Merge tag 'powerpc-4.21-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Mitigations for Spectre v2 on some Freescale (NXP) CPUs.

   - A large series adding support for pass-through of Nvidia V100 GPUs
     to guests on Power9.

   - Another large series to enable hardware assistance for TLB table
     walk on MPC8xx CPUs.

   - Some preparatory changes to our DMA code, to make way for further
     cleanups from Christoph.

   - Several fixes for our Transactional Memory handling discovered by
     fuzzing the signal return path.

   - Support for generating our system call table(s) from a text file
     like other architectures.

   - A fix to our page fault handler so that instead of generating a
     WARN_ON_ONCE, user accesses of kernel addresses instead print a
     ratelimited and appropriately scary warning.

   - A cosmetic change to make our unhandled page fault messages more
     similar to other arches and also more compact and informative.

   - Freescale updates from Scott:
       "Highlights include elimination of legacy clock bindings use from
        dts files, an 83xx watchdog handler, fixes to old dts interrupt
        errors, and some minor cleanup."

  And many clean-ups, reworks and minor fixes etc.

  Thanks to: Alexandre Belloni, Alexey Kardashevskiy, Andrew Donnellan,
  Aneesh Kumar K.V, Arnd Bergmann, Benjamin Herrenschmidt, Breno Leitao,
  Christian Lamparter, Christophe Leroy, Christoph Hellwig, Daniel
  Axtens, Darren Stevens, David Gibson, Diana Craciun, Dmitry V. Levin,
  Firoz Khan, Geert Uytterhoeven, Greg Kurz, Gustavo Romero, Hari
  Bathini, Joel Stanley, Kees Cook, Madhavan Srinivasan, Mahesh
  Salgaonkar, Markus Elfring, Mathieu Malaterre, Michal Suchánek, Naveen
  N. Rao, Nick Desaulniers, Oliver O'Halloran, Paul Mackerras, Ram Pai,
  Ravi Bangoria, Rob Herring, Russell Currey, Sabyasachi Gupta, Sam
  Bobroff, Satheesh Rajendran, Scott Wood, Segher Boessenkool, Stephen
  Rothwell, Tang Yuantian, Thiago Jung Bauermann, Yangtao Li, Yuantian
  Tang, Yue Haibing"

* tag 'powerpc-4.21-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (201 commits)
  Revert "powerpc/fsl_pci: simplify fsl_pci_dma_set_mask"
  powerpc/zImage: Also check for stdout-path
  powerpc: Fix HMIs on big-endian with CONFIG_RELOCATABLE=y
  macintosh: Use of_node_name_{eq, prefix} for node name comparisons
  ide: Use of_node_name_eq for node name comparisons
  powerpc: Use of_node_name_eq for node name comparisons
  powerpc/pseries/pmem: Convert to %pOFn instead of device_node.name
  powerpc/mm: Remove very old comment in hash-4k.h
  powerpc/pseries: Fix node leak in update_lmb_associativity_index()
  powerpc/configs/85xx: Enable CONFIG_DEBUG_KERNEL
  powerpc/dts/fsl: Fix dtc-flagged interrupt errors
  clk: qoriq: add more compatibles strings
  powerpc/fsl: Use new clockgen binding
  powerpc/83xx: handle machine check caused by watchdog timer
  powerpc/fsl-rio: fix spelling mistake "reserverd" -> "reserved"
  powerpc/fsl_pci: simplify fsl_pci_dma_set_mask
  arch/powerpc/fsl_rmu: Use dma_zalloc_coherent
  vfio_pci: Add NVIDIA GV100GL [Tesla V100 SXM2] subdriver
  vfio_pci: Allow regions to add own capabilities
  vfio_pci: Allow mapping extra regions
  ...

1 files changed, 92 insertions, 18 deletions

diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index 56c2234cc6ae..a712a650a8b6 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -36,6 +36,8 @@ struct mm_iommu_table_group_mem_t {
 	u64 ua;			/* userspace address */
 	u64 entries;		/* number of entries in hpas[] */
 	u64 *hpas;		/* vmalloc'ed */
+#define MM_IOMMU_TABLE_INVALID_HPA	((uint64_t)-1)
+	u64 dev_hpa;		/* Device memory base address */
 };
 
 static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
@@ -126,7 +128,8 @@ static int mm_iommu_move_page_from_cma(struct page *page)
 	return 0;
 }
 
-long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
+static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
+		unsigned long entries, unsigned long dev_hpa,
 		struct mm_iommu_table_group_mem_t **pmem)
 {
 	struct mm_iommu_table_group_mem_t *mem;
@@ -140,12 +143,6 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 
 	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list,
 			next) {
-		if ((mem->ua == ua) && (mem->entries == entries)) {
-			++mem->used;
-			*pmem = mem;
-			goto unlock_exit;
-		}
-
 		/* Overlap? */
 		if ((mem->ua < (ua + (entries << PAGE_SHIFT))) &&
 				(ua < (mem->ua +
@@ -156,11 +153,13 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 
 	}
 
-	ret = mm_iommu_adjust_locked_vm(mm, entries, true);
-	if (ret)
-		goto unlock_exit;
+	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
+		ret = mm_iommu_adjust_locked_vm(mm, entries, true);
+		if (ret)
+			goto unlock_exit;
 
-	locked_entries = entries;
+		locked_entries = entries;
+	}
 
 	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
 	if (!mem) {
@@ -168,6 +167,13 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 		goto unlock_exit;
 	}
 
+	if (dev_hpa != MM_IOMMU_TABLE_INVALID_HPA) {
+		mem->pageshift = __ffs(dev_hpa | (entries << PAGE_SHIFT));
+		mem->dev_hpa = dev_hpa;
+		goto good_exit;
+	}
+	mem->dev_hpa = MM_IOMMU_TABLE_INVALID_HPA;
+
 	/*
 	 * For a starting point for a maximum page size calculation
 	 * we use @ua and @entries natural alignment to allow IOMMU pages
@@ -236,6 +242,7 @@ populate:
 		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
 	}
 
+good_exit:
 	atomic64_set(&mem->mapped, 1);
 	mem->used = 1;
 	mem->ua = ua;
@@ -252,13 +259,31 @@ unlock_exit:
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(mm_iommu_get);
+
+long mm_iommu_new(struct mm_struct *mm, unsigned long ua, unsigned long entries,
+		struct mm_iommu_table_group_mem_t **pmem)
+{
+	return mm_iommu_do_alloc(mm, ua, entries, MM_IOMMU_TABLE_INVALID_HPA,
+			pmem);
+}
+EXPORT_SYMBOL_GPL(mm_iommu_new);
+
+long mm_iommu_newdev(struct mm_struct *mm, unsigned long ua,
+		unsigned long entries, unsigned long dev_hpa,
+		struct mm_iommu_table_group_mem_t **pmem)
+{
+	return mm_iommu_do_alloc(mm, ua, entries, dev_hpa, pmem);
+}
+EXPORT_SYMBOL_GPL(mm_iommu_newdev);
 
 static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem)
 {
 	long i;
 	struct page *page = NULL;
 
+	if (!mem->hpas)
+		return;
+
 	for (i = 0; i < mem->entries; ++i) {
 		if (!mem->hpas[i])
 			continue;
@@ -300,6 +325,7 @@ static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
 long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
 {
 	long ret = 0;
+	unsigned long entries, dev_hpa;
 
 	mutex_lock(&mem_list_mutex);
 
@@ -321,9 +347,12 @@ long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
 	}
 
 	/* @mapped became 0 so now mappings are disabled, release the region */
+	entries = mem->entries;
+	dev_hpa = mem->dev_hpa;
 	mm_iommu_release(mem);
 
-	mm_iommu_adjust_locked_vm(mm, mem->entries, false);
+	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
+		mm_iommu_adjust_locked_vm(mm, entries, false);
 
 unlock_exit:
 	mutex_unlock(&mem_list_mutex);
@@ -368,27 +397,32 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm,
 	return ret;
 }
 
-struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
+struct mm_iommu_table_group_mem_t *mm_iommu_get(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries)
 {
 	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
 
+	mutex_lock(&mem_list_mutex);
+
 	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
 		if ((mem->ua == ua) && (mem->entries == entries)) {
 			ret = mem;
+			++mem->used;
 			break;
 		}
 	}
 
+	mutex_unlock(&mem_list_mutex);
+
 	return ret;
 }
-EXPORT_SYMBOL_GPL(mm_iommu_find);
+EXPORT_SYMBOL_GPL(mm_iommu_get);
 
 long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
-	u64 *va = &mem->hpas[entry];
+	u64 *va;
 
 	if (entry >= mem->entries)
 		return -EFAULT;
@@ -396,6 +430,12 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 	if (pageshift > mem->pageshift)
 		return -EFAULT;
 
+	if (!mem->hpas) {
+		*hpa = mem->dev_hpa + (ua - mem->ua);
+		return 0;
+	}
+
+	va = &mem->hpas[entry];
 	*hpa = (*va & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);
 
 	return 0;
@@ -406,7 +446,6 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
 		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
-	void *va = &mem->hpas[entry];
 	unsigned long *pa;
 
 	if (entry >= mem->entries)
@@ -415,7 +454,12 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
 	if (pageshift > mem->pageshift)
 		return -EFAULT;
 
-	pa = (void *) vmalloc_to_phys(va);
+	if (!mem->hpas) {
+		*hpa = mem->dev_hpa + (ua - mem->ua);
+		return 0;
+	}
+
+	pa = (void *) vmalloc_to_phys(&mem->hpas[entry]);
 	if (!pa)
 		return -EFAULT;
 
@@ -435,6 +479,9 @@ extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua)
 	if (!mem)
 		return;
 
+	if (mem->dev_hpa != MM_IOMMU_TABLE_INVALID_HPA)
+		return;
+
 	entry = (ua - mem->ua) >> PAGE_SHIFT;
 	va = &mem->hpas[entry];
 
@@ -445,6 +492,33 @@ extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua)
 	*pa |= MM_IOMMU_TABLE_GROUP_PAGE_DIRTY;
 }
 
+bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa,
+		unsigned int pageshift, unsigned long *size)
+{
+	struct mm_iommu_table_group_mem_t *mem;
+	unsigned long end;
+
+	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
+		if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
+			continue;
+
+		end = mem->dev_hpa + (mem->entries << PAGE_SHIFT);
+		if ((mem->dev_hpa <= hpa) && (hpa < end)) {
+			/*
+			 * Since the IOMMU page size might be bigger than
+			 * PAGE_SIZE, the amount of preregistered memory
+			 * starting from @hpa might be smaller than 1<<pageshift
+			 * and the caller needs to distinguish this situation.
+			 */
+			*size = min(1UL << pageshift, end - hpa);
+			return true;
+		}
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_is_devmem);
+
 long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
 {
 	if (atomic64_inc_not_zero(&mem->mapped))