Merge tag 'powerpc-4.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - A fix for a bug in our page table fragment allocator, where a page
     table page could be freed and reallocated for something else while
     still in use, leading to memory corruption etc. The fix reuses
     pt_mm in struct page (x86 only) for a powerpc only refcount.

   - Fixes to our pkey support. Several are user-visible changes, but
     bring us in to line with x86 behaviour and/or fix outright bugs.
     Thanks to Florian Weimer for reporting many of these.

   - A series to improve the hvc driver & related OPAL console code,
     which have been seen to cause hardlockups at times. The hvc driver
     changes in particular have been in linux-next for ~month.

   - Increase our MAX_PHYSMEM_BITS to 128TB when SPARSEMEM_VMEMMAP=y.

   - Remove Power8 DD1 and Power9 DD1 support, neither chip should be in
     use anywhere other than as a paper weight.

   - An optimised memcmp implementation using Power7-or-later VMX
     instructions

   - Support for barrier_nospec on some NXP CPUs.

   - Support for flushing the count cache on context switch on some IBM
     CPUs (controlled by firmware), as a Spectre v2 mitigation.

   - A series to enhance the information we print on unhandled signals
     to bring it into line with other arches, including showing the
     offending VMA and dumping the instructions around the fault.

  Thanks to: Aaro Koskinen, Akshay Adiga, Alastair D'Silva, Alexey
  Kardashevskiy, Alexey Spirkov, Alistair Popple, Andrew Donnellan,
  Aneesh Kumar K.V, Anju T Sudhakar, Arnd Bergmann, Bartosz Golaszewski,
  Benjamin Herrenschmidt, Bharat Bhushan, Bjoern Noetel, Boqun Feng,
  Breno Leitao, Bryant G. Ly, Camelia Groza, Christophe Leroy, Christoph
  Hellwig, Cyril Bur, Dan Carpenter, Daniel Klamt, Darren Stevens, Dave
  Young, David Gibson, Diana Craciun, Finn Thain, Florian Weimer,
  Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven, Geoff Levand,
  Guenter Roeck, Gustavo Romero, Haren Myneni, Hari Bathini, Joel
  Stanley, Jonathan Neuschäfer, Kees Cook, Madhavan Srinivasan, Mahesh
  Salgaonkar, Markus Elfring, Mathieu Malaterre, Mauro S. M. Rodrigues,
  Michael Hanselmann, Michael Neuling, Michael Schmitz, Mukesh Ojha,
  Murilo Opsfelder Araujo, Nicholas Piggin, Parth Y Shah, Paul
  Mackerras, Paul Menzel, Ram Pai, Randy Dunlap, Rashmica Gupta, Reza
  Arbab, Rodrigo R. Galvao, Russell Currey, Sam Bobroff, Scott Wood,
  Shilpasri G Bhat, Simon Guo, Souptick Joarder, Stan Johnson, Thiago
  Jung Bauermann, Tyrel Datwyler, Vaibhav Jain, Vasant Hegde, Venkat
  Rao, zhong jiang"

* tag 'powerpc-4.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (234 commits)
  powerpc/mm/book3s/radix: Add mapping statistics
  powerpc/uaccess: Enable get_user(u64, *p) on 32-bit
  powerpc/mm/hash: Remove unnecessary do { } while(0) loop
  powerpc/64s: move machine check SLB flushing to mm/slb.c
  powerpc/powernv/idle: Fix build error
  powerpc/mm/tlbflush: update the mmu_gather page size while iterating address range
  powerpc/mm: remove warning about ‘type’ being set
  powerpc/32: Include setup.h header file to fix warnings
  powerpc: Move `path` variable inside DEBUG_PROM
  powerpc/powermac: Make some functions static
  powerpc/powermac: Remove variable x that's never read
  cxl: remove a dead branch
  powerpc/powermac: Add missing include of header pmac.h
  powerpc/kexec: Use common error handling code in setup_new_fdt()
  powerpc/xmon: Add address lookup for percpu symbols
  powerpc/mm: remove huge_pte_offset_and_shift() prototype
  powerpc/lib: Use patch_site to patch copy_32 functions once cache is enabled
  powerpc/pseries: Fix endianness while restoring of r3 in MCE handler.
  powerpc/fadump: merge adjacent memory ranges to reduce PT_LOAD segements
  powerpc/fadump: handle crash memory ranges array index overflow
  ...

1 files changed, 24 insertions, 184 deletions

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 70b2e1e0f23c..4e6302bf4073 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -52,12 +52,8 @@
 #define PNV_IODA1_M64_SEGS	8	/* Segments per M64 BAR	*/
 #define PNV_IODA1_DMA32_SEGSIZE	0x10000000
 
-#define POWERNV_IOMMU_DEFAULT_LEVELS	1
-#define POWERNV_IOMMU_MAX_LEVELS	5
-
 static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_NVLINK",
 					      "NPU_OCAPI" };
-static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl);
 
 void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 			    const char *fmt, ...)
@@ -2008,7 +2004,7 @@ static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index,
 static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
 		unsigned long *hpa, enum dma_data_direction *direction)
 {
-	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction, true);
 
 	if (!ret)
 		pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, false);
@@ -2019,7 +2015,7 @@ static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
 static int pnv_ioda1_tce_xchg_rm(struct iommu_table *tbl, long index,
 		unsigned long *hpa, enum dma_data_direction *direction)
 {
-	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction, false);
 
 	if (!ret)
 		pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, true);
@@ -2041,6 +2037,7 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = {
 #ifdef CONFIG_IOMMU_API
 	.exchange = pnv_ioda1_tce_xchg,
 	.exchange_rm = pnv_ioda1_tce_xchg_rm,
+	.useraddrptr = pnv_tce_useraddrptr,
 #endif
 	.clear = pnv_ioda1_tce_free,
 	.get = pnv_tce_get,
@@ -2172,7 +2169,7 @@ static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index,
 static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
 		unsigned long *hpa, enum dma_data_direction *direction)
 {
-	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction, true);
 
 	if (!ret)
 		pnv_pci_ioda2_tce_invalidate(tbl, index, 1, false);
@@ -2183,7 +2180,7 @@ static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
 static int pnv_ioda2_tce_xchg_rm(struct iommu_table *tbl, long index,
 		unsigned long *hpa, enum dma_data_direction *direction)
 {
-	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction, false);
 
 	if (!ret)
 		pnv_pci_ioda2_tce_invalidate(tbl, index, 1, true);
@@ -2200,20 +2197,16 @@ static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
 	pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
 }
 
-static void pnv_ioda2_table_free(struct iommu_table *tbl)
-{
-	pnv_pci_ioda2_table_free_pages(tbl);
-}
-
 static struct iommu_table_ops pnv_ioda2_iommu_ops = {
 	.set = pnv_ioda2_tce_build,
 #ifdef CONFIG_IOMMU_API
 	.exchange = pnv_ioda2_tce_xchg,
 	.exchange_rm = pnv_ioda2_tce_xchg_rm,
+	.useraddrptr = pnv_tce_useraddrptr,
 #endif
 	.clear = pnv_ioda2_tce_free,
 	.get = pnv_tce_get,
-	.free = pnv_ioda2_table_free,
+	.free = pnv_pci_ioda2_table_free_pages,
 };
 
 static int pnv_pci_ioda_dev_dma_weight(struct pci_dev *dev, void *data)
@@ -2463,13 +2456,9 @@ void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable)
 		pe->tce_bypass_enabled = enable;
 }
 
-static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
-		__u32 page_shift, __u64 window_size, __u32 levels,
-		struct iommu_table *tbl);
-
 static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
 		int num, __u32 page_shift, __u64 window_size, __u32 levels,
-		struct iommu_table **ptbl)
+		bool alloc_userspace_copy, struct iommu_table **ptbl)
 {
 	struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
 			table_group);
@@ -2486,7 +2475,7 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
 
 	ret = pnv_pci_ioda2_table_alloc_pages(nid,
 			bus_offset, page_shift, window_size,
-			levels, tbl);
+			levels, alloc_userspace_copy, tbl);
 	if (ret) {
 		iommu_tce_table_put(tbl);
 		return ret;
@@ -2519,7 +2508,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 	rc = pnv_pci_ioda2_create_table(&pe->table_group, 0,
 			IOMMU_PAGE_SHIFT_4K,
 			window_size,
-			POWERNV_IOMMU_DEFAULT_LEVELS, &tbl);
+			POWERNV_IOMMU_DEFAULT_LEVELS, false, &tbl);
 	if (rc) {
 		pe_err(pe, "Failed to create 32-bit TCE table, err %ld",
 				rc);
@@ -2606,7 +2595,16 @@ static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
 				tce_table_size, direct_table_size);
 	}
 
-	return bytes;
+	return bytes + bytes; /* one for HW table, one for userspace copy */
+}
+
+static long pnv_pci_ioda2_create_table_userspace(
+		struct iommu_table_group *table_group,
+		int num, __u32 page_shift, __u64 window_size, __u32 levels,
+		struct iommu_table **ptbl)
+{
+	return pnv_pci_ioda2_create_table(table_group,
+			num, page_shift, window_size, levels, true, ptbl);
 }
 
 static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
@@ -2635,7 +2633,7 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
 
 static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
 	.get_table_size = pnv_pci_ioda2_get_table_size,
-	.create_table = pnv_pci_ioda2_create_table,
+	.create_table = pnv_pci_ioda2_create_table_userspace,
 	.set_window = pnv_pci_ioda2_set_window,
 	.unset_window = pnv_pci_ioda2_unset_window,
 	.take_ownership = pnv_ioda2_take_ownership,
@@ -2740,7 +2738,7 @@ static void pnv_ioda2_npu_take_ownership(struct iommu_table_group *table_group)
 
 static struct iommu_table_group_ops pnv_pci_ioda2_npu_ops = {
 	.get_table_size = pnv_pci_ioda2_get_table_size,
-	.create_table = pnv_pci_ioda2_create_table,
+	.create_table = pnv_pci_ioda2_create_table_userspace,
 	.set_window = pnv_pci_ioda2_npu_set_window,
 	.unset_window = pnv_pci_ioda2_npu_unset_window,
 	.take_ownership = pnv_ioda2_npu_take_ownership,
@@ -2774,144 +2772,6 @@ static void pnv_pci_ioda_setup_iommu_api(void)
 static void pnv_pci_ioda_setup_iommu_api(void) { };
 #endif
 
-static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift,
-		unsigned levels, unsigned long limit,
-		unsigned long *current_offset, unsigned long *total_allocated)
-{
-	struct page *tce_mem = NULL;
-	__be64 *addr, *tmp;
-	unsigned order = max_t(unsigned, shift, PAGE_SHIFT) - PAGE_SHIFT;
-	unsigned long allocated = 1UL << (order + PAGE_SHIFT);
-	unsigned entries = 1UL << (shift - 3);
-	long i;
-
-	tce_mem = alloc_pages_node(nid, GFP_KERNEL, order);
-	if (!tce_mem) {
-		pr_err("Failed to allocate a TCE memory, order=%d\n", order);
-		return NULL;
-	}
-	addr = page_address(tce_mem);
-	memset(addr, 0, allocated);
-	*total_allocated += allocated;
-
-	--levels;
-	if (!levels) {
-		*current_offset += allocated;
-		return addr;
-	}
-
-	for (i = 0; i < entries; ++i) {
-		tmp = pnv_pci_ioda2_table_do_alloc_pages(nid, shift,
-				levels, limit, current_offset, total_allocated);
-		if (!tmp)
-			break;
-
-		addr[i] = cpu_to_be64(__pa(tmp) |
-				TCE_PCI_READ | TCE_PCI_WRITE);
-
-		if (*current_offset >= limit)
-			break;
-	}
-
-	return addr;
-}
-
-static void pnv_pci_ioda2_table_do_free_pages(__be64 *addr,
-		unsigned long size, unsigned level);
-
-static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
-		__u32 page_shift, __u64 window_size, __u32 levels,
-		struct iommu_table *tbl)
-{
-	void *addr;
-	unsigned long offset = 0, level_shift, total_allocated = 0;
-	const unsigned window_shift = ilog2(window_size);
-	unsigned entries_shift = window_shift - page_shift;
-	unsigned table_shift = max_t(unsigned, entries_shift + 3, PAGE_SHIFT);
-	const unsigned long tce_table_size = 1UL << table_shift;
-
-	if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS))
-		return -EINVAL;
-
-	if (!is_power_of_2(window_size))
-		return -EINVAL;
-
-	/* Adjust direct table size from window_size and levels */
-	entries_shift = (entries_shift + levels - 1) / levels;
-	level_shift = entries_shift + 3;
-	level_shift = max_t(unsigned, level_shift, PAGE_SHIFT);
-
-	if ((level_shift - 3) * levels + page_shift >= 60)
-		return -EINVAL;
-
-	/* Allocate TCE table */
-	addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
-			levels, tce_table_size, &offset, &total_allocated);
-
-	/* addr==NULL means that the first level allocation failed */
-	if (!addr)
-		return -ENOMEM;
-
-	/*
-	 * First level was allocated but some lower level failed as
-	 * we did not allocate as much as we wanted,
-	 * release partially allocated table.
-	 */
-	if (offset < tce_table_size) {
-		pnv_pci_ioda2_table_do_free_pages(addr,
-				1ULL << (level_shift - 3), levels - 1);
-		return -ENOMEM;
-	}
-
-	/* Setup linux iommu table */
-	pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, bus_offset,
-			page_shift);
-	tbl->it_level_size = 1ULL << (level_shift - 3);
-	tbl->it_indirect_levels = levels - 1;
-	tbl->it_allocated_size = total_allocated;
-
-	pr_devel("Created TCE table: ws=%08llx ts=%lx @%08llx\n",
-			window_size, tce_table_size, bus_offset);
-
-	return 0;
-}
-
-static void pnv_pci_ioda2_table_do_free_pages(__be64 *addr,
-		unsigned long size, unsigned level)
-{
-	const unsigned long addr_ul = (unsigned long) addr &
-			~(TCE_PCI_READ | TCE_PCI_WRITE);
-
-	if (level) {
-		long i;
-		u64 *tmp = (u64 *) addr_ul;
-
-		for (i = 0; i < size; ++i) {
-			unsigned long hpa = be64_to_cpu(tmp[i]);
-
-			if (!(hpa & (TCE_PCI_READ | TCE_PCI_WRITE)))
-				continue;
-
-			pnv_pci_ioda2_table_do_free_pages(__va(hpa), size,
-					level - 1);
-		}
-	}
-
-	free_pages(addr_ul, get_order(size << 3));
-}
-
-static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl)
-{
-	const unsigned long size = tbl->it_indirect_levels ?
-			tbl->it_level_size : tbl->it_size;
-
-	if (!tbl->it_size)
-		return;
-
-	pnv_pci_ioda2_table_do_free_pages((__be64 *)tbl->it_base, size,
-			tbl->it_indirect_levels);
-}
-
 static unsigned long pnv_ioda_parse_tce_sizes(struct pnv_phb *phb)
 {
 	struct pci_controller *hose = phb->hose;
@@ -2926,7 +2786,7 @@ static unsigned long pnv_ioda_parse_tce_sizes(struct pnv_phb *phb)
 		/* Add 16M for POWER8 by default */
 		if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
 				!cpu_has_feature(CPU_FTR_ARCH_300))
-			mask |= SZ_16M;
+			mask |= SZ_16M | SZ_256M;
 		return mask;
 	}
 
@@ -3576,7 +3436,7 @@ static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev,
 /* Prevent enabling devices for which we couldn't properly
  * assign a PE
  */
-bool pnv_pci_enable_device_hook(struct pci_dev *dev)
+static bool pnv_pci_enable_device_hook(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
 	struct pnv_phb *phb = hose->private_data;
@@ -3844,26 +3704,6 @@ static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = {
 	.shutdown		= pnv_pci_ioda_shutdown,
 };
 
-#ifdef CONFIG_CXL_BASE
-const struct pci_controller_ops pnv_cxl_cx4_ioda_controller_ops = {
-	.dma_dev_setup		= pnv_pci_dma_dev_setup,
-	.dma_bus_setup		= pnv_pci_dma_bus_setup,
-#ifdef CONFIG_PCI_MSI
-	.setup_msi_irqs		= pnv_cxl_cx4_setup_msi_irqs,
-	.teardown_msi_irqs	= pnv_cxl_cx4_teardown_msi_irqs,
-#endif
-	.enable_device_hook	= pnv_cxl_enable_device_hook,
-	.disable_device		= pnv_cxl_disable_device,
-	.release_device		= pnv_pci_release_device,
-	.window_alignment	= pnv_pci_window_alignment,
-	.setup_bridge		= pnv_pci_setup_bridge,
-	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
-	.dma_set_mask		= pnv_pci_ioda_dma_set_mask,
-	.dma_get_required_mask	= pnv_pci_ioda_dma_get_required_mask,
-	.shutdown		= pnv_pci_ioda_shutdown,
-};
-#endif
-
 static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 					 u64 hub_id, int ioda_type)
 {