++EXPORT_SYMBOL_GPL(m2p_add_override);
++++int m2p_remove_override(struct page *page, bool clear_pte)
{
unsigned long flags;
unsigned long mfn;
unsigned long pfn;
- unsigned long address;
+ unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
spin_lock_irqsave(&m2p_override_lock, flags);
list_del(&page->lru);
spin_unlock_irqrestore(&m2p_override_lock, flags);
- __set_phys_to_machine(pfn, page->index);
+ set_phys_to_machine(pfn, page->index);
---- if (!PageHighMem(page))
++++ if (clear_pte && !PageHighMem(page))
set_pte_at(&init_mm, address, ptep,
pfn_pte(pfn, PAGE_KERNEL));
/* No tlb flush necessary because the caller already
return 0;
}
++++EXPORT_SYMBOL_GPL(m2p_remove_override);
struct page *m2p_find_override(unsigned long mfn)
{
return ret;
}
EXPORT_SYMBOL_GPL(m2p_find_override_pfn);
+
+#ifdef CONFIG_XEN_DEBUG_FS
+
+int p2m_dump_show(struct seq_file *m, void *v)
+{
+ static const char * const level_name[] = { "top", "middle",
+ "entry", "abnormal" };
+ static const char * const type_name[] = { "identity", "missing",
+ "pfn", "abnormal"};
+#define TYPE_IDENTITY 0
+#define TYPE_MISSING 1
+#define TYPE_PFN 2
+#define TYPE_UNKNOWN 3
+ 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;
+ 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;
+ }
+ }
+ return 0;
+#undef TYPE_IDENTITY
+#undef TYPE_MISSING
+#undef TYPE_PFN
+#undef TYPE_UNKNOWN
+}
+#endif
* domain gets 1024 event channels, but NR_IRQ is not that large, we
* must dynamically map irqs<->event channels. The event channels
* interface with the rest of the kernel by defining a xen interrupt
- - * chip. When an event is recieved, it is mapped to an irq and sent
+ + * chip. When an event is received, it is mapped to an irq and sent
* through the normal interrupt processing path.
*
* There are four kinds of events which can be mapped to an event
*/
static DEFINE_SPINLOCK(irq_mapping_update_lock);
+static LIST_HEAD(xen_irq_list_head);
+
/* IRQ <-> VIRQ mapping. */
static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};
*/
struct irq_info
{
+ struct list_head list;
enum xen_irq_type type; /* type */
+ unsigned irq;
unsigned short evtchn; /* event channel */
unsigned short cpu; /* cpu bound */
unsigned short gsi;
unsigned char vector;
unsigned char flags;
++++ uint16_t domid;
} pirq;
} u;
};
#define PIRQ_NEEDS_EOI (1 << 0)
#define PIRQ_SHAREABLE (1 << 1)
-static struct irq_info *irq_info;
-static int *pirq_to_irq;
-
static int *evtchn_to_irq;
-struct cpu_evtchn_s {
- unsigned long bits[NR_EVENT_CHANNELS/BITS_PER_LONG];
-};
-static __initdata struct cpu_evtchn_s init_evtchn_mask = {
- .bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul,
-};
-static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask;
-
-static inline unsigned long *cpu_evtchn_mask(int cpu)
-{
- return cpu_evtchn_mask_p[cpu].bits;
-}
+static DEFINE_PER_CPU(unsigned long [NR_EVENT_CHANNELS/BITS_PER_LONG],
+ cpu_evtchn_mask);
/* Xen will never allocate port zero for any purpose. */
#define VALID_EVTCHN(chn) ((chn) != 0)
static struct irq_chip xen_dynamic_chip;
static struct irq_chip xen_percpu_chip;
static struct irq_chip xen_pirq_chip;
+ +++static void enable_dynirq(struct irq_data *data);
+ +++static void disable_dynirq(struct irq_data *data);
+
+/* Get info for IRQ */
+static struct irq_info *info_for_irq(unsigned irq)
+{
+ return irq_get_handler_data(irq);
+}
-/* Constructor for packed IRQ information. */
-static struct irq_info mk_unbound_info(void)
+/* Constructors for packed IRQ information. */
+static void xen_irq_info_common_init(struct irq_info *info,
+ unsigned irq,
+ enum xen_irq_type type,
+ unsigned short evtchn,
+ unsigned short cpu)
{
- return (struct irq_info) { .type = IRQT_UNBOUND };
+
+ BUG_ON(info->type != IRQT_UNBOUND && info->type != type);
+
+ info->type = type;
+ info->irq = irq;
+ info->evtchn = evtchn;
+ info->cpu = cpu;
+
+ evtchn_to_irq[evtchn] = irq;
}
-static struct irq_info mk_evtchn_info(unsigned short evtchn)
+static void xen_irq_info_evtchn_init(unsigned irq,
+ unsigned short evtchn)
{
- return (struct irq_info) { .type = IRQT_EVTCHN, .evtchn = evtchn,
- .cpu = 0 };
+ struct irq_info *info = info_for_irq(irq);
+
+ xen_irq_info_common_init(info, irq, IRQT_EVTCHN, evtchn, 0);
}
-static struct irq_info mk_ipi_info(unsigned short evtchn, enum ipi_vector ipi)
+static void xen_irq_info_ipi_init(unsigned cpu,
+ unsigned irq,
+ unsigned short evtchn,
+ enum ipi_vector ipi)
{
- return (struct irq_info) { .type = IRQT_IPI, .evtchn = evtchn,
- .cpu = 0, .u.ipi = ipi };
+ struct irq_info *info = info_for_irq(irq);
+
+ xen_irq_info_common_init(info, irq, IRQT_IPI, evtchn, 0);
+
+ info->u.ipi = ipi;
+
+ per_cpu(ipi_to_irq, cpu)[ipi] = irq;
}
-static struct irq_info mk_virq_info(unsigned short evtchn, unsigned short virq)
+static void xen_irq_info_virq_init(unsigned cpu,
+ unsigned irq,
+ unsigned short evtchn,
+ unsigned short virq)
{
- return (struct irq_info) { .type = IRQT_VIRQ, .evtchn = evtchn,
- .cpu = 0, .u.virq = virq };
+ struct irq_info *info = info_for_irq(irq);
+
+ xen_irq_info_common_init(info, irq, IRQT_VIRQ, evtchn, 0);
+
+ info->u.virq = virq;
+
+ per_cpu(virq_to_irq, cpu)[virq] = irq;
}
-static struct irq_info mk_pirq_info(unsigned short evtchn, unsigned short pirq,
- unsigned short gsi, unsigned short vector)
+static void xen_irq_info_pirq_init(unsigned irq,
+ unsigned short evtchn,
+ unsigned short pirq,
+ unsigned short gsi,
+ unsigned short vector,
++++ uint16_t domid,
+ unsigned char flags)
{
- return (struct irq_info) { .type = IRQT_PIRQ, .evtchn = evtchn,
- .cpu = 0,
- .u.pirq = { .pirq = pirq, .gsi = gsi, .vector = vector } };
+ struct irq_info *info = info_for_irq(irq);
+
+ xen_irq_info_common_init(info, irq, IRQT_PIRQ, evtchn, 0);
+
+ info->u.pirq.pirq = pirq;
+ info->u.pirq.gsi = gsi;
+ info->u.pirq.vector = vector;
++++ info->u.pirq.domid = domid;
+ info->u.pirq.flags = flags;
}
/*
* Accessors for packed IRQ information.
*/
-static struct irq_info *info_for_irq(unsigned irq)
-{
- return &irq_info[irq];
-}
-
static unsigned int evtchn_from_irq(unsigned irq)
{
if (unlikely(WARN(irq < 0 || irq >= nr_irqs, "Invalid irq %d!\n", irq)))
return info->u.pirq.pirq;
}
-static unsigned gsi_from_irq(unsigned irq)
-{
- struct irq_info *info = info_for_irq(irq);
-
- BUG_ON(info == NULL);
- BUG_ON(info->type != IRQT_PIRQ);
-
- return info->u.pirq.gsi;
-}
-
-static unsigned vector_from_irq(unsigned irq)
-{
- struct irq_info *info = info_for_irq(irq);
-
- BUG_ON(info == NULL);
- BUG_ON(info->type != IRQT_PIRQ);
-
- return info->u.pirq.vector;
-}
-
static enum xen_irq_type type_from_irq(unsigned irq)
{
return info_for_irq(irq)->type;
unsigned int idx)
{
return (sh->evtchn_pending[idx] &
- cpu_evtchn_mask(cpu)[idx] &
+ per_cpu(cpu_evtchn_mask, cpu)[idx] &
~sh->evtchn_mask[idx]);
}
BUG_ON(irq == -1);
#ifdef CONFIG_SMP
- cpumask_copy(irq_to_desc(irq)->affinity, cpumask_of(cpu));
+ cpumask_copy(irq_to_desc(irq)->irq_data.affinity, cpumask_of(cpu));
#endif
- clear_bit(chn, cpu_evtchn_mask(cpu_from_irq(irq)));
- set_bit(chn, cpu_evtchn_mask(cpu));
+ clear_bit(chn, per_cpu(cpu_evtchn_mask, cpu_from_irq(irq)));
+ set_bit(chn, per_cpu(cpu_evtchn_mask, cpu));
- irq_info[irq].cpu = cpu;
+ info_for_irq(irq)->cpu = cpu;
}
static void init_evtchn_cpu_bindings(void)
{
int i;
#ifdef CONFIG_SMP
- struct irq_desc *desc;
+ struct irq_info *info;
/* By default all event channels notify CPU#0. */
- for_each_irq_desc(i, desc) {
- cpumask_copy(desc->affinity, cpumask_of(0));
+ list_for_each_entry(info, &xen_irq_list_head, list) {
+ struct irq_desc *desc = irq_to_desc(info->irq);
+ cpumask_copy(desc->irq_data.affinity, cpumask_of(0));
}
#endif
for_each_possible_cpu(i)
- memset(cpu_evtchn_mask(i),
- (i == 0) ? ~0 : 0, sizeof(struct cpu_evtchn_s));
-
+ memset(per_cpu(cpu_evtchn_mask, i),
+ (i == 0) ? ~0 : 0, sizeof(*per_cpu(cpu_evtchn_mask, i)));
}
static inline void clear_evtchn(int port)
put_cpu();
}
-static int get_nr_hw_irqs(void)
+static void xen_irq_init(unsigned irq)
{
- int ret = 1;
+ struct irq_info *info;
+ struct irq_desc *desc = irq_to_desc(irq);
-#ifdef CONFIG_X86_IO_APIC
- ret = get_nr_irqs_gsi();
+#ifdef CONFIG_SMP
+ /* By default all event channels notify CPU#0. */
+ cpumask_copy(desc->irq_data.affinity, cpumask_of(0));
#endif
- return ret;
-}
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+ if (info == NULL)
+ panic("Unable to allocate metadata for IRQ%d\n", irq);
-static int find_unbound_pirq(int type)
-{
- int rc, i;
- struct physdev_get_free_pirq op_get_free_pirq;
- op_get_free_pirq.type = type;
+ info->type = IRQT_UNBOUND;
- rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);
- if (!rc)
- return op_get_free_pirq.pirq;
+ irq_set_handler_data(irq, info);
- for (i = 0; i < nr_irqs; i++) {
- if (pirq_to_irq[i] < 0)
- return i;
- }
- return -1;
+ list_add_tail(&info->list, &xen_irq_list_head);
}
-static int find_unbound_irq(void)
+static int __must_check xen_allocate_irq_dynamic(void)
{
- struct irq_data *data;
- int irq, res;
- int bottom = get_nr_hw_irqs();
- int top = nr_irqs-1;
-
- if (bottom == nr_irqs)
- goto no_irqs;
+ int first = 0;
+ int irq;
- /* This loop starts from the top of IRQ space and goes down.
- * We need this b/c if we have a PCI device in a Xen PV guest
- * we do not have an IO-APIC (though the backend might have them)
- * mapped in. To not have a collision of physical IRQs with the Xen
- * event channels start at the top of the IRQ space for virtual IRQs.
+#ifdef CONFIG_X86_IO_APIC
+ /*
+ * For an HVM guest or domain 0 which see "real" (emulated or
- * actual repectively) GSIs we allocate dynamic IRQs
+ + * actual respectively) GSIs we allocate dynamic IRQs
+ * e.g. those corresponding to event channels or MSIs
+ * etc. from the range above those "real" GSIs to avoid
+ * collisions.
*/
- for (irq = top; irq > bottom; irq--) {
- data = irq_get_irq_data(irq);
- /* only 15->0 have init'd desc; handle irq > 16 */
- if (!data)
- break;
- if (data->chip == &no_irq_chip)
- break;
- if (data->chip != &xen_dynamic_chip)
- continue;
- if (irq_info[irq].type == IRQT_UNBOUND)
- return irq;
- }
-
- if (irq == bottom)
- goto no_irqs;
+ if (xen_initial_domain() || xen_hvm_domain())
+ first = get_nr_irqs_gsi();
+#endif
- res = irq_alloc_desc_at(irq, -1);
+ irq = irq_alloc_desc_from(first, -1);
- if (WARN_ON(res != irq))
- return -1;
+ xen_irq_init(irq);
return irq;
-
-no_irqs:
- panic("No available IRQ to bind to: increase nr_irqs!\n");
}
-static bool identity_mapped_irq(unsigned irq)
+static int __must_check xen_allocate_irq_gsi(unsigned gsi)
{
- /* identity map all the hardware irqs */
- return irq < get_nr_hw_irqs();
+ int irq;
+
+ /*
+ * A PV guest has no concept of a GSI (since it has no ACPI
+ * nor access to/knowledge of the physical APICs). Therefore
+ * all IRQs are dynamically allocated from the entire IRQ
+ * space.
+ */
+ if (xen_pv_domain() && !xen_initial_domain())
+ return xen_allocate_irq_dynamic();
+
+ /* Legacy IRQ descriptors are already allocated by the arch. */
+ if (gsi < NR_IRQS_LEGACY)
+ irq = gsi;
+ else
+ irq = irq_alloc_desc_at(gsi, -1);
+
+ xen_irq_init(irq);
+
+ return irq;
}
-static void pirq_unmask_notify(int irq)
+static void xen_free_irq(unsigned irq)
{
- struct physdev_eoi eoi = { .irq = pirq_from_irq(irq) };
+ struct irq_info *info = irq_get_handler_data(irq);
- if (unlikely(pirq_needs_eoi(irq))) {
- int rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
- WARN_ON(rc);
- }
+ list_del(&info->list);
+
+ irq_set_handler_data(irq, NULL);
+
+ kfree(info);
+
+ /* Legacy IRQ descriptors are managed by the arch. */
+ if (irq < NR_IRQS_LEGACY)
+ return;
+
+ irq_free_desc(irq);
}
- -- static void pirq_unmask_notify(int irq)
- -- {
- -- struct physdev_eoi eoi = { .irq = pirq_from_irq(irq) };
- --
- -- if (unlikely(pirq_needs_eoi(irq))) {
- -- int rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
- -- WARN_ON(rc);
- -- }
- -- }
- --
static void pirq_query_unmask(int irq)
{
struct physdev_irq_status_query irq_status;
return desc && desc->action == NULL;
}
-static unsigned int startup_pirq(unsigned int irq)
+ +++static void eoi_pirq(struct irq_data *data)
+ +++{
+ +++ int evtchn = evtchn_from_irq(data->irq);
+ +++ struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
+ +++ int rc = 0;
+ +++
+ +++ irq_move_irq(data);
+ +++
+ +++ if (VALID_EVTCHN(evtchn))
+ +++ clear_evtchn(evtchn);
+ +++
+ +++ if (pirq_needs_eoi(data->irq)) {
+ +++ rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
+ +++ WARN_ON(rc);
+ +++ }
+ +++}
+ +++
+ +++static void mask_ack_pirq(struct irq_data *data)
+ +++{
+ +++ disable_dynirq(data);
+ +++ eoi_pirq(data);
+ +++}
+ +++
+static unsigned int __startup_pirq(unsigned int irq)
{
struct evtchn_bind_pirq bind_pirq;
struct irq_info *info = info_for_irq(irq);
out:
unmask_evtchn(evtchn);
- --- pirq_unmask_notify(irq);
+ +++ eoi_pirq(irq_get_irq_data(irq));
return 0;
}
-static void shutdown_pirq(unsigned int irq)
+static unsigned int startup_pirq(struct irq_data *data)
+{
+ return __startup_pirq(data->irq);
+}
+
+static void shutdown_pirq(struct irq_data *data)
{
struct evtchn_close close;
+ unsigned int irq = data->irq;
struct irq_info *info = info_for_irq(irq);
int evtchn = evtchn_from_irq(irq);
info->evtchn = 0;
}
-static void enable_pirq(unsigned int irq)
+static void enable_pirq(struct irq_data *data)
{
- startup_pirq(irq);
+ startup_pirq(data);
}
-static void disable_pirq(unsigned int irq)
+static void disable_pirq(struct irq_data *data)
{
- ---}
- ---
- -- static void ack_pirq(struct irq_data *data)
-static void ack_pirq(unsigned int irq)
- ---{
- -- int evtchn = evtchn_from_irq(data->irq);
- int evtchn = evtchn_from_irq(irq);
- ---
- -- irq_move_irq(data);
- move_native_irq(irq);
- ---
- --- if (VALID_EVTCHN(evtchn)) {
- --- mask_evtchn(evtchn);
- --- clear_evtchn(evtchn);
- }
-}
-
-static void end_pirq(unsigned int irq)
-{
- int evtchn = evtchn_from_irq(irq);
- struct irq_desc *desc = irq_to_desc(irq);
-
- if (WARN_ON(!desc))
- return;
-
- if ((desc->status & (IRQ_DISABLED|IRQ_PENDING)) ==
- (IRQ_DISABLED|IRQ_PENDING)) {
- shutdown_pirq(irq);
- } else if (VALID_EVTCHN(evtchn)) {
- unmask_evtchn(evtchn);
- pirq_unmask_notify(irq);
- --- }
+ +++ disable_dynirq(data);
}
static int find_irq_by_gsi(unsigned gsi)
{
- int irq;
-
- for (irq = 0; irq < nr_irqs; irq++) {
- struct irq_info *info = info_for_irq(irq);
+ struct irq_info *info;
- if (info == NULL || info->type != IRQT_PIRQ)
+ list_for_each_entry(info, &xen_irq_list_head, list) {
+ if (info->type != IRQT_PIRQ)
continue;
- if (gsi_from_irq(irq) == gsi)
- return irq;
+ if (info->u.pirq.gsi == gsi)
+ return info->irq;
}
return -1;
}
-int xen_allocate_pirq(unsigned gsi, int shareable, char *name)
+int xen_allocate_pirq_gsi(unsigned gsi)
{
- return xen_map_pirq_gsi(gsi, gsi, shareable, name);
+ return gsi;
}
-/* xen_map_pirq_gsi might allocate irqs from the top down, as a
- * consequence don't assume that the irq number returned has a low value
- * or can be used as a pirq number unless you know otherwise.
- *
- * One notable exception is when xen_map_pirq_gsi is called passing an
- * hardware gsi as argument, in that case the irq number returned
- * matches the gsi number passed as second argument.
+/*
+ * Do not make any assumptions regarding the relationship between the
+ * IRQ number returned here and the Xen pirq argument.
*
* Note: We don't assign an event channel until the irq actually started
* up. Return an existing irq if we've already got one for the gsi.
*/
-int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name)
+int xen_bind_pirq_gsi_to_irq(unsigned gsi,
+ unsigned pirq, int shareable, char *name)
{
- int irq = 0;
+ int irq = -1;
struct physdev_irq irq_op;
spin_lock(&irq_mapping_update_lock);
- if ((pirq > nr_irqs) || (gsi > nr_irqs)) {
- printk(KERN_WARNING "xen_map_pirq_gsi: %s %s is incorrect!\n",
- pirq > nr_irqs ? "pirq" :"",
- gsi > nr_irqs ? "gsi" : "");
- goto out;
- }
-
irq = find_irq_by_gsi(gsi);
if (irq != -1) {
printk(KERN_INFO "xen_map_pirq_gsi: returning irq %d for gsi %u\n",
goto out; /* XXX need refcount? */
}
- /* If we are a PV guest, we don't have GSIs (no ACPI passed). Therefore
- * we are using the !xen_initial_domain() to drop in the function.*/
- if (identity_mapped_irq(gsi) || (!xen_initial_domain() &&
- xen_pv_domain())) {
- irq = gsi;
- irq_alloc_desc_at(irq, -1);
- } else
- irq = find_unbound_irq();
-
- set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
- handle_level_irq, name);
+ irq = xen_allocate_irq_gsi(gsi);
+ if (irq < 0)
+ goto out;
- -- irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_level_irq,
- -- name);
- --
irq_op.irq = irq;
irq_op.vector = 0;
* this in the priv domain. */
if (xen_initial_domain() &&
HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
- irq_free_desc(irq);
+ xen_free_irq(irq);
irq = -ENOSPC;
goto out;
}
--- xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector,
- irq_info[irq] = mk_pirq_info(0, pirq, gsi, irq_op.vector);
- irq_info[irq].u.pirq.flags |= shareable ? PIRQ_SHAREABLE : 0;
- pirq_to_irq[pirq] = irq;
++++ xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector, DOMID_SELF,
+ shareable ? PIRQ_SHAREABLE : 0);
+
+ +++ pirq_query_unmask(irq);
+ +++ /* We try to use the handler with the appropriate semantic for the
+ +++ * type of interrupt: if the interrupt doesn't need an eoi
+ +++ * (pirq_needs_eoi returns false), we treat it like an edge
+ +++ * triggered interrupt so we use handle_edge_irq.
+ +++ * As a matter of fact this only happens when the corresponding
+ +++ * physical interrupt is edge triggered or an msi.
+ +++ *
+ +++ * On the other hand if the interrupt needs an eoi (pirq_needs_eoi
+ +++ * returns true) we treat it like a level triggered interrupt so we
+ +++ * use handle_fasteoi_irq like the native code does for this kind of
+ +++ * interrupts.
+ +++ * Depending on the Xen version, pirq_needs_eoi might return true
+ +++ * not only for level triggered interrupts but for edge triggered
+ +++ * interrupts too. In any case Xen always honors the eoi mechanism,
+ +++ * not injecting any more pirqs of the same kind if the first one
+ +++ * hasn't received an eoi yet. Therefore using the fasteoi handler
+ +++ * is the right choice either way.
+ +++ */
+ +++ if (pirq_needs_eoi(irq))
+ +++ irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+ +++ handle_fasteoi_irq, name);
+ +++ else
+ +++ irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+ +++ handle_edge_irq, name);
+ ++
out:
spin_unlock(&irq_mapping_update_lock);
}
#ifdef CONFIG_PCI_MSI
-#include <linux/msi.h>
-#include "../pci/msi.h"
-
-void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc)
+int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
{
- spin_lock(&irq_mapping_update_lock);
-
- if (alloc & XEN_ALLOC_IRQ) {
- *irq = find_unbound_irq();
- if (*irq == -1)
- goto out;
- }
-
- if (alloc & XEN_ALLOC_PIRQ) {
- *pirq = find_unbound_pirq(MAP_PIRQ_TYPE_MSI);
- if (*pirq == -1)
- goto out;
- }
+ int rc;
+ struct physdev_get_free_pirq op_get_free_pirq;
- set_irq_chip_and_handler_name(*irq, &xen_pirq_chip,
- handle_level_irq, name);
+ op_get_free_pirq.type = MAP_PIRQ_TYPE_MSI;
+ rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);
- irq_info[*irq] = mk_pirq_info(0, *pirq, 0, 0);
- pirq_to_irq[*pirq] = *irq;
+ WARN_ONCE(rc == -ENOSYS,
+ "hypervisor does not support the PHYSDEVOP_get_free_pirq interface\n");
-out:
- spin_unlock(&irq_mapping_update_lock);
+ return rc ? -1 : op_get_free_pirq.pirq;
}
-int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type)
+int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
--- int pirq, int vector, const char *name)
++++ int pirq, int vector, const char *name,
++++ domid_t domid)
{
- int irq = -1;
- struct physdev_map_pirq map_irq;
- int rc;
- int pos;
- u32 table_offset, bir;
-
- memset(&map_irq, 0, sizeof(map_irq));
- map_irq.domid = DOMID_SELF;
- map_irq.type = MAP_PIRQ_TYPE_MSI;
- map_irq.index = -1;
- map_irq.pirq = -1;
- map_irq.bus = dev->bus->number;
- map_irq.devfn = dev->devfn;
-
- if (type == PCI_CAP_ID_MSIX) {
- pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
-
- pci_read_config_dword(dev, msix_table_offset_reg(pos),
- &table_offset);
- bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
-
- map_irq.table_base = pci_resource_start(dev, bir);
- map_irq.entry_nr = msidesc->msi_attrib.entry_nr;
- }
+ int irq, ret;
spin_lock(&irq_mapping_update_lock);
- irq = find_unbound_irq();
-
+ irq = xen_allocate_irq_dynamic();
if (irq == -1)
goto out;
- -- irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_level_irq,
- -- name);
- rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
- if (rc) {
- printk(KERN_WARNING "xen map irq failed %d\n", rc);
-
- irq_free_desc(irq);
-
- irq = -1;
- goto out;
- }
- irq_info[irq] = mk_pirq_info(0, map_irq.pirq, 0, map_irq.index);
-
- set_irq_chip_and_handler_name(irq, &xen_pirq_chip,
- handle_level_irq,
- (type == PCI_CAP_ID_MSIX) ? "msi-x":"msi");
+ +++ irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq,
+ +++ name);
--- xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, 0);
++++ xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, domid, 0);
+ ret = irq_set_msi_desc(irq, msidesc);
+ if (ret < 0)
+ goto error_irq;
out:
spin_unlock(&irq_mapping_update_lock);
return irq;
+error_irq:
+ spin_unlock(&irq_mapping_update_lock);
+ xen_free_irq(irq);
+ return -1;
}
#endif
if (xen_initial_domain()) {
unmap_irq.pirq = info->u.pirq.pirq;
---- unmap_irq.domid = DOMID_SELF;
++++ unmap_irq.domid = info->u.pirq.domid;
rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq);
---- if (rc) {
++++ /* If another domain quits without making the pci_disable_msix
++++ * call, the Xen hypervisor takes care of freeing the PIRQs
++++ * (free_domain_pirqs).
++++ */
++++ if ((rc == -ESRCH && info->u.pirq.domid != DOMID_SELF))
++++ printk(KERN_INFO "domain %d does not have %d anymore\n",
++++ info->u.pirq.domid, info->u.pirq.pirq);
++++ else if (rc) {
printk(KERN_WARNING "unmap irq failed %d\n", rc);
goto out;
}
- pirq_to_irq[info->u.pirq.pirq] = -1;
}
- irq_info[irq] = mk_unbound_info();
- irq_free_desc(irq);
+ xen_free_irq(irq);
out:
spin_unlock(&irq_mapping_update_lock);
return rc;
}
-int xen_vector_from_irq(unsigned irq)
+int xen_irq_from_pirq(unsigned pirq)
{
- return vector_from_irq(irq);
-}
+ int irq;
-int xen_gsi_from_irq(unsigned irq)
-{
- return gsi_from_irq(irq);
+ struct irq_info *info;
+
+ spin_lock(&irq_mapping_update_lock);
+
+ list_for_each_entry(info, &xen_irq_list_head, list) {
+ if (info == NULL || info->type != IRQT_PIRQ)
+ continue;
+ irq = info->irq;
+ if (info->u.pirq.pirq == pirq)
+ goto out;
+ }
+ irq = -1;
+out:
+ spin_unlock(&irq_mapping_update_lock);
+
+ return irq;
}
-int xen_irq_from_pirq(unsigned pirq)
++++
++++int xen_pirq_from_irq(unsigned irq)
+++ {
- return pirq_to_irq[pirq];
++++ return pirq_from_irq(irq);
+++ }
-
++++EXPORT_SYMBOL_GPL(xen_pirq_from_irq);
int bind_evtchn_to_irq(unsigned int evtchn)
{
int irq;
irq = evtchn_to_irq[evtchn];
if (irq == -1) {
- irq = find_unbound_irq();
+ irq = xen_allocate_irq_dynamic();
+ if (irq == -1)
+ goto out;
- set_irq_chip_and_handler_name(irq, &xen_dynamic_chip,
- handle_fasteoi_irq, "event");
+ irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
- -- handle_fasteoi_irq, "event");
+ +++ handle_edge_irq, "event");
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_evtchn_info(evtchn);
+ xen_irq_info_evtchn_init(irq, evtchn);
}
+out:
spin_unlock(&irq_mapping_update_lock);
return irq;
irq = per_cpu(ipi_to_irq, cpu)[ipi];
if (irq == -1) {
- irq = find_unbound_irq();
+ irq = xen_allocate_irq_dynamic();
if (irq < 0)
goto out;
- set_irq_chip_and_handler_name(irq, &xen_percpu_chip,
+ irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
handle_percpu_irq, "ipi");
bind_ipi.vcpu = cpu;
BUG();
evtchn = bind_ipi.port;
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_ipi_info(evtchn, ipi);
- per_cpu(ipi_to_irq, cpu)[ipi] = irq;
+ xen_irq_info_ipi_init(cpu, irq, evtchn, ipi);
bind_evtchn_to_cpu(evtchn, cpu);
}
return irq;
}
+static int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
+ unsigned int remote_port)
+{
+ struct evtchn_bind_interdomain bind_interdomain;
+ int err;
+
+ bind_interdomain.remote_dom = remote_domain;
+ bind_interdomain.remote_port = remote_port;
+
+ err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
+ &bind_interdomain);
+
+ return err ? : bind_evtchn_to_irq(bind_interdomain.local_port);
+}
+
int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
{
irq = per_cpu(virq_to_irq, cpu)[virq];
if (irq == -1) {
- irq = find_unbound_irq();
+ irq = xen_allocate_irq_dynamic();
+ if (irq == -1)
+ goto out;
- set_irq_chip_and_handler_name(irq, &xen_percpu_chip,
+ irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
handle_percpu_irq, "virq");
bind_virq.virq = virq;
BUG();
evtchn = bind_virq.port;
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_virq_info(evtchn, virq);
-
- per_cpu(virq_to_irq, cpu)[virq] = irq;
+ xen_irq_info_virq_init(cpu, irq, evtchn, virq);
bind_evtchn_to_cpu(evtchn, cpu);
}
+out:
spin_unlock(&irq_mapping_update_lock);
return irq;
evtchn_to_irq[evtchn] = -1;
}
- if (irq_info[irq].type != IRQT_UNBOUND) {
- irq_info[irq] = mk_unbound_info();
+ BUG_ON(info_for_irq(irq)->type == IRQT_UNBOUND);
- irq_free_desc(irq);
- }
+ xen_free_irq(irq);
spin_unlock(&irq_mapping_update_lock);
}
unsigned long irqflags,
const char *devname, void *dev_id)
{
- - unsigned int irq;
- - int retval;
+ + int irq, retval;
irq = bind_evtchn_to_irq(evtchn);
+ if (irq < 0)
+ return irq;
retval = request_irq(irq, handler, irqflags, devname, dev_id);
if (retval != 0) {
unbind_from_irq(irq);
}
EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler);
+int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
+ unsigned int remote_port,
+ irq_handler_t handler,
+ unsigned long irqflags,
+ const char *devname,
+ void *dev_id)
+{
+ int irq, retval;
+
+ irq = bind_interdomain_evtchn_to_irq(remote_domain, remote_port);
+ if (irq < 0)
+ return irq;
+
+ retval = request_irq(irq, handler, irqflags, devname, dev_id);
+ if (retval != 0) {
+ unbind_from_irq(irq);
+ return retval;
+ }
+
+ return irq;
+}
+EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler);
+
int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
irq_handler_t handler,
unsigned long irqflags, const char *devname, void *dev_id)
{
- - unsigned int irq;
- - int retval;
+ + int irq, retval;
irq = bind_virq_to_irq(virq, cpu);
+ if (irq < 0)
+ return irq;
retval = request_irq(irq, handler, irqflags, devname, dev_id);
if (retval != 0) {
unbind_from_irq(irq);
if (irq < 0)
return irq;
- irqflags |= IRQF_NO_SUSPEND;
+ irqflags |= IRQF_NO_SUSPEND | IRQF_FORCE_RESUME;
retval = request_irq(irq, handler, irqflags, devname, dev_id);
if (retval != 0) {
unbind_from_irq(irq);
{
struct shared_info *sh = HYPERVISOR_shared_info;
int cpu = smp_processor_id();
- unsigned long *cpu_evtchn = cpu_evtchn_mask(cpu);
+ unsigned long *cpu_evtchn = per_cpu(cpu_evtchn_mask, cpu);
int i;
unsigned long flags;
static DEFINE_SPINLOCK(debug_lock);
}
static DEFINE_PER_CPU(unsigned, xed_nesting_count);
+static DEFINE_PER_CPU(unsigned int, current_word_idx);
+static DEFINE_PER_CPU(unsigned int, current_bit_idx);
+
+/*
+ * Mask out the i least significant bits of w
+ */
+#define MASK_LSBS(w, i) (w & ((~0UL) << i))
/*
* Search the CPUs pending events bitmasks. For each one found, map
*/
static void __xen_evtchn_do_upcall(void)
{
+ int start_word_idx, start_bit_idx;
+ int word_idx, bit_idx;
+ int i;
int cpu = get_cpu();
struct shared_info *s = HYPERVISOR_shared_info;
struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu);
wmb();
#endif
pending_words = xchg(&vcpu_info->evtchn_pending_sel, 0);
- while (pending_words != 0) {
+
+ start_word_idx = __this_cpu_read(current_word_idx);
+ start_bit_idx = __this_cpu_read(current_bit_idx);
+
+ word_idx = start_word_idx;
+
+ for (i = 0; pending_words != 0; i++) {
unsigned long pending_bits;
- int word_idx = __ffs(pending_words);
- pending_words &= ~(1UL << word_idx);
+ unsigned long words;
+
+ words = MASK_LSBS(pending_words, word_idx);
+
+ /*
+ * If we masked out all events, wrap to beginning.
+ */
+ if (words == 0) {
+ word_idx = 0;
+ bit_idx = 0;
+ continue;
+ }
+ word_idx = __ffs(words);
+
+ pending_bits = active_evtchns(cpu, s, word_idx);
+ bit_idx = 0; /* usually scan entire word from start */
+ if (word_idx == start_word_idx) {
+ /* We scan the starting word in two parts */
+ if (i == 0)
+ /* 1st time: start in the middle */
+ bit_idx = start_bit_idx;
+ else
+ /* 2nd time: mask bits done already */
+ bit_idx &= (1UL << start_bit_idx) - 1;
+ }
- while ((pending_bits = active_evtchns(cpu, s, word_idx)) != 0) {
- int bit_idx = __ffs(pending_bits);
- int port = (word_idx * BITS_PER_LONG) + bit_idx;
- int irq = evtchn_to_irq[port];
+ do {
+ unsigned long bits;
+ int port, irq;
struct irq_desc *desc;
- mask_evtchn(port);
- clear_evtchn(port);
+ bits = MASK_LSBS(pending_bits, bit_idx);
+
+ /* If we masked out all events, move on. */
+ if (bits == 0)
+ break;
+
+ bit_idx = __ffs(bits);
+
+ /* Process port. */
+ port = (word_idx * BITS_PER_LONG) + bit_idx;
+ irq = evtchn_to_irq[port];
- -- mask_evtchn(port);
- -- clear_evtchn(port);
- --
if (irq != -1) {
desc = irq_to_desc(irq);
if (desc)
generic_handle_irq_desc(irq, desc);
}
- }
+
+ bit_idx = (bit_idx + 1) % BITS_PER_LONG;
+
+ /* Next caller starts at last processed + 1 */
+ __this_cpu_write(current_word_idx,
+ bit_idx ? word_idx :
+ (word_idx+1) % BITS_PER_LONG);
+ __this_cpu_write(current_bit_idx, bit_idx);
+ } while (bit_idx != 0);
+
+ /* Scan start_l1i twice; all others once. */
+ if ((word_idx != start_word_idx) || (i != 0))
+ pending_words &= ~(1UL << word_idx);
+
+ word_idx = (word_idx + 1) % BITS_PER_LONG;
}
BUG_ON(!irqs_disabled());
so there should be a proper type */
BUG_ON(info->type == IRQT_UNBOUND);
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_evtchn_info(evtchn);
+ xen_irq_info_evtchn_init(irq, evtchn);
spin_unlock(&irq_mapping_update_lock);
struct evtchn_bind_vcpu bind_vcpu;
int evtchn = evtchn_from_irq(irq);
- /* events delivered via platform PCI interrupts are always
- * routed to vcpu 0 */
- if (!VALID_EVTCHN(evtchn) ||
- (xen_hvm_domain() && !xen_have_vector_callback))
+ if (!VALID_EVTCHN(evtchn))
+ return -1;
+
+ /*
+ * Events delivered via platform PCI interrupts are always
+ * routed to vcpu 0 and hence cannot be rebound.
+ */
+ if (xen_hvm_domain() && !xen_have_vector_callback)
return -1;
/* Send future instances of this interrupt to other vcpu. */
return 0;
}
-static int set_affinity_irq(unsigned irq, const struct cpumask *dest)
+static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
+ bool force)
{
unsigned tcpu = cpumask_first(dest);
- return rebind_irq_to_cpu(irq, tcpu);
+ return rebind_irq_to_cpu(data->irq, tcpu);
}
int resend_irq_on_evtchn(unsigned int irq)
return 1;
}
-static void enable_dynirq(unsigned int irq)
+static void enable_dynirq(struct irq_data *data)
{
- int evtchn = evtchn_from_irq(irq);
+ int evtchn = evtchn_from_irq(data->irq);
if (VALID_EVTCHN(evtchn))
unmask_evtchn(evtchn);
}
-static void disable_dynirq(unsigned int irq)
+static void disable_dynirq(struct irq_data *data)
{
- int evtchn = evtchn_from_irq(irq);
+ int evtchn = evtchn_from_irq(data->irq);
if (VALID_EVTCHN(evtchn))
mask_evtchn(evtchn);
}
-static void ack_dynirq(unsigned int irq)
+static void ack_dynirq(struct irq_data *data)
{
- int evtchn = evtchn_from_irq(irq);
+ int evtchn = evtchn_from_irq(data->irq);
- -- irq_move_masked_irq(data);
- move_masked_irq(irq);
+ +++ irq_move_irq(data);
if (VALID_EVTCHN(evtchn))
- --- unmask_evtchn(evtchn);
+ +++ clear_evtchn(evtchn);
+ ++ }
+ ++
-static int retrigger_dynirq(unsigned int irq)
+ +++static void mask_ack_dynirq(struct irq_data *data)
+ ++ {
- int evtchn = evtchn_from_irq(irq);
+ +++ disable_dynirq(data);
+ +++ ack_dynirq(data);
+}
+
+static int retrigger_dynirq(struct irq_data *data)
+{
+ int evtchn = evtchn_from_irq(data->irq);
struct shared_info *sh = HYPERVISOR_shared_info;
int ret = 0;
return ret;
}
-static void restore_cpu_pirqs(void)
+static void restore_pirqs(void)
{
int pirq, rc, irq, gsi;
struct physdev_map_pirq map_irq;
+ struct irq_info *info;
- for (pirq = 0; pirq < nr_irqs; pirq++) {
- irq = pirq_to_irq[pirq];
- if (irq == -1)
+ list_for_each_entry(info, &xen_irq_list_head, list) {
+ if (info->type != IRQT_PIRQ)
continue;
+ pirq = info->u.pirq.pirq;
+ gsi = info->u.pirq.gsi;
+ irq = info->irq;
+
/* save/restore of PT devices doesn't work, so at this point the
* only devices present are GSI based emulated devices */
- gsi = gsi_from_irq(irq);
if (!gsi)
continue;
if (rc) {
printk(KERN_WARNING "xen map irq failed gsi=%d irq=%d pirq=%d rc=%d\n",
gsi, irq, pirq, rc);
- irq_info[irq] = mk_unbound_info();
- pirq_to_irq[pirq] = -1;
+ xen_free_irq(irq);
continue;
}
printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq);
- startup_pirq(irq);
+ __startup_pirq(irq);
}
}
evtchn = bind_virq.port;
/* Record the new mapping. */
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_virq_info(evtchn, virq);
+ xen_irq_info_virq_init(cpu, irq, evtchn, virq);
bind_evtchn_to_cpu(evtchn, cpu);
}
}
evtchn = bind_ipi.port;
/* Record the new mapping. */
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_ipi_info(evtchn, ipi);
+ xen_irq_info_ipi_init(cpu, irq, evtchn, ipi);
bind_evtchn_to_cpu(evtchn, cpu);
}
}
xen_poll_irq_timeout(irq, 0 /* no timeout */);
}
++++/* Check whether the IRQ line is shared with other guests. */
++++int xen_test_irq_shared(int irq)
++++{
++++ struct irq_info *info = info_for_irq(irq);
++++ struct physdev_irq_status_query irq_status = { .irq = info->u.pirq.pirq };
++++
++++ if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
++++ return 0;
++++ return !(irq_status.flags & XENIRQSTAT_shared);
++++}
++++EXPORT_SYMBOL_GPL(xen_test_irq_shared);
++++
void xen_irq_resume(void)
{
- unsigned int cpu, irq, evtchn;
- struct irq_desc *desc;
+ unsigned int cpu, evtchn;
+ struct irq_info *info;
init_evtchn_cpu_bindings();
mask_evtchn(evtchn);
/* No IRQ <-> event-channel mappings. */
- for (irq = 0; irq < nr_irqs; irq++)
- irq_info[irq].evtchn = 0; /* zap event-channel binding */
+ list_for_each_entry(info, &xen_irq_list_head, list)
+ info->evtchn = 0; /* zap event-channel binding */
for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
evtchn_to_irq[evtchn] = -1;
restore_cpu_ipis(cpu);
}
- /*
- * Unmask any IRQF_NO_SUSPEND IRQs which are enabled. These
- * are not handled by the IRQ core.
- */
- for_each_irq_desc(irq, desc) {
- if (!desc->action || !(desc->action->flags & IRQF_NO_SUSPEND))
- continue;
- if (desc->status & IRQ_DISABLED)
- continue;
-
- evtchn = evtchn_from_irq(irq);
- if (evtchn == -1)
- continue;
-
- unmask_evtchn(evtchn);
- }
-
- restore_cpu_pirqs();
+ restore_pirqs();
}
static struct irq_chip xen_dynamic_chip __read_mostly = {
- .name = "xen-dyn",
+ .name = "xen-dyn",
- .disable = disable_dynirq,
- .mask = disable_dynirq,
- .unmask = enable_dynirq,
+ .irq_disable = disable_dynirq,
+ .irq_mask = disable_dynirq,
+ .irq_unmask = enable_dynirq,
- -- .irq_eoi = ack_dynirq,
- .eoi = ack_dynirq,
- .set_affinity = set_affinity_irq,
- .retrigger = retrigger_dynirq,
+ +++ .irq_ack = ack_dynirq,
+ +++ .irq_mask_ack = mask_ack_dynirq,
+ +++
+ .irq_set_affinity = set_affinity_irq,
+ .irq_retrigger = retrigger_dynirq,
};
static struct irq_chip xen_pirq_chip __read_mostly = {
- .name = "xen-pirq",
-
- .startup = startup_pirq,
- .shutdown = shutdown_pirq,
+ .name = "xen-pirq",
- .enable = enable_pirq,
- .unmask = enable_pirq,
+ .irq_startup = startup_pirq,
+ .irq_shutdown = shutdown_pirq,
- --
+ .irq_enable = enable_pirq,
- -- .irq_unmask = enable_pirq,
- --
+ .irq_disable = disable_pirq,
- -- .irq_mask = disable_pirq,
- -- .irq_ack = ack_pirq,
- .disable = disable_pirq,
- .mask = disable_pirq,
+ +++ .irq_mask = disable_dynirq,
+ +++ .irq_unmask = enable_dynirq,
+ ++
- .ack = ack_pirq,
- .end = end_pirq,
+ +++ .irq_ack = eoi_pirq,
+ +++ .irq_eoi = eoi_pirq,
+ +++ .irq_mask_ack = mask_ack_pirq,
- .set_affinity = set_affinity_irq,
+ .irq_set_affinity = set_affinity_irq,
- .retrigger = retrigger_dynirq,
+ .irq_retrigger = retrigger_dynirq,
};
static struct irq_chip xen_percpu_chip __read_mostly = {
- .name = "xen-percpu",
+ .name = "xen-percpu",
- .disable = disable_dynirq,
- .mask = disable_dynirq,
- .unmask = enable_dynirq,
+ .irq_disable = disable_dynirq,
+ .irq_mask = disable_dynirq,
+ .irq_unmask = enable_dynirq,
- .ack = ack_dynirq,
+ .irq_ack = ack_dynirq,
};
int xen_set_callback_via(uint64_t via)
{
int i;
- cpu_evtchn_mask_p = kcalloc(nr_cpu_ids, sizeof(struct cpu_evtchn_s),
- GFP_KERNEL);
- irq_info = kcalloc(nr_irqs, sizeof(*irq_info), GFP_KERNEL);
-
- /* We are using nr_irqs as the maximum number of pirq available but
- * that number is actually chosen by Xen and we don't know exactly
- * what it is. Be careful choosing high pirq numbers. */
- pirq_to_irq = kcalloc(nr_irqs, sizeof(*pirq_to_irq), GFP_KERNEL);
- for (i = 0; i < nr_irqs; i++)
- pirq_to_irq[i] = -1;
-
evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq),
GFP_KERNEL);
for (i = 0; i < NR_EVENT_CHANNELS; i++)
projects / linux.git / commitdiff