36 files changed, 259 insertions, 151 deletions

diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 4f798aa671dd..3817a3e2146c 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -24,6 +24,7 @@ config MICROBLAZE
         select HAVE_FTRACE_MCOUNT_RECORD
         select HAVE_FUNCTION_GRAPH_TRACER
         select HAVE_FUNCTION_TRACER
+        select NO_BOOTMEM
         select HAVE_MEMBLOCK
         select HAVE_MEMBLOCK_NODE_MAP
         select HAVE_OPROFILE
diff --git a/arch/microblaze/Kconfig.platform b/arch/microblaze/Kconfig.platform
index 6996f397c16c..f7f1739c11b9 100644
--- a/arch/microblaze/Kconfig.platform
+++ b/arch/microblaze/Kconfig.platform
@@ -8,7 +8,6 @@ menu "Platform options"
 
 config OPT_LIB_FUNCTION
         bool "Optimalized lib function"
-        depends on CPU_LITTLE_ENDIAN
         default y
         help
           Allows turn on optimalized library function (memcpy and memmove).
@@ -21,6 +20,7 @@ config OPT_LIB_FUNCTION
 config OPT_LIB_ASM
         bool "Optimalized lib function ASM"
         depends on OPT_LIB_FUNCTION && (XILINX_MICROBLAZE0_USE_BARREL = 1)
+        depends on CPU_BIG_ENDIAN
         default n
         help
           Allows turn on optimalized library function (memcpy and memmove).
diff --git a/arch/microblaze/include/asm/setup.h b/arch/microblaze/include/asm/setup.h
index be84a4d3917f..7c968c1d1729 100644
--- a/arch/microblaze/include/asm/setup.h
+++ b/arch/microblaze/include/asm/setup.h
@@ -44,7 +44,6 @@ void machine_shutdown(void);
 void machine_halt(void);
 void machine_power_off(void);
 
-extern void *alloc_maybe_bootmem(size_t size, gfp_t mask);
 extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
 
 # endif /* __ASSEMBLY__ */
diff --git a/arch/microblaze/lib/fastcopy.S b/arch/microblaze/lib/fastcopy.S
index 62021d7e249e..fdc48bb065d8 100644
--- a/arch/microblaze/lib/fastcopy.S
+++ b/arch/microblaze/lib/fastcopy.S
@@ -29,10 +29,6 @@
  *      between mem locations with size of xfer spec'd in bytes
  */
 
-#ifdef __MICROBLAZEEL__
-#error Microblaze LE not support ASM optimized lib func. Disable OPT_LIB_ASM.
-#endif
-
 #include <linux/linkage.h>
         .text
         .globl  memcpy
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 434639f9a3a6..df6de7ccdc2e 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -32,9 +32,6 @@ int mem_init_done;
 #ifndef CONFIG_MMU
 unsigned int __page_offset;
 EXPORT_SYMBOL(__page_offset);
-
-#else
-static int init_bootmem_done;
 #endif /* CONFIG_MMU */
 
 char *klimit = _end;
@@ -117,7 +114,6 @@ static void __init paging_init(void)
 
 void __init setup_memory(void)
 {
-        unsigned long map_size;
         struct memblock_region *reg;
 
 #ifndef CONFIG_MMU
@@ -174,17 +170,6 @@ void __init setup_memory(void)
         pr_info("%s: max_low_pfn: %#lx\n", __func__, max_low_pfn);
         pr_info("%s: max_pfn: %#lx\n", __func__, max_pfn);
 
-        /*
-         * Find an area to use for the bootmem bitmap.
-         * We look for the first area which is at least
-         * 128kB in length (128kB is enough for a bitmap
-         * for 4GB of memory, using 4kB pages), plus 1 page
-         * (in case the address isn't page-aligned).
-         */
-        map_size = init_bootmem_node(NODE_DATA(0),
-                PFN_UP(TOPHYS((u32)klimit)), min_low_pfn, max_low_pfn);
-        memblock_reserve(PFN_UP(TOPHYS((u32)klimit)) << PAGE_SHIFT, map_size);
-
         /* Add active regions with valid PFNs */
         for_each_memblock(memory, reg) {
                 unsigned long start_pfn, end_pfn;
@@ -196,32 +181,9 @@ void __init setup_memory(void)
                                   &memblock.memory, 0);
         }
 
-        /* free bootmem is whole main memory */
-        free_bootmem_with_active_regions(0, max_low_pfn);
-
-        /* reserve allocate blocks */
-        for_each_memblock(reserved, reg) {
-                unsigned long top = reg->base + reg->size - 1;
-
-                pr_debug("reserved - 0x%08x-0x%08x, %lx, %lx\n",
-                         (u32) reg->base, (u32) reg->size, top,
-                                                memory_start + lowmem_size - 1);
-
-                if (top <= (memory_start + lowmem_size - 1)) {
-                        reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
-                } else if (reg->base < (memory_start + lowmem_size - 1)) {
-                        unsigned long trunc_size = memory_start + lowmem_size -
-                                                                reg->base;
-                        reserve_bootmem(reg->base, trunc_size, BOOTMEM_DEFAULT);
-                }
-        }
-
         /* XXX need to clip this if using highmem? */
         sparse_memory_present_with_active_regions(0);
 
-#ifdef CONFIG_MMU
-        init_bootmem_done = 1;
-#endif
         paging_init();
 }
 
@@ -398,30 +360,16 @@ asmlinkage void __init mmu_init(void)
 /* This is only called until mem_init is done. */
 void __init *early_get_page(void)
 {
-        void *p;
-        if (init_bootmem_done) {
-                p = alloc_bootmem_pages(PAGE_SIZE);
-        } else {
-                /*
-                 * Mem start + kernel_tlb -> here is limit
-                 * because of mem mapping from head.S
-                 */
-                p = __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE,
-                                        memory_start + kernel_tlb));
-        }
-        return p;
+        /*
+         * Mem start + kernel_tlb -> here is limit
+         * because of mem mapping from head.S
+         */
+        return __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE,
+                                memory_start + kernel_tlb));
 }
 
 #endif /* CONFIG_MMU */
 
-void * __ref alloc_maybe_bootmem(size_t size, gfp_t mask)
-{
-        if (mem_init_done)
-                return kmalloc(size, mask);
-        else
-                return alloc_bootmem(size);
-}
-
 void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask)
 {
         void *p;
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 79089778725b..e3b45546d589 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -543,7 +543,8 @@ void flush_cache_mm(struct mm_struct *mm)
            rp3440, etc.  So, avoid it if the mm isn't too big.  */
         if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
             mm_total_size(mm) >= parisc_cache_flush_threshold) {
-                flush_tlb_all();
+                if (mm->context)
+                        flush_tlb_all();
                 flush_cache_all();
                 return;
         }
@@ -571,6 +572,8 @@ void flush_cache_mm(struct mm_struct *mm)
                         pfn = pte_pfn(*ptep);
                         if (!pfn_valid(pfn))
                                 continue;
+                        if (unlikely(mm->context))
+                                flush_tlb_page(vma, addr);
                         __flush_cache_page(vma, addr, PFN_PHYS(pfn));
                 }
         }
@@ -579,26 +582,46 @@ void flush_cache_mm(struct mm_struct *mm)
 void flush_cache_range(struct vm_area_struct *vma,
                 unsigned long start, unsigned long end)
 {
+        pgd_t *pgd;
+        unsigned long addr;
+
         if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
             end - start >= parisc_cache_flush_threshold) {
-                flush_tlb_range(vma, start, end);
+                if (vma->vm_mm->context)
+                        flush_tlb_range(vma, start, end);
                 flush_cache_all();
                 return;
         }
 
-        flush_user_dcache_range_asm(start, end);
-        if (vma->vm_flags & VM_EXEC)
-                flush_user_icache_range_asm(start, end);
-        flush_tlb_range(vma, start, end);
+        if (vma->vm_mm->context == mfsp(3)) {
+                flush_user_dcache_range_asm(start, end);
+                if (vma->vm_flags & VM_EXEC)
+                        flush_user_icache_range_asm(start, end);
+                flush_tlb_range(vma, start, end);
+                return;
+        }
+
+        pgd = vma->vm_mm->pgd;
+        for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) {
+                unsigned long pfn;
+                pte_t *ptep = get_ptep(pgd, addr);
+                if (!ptep)
+                        continue;
+                pfn = pte_pfn(*ptep);
+                if (pfn_valid(pfn)) {
+                        if (unlikely(vma->vm_mm->context))
+                                flush_tlb_page(vma, addr);
+                        __flush_cache_page(vma, addr, PFN_PHYS(pfn));
+                }
+        }
 }
 
 void
 flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn)
 {
-        BUG_ON(!vma->vm_mm->context);
-
         if (pfn_valid(pfn)) {
-                flush_tlb_page(vma, vmaddr);
+                if (likely(vma->vm_mm->context))
+                        flush_tlb_page(vma, vmaddr);
                 __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
         }
 }
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 847ddffbf38a..b5cfab711651 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -163,13 +163,10 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
         pte_unmap(pte);
 }
 
-void set_pmd_at(struct mm_struct *mm, unsigned long addr,
-                pmd_t *pmdp, pmd_t pmd)
-{
-        pmd_t orig = *pmdp;
-
-        *pmdp = pmd;
 
+static void __set_pmd_acct(struct mm_struct *mm, unsigned long addr,
+                           pmd_t orig, pmd_t pmd)
+{
         if (mm == &init_mm)
                 return;
 
@@ -219,6 +216,15 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
         }
 }
 
+void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+                pmd_t *pmdp, pmd_t pmd)
+{
+        pmd_t orig = *pmdp;
+
+        *pmdp = pmd;
+        __set_pmd_acct(mm, addr, orig, pmd);
+}
+
 static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
                 unsigned long address, pmd_t *pmdp, pmd_t pmd)
 {
@@ -227,6 +233,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
         do {
                 old = *pmdp;
         } while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd);
+        __set_pmd_acct(vma->vm_mm, address, old, pmd);
 
         return old;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 74d2efaec52f..7a073ac5f9c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -69,25 +69,18 @@ void amdgpu_connector_hotplug(struct drm_connector *connector)
                 /* don't do anything if sink is not display port, i.e.,
                  * passive dp->(dvi|hdmi) adaptor
                  */
-                if (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) {
-                        int saved_dpms = connector->dpms;
-                        /* Only turn off the display if it's physically disconnected */
-                        if (!amdgpu_display_hpd_sense(adev, amdgpu_connector->hpd.hpd)) {
-                                drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
-                        } else if (amdgpu_atombios_dp_needs_link_train(amdgpu_connector)) {
-                                /* Don't try to start link training before we
-                                 * have the dpcd */
-                                if (amdgpu_atombios_dp_get_dpcd(amdgpu_connector))
-                                        return;
-
-                                /* set it to OFF so that drm_helper_connector_dpms()
-                                 * won't return immediately since the current state
-                                 * is ON at this point.
-                                 */
-                                connector->dpms = DRM_MODE_DPMS_OFF;
-                                drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
-                        }
-                        connector->dpms = saved_dpms;
+                if (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT &&
+                    amdgpu_display_hpd_sense(adev, amdgpu_connector->hpd.hpd) &&
+                    amdgpu_atombios_dp_needs_link_train(amdgpu_connector)) {
+                        /* Don't start link training before we have the DPCD */
+                        if (amdgpu_atombios_dp_get_dpcd(amdgpu_connector))
+                                return;
+
+                        /* Turn the connector off and back on immediately, which
+                         * will trigger link training
+                         */
+                        drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
+                        drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
                 }
         }
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index e48b4ec88c8c..ca6c931dabfa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -36,8 +36,6 @@ void amdgpu_gem_object_free(struct drm_gem_object *gobj)
         struct amdgpu_bo *robj = gem_to_amdgpu_bo(gobj);
 
         if (robj) {
-                if (robj->gem_base.import_attach)
-                        drm_prime_gem_destroy(&robj->gem_base, robj->tbo.sg);
                 amdgpu_mn_unregister(robj);
                 amdgpu_bo_unref(&robj);
         }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index 54f06c959340..2264c5c97009 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -352,6 +352,7 @@ struct amdgpu_mode_info {
         u16 firmware_flags;
         /* pointer to backlight encoder */
         struct amdgpu_encoder *bl_encoder;
+        u8 bl_level; /* saved backlight level */
         struct amdgpu_audio     audio; /* audio stuff */
         int                     num_crtc; /* number of crtcs */
         int                     num_hpd; /* number of hpd pins */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 5c4c3e0d527b..1220322c1680 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -56,6 +56,8 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 
         amdgpu_bo_kunmap(bo);
 
+        if (bo->gem_base.import_attach)
+                drm_prime_gem_destroy(&bo->gem_base, bo->tbo.sg);
         drm_gem_object_release(&bo->gem_base);
         amdgpu_bo_unref(&bo->parent);
         if (!list_empty(&bo->shadow_list)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
index 2af26d2da127..d702fb8e3427 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
@@ -34,7 +34,7 @@
 #include <linux/backlight.h>
 #include "bif/bif_4_1_d.h"
 
-static u8
+u8
 amdgpu_atombios_encoder_get_backlight_level_from_reg(struct amdgpu_device *adev)
 {
         u8 backlight_level;
@@ -48,7 +48,7 @@ amdgpu_atombios_encoder_get_backlight_level_from_reg(struct amdgpu_device *adev)
         return backlight_level;
 }
 
-static void
+void
 amdgpu_atombios_encoder_set_backlight_level_to_reg(struct amdgpu_device *adev,
                                             u8 backlight_level)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.h b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.h
index 2bdec40515ce..f77cbdef679e 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.h
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.h
@@ -25,6 +25,11 @@
 #define __ATOMBIOS_ENCODER_H__
 
 u8
+amdgpu_atombios_encoder_get_backlight_level_from_reg(struct amdgpu_device *adev);
+void
+amdgpu_atombios_encoder_set_backlight_level_to_reg(struct amdgpu_device *adev,
+                                                   u8 backlight_level);
+u8
 amdgpu_atombios_encoder_get_backlight_level(struct amdgpu_encoder *amdgpu_encoder);
 void
 amdgpu_atombios_encoder_set_backlight_level(struct amdgpu_encoder *amdgpu_encoder,
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index f34bc68aadfb..022f303463fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -2921,6 +2921,11 @@ static int dce_v10_0_hw_fini(void *handle)
 
 static int dce_v10_0_suspend(void *handle)
 {
+        struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+        adev->mode_info.bl_level =
+                amdgpu_atombios_encoder_get_backlight_level_from_reg(adev);
+
         return dce_v10_0_hw_fini(handle);
 }
 
@@ -2929,6 +2934,9 @@ static int dce_v10_0_resume(void *handle)
         struct amdgpu_device *adev = (struct amdgpu_device *)handle;
         int ret;
 
+        amdgpu_atombios_encoder_set_backlight_level_to_reg(adev,
+                                                           adev->mode_info.bl_level);
+
         ret = dce_v10_0_hw_init(handle);
 
         /* turn on the BL */
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 26378bd6aba4..800a9f36ab4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -3047,6 +3047,11 @@ static int dce_v11_0_hw_fini(void *handle)
 
 static int dce_v11_0_suspend(void *handle)
 {
+        struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+        adev->mode_info.bl_level =
+                amdgpu_atombios_encoder_get_backlight_level_from_reg(adev);
+
         return dce_v11_0_hw_fini(handle);
 }
 
@@ -3055,6 +3060,9 @@ static int dce_v11_0_resume(void *handle)
         struct amdgpu_device *adev = (struct amdgpu_device *)handle;
         int ret;
 
+        amdgpu_atombios_encoder_set_backlight_level_to_reg(adev,
+                                                           adev->mode_info.bl_level);
+
         ret = dce_v11_0_hw_init(handle);
 
         /* turn on the BL */
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index a712f4b285f6..b8368f69ce1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -2787,6 +2787,11 @@ static int dce_v6_0_hw_fini(void *handle)
 
 static int dce_v6_0_suspend(void *handle)
 {
+        struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+        adev->mode_info.bl_level =
+                amdgpu_atombios_encoder_get_backlight_level_from_reg(adev);
+
         return dce_v6_0_hw_fini(handle);
 }
 
@@ -2795,6 +2800,9 @@ static int dce_v6_0_resume(void *handle)
         struct amdgpu_device *adev = (struct amdgpu_device *)handle;
         int ret;
 
+        amdgpu_atombios_encoder_set_backlight_level_to_reg(adev,
+                                                           adev->mode_info.bl_level);
+
         ret = dce_v6_0_hw_init(handle);
 
         /* turn on the BL */
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index c008dc030687..012e0a9ae0ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -2819,6 +2819,11 @@ static int dce_v8_0_hw_fini(void *handle)
 
 static int dce_v8_0_suspend(void *handle)
 {
+        struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+        adev->mode_info.bl_level =
+                amdgpu_atombios_encoder_get_backlight_level_from_reg(adev);
+
         return dce_v8_0_hw_fini(handle);
 }
 
@@ -2827,6 +2832,9 @@ static int dce_v8_0_resume(void *handle)
         struct amdgpu_device *adev = (struct amdgpu_device *)handle;
         int ret;
 
+        amdgpu_atombios_encoder_set_backlight_level_to_reg(adev,
+                                                           adev->mode_info.bl_level);
+
         ret = dce_v8_0_hw_init(handle);
 
         /* turn on the BL */
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index c8454ac43fae..db6b94dda5df 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -471,6 +471,7 @@ struct parser_exec_state {
          * used when ret from 2nd level batch buffer
          */
         int saved_buf_addr_type;
+        bool is_ctx_wa;
 
         struct cmd_info *info;
 
@@ -1715,6 +1716,11 @@ static int perform_bb_shadow(struct parser_exec_state *s)
         bb->accessing = true;
         bb->bb_start_cmd_va = s->ip_va;
 
+        if ((s->buf_type == BATCH_BUFFER_INSTRUCTION) && (!s->is_ctx_wa))
+                bb->bb_offset = s->ip_va - s->rb_va;
+        else
+                bb->bb_offset = 0;
+
         /*
          * ip_va saves the virtual address of the shadow batch buffer, while
          * ip_gma saves the graphics address of the original batch buffer.
@@ -2571,6 +2577,7 @@ static int scan_workload(struct intel_vgpu_workload *workload)
         s.ring_tail = gma_tail;
         s.rb_va = workload->shadow_ring_buffer_va;
         s.workload = workload;
+        s.is_ctx_wa = false;
 
         if ((bypass_scan_mask & (1 << workload->ring_id)) ||
                 gma_head == gma_tail)
@@ -2624,6 +2631,7 @@ static int scan_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
         s.ring_tail = gma_tail;
         s.rb_va = wa_ctx->indirect_ctx.shadow_va;
         s.workload = workload;
+        s.is_ctx_wa = true;
 
         if (!intel_gvt_ggtt_validate_range(s.vgpu, s.ring_start, s.ring_size)) {
                 ret = -EINVAL;
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 256f1bb522b7..152df3d0291e 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -394,9 +394,11 @@ void intel_gvt_switch_mmio(struct intel_vgpu *pre,
          * performace for batch mmio read/write, so we need
          * handle forcewake mannually.
          */
+        intel_runtime_pm_get(dev_priv);
         intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
         switch_mmio(pre, next, ring_id);
         intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+        intel_runtime_pm_put(dev_priv);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index b55b3580ca1d..d74d6f05c62c 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -52,6 +52,54 @@ static void set_context_pdp_root_pointer(
                 pdp_pair[i].val = pdp[7 - i];
 }
 
+/*
+ * when populating shadow ctx from guest, we should not overrride oa related
+ * registers, so that they will not be overlapped by guest oa configs. Thus
+ * made it possible to capture oa data from host for both host and guests.
+ */
+static void sr_oa_regs(struct intel_vgpu_workload *workload,
+                u32 *reg_state, bool save)
+{
+        struct drm_i915_private *dev_priv = workload->vgpu->gvt->dev_priv;
+        u32 ctx_oactxctrl = dev_priv->perf.oa.ctx_oactxctrl_offset;
+        u32 ctx_flexeu0 = dev_priv->perf.oa.ctx_flexeu0_offset;
+        int i = 0;
+        u32 flex_mmio[] = {
+                i915_mmio_reg_offset(EU_PERF_CNTL0),
+                i915_mmio_reg_offset(EU_PERF_CNTL1),
+                i915_mmio_reg_offset(EU_PERF_CNTL2),
+                i915_mmio_reg_offset(EU_PERF_CNTL3),
+                i915_mmio_reg_offset(EU_PERF_CNTL4),
+                i915_mmio_reg_offset(EU_PERF_CNTL5),
+                i915_mmio_reg_offset(EU_PERF_CNTL6),
+        };
+
+        if (!workload || !reg_state || workload->ring_id != RCS)
+                return;
+
+        if (save) {
+                workload->oactxctrl = reg_state[ctx_oactxctrl + 1];
+
+                for (i = 0; i < ARRAY_SIZE(workload->flex_mmio); i++) {
+                        u32 state_offset = ctx_flexeu0 + i * 2;
+
+                        workload->flex_mmio[i] = reg_state[state_offset + 1];
+                }
+        } else {
+                reg_state[ctx_oactxctrl] =
+                        i915_mmio_reg_offset(GEN8_OACTXCONTROL);
+                reg_state[ctx_oactxctrl + 1] = workload->oactxctrl;
+
+                for (i = 0; i < ARRAY_SIZE(workload->flex_mmio); i++) {
+                        u32 state_offset = ctx_flexeu0 + i * 2;
+                        u32 mmio = flex_mmio[i];
+
+                        reg_state[state_offset] = mmio;
+                        reg_state[state_offset + 1] = workload->flex_mmio[i];
+                }
+        }
+}
+
 static int populate_shadow_context(struct intel_vgpu_workload *workload)
 {
         struct intel_vgpu *vgpu = workload->vgpu;
@@ -98,6 +146,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
         page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
         shadow_ring_context = kmap(page);
 
+        sr_oa_regs(workload, (u32 *)shadow_ring_context, true);
 #define COPY_REG(name) \
         intel_gvt_hypervisor_read_gpa(vgpu, workload->ring_context_gpa \
                 + RING_CTX_OFF(name.val), &shadow_ring_context->name.val, 4)
@@ -122,6 +171,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
                         sizeof(*shadow_ring_context),
                         I915_GTT_PAGE_SIZE - sizeof(*shadow_ring_context));
 
+        sr_oa_regs(workload, (u32 *)shadow_ring_context, false);
         kunmap(page);
         return 0;
 }
@@ -376,6 +426,17 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
                         goto err;
                 }
 
+                /* For privilge batch buffer and not wa_ctx, the bb_start_cmd_va
+                 * is only updated into ring_scan_buffer, not real ring address
+                 * allocated in later copy_workload_to_ring_buffer. pls be noted
+                 * shadow_ring_buffer_va is now pointed to real ring buffer va
+                 * in copy_workload_to_ring_buffer.
+                 */
+
+                if (bb->bb_offset)
+                        bb->bb_start_cmd_va = workload->shadow_ring_buffer_va
+                                + bb->bb_offset;
+
                 /* relocate shadow batch buffer */
                 bb->bb_start_cmd_va[1] = i915_ggtt_offset(bb->vma);
                 if (gmadr_bytes == 8)
@@ -1044,10 +1105,12 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 
         bitmap_zero(s->shadow_ctx_desc_updated, I915_NUM_ENGINES);
 
-        s->workloads = kmem_cache_create("gvt-g_vgpu_workload",
-                        sizeof(struct intel_vgpu_workload), 0,
-                        SLAB_HWCACHE_ALIGN,
-                        NULL);
+        s->workloads = kmem_cache_create_usercopy("gvt-g_vgpu_workload",
+                                                  sizeof(struct intel_vgpu_workload), 0,
+                                                  SLAB_HWCACHE_ALIGN,
+                                                  offsetof(struct intel_vgpu_workload, rb_tail),
+                                                  sizeof_field(struct intel_vgpu_workload, rb_tail),
+                                                  NULL);
 
         if (!s->workloads) {
                 ret = -ENOMEM;
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index ff175a98b19e..a79a4f60637e 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -110,6 +110,10 @@ struct intel_vgpu_workload {
         /* shadow batch buffer */
         struct list_head shadow_bb;
         struct intel_shadow_wa_ctx wa_ctx;
+
+        /* oa registers */
+        u32 oactxctrl;
+        u32 flex_mmio[7];
 };
 
 struct intel_vgpu_shadow_bb {
@@ -120,6 +124,7 @@ struct intel_vgpu_shadow_bb {
         u32 *bb_start_cmd_va;
         unsigned int clflush;
         bool accessing;
+        unsigned long bb_offset;
 };
 
 #define workload_q_head(vgpu, ring_id) \
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 66ee9d888d16..6ff5d655c202 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -434,20 +434,28 @@ i915_gem_object_wait_reservation(struct reservation_object *resv,
                         dma_fence_put(shared[i]);
                 kfree(shared);
 
+                /*
+                 * If both shared fences and an exclusive fence exist,
+                 * then by construction the shared fences must be later
+                 * than the exclusive fence. If we successfully wait for
+                 * all the shared fences, we know that the exclusive fence
+                 * must all be signaled. If all the shared fences are
+                 * signaled, we can prune the array and recover the
+                 * floating references on the fences/requests.
+                 */
                 prune_fences = count && timeout >= 0;
         } else {
                 excl = reservation_object_get_excl_rcu(resv);
         }
 
-        if (excl && timeout >= 0) {
+        if (excl && timeout >= 0)
                 timeout = i915_gem_object_wait_fence(excl, flags, timeout,
                                                      rps_client);
-                prune_fences = timeout >= 0;
-        }
 
         dma_fence_put(excl);
 
-        /* Oportunistically prune the fences iff we know they have *all* been
+        /*
+         * Opportunistically prune the fences iff we know they have *all* been
          * signaled and that the reservation object has not been changed (i.e.
          * no new fences have been added).
          */
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index b33d2158c234..e5e6f6bb2b05 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -304,8 +304,9 @@ static ssize_t gt_boost_freq_mhz_store(struct device *kdev,
 {
         struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
         struct intel_rps *rps = &dev_priv->gt_pm.rps;
-        u32 val;
+        bool boost = false;
         ssize_t ret;
+        u32 val;
 
         ret = kstrtou32(buf, 0, &val);
         if (ret)
@@ -317,8 +318,13 @@ static ssize_t gt_boost_freq_mhz_store(struct device *kdev,
                 return -EINVAL;
 
         mutex_lock(&dev_priv->pcu_lock);
-        rps->boost_freq = val;
+        if (val != rps->boost_freq) {
+                rps->boost_freq = val;
+                boost = atomic_read(&rps->num_waiters);
+        }
         mutex_unlock(&dev_priv->pcu_lock);
+        if (boost)
+                schedule_work(&rps->work);
 
         return count;
 }
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 35c5299feab6..a29868cd30c7 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -620,19 +620,15 @@ static int
 bxt_power_sequencer_idx(struct intel_dp *intel_dp)
 {
         struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
+        int backlight_controller = dev_priv->vbt.backlight.controller;
 
         lockdep_assert_held(&dev_priv->pps_mutex);
 
         /* We should never land here with regular DP ports */
         WARN_ON(!intel_dp_is_edp(intel_dp));
 
-        /*
-         * TODO: BXT has 2 PPS instances. The correct port->PPS instance
-         * mapping needs to be retrieved from VBT, for now just hard-code to
-         * use instance #0 always.
-         */
         if (!intel_dp->pps_reset)
-                return 0;
+                return backlight_controller;
 
         intel_dp->pps_reset = false;
 
@@ -642,7 +638,7 @@ bxt_power_sequencer_idx(struct intel_dp *intel_dp)
          */
         intel_dp_init_panel_power_sequencer_registers(intel_dp, false);
 
-        return 0;
+        return backlight_controller;
 }
 
 typedef bool (*vlv_pipe_check)(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index 380f340204e8..debbbf0fd4bd 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -134,7 +134,7 @@ nv50_get_intensity(struct backlight_device *bd)
         struct nouveau_encoder *nv_encoder = bl_get_data(bd);
         struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev);
         struct nvif_object *device = &drm->client.device.object;
-        int or = nv_encoder->or;
+        int or = ffs(nv_encoder->dcb->or) - 1;
         u32 div = 1025;
         u32 val;
 
@@ -149,7 +149,7 @@ nv50_set_intensity(struct backlight_device *bd)
         struct nouveau_encoder *nv_encoder = bl_get_data(bd);
         struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev);
         struct nvif_object *device = &drm->client.device.object;
-        int or = nv_encoder->or;
+        int or = ffs(nv_encoder->dcb->or) - 1;
         u32 div = 1025;
         u32 val = (bd->props.brightness * div) / 100;
 
@@ -170,7 +170,7 @@ nva3_get_intensity(struct backlight_device *bd)
         struct nouveau_encoder *nv_encoder = bl_get_data(bd);
         struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev);
         struct nvif_object *device = &drm->client.device.object;
-        int or = nv_encoder->or;
+        int or = ffs(nv_encoder->dcb->or) - 1;
         u32 div, val;
 
         div  = nvif_rd32(device, NV50_PDISP_SOR_PWM_DIV(or));
@@ -188,7 +188,7 @@ nva3_set_intensity(struct backlight_device *bd)
         struct nouveau_encoder *nv_encoder = bl_get_data(bd);
         struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev);
         struct nvif_object *device = &drm->client.device.object;
-        int or = nv_encoder->or;
+        int or = ffs(nv_encoder->dcb->or) - 1;
         u32 div, val;
 
         div = nvif_rd32(device, NV50_PDISP_SOR_PWM_DIV(or));
@@ -228,7 +228,7 @@ nv50_backlight_init(struct drm_connector *connector)
                         return -ENODEV;
         }
 
-        if (!nvif_rd32(device, NV50_PDISP_SOR_PWM_CTL(nv_encoder->or)))
+        if (!nvif_rd32(device, NV50_PDISP_SOR_PWM_CTL(ffs(nv_encoder->dcb->or) - 1)))
                 return 0;
 
         if (drm->client.device.info.chipset <= 0xa0 ||
@@ -268,13 +268,13 @@ nouveau_backlight_init(struct drm_device *dev)
         struct nvif_device *device = &drm->client.device;
         struct drm_connector *connector;
 
+        INIT_LIST_HEAD(&drm->bl_connectors);
+
         if (apple_gmux_present()) {
                 NV_INFO(drm, "Apple GMUX detected: not registering Nouveau backlight interface\n");
                 return 0;
         }
 
-        INIT_LIST_HEAD(&drm->bl_connectors);
-
         list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
                 if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS &&
                     connector->connector_type != DRM_MODE_CONNECTOR_eDP)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c
index 93946dcee319..1c12e58f44c2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c
@@ -1354,7 +1354,7 @@ nvkm_vmm_get_locked(struct nvkm_vmm *vmm, bool getref, bool mapref, bool sparse,
 
                 tail = this->addr + this->size;
                 if (vmm->func->page_block && next && next->page != p)
-                        tail = ALIGN_DOWN(addr, vmm->func->page_block);
+                        tail = ALIGN_DOWN(tail, vmm->func->page_block);
 
                 if (addr <= tail && tail - addr >= size) {
                         rb_erase(&this->tree, &vmm->free);
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index a9962ffba720..27d8e7dd2d06 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -34,8 +34,6 @@ void radeon_gem_object_free(struct drm_gem_object *gobj)
         struct radeon_bo *robj = gem_to_radeon_bo(gobj);
 
         if (robj) {
-                if (robj->gem_base.import_attach)
-                        drm_prime_gem_destroy(&robj->gem_base, robj->tbo.sg);
                 radeon_mn_unregister(robj);
                 radeon_bo_unref(&robj);
         }
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 15404af9d740..31f5ad605e59 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -82,6 +82,8 @@ static void radeon_ttm_bo_destroy(struct ttm_buffer_object *tbo)
         mutex_unlock(&bo->rdev->gem.mutex);
         radeon_bo_clear_surface_reg(bo);
         WARN_ON_ONCE(!list_empty(&bo->va));
+        if (bo->gem_base.import_attach)
+                drm_prime_gem_destroy(&bo->gem_base, bo->tbo.sg);
         drm_gem_object_release(&bo->gem_base);
         kfree(bo);
 }
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index f94b2d8c744a..26484648d090 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1519,6 +1519,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr)
                 if (!node)
                         break;
                 bytenr = node->val;
+                shared.share_count = 0;
                 cond_resched();
         }
 
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index dec0907dfb8a..fcfc20de2df3 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1370,6 +1370,7 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio,
                 stripe_start = stripe->physical;
                 if (physical >= stripe_start &&
                     physical < stripe_start + rbio->stripe_len &&
+                    stripe->dev->bdev &&
                     bio->bi_disk == stripe->dev->bdev->bd_disk &&
                     bio->bi_partno == stripe->dev->bdev->bd_partno) {
                         return i;
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index d11c70bff5a9..a8bafed931f4 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -423,7 +423,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj,
 {
         struct btrfs_fs_info *fs_info = to_fs_info(kobj);
 
-        return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->nodesize);
+        return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->nodesize);
 }
 
 BTRFS_ATTR(, nodesize, btrfs_nodesize_show);
@@ -433,7 +433,8 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj,
 {
         struct btrfs_fs_info *fs_info = to_fs_info(kobj);
 
-        return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
+        return snprintf(buf, PAGE_SIZE, "%u\n",
+                        fs_info->super_copy->sectorsize);
 }
 
 BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show);
@@ -443,7 +444,8 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
 {
         struct btrfs_fs_info *fs_info = to_fs_info(kobj);
 
-        return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
+        return snprintf(buf, PAGE_SIZE, "%u\n",
+                        fs_info->super_copy->sectorsize);
 }
 
 BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 9220f004001c..04f07144b45c 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1722,23 +1722,19 @@ static void update_super_roots(struct btrfs_fs_info *fs_info)
 
         super = fs_info->super_copy;
 
-        /* update latest btrfs_super_block::chunk_root refs */
         root_item = &fs_info->chunk_root->root_item;
-        btrfs_set_super_chunk_root(super, root_item->bytenr);
-        btrfs_set_super_chunk_root_generation(super, root_item->generation);
-        btrfs_set_super_chunk_root_level(super, root_item->level);
+        super->chunk_root = root_item->bytenr;
+        super->chunk_root_generation = root_item->generation;
+        super->chunk_root_level = root_item->level;
 
-        /* update latest btrfs_super_block::root refs */
         root_item = &fs_info->tree_root->root_item;
-        btrfs_set_super_root(super, root_item->bytenr);
-        btrfs_set_super_generation(super, root_item->generation);
-        btrfs_set_super_root_level(super, root_item->level);
-
+        super->root = root_item->bytenr;
+        super->generation = root_item->generation;
+        super->root_level = root_item->level;
         if (btrfs_test_opt(fs_info, SPACE_CACHE))
-                btrfs_set_super_cache_generation(super, root_item->generation);
+                super->cache_generation = root_item->generation;
         if (test_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags))
-                btrfs_set_super_uuid_tree_generation(super,
-                                                     root_item->generation);
+                super->uuid_tree_generation = root_item->generation;
 }
 
 int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
diff --git a/fs/dcache.c b/fs/dcache.c
index 7c38f39958bc..8945e6cabd93 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -647,11 +647,16 @@ again:
                 spin_unlock(&parent->d_lock);
                 goto again;
         }
-        rcu_read_unlock();
-        if (parent != dentry)
+        if (parent != dentry) {
                 spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-        else
+                if (unlikely(dentry->d_lockref.count < 0)) {
+                        spin_unlock(&parent->d_lock);
+                        parent = NULL;
+                }
+        } else {
                 parent = NULL;
+        }
+        rcu_read_unlock();
         return parent;
 }
 
@@ -2474,7 +2479,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent,
 
 retry:
         rcu_read_lock();
-        seq = smp_load_acquire(&parent->d_inode->i_dir_seq) & ~1;
+        seq = smp_load_acquire(&parent->d_inode->i_dir_seq);
         r_seq = read_seqbegin(&rename_lock);
         dentry = __d_lookup_rcu(parent, name, &d_seq);
         if (unlikely(dentry)) {
@@ -2495,8 +2500,14 @@ retry:
                 rcu_read_unlock();
                 goto retry;
         }
+
+        if (unlikely(seq & 1)) {
+                rcu_read_unlock();
+                goto retry;
+        }
+
         hlist_bl_lock(b);
-        if (unlikely(parent->d_inode->i_dir_seq != seq)) {
+        if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) {
                 hlist_bl_unlock(b);
                 rcu_read_unlock();
                 goto retry;
diff --git a/fs/namei.c b/fs/namei.c
index 921ae32dbc80..cafa365eeb70 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -559,9 +559,10 @@ static int __nd_alloc_stack(struct nameidata *nd)
 static bool path_connected(const struct path *path)
 {
         struct vfsmount *mnt = path->mnt;
+        struct super_block *sb = mnt->mnt_sb;
 
-        /* Only bind mounts can have disconnected paths */
-        if (mnt->mnt_root == mnt->mnt_sb->s_root)
+        /* Bind mounts and multi-root filesystems can have disconnected paths */
+        if (!(sb->s_iflags & SB_I_MULTIROOT) && (mnt->mnt_root == sb->s_root))
                 return true;
 
         return is_subdir(path->dentry, mnt->mnt_root);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 29bacdc56f6a..5e470e233c83 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2631,6 +2631,8 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
                 /* initial superblock/root creation */
                 mount_info->fill_super(s, mount_info);
                 nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned);
+                if (!(server->flags & NFS_MOUNT_UNSHARED))
+                        s->s_iflags |= SB_I_MULTIROOT;
         }
 
         mntroot = nfs_get_root(s, mount_info->mntfh, dev_name);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 79c413985305..c6baf767619e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1317,6 +1317,7 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_I_CGROUPWB   0x00000001      /* cgroup-aware writeback enabled */
 #define SB_I_NOEXEC     0x00000002      /* Ignore executables on this fs */
 #define SB_I_NODEV      0x00000004      /* Ignore devices on this fs */
+#define SB_I_MULTIROOT  0x00000008      /* Multiple roots to the dentry tree */
 
 /* sb->s_iflags to limit user namespace mounts */
 #define SB_I_USERNS_VISIBLE             0x00000010 /* fstype already mounted */