Merge branch 'mm-everything' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

# Conflicts:
#	drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
#	include/linux/hugetlb.h
#	mm/gup.c
#	mm/hugetlb.c

.mailmap

@@ -137,6 +137,7 @@ Filipe Lautert <filipe@icewall.org>
 Finn Thain <fthain@linux-m68k.org> <fthain@telegraphics.com.au>
 Franck Bui-Huu <vagabon.xyz@gmail.com>
 Frank Rowand <frowand.list@gmail.com> <frank.rowand@am.sony.com>
+Frank Rowand <frowand.list@gmail.com> <frank.rowand@sony.com>
 Frank Rowand <frowand.list@gmail.com> <frank.rowand@sonymobile.com>
 Frank Rowand <frowand.list@gmail.com> <frowand@mvista.com>
 Frank Zago <fzago@systemfabricworks.com>

Documentation/admin-guide/sysctl/kernel.rst

@@ -174,6 +174,7 @@ core_pattern
 	%f      	executable filename
 	%E		executable path
 	%c		maximum size of core file by resource limit RLIMIT_CORE
+	%C		CPU the task ran on
 	%<OTHER>	both are dropped
 	========	==========================================
 

Documentation/fault-injection/fault-injection.rst

@@ -83,9 +83,7 @@ configuration of fault-injection capabilities.
 - /sys/kernel/debug/fail*/times:
 
 	specifies how many times failures may happen at most. A value of -1
-	means "no limit". Note, though, that this file only accepts unsigned
-	values. So, if you want to specify -1, you better use 'printf' instead
-	of 'echo', e.g.: $ printf %#x -1 > times
+	means "no limit".
 
 - /sys/kernel/debug/fail*/space:
 
@@ -284,7 +282,7 @@ Application Examples
     echo Y > /sys/kernel/debug/$FAILTYPE/task-filter
     echo 10 > /sys/kernel/debug/$FAILTYPE/probability
     echo 100 > /sys/kernel/debug/$FAILTYPE/interval
-    printf %#x -1 > /sys/kernel/debug/$FAILTYPE/times
+    echo -1 > /sys/kernel/debug/$FAILTYPE/times
     echo 0 > /sys/kernel/debug/$FAILTYPE/space
     echo 2 > /sys/kernel/debug/$FAILTYPE/verbose
     echo Y > /sys/kernel/debug/$FAILTYPE/ignore-gfp-wait
@@ -338,7 +336,7 @@ Application Examples
     echo N > /sys/kernel/debug/$FAILTYPE/task-filter
     echo 10 > /sys/kernel/debug/$FAILTYPE/probability
     echo 100 > /sys/kernel/debug/$FAILTYPE/interval
-    printf %#x -1 > /sys/kernel/debug/$FAILTYPE/times
+    echo -1 > /sys/kernel/debug/$FAILTYPE/times
     echo 0 > /sys/kernel/debug/$FAILTYPE/space
     echo 2 > /sys/kernel/debug/$FAILTYPE/verbose
     echo Y > /sys/kernel/debug/$FAILTYPE/ignore-gfp-wait
@@ -369,7 +367,7 @@ Application Examples
     echo N > /sys/kernel/debug/$FAILTYPE/task-filter
     echo 100 > /sys/kernel/debug/$FAILTYPE/probability
     echo 0 > /sys/kernel/debug/$FAILTYPE/interval
-    printf %#x -1 > /sys/kernel/debug/$FAILTYPE/times
+    echo -1 > /sys/kernel/debug/$FAILTYPE/times
     echo 0 > /sys/kernel/debug/$FAILTYPE/space
     echo 1 > /sys/kernel/debug/$FAILTYPE/verbose
 

Documentation/mm/balance.rst

@@ -6,7 +6,7 @@ Memory Balancing
 
 Started Jan 2000 by Kanoj Sarcar <kanoj@sgi.com>
 
-Memory balancing is needed for !__GFP_ATOMIC and !__GFP_KSWAPD_RECLAIM as
+Memory balancing is needed for !__GFP_HIGH and !__GFP_KSWAPD_RECLAIM as
 well as for non __GFP_IO allocations.
 
 The first reason why a caller may avoid reclaim is that the caller can not

arch/ia64/configs/bigsur_defconfig

@@ -20,7 +20,6 @@ CONFIG_UNIX=y
 CONFIG_INET=y
 # CONFIG_IPV6 is not set
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=m
 CONFIG_ATA=m
@@ -91,7 +90,6 @@ CONFIG_NFS_V4=m
 CONFIG_NFSD=m
 CONFIG_NFSD_V4=y
 CONFIG_CIFS=m
-CONFIG_CIFS_STATS=y
 CONFIG_CIFS_XATTR=y
 CONFIG_CIFS_POSIX=y
 CONFIG_NLS_CODEPAGE_437=y

arch/ia64/configs/generic_defconfig

@@ -39,7 +39,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 # CONFIG_PNP_DEBUG_MESSAGES is not set
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_SGI_XP=m
@@ -91,7 +90,6 @@ CONFIG_SERIAL_8250_SHARE_IRQ=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_EFI=y
-CONFIG_RAW_DRIVER=m
 CONFIG_HPET=y
 CONFIG_AGP=m
 CONFIG_AGP_I460=m

arch/ia64/configs/gensparse_defconfig

@@ -31,11 +31,9 @@ CONFIG_IP_MULTICAST=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_ATA=y
-CONFIG_BLK_DEV_IDECD=y
 CONFIG_ATA_GENERIC=y
 CONFIG_PATA_CMD64X=y
 CONFIG_ATA_PIIX=y
@@ -81,7 +79,6 @@ CONFIG_SERIAL_8250_SHARE_IRQ=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_EFI=y
-CONFIG_RAW_DRIVER=m
 CONFIG_HPET=y
 CONFIG_AGP=m
 CONFIG_AGP_I460=m

arch/ia64/configs/tiger_defconfig

@@ -36,7 +36,6 @@ CONFIG_IP_MULTICAST=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_ATA=y
@@ -85,7 +84,6 @@ CONFIG_SERIAL_8250_SHARE_IRQ=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_EFI=y
-CONFIG_RAW_DRIVER=m
 CONFIG_HPET=y
 CONFIG_AGP=m
 CONFIG_AGP_I460=m

arch/ia64/configs/zx1_defconfig

@@ -30,7 +30,6 @@ CONFIG_PATA_CMD64X=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=y
-CONFIG_CHR_DEV_OSST=y
 CONFIG_BLK_DEV_SR=y
 CONFIG_CHR_DEV_SG=y
 CONFIG_SCSI_CONSTANTS=y

arch/ia64/kernel/mca.c

@@ -1793,7 +1793,7 @@ format_mca_init_stack(void *mca_data, unsigned long offset,
 	p->parent = p->real_parent = p->group_leader = p;
 	INIT_LIST_HEAD(&p->children);
 	INIT_LIST_HEAD(&p->sibling);
-	strncpy(p->comm, type, sizeof(p->comm)-1);
+	strscpy(p->comm, type, sizeof(p->comm)-1);
 }
 
 /* Caller prevents this from being called after init */

arch/ia64/mm/hugetlbpage.c

@@ -91,21 +91,6 @@ int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-struct page *follow_huge_addr(struct mm_struct *mm, unsigned long addr, int write)
-{
-	struct page *page;
-	pte_t *ptep;
-
-	if (REGION_NUMBER(addr) != RGN_HPAGE)
-		return ERR_PTR(-EINVAL);
-
-	ptep = huge_pte_offset(mm, addr, HPAGE_SIZE);
-	if (!ptep || pte_none(*ptep))
-		return NULL;
-	page = pte_page(*ptep);
-	page += ((addr & ~HPAGE_MASK) >> PAGE_SHIFT);
-	return page;
-}
 int pmd_huge(pmd_t pmd)
 {
 	return 0;

arch/loongarch/include/asm/pgtable.h

@@ -412,6 +412,9 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 	__update_tlb(vma, address, ptep);
 }
 
+#define __HAVE_ARCH_UPDATE_MMU_TLB
+#define update_mmu_tlb	update_mmu_cache
+
 static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 			unsigned long address, pmd_t *pmdp)
 {

arch/powerpc/kvm/book3s_hv_uvmem.c

@@ -508,10 +508,10 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
 		unsigned long start,
 		unsigned long end, unsigned long page_shift,
-		struct kvm *kvm, unsigned long gpa)
+		struct kvm *kvm, unsigned long gpa, struct page *fault_page)
 {
 	unsigned long src_pfn, dst_pfn = 0;
-	struct migrate_vma mig;
+	struct migrate_vma mig = { 0 };
 	struct page *dpage, *spage;
 	struct kvmppc_uvmem_page_pvt *pvt;
 	unsigned long pfn;
@@ -525,6 +525,7 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
 	mig.dst = &dst_pfn;
 	mig.pgmap_owner = &kvmppc_uvmem_pgmap;
 	mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
+	mig.fault_page = fault_page;
 
 	/* The requested page is already paged-out, nothing to do */
 	if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL))
@@ -580,12 +581,14 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
 static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
 				      unsigned long start, unsigned long end,
 				      unsigned long page_shift,
-				      struct kvm *kvm, unsigned long gpa)
+				      struct kvm *kvm, unsigned long gpa,
+				      struct page *fault_page)
 {
 	int ret;
 
 	mutex_lock(&kvm->arch.uvmem_lock);
-	ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa);
+	ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa,
+				fault_page);
 	mutex_unlock(&kvm->arch.uvmem_lock);
 
 	return ret;
@@ -634,7 +637,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
 			pvt->remove_gfn = true;
 
 			if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE,
-						  PAGE_SHIFT, kvm, pvt->gpa))
+						  PAGE_SHIFT, kvm, pvt->gpa, NULL))
 				pr_err("Can't page out gpa:0x%lx addr:0x%lx\n",
 				       pvt->gpa, addr);
 		} else {
@@ -715,7 +718,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
 
 	dpage = pfn_to_page(uvmem_pfn);
 	dpage->zone_device_data = pvt;
-	lock_page(dpage);
+	zone_device_page_init(dpage);
 	return dpage;
 out_clear:
 	spin_lock(&kvmppc_uvmem_bitmap_lock);
@@ -736,7 +739,7 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma,
 		bool pagein)
 {
 	unsigned long src_pfn, dst_pfn = 0;
-	struct migrate_vma mig;
+	struct migrate_vma mig = { 0 };
 	struct page *spage;
 	unsigned long pfn;
 	struct page *dpage;
@@ -994,7 +997,7 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
 
 	if (kvmppc_svm_page_out(vmf->vma, vmf->address,
 				vmf->address + PAGE_SIZE, PAGE_SHIFT,
-				pvt->kvm, pvt->gpa))
+				pvt->kvm, pvt->gpa, vmf->page))
 		return VM_FAULT_SIGBUS;
 	else
 		return 0;
@@ -1065,7 +1068,7 @@ kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gpa,
 	if (!vma || vma->vm_start > start || vma->vm_end < end)
 		goto out;
 
-	if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa))
+	if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa, NULL))
 		ret = H_SUCCESS;
 out:
 	mmap_read_unlock(kvm->mm);

arch/powerpc/mm/hugetlbpage.c

@@ -506,43 +506,6 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 	} while (addr = next, addr != end);
 }
 
-struct page *follow_huge_pd(struct vm_area_struct *vma,
-			    unsigned long address, hugepd_t hpd,
-			    int flags, int pdshift)
-{
-	pte_t *ptep;
-	spinlock_t *ptl;
-	struct page *page = NULL;
-	unsigned long mask;
-	int shift = hugepd_shift(hpd);
-	struct mm_struct *mm = vma->vm_mm;
-
-retry:
-	/*
-	 * hugepage directory entries are protected by mm->page_table_lock
-	 * Use this instead of huge_pte_lockptr
-	 */
-	ptl = &mm->page_table_lock;
-	spin_lock(ptl);
-
-	ptep = hugepte_offset(hpd, address, pdshift);
-	if (pte_present(*ptep)) {
-		mask = (1UL << shift) - 1;
-		page = pte_page(*ptep);
-		page += ((address & mask) >> PAGE_SHIFT);
-		if (flags & FOLL_GET)
-			get_page(page);
-	} else {
-		if (is_hugetlb_entry_migration(*ptep)) {
-			spin_unlock(ptl);
-			__migration_entry_wait(mm, ptep, ptl);
-			goto retry;
-		}
-	}
-	spin_unlock(ptl);
-	return page;
-}
-
 bool __init arch_hugetlb_valid_size(unsigned long size)
 {
 	int shift = __ffs(size);

drivers/block/zram/zram_drv.c

@@ -52,9 +52,6 @@ static unsigned int num_devices = 1;
 static size_t huge_class_size;
 
 static const struct block_device_operations zram_devops;
-#ifdef CONFIG_ZRAM_WRITEBACK
-static const struct block_device_operations zram_wb_devops;
-#endif
 
 static void zram_free_page(struct zram *zram, size_t index);
 static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
@@ -546,17 +543,6 @@ static ssize_t backing_dev_store(struct device *dev,
 	zram->backing_dev = backing_dev;
 	zram->bitmap = bitmap;
 	zram->nr_pages = nr_pages;
-	/*
-	 * With writeback feature, zram does asynchronous IO so it's no longer
-	 * synchronous device so let's remove synchronous io flag. Othewise,
-	 * upper layer(e.g., swap) could wait IO completion rather than
-	 * (submit and return), which will cause system sluggish.
-	 * Furthermore, when the IO function returns(e.g., swap_readpage),
-	 * upper layer expects IO was done so it could deallocate the page
-	 * freely but in fact, IO is going on so finally could cause
-	 * use-after-free when the IO is really done.
-	 */
-	zram->disk->fops = &zram_wb_devops;
 	up_write(&zram->init_lock);
 
 	pr_info("setup backing device %s\n", file_name);
@@ -1270,6 +1256,9 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
 		struct bio_vec bvec;
 
 		zram_slot_unlock(zram, index);
+		/* A null bio means rw_page was used, we must fallback to bio */
+		if (!bio)
+			return -EOPNOTSUPP;
 
 		bvec.bv_page = page;
 		bvec.bv_len = PAGE_SIZE;
@@ -1856,15 +1845,6 @@ static const struct block_device_operations zram_devops = {
 	.owner = THIS_MODULE
 };
 
-#ifdef CONFIG_ZRAM_WRITEBACK
-static const struct block_device_operations zram_wb_devops = {
-	.open = zram_open,
-	.submit_bio = zram_submit_bio,
-	.swap_slot_free_notify = zram_slot_free_notify,
-	.owner = THIS_MODULE
-};
-#endif
-
 static DEVICE_ATTR_WO(compact);
 static DEVICE_ATTR_RW(disksize);
 static DEVICE_ATTR_RO(initstate);

drivers/gpu/drm/amd/amdkfd/kfd_migrate.c

@@ -223,7 +223,7 @@ svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn)
 	page = pfn_to_page(pfn);
 	svm_range_bo_ref(prange->svm_bo);
 	page->zone_device_data = prange->svm_bo;
-	lock_page(page);
+	zone_device_page_init(page);
 }
 
 static void
@@ -410,7 +410,7 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 	uint64_t npages = (end - start) >> PAGE_SHIFT;
 	struct kfd_process_device *pdd;
 	struct dma_fence *mfence = NULL;
-	struct migrate_vma migrate;
+	struct migrate_vma migrate = { 0 };
 	unsigned long cpages = 0;
 	dma_addr_t *scratch;
 	void *buf;
@@ -666,7 +666,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 static long
 svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 		       struct vm_area_struct *vma, uint64_t start, uint64_t end,
-		       uint32_t trigger)
+		       uint32_t trigger, struct page *fault_page)
 {
 	struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms);
 	uint64_t npages = (end - start) >> PAGE_SHIFT;
@@ -674,7 +674,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	unsigned long cpages = 0;
 	struct kfd_process_device *pdd;
 	struct dma_fence *mfence = NULL;
-	struct migrate_vma migrate;
+	struct migrate_vma migrate = { 0 };
 	dma_addr_t *scratch;
 	void *buf;
 	int r = -ENOMEM;
@@ -697,6 +697,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 
 	migrate.src = buf;
 	migrate.dst = migrate.src + npages;
+	migrate.fault_page = fault_page;
 	scratch = (dma_addr_t *)(migrate.dst + npages);
 
 	kfd_smi_event_migration_start(adev->kfd.dev, p->lead_thread->pid,
@@ -764,7 +765,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
  * 0 - OK, otherwise error code
  */
 int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm,
-			    uint32_t trigger)
+			    uint32_t trigger, struct page *fault_page)
 {
 	struct amdgpu_device *adev;
 	struct vm_area_struct *vma;
@@ -805,7 +806,8 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm,
 		}
 
 		next = min(vma->vm_end, end);
-		r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next, trigger);
+		r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next, trigger,
+			fault_page);
 		if (r < 0) {
 			pr_debug("failed %ld to migrate prange %p\n", r, prange);
 			break;
@@ -849,7 +851,7 @@ svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc,
 	pr_debug("from gpu 0x%x to gpu 0x%x\n", prange->actual_loc, best_loc);
 
 	do {
-		r = svm_migrate_vram_to_ram(prange, mm, trigger);
+		r = svm_migrate_vram_to_ram(prange, mm, trigger, NULL);
 		if (r)
 			return r;
 	} while (prange->actual_loc && --retries);
@@ -950,7 +952,8 @@ static vm_fault_t svm_migrate_to_ram(struct vm_fault *vmf)
 	}
 
 	r = svm_migrate_vram_to_ram(prange, vmf->vma->vm_mm,
-				    KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU);
+				    KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU,
+				    vmf->page);
 	if (r)
 		pr_debug("failed %d migrate svms 0x%p range 0x%p [0x%lx 0x%lx]\n",
 			 r, prange->svms, prange, prange->start, prange->last);

drivers/gpu/drm/amd/amdkfd/kfd_migrate.h

@@ -43,7 +43,7 @@ enum MIGRATION_COPY_DIR {
 int svm_migrate_to_vram(struct svm_range *prange,  uint32_t best_loc,
 			struct mm_struct *mm, uint32_t trigger);
 int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm,
-			    uint32_t trigger);
+			    uint32_t trigger, struct page *fault_page);
 unsigned long
 svm_migrate_addr_to_pfn(struct amdgpu_device *adev, unsigned long addr);
 

drivers/gpu/drm/amd/amdkfd/kfd_svm.c

@@ -2913,13 +2913,15 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,
 				 */
 				if (prange->actual_loc)
 					r = svm_migrate_vram_to_ram(prange, mm,
-					   KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU);
+					   KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU,
+					   NULL);
 				else
 					r = 0;
 			}
 		} else {
 			r = svm_migrate_vram_to_ram(prange, mm,
-					KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU);
+					KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU,
+					NULL);
 		}
 		if (r) {
 			pr_debug("failed %d to migrate svms %p [0x%lx 0x%lx]\n",
@@ -3278,7 +3280,8 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange,
 		return 0;
 
 	if (!best_loc) {
-		r = svm_migrate_vram_to_ram(prange, mm, KFD_MIGRATE_TRIGGER_PREFETCH);
+		r = svm_migrate_vram_to_ram(prange, mm,
+					KFD_MIGRATE_TRIGGER_PREFETCH, NULL);
 		*migrated = !r;
 		return r;
 	}
@@ -3339,7 +3342,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 		mutex_lock(&prange->migrate_mutex);
 		do {
 			r = svm_migrate_vram_to_ram(prange, mm,
-						KFD_MIGRATE_TRIGGER_TTM_EVICTION);
+					KFD_MIGRATE_TRIGGER_TTM_EVICTION, NULL);
 		} while (!r && prange->actual_loc && --retries);
 
 		if (!r && prange->actual_loc)

drivers/gpu/drm/nouveau/nouveau_dmem.c

@@ -139,44 +139,24 @@ static void nouveau_dmem_fence_done(struct nouveau_fence **fence)
 	}
 }
 
-static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm,
-		struct vm_fault *vmf, struct migrate_vma *args,
-		dma_addr_t *dma_addr)
+static int nouveau_dmem_copy_one(struct nouveau_drm *drm, struct page *spage,
+				struct page *dpage, dma_addr_t *dma_addr)
 {
 	struct device *dev = drm->dev->dev;
-	struct page *dpage, *spage;
-	struct nouveau_svmm *svmm;
-
-	spage = migrate_pfn_to_page(args->src[0]);
-	if (!spage || !(args->src[0] & MIGRATE_PFN_MIGRATE))
-		return 0;
 
-	dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address);
-	if (!dpage)
-		return VM_FAULT_SIGBUS;
 	lock_page(dpage);
 
 	*dma_addr = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(dev, *dma_addr))
-		goto error_free_page;
+		return -EIO;
 
-	svmm = spage->zone_device_data;
-	mutex_lock(&svmm->mutex);
-	nouveau_svmm_invalidate(svmm, args->start, args->end);
 	if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_HOST, *dma_addr,
-			NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage)))
-		goto error_dma_unmap;
-	mutex_unlock(&svmm->mutex);
+					 NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage))) {
+		dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
+		return -EIO;
+	}
 
-	args->dst[0] = migrate_pfn(page_to_pfn(dpage));
 	return 0;
-
-error_dma_unmap:
-	mutex_unlock(&svmm->mutex);
-	dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
-error_free_page:
-	__free_page(dpage);
-	return VM_FAULT_SIGBUS;
 }
 
 static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
@@ -184,9 +164,11 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
 	struct nouveau_drm *drm = page_to_drm(vmf->page);
 	struct nouveau_dmem *dmem = drm->dmem;
 	struct nouveau_fence *fence;
+	struct nouveau_svmm *svmm;
+	struct page *spage, *dpage;
 	unsigned long src = 0, dst = 0;
 	dma_addr_t dma_addr = 0;
-	vm_fault_t ret;
+	vm_fault_t ret = 0;
 	struct migrate_vma args = {
 		.vma		= vmf->vma,
 		.start		= vmf->address,
@@ -207,10 +189,26 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
 	if (!args.cpages)
 		return 0;
 
-	ret = nouveau_dmem_fault_copy_one(drm, vmf, &args, &dma_addr);
-	if (ret || dst == 0)
+	spage = migrate_pfn_to_page(src);
+	if (!spage || !(src & MIGRATE_PFN_MIGRATE))
+		goto done;
+
+	dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address);
+	if (!dpage)
 		goto done;
 
+	dst = migrate_pfn(page_to_pfn(dpage));
+
+	svmm = spage->zone_device_data;
+	mutex_lock(&svmm->mutex);
+	nouveau_svmm_invalidate(svmm, args.start, args.end);
+	ret = nouveau_dmem_copy_one(drm, spage, dpage, &dma_addr);
+	mutex_unlock(&svmm->mutex);
+	if (ret) {
+		ret = VM_FAULT_SIGBUS;
+		goto done;
+	}
+
 	nouveau_fence_new(dmem->migrate.chan, false, &fence);
 	migrate_vma_pages(&args);
 	nouveau_dmem_fence_done(&fence);
@@ -326,7 +324,7 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm)
 			return NULL;
 	}
 
-	lock_page(page);
+	zone_device_page_init(page);
 	return page;
 }
 
@@ -369,6 +367,52 @@ nouveau_dmem_suspend(struct nouveau_drm *drm)
 	mutex_unlock(&drm->dmem->mutex);
 }
 
+/*
+ * Evict all pages mapping a chunk.
+ */
+static void
+nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
+{
+	unsigned long i, npages = range_len(&chunk->pagemap.range) >> PAGE_SHIFT;
+	unsigned long *src_pfns, *dst_pfns;
+	dma_addr_t *dma_addrs;
+	struct nouveau_fence *fence;
+
+	src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL);
+	dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL);
+	dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL);
+
+	migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT,
+			npages);
+
+	for (i = 0; i < npages; i++) {
+		if (src_pfns[i] & MIGRATE_PFN_MIGRATE) {
+			struct page *dpage;
+
+			/*
+			 * _GFP_NOFAIL because the GPU is going away and there
+			 * is nothing sensible we can do if we can't copy the
+			 * data back.
+			 */
+			dpage = alloc_page(GFP_HIGHUSER | __GFP_NOFAIL);
+			dst_pfns[i] = migrate_pfn(page_to_pfn(dpage));
+			nouveau_dmem_copy_one(chunk->drm,
+					migrate_pfn_to_page(src_pfns[i]), dpage,
+					&dma_addrs[i]);
+		}
+	}
+
+	nouveau_fence_new(chunk->drm->dmem->migrate.chan, false, &fence);
+	migrate_device_pages(src_pfns, dst_pfns, npages);
+	nouveau_dmem_fence_done(&fence);
+	migrate_device_finalize(src_pfns, dst_pfns, npages);
+	kfree(src_pfns);
+	kfree(dst_pfns);
+	for (i = 0; i < npages; i++)
+		dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL);
+	kfree(dma_addrs);
+}
+
 void
 nouveau_dmem_fini(struct nouveau_drm *drm)
 {
@@ -380,8 +424,10 @@ nouveau_dmem_fini(struct nouveau_drm *drm)
 	mutex_lock(&drm->dmem->mutex);
 
 	list_for_each_entry_safe(chunk, tmp, &drm->dmem->chunks, list) {
+		nouveau_dmem_evict_chunk(chunk);
 		nouveau_bo_unpin(chunk->bo);
 		nouveau_bo_ref(NULL, &chunk->bo);
+		WARN_ON(chunk->callocated);
 		list_del(&chunk->list);
 		memunmap_pages(&chunk->pagemap);
 		release_mem_region(chunk->pagemap.range.start,

drivers/iommu/tegra-smmu.c

@@ -671,12 +671,12 @@ static struct page *as_get_pde_page(struct tegra_smmu_as *as,
 	 * allocate page in a sleeping context if GFP flags permit. Hence
 	 * spinlock needs to be unlocked and re-locked after allocation.
 	 */
-	if (!(gfp & __GFP_ATOMIC))
+	if (gfp & __GFP_DIRECT_RECLAIM)
 		spin_unlock_irqrestore(&as->lock, *flags);
 
 	page = alloc_page(gfp | __GFP_DMA | __GFP_ZERO);
 
-	if (!(gfp & __GFP_ATOMIC))
+	if (gfp & __GFP_DIRECT_RECLAIM)
 		spin_lock_irqsave(&as->lock, *flags);
 
 	/*