powerpc: Fix reverse map real-mode address lookup with huge vmalloc

real_vmalloc_addr() does not currently work for huge vmalloc, which is
what the reverse map can be allocated with for radix host, hash guest.

Extract the hugepage aware equivalent from eeh code into a helper, and
convert existing sites including this one to use it.

Fixes: 8abddd9 ("powerpc/64s/radix: Enable huge vmalloc mappings")
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210526120005.3432222-1-npiggin@gmail.com

Author: npiggin

arch/powerpc/include/asm/pte-walk.h

@@ -31,6 +31,35 @@ static inline pte_t *find_init_mm_pte(unsigned long ea, unsigned *hshift)
 	pgd_t *pgdir = init_mm.pgd;
 	return __find_linux_pte(pgdir, ea, NULL, hshift);
 }
+
+/*
+ * Convert a kernel vmap virtual address (vmalloc or ioremap space) to a
+ * physical address, without taking locks. This can be used in real-mode.
+ */
+static inline phys_addr_t ppc_find_vmap_phys(unsigned long addr)
+{
+	pte_t *ptep;
+	phys_addr_t pa;
+	int hugepage_shift;
+
+	/*
+	 * init_mm does not free page tables, and does not do THP. It may
+	 * have huge pages from huge vmalloc / ioremap etc.
+	 */
+	ptep = find_init_mm_pte(addr, &hugepage_shift);
+	if (WARN_ON(!ptep))
+		return 0;
+
+	pa = PFN_PHYS(pte_pfn(*ptep));
+
+	if (!hugepage_shift)
+		hugepage_shift = PAGE_SHIFT;
+
+	pa |= addr & ((1ul << hugepage_shift) - 1);
+
+	return pa;
+}
+
 /*
  * This is what we should always use. Any other lockless page table lookup needs
  * careful audit against THP split.

arch/powerpc/kernel/eeh.c

@@ -346,28 +346,7 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
  */
 static inline unsigned long eeh_token_to_phys(unsigned long token)
 {
-	pte_t *ptep;
-	unsigned long pa;
-	int hugepage_shift;
-
-	/*
-	 * We won't find hugepages here(this is iomem). Hence we are not
-	 * worried about _PAGE_SPLITTING/collapse. Also we will not hit
-	 * page table free, because of init_mm.
-	 */
-	ptep = find_init_mm_pte(token, &hugepage_shift);
-	if (!ptep)
-		return token;
-
-	pa = pte_pfn(*ptep);
-
-	/* On radix we can do hugepage mappings for io, so handle that */
-	if (!hugepage_shift)
-		hugepage_shift = PAGE_SHIFT;
-
-	pa <<= PAGE_SHIFT;
-	pa |= token & ((1ul << hugepage_shift) - 1);
-	return pa;
+	return ppc_find_vmap_phys(token);
 }
 
 /*

arch/powerpc/kernel/io-workarounds.c

@@ -55,7 +55,6 @@ static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr)
 #ifdef CONFIG_PPC_INDIRECT_MMIO
 struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 {
-	unsigned hugepage_shift;
 	struct iowa_bus *bus;
 	int token;
 
@@ -65,22 +64,13 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 		bus = &iowa_busses[token - 1];
 	else {
 		unsigned long vaddr, paddr;
-		pte_t *ptep;
 
 		vaddr = (unsigned long)PCI_FIX_ADDR(addr);
 		if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
 			return NULL;
-		/*
-		 * We won't find huge pages here (iomem). Also can't hit
-		 * a page table free due to init_mm
-		 */
-		ptep = find_init_mm_pte(vaddr, &hugepage_shift);
-		if (ptep == NULL)
-			paddr = 0;
-		else {
-			WARN_ON(hugepage_shift);
-			paddr = pte_pfn(*ptep) << PAGE_SHIFT;
-		}
+
+		paddr = ppc_find_vmap_phys(vaddr);
+
 		bus = iowa_pci_find(vaddr, paddr);
 
 		if (bus == NULL)

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -23,20 +23,9 @@
 #include <asm/pte-walk.h>
 
 /* Translate address of a vmalloc'd thing to a linear map address */
-static void *real_vmalloc_addr(void *x)
+static void *real_vmalloc_addr(void *addr)
 {
-	unsigned long addr = (unsigned long) x;
-	pte_t *p;
-	/*
-	 * assume we don't have huge pages in vmalloc space...
-	 * So don't worry about THP collapse/split. Called
-	 * Only in realmode with MSR_EE = 0, hence won't need irq_save/restore.
-	 */
-	p = find_init_mm_pte(addr, NULL);
-	if (!p || !pte_present(*p))
-		return NULL;
-	addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
-	return __va(addr);
+	return __va(ppc_find_vmap_phys((unsigned long)addr));
 }
 
 /* Return 1 if we need to do a global tlbie, 0 if we can use tlbiel */