Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 2c84c6a..c8dbee6 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1,3 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+
/*
* Xen mmu operations
*
@@ -99,6 +101,12 @@
#endif /* CONFIG_X86_64 */
/*
+ * Protects atomic reservation decrease/increase against concurrent increases.
+ * Also protects non-atomic updates of current_pages and balloon lists.
+ */
+static DEFINE_SPINLOCK(xen_reservation_lock);
+
+/*
* Note about cr3 (pagetable base) values:
*
* xen_cr3 contains the current logical cr3 value; it contains the
@@ -298,20 +306,20 @@
__xen_set_pte(ptep, pteval);
}
-pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
+pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
/* Just return the pte as-is. We preserve the bits on commit */
- trace_xen_mmu_ptep_modify_prot_start(mm, addr, ptep, *ptep);
+ trace_xen_mmu_ptep_modify_prot_start(vma->vm_mm, addr, ptep, *ptep);
return *ptep;
}
-void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep, pte_t pte)
{
struct mmu_update u;
- trace_xen_mmu_ptep_modify_prot_commit(mm, addr, ptep, pte);
+ trace_xen_mmu_ptep_modify_prot_commit(vma->vm_mm, addr, ptep, pte);
xen_mc_batch();
u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
@@ -640,19 +648,20 @@
unsigned long limit)
{
int i, nr, flush = 0;
- unsigned hole_low, hole_high;
+ unsigned hole_low = 0, hole_high = 0;
/* The limit is the last byte to be touched */
limit--;
BUG_ON(limit >= FIXADDR_TOP);
+#ifdef CONFIG_X86_64
/*
* 64-bit has a great big hole in the middle of the address
- * space, which contains the Xen mappings. On 32-bit these
- * will end up making a zero-sized hole and so is a no-op.
+ * space, which contains the Xen mappings.
*/
- hole_low = pgd_index(USER_LIMIT);
- hole_high = pgd_index(PAGE_OFFSET);
+ hole_low = pgd_index(GUARD_HOLE_BASE_ADDR);
+ hole_high = pgd_index(GUARD_HOLE_END_ADDR);
+#endif
nr = pgd_index(limit) + 1;
for (i = 0; i < nr; i++) {
@@ -856,7 +865,7 @@
* The init_mm pagetable is really pinned as soon as its created, but
* that's before we have page structures to store the bits. So do all
* the book-keeping now once struct pages for allocated pages are
- * initialized. This happens only after free_all_bootmem() is called.
+ * initialized. This happens only after memblock_free_all() is called.
*/
static void __init xen_after_bootmem(void)
{
@@ -1298,16 +1307,6 @@
this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
}
-static unsigned long xen_read_cr2(void)
-{
- return this_cpu_read(xen_vcpu)->arch.cr2;
-}
-
-unsigned long xen_read_cr2_direct(void)
-{
- return this_cpu_read(xen_vcpu_info.arch.cr2);
-}
-
static noinline void xen_flush_tlb(void)
{
struct mmuext_op *op;
@@ -2105,10 +2104,10 @@
pt = early_memremap(pt_phys, PAGE_SIZE);
clear_page(pt);
for (idx_pte = 0;
- idx_pte < min(n_pte, PTRS_PER_PTE);
- idx_pte++) {
- set_pte(pt + idx_pte,
- pfn_pte(p2m_pfn, PAGE_KERNEL));
+ idx_pte < min(n_pte, PTRS_PER_PTE);
+ idx_pte++) {
+ pt[idx_pte] = pfn_pte(p2m_pfn,
+ PAGE_KERNEL);
p2m_pfn++;
}
n_pte -= PTRS_PER_PTE;
@@ -2116,8 +2115,7 @@
make_lowmem_page_readonly(__va(pt_phys));
pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE,
PFN_DOWN(pt_phys));
- set_pmd(pmd + idx_pt,
- __pmd(_PAGE_TABLE | pt_phys));
+ pmd[idx_pt] = __pmd(_PAGE_TABLE | pt_phys);
pt_phys += PAGE_SIZE;
}
n_pt -= PTRS_PER_PMD;
@@ -2125,7 +2123,7 @@
make_lowmem_page_readonly(__va(pmd_phys));
pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE,
PFN_DOWN(pmd_phys));
- set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys));
+ pud[idx_pmd] = __pud(_PAGE_TABLE | pmd_phys);
pmd_phys += PAGE_SIZE;
}
n_pmd -= PTRS_PER_PUD;
@@ -2209,7 +2207,7 @@
set_page_prot(initial_page_table, PAGE_KERNEL);
set_page_prot(initial_kernel_pmd, PAGE_KERNEL);
- pv_mmu_ops.write_cr3 = &xen_write_cr3;
+ pv_ops.mmu.write_cr3 = &xen_write_cr3;
}
/*
@@ -2310,8 +2308,6 @@
#elif defined(CONFIG_X86_VSYSCALL_EMULATION)
case VSYSCALL_PAGE:
#endif
- case FIX_TEXT_POKE0:
- case FIX_TEXT_POKE1:
/* All local page mappings */
pte = pfn_pte(phys, prot);
break;
@@ -2358,27 +2354,27 @@
static void __init xen_post_allocator_init(void)
{
- pv_mmu_ops.set_pte = xen_set_pte;
- pv_mmu_ops.set_pmd = xen_set_pmd;
- pv_mmu_ops.set_pud = xen_set_pud;
+ pv_ops.mmu.set_pte = xen_set_pte;
+ pv_ops.mmu.set_pmd = xen_set_pmd;
+ pv_ops.mmu.set_pud = xen_set_pud;
#ifdef CONFIG_X86_64
- pv_mmu_ops.set_p4d = xen_set_p4d;
+ pv_ops.mmu.set_p4d = xen_set_p4d;
#endif
/* This will work as long as patching hasn't happened yet
(which it hasn't) */
- pv_mmu_ops.alloc_pte = xen_alloc_pte;
- pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
- pv_mmu_ops.release_pte = xen_release_pte;
- pv_mmu_ops.release_pmd = xen_release_pmd;
+ pv_ops.mmu.alloc_pte = xen_alloc_pte;
+ pv_ops.mmu.alloc_pmd = xen_alloc_pmd;
+ pv_ops.mmu.release_pte = xen_release_pte;
+ pv_ops.mmu.release_pmd = xen_release_pmd;
#ifdef CONFIG_X86_64
- pv_mmu_ops.alloc_pud = xen_alloc_pud;
- pv_mmu_ops.release_pud = xen_release_pud;
+ pv_ops.mmu.alloc_pud = xen_alloc_pud;
+ pv_ops.mmu.release_pud = xen_release_pud;
#endif
- pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte);
+ pv_ops.mmu.make_pte = PV_CALLEE_SAVE(xen_make_pte);
#ifdef CONFIG_X86_64
- pv_mmu_ops.write_cr3 = &xen_write_cr3;
+ pv_ops.mmu.write_cr3 = &xen_write_cr3;
#endif
}
@@ -2391,7 +2387,7 @@
}
static const struct pv_mmu_ops xen_mmu_ops __initconst = {
- .read_cr2 = xen_read_cr2,
+ .read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2),
.write_cr2 = xen_write_cr2,
.read_cr3 = xen_read_cr3,
@@ -2466,7 +2462,7 @@
x86_init.paging.pagetable_init = xen_pagetable_init;
x86_init.hyper.init_after_bootmem = xen_after_bootmem;
- pv_mmu_ops = xen_mmu_ops;
+ pv_ops.mmu = xen_mmu_ops;
memset(dummy_mapping, 0xff, PAGE_SIZE);
}
@@ -2629,7 +2625,6 @@
*dma_handle = virt_to_machine(vstart).maddr;
return success ? 0 : -ENOMEM;
}
-EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
{
@@ -2664,7 +2659,137 @@
spin_unlock_irqrestore(&xen_reservation_lock, flags);
}
-EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
+
+static noinline void xen_flush_tlb_all(void)
+{
+ struct mmuext_op *op;
+ struct multicall_space mcs;
+
+ preempt_disable();
+
+ mcs = xen_mc_entry(sizeof(*op));
+
+ op = mcs.args;
+ op->cmd = MMUEXT_TLB_FLUSH_ALL;
+ MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+ preempt_enable();
+}
+
+#define REMAP_BATCH_SIZE 16
+
+struct remap_data {
+ xen_pfn_t *pfn;
+ bool contiguous;
+ bool no_translate;
+ pgprot_t prot;
+ struct mmu_update *mmu_update;
+};
+
+static int remap_area_pfn_pte_fn(pte_t *ptep, unsigned long addr, void *data)
+{
+ struct remap_data *rmd = data;
+ pte_t pte = pte_mkspecial(mfn_pte(*rmd->pfn, rmd->prot));
+
+ /*
+ * If we have a contiguous range, just update the pfn itself,
+ * else update pointer to be "next pfn".
+ */
+ if (rmd->contiguous)
+ (*rmd->pfn)++;
+ else
+ rmd->pfn++;
+
+ rmd->mmu_update->ptr = virt_to_machine(ptep).maddr;
+ rmd->mmu_update->ptr |= rmd->no_translate ?
+ MMU_PT_UPDATE_NO_TRANSLATE :
+ MMU_NORMAL_PT_UPDATE;
+ rmd->mmu_update->val = pte_val_ma(pte);
+ rmd->mmu_update++;
+
+ return 0;
+}
+
+int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr,
+ xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot,
+ unsigned int domid, bool no_translate, struct page **pages)
+{
+ int err = 0;
+ struct remap_data rmd;
+ struct mmu_update mmu_update[REMAP_BATCH_SIZE];
+ unsigned long range;
+ int mapped = 0;
+
+ BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO)));
+
+ rmd.pfn = pfn;
+ rmd.prot = prot;
+ /*
+ * We use the err_ptr to indicate if there we are doing a contiguous
+ * mapping or a discontigious mapping.
+ */
+ rmd.contiguous = !err_ptr;
+ rmd.no_translate = no_translate;
+
+ while (nr) {
+ int index = 0;
+ int done = 0;
+ int batch = min(REMAP_BATCH_SIZE, nr);
+ int batch_left = batch;
+
+ range = (unsigned long)batch << PAGE_SHIFT;
+
+ rmd.mmu_update = mmu_update;
+ err = apply_to_page_range(vma->vm_mm, addr, range,
+ remap_area_pfn_pte_fn, &rmd);
+ if (err)
+ goto out;
+
+ /*
+ * We record the error for each page that gives an error, but
+ * continue mapping until the whole set is done
+ */
+ do {
+ int i;
+
+ err = HYPERVISOR_mmu_update(&mmu_update[index],
+ batch_left, &done, domid);
+
+ /*
+ * @err_ptr may be the same buffer as @gfn, so
+ * only clear it after each chunk of @gfn is
+ * used.
+ */
+ if (err_ptr) {
+ for (i = index; i < index + done; i++)
+ err_ptr[i] = 0;
+ }
+ if (err < 0) {
+ if (!err_ptr)
+ goto out;
+ err_ptr[i] = err;
+ done++; /* Skip failed frame. */
+ } else
+ mapped += done;
+ batch_left -= done;
+ index += done;
+ } while (batch_left);
+
+ nr -= batch;
+ addr += range;
+ if (err_ptr)
+ err_ptr += batch;
+ cond_resched();
+ }
+out:
+
+ xen_flush_tlb_all();
+
+ return err < 0 ? err : mapped;
+}
+EXPORT_SYMBOL_GPL(xen_remap_pfn);
#ifdef CONFIG_KEXEC_CORE
phys_addr_t paddr_vmcoreinfo_note(void)