diff --git a/Makefile b/Makefile
index 1071ec486aa5b..fa98893aae615 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 10
-SUBLEVEL = 94
+SUBLEVEL = 95
 EXTRAVERSION =
 NAME = Dare mighty things
 
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index f2ddf663e72e9..7e08efb068393 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1130,12 +1130,12 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root,
 	bool spte_set = false;
 
 	tdp_root_for_each_leaf_pte(iter, root, gfn, gfn + 1) {
-		if (!is_writable_pte(iter.old_spte))
-			break;
-
 		new_spte = iter.old_spte &
 			~(PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE);
 
+		if (new_spte == iter.old_spte)
+			break;
+
 		tdp_mmu_set_spte(kvm, &iter, new_spte);
 		spte_set = true;
 	}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index d6711caa7f399..dbc88fc7136bf 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -159,6 +159,7 @@ struct drm_i915_gem_object {
 #define I915_BO_ALLOC_VOLATILE   BIT(1)
 #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | I915_BO_ALLOC_VOLATILE)
 #define I915_BO_READONLY         BIT(2)
+#define I915_BO_WAS_BOUND_BIT    3
 
 	/*
 	 * Is the object to be mapped as read-only to the GPU
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index f60ca6dc911f2..27d24cb38c0d2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -10,6 +10,8 @@
 #include "i915_gem_lmem.h"
 #include "i915_gem_mman.h"
 
+#include "gt/intel_gt.h"
+
 void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
 				 struct sg_table *pages,
 				 unsigned int sg_page_sizes)
@@ -186,6 +188,14 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 	__i915_gem_object_reset_page_iter(obj);
 	obj->mm.page_sizes.phys = obj->mm.page_sizes.sg = 0;
 
+	if (test_and_clear_bit(I915_BO_WAS_BOUND_BIT, &obj->flags)) {
+		struct drm_i915_private *i915 = to_i915(obj->base.dev);
+		intel_wakeref_t wakeref;
+
+		with_intel_runtime_pm_if_active(&i915->runtime_pm, wakeref)
+			intel_gt_invalidate_tlbs(&i915->gt);
+	}
+
 	return pages;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 39b428c5049c0..6615eb5147e23 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -26,6 +26,8 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 
 	spin_lock_init(&gt->irq_lock);
 
+	mutex_init(&gt->tlb_invalidate_lock);
+
 	INIT_LIST_HEAD(&gt->closed_vma);
 	spin_lock_init(&gt->closed_lock);
 
@@ -661,3 +663,103 @@ void intel_gt_info_print(const struct intel_gt_info *info,
 
 	intel_sseu_dump(&info->sseu, p);
 }
+
+struct reg_and_bit {
+	i915_reg_t reg;
+	u32 bit;
+};
+
+static struct reg_and_bit
+get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
+		const i915_reg_t *regs, const unsigned int num)
+{
+	const unsigned int class = engine->class;
+	struct reg_and_bit rb = { };
+
+	if (drm_WARN_ON_ONCE(&engine->i915->drm,
+			     class >= num || !regs[class].reg))
+		return rb;
+
+	rb.reg = regs[class];
+	if (gen8 && class == VIDEO_DECODE_CLASS)
+		rb.reg.reg += 4 * engine->instance; /* GEN8_M2TCR */
+	else
+		rb.bit = engine->instance;
+
+	rb.bit = BIT(rb.bit);
+
+	return rb;
+}
+
+void intel_gt_invalidate_tlbs(struct intel_gt *gt)
+{
+	static const i915_reg_t gen8_regs[] = {
+		[RENDER_CLASS]			= GEN8_RTCR,
+		[VIDEO_DECODE_CLASS]		= GEN8_M1TCR, /* , GEN8_M2TCR */
+		[VIDEO_ENHANCEMENT_CLASS]	= GEN8_VTCR,
+		[COPY_ENGINE_CLASS]		= GEN8_BTCR,
+	};
+	static const i915_reg_t gen12_regs[] = {
+		[RENDER_CLASS]			= GEN12_GFX_TLB_INV_CR,
+		[VIDEO_DECODE_CLASS]		= GEN12_VD_TLB_INV_CR,
+		[VIDEO_ENHANCEMENT_CLASS]	= GEN12_VE_TLB_INV_CR,
+		[COPY_ENGINE_CLASS]		= GEN12_BLT_TLB_INV_CR,
+	};
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_uncore *uncore = gt->uncore;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	const i915_reg_t *regs;
+	unsigned int num = 0;
+
+	if (I915_SELFTEST_ONLY(gt->awake == -ENODEV))
+		return;
+
+	if (INTEL_GEN(i915) == 12) {
+		regs = gen12_regs;
+		num = ARRAY_SIZE(gen12_regs);
+	} else if (INTEL_GEN(i915) >= 8 && INTEL_GEN(i915) <= 11) {
+		regs = gen8_regs;
+		num = ARRAY_SIZE(gen8_regs);
+	} else if (INTEL_GEN(i915) < 8) {
+		return;
+	}
+
+	if (drm_WARN_ONCE(&i915->drm, !num,
+			  "Platform does not implement TLB invalidation!"))
+		return;
+
+	GEM_TRACE("\n");
+
+	assert_rpm_wakelock_held(&i915->runtime_pm);
+
+	mutex_lock(&gt->tlb_invalidate_lock);
+	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
+
+	for_each_engine(engine, gt, id) {
+		/*
+		 * HW architecture suggest typical invalidation time at 40us,
+		 * with pessimistic cases up to 100us and a recommendation to
+		 * cap at 1ms. We go a bit higher just in case.
+		 */
+		const unsigned int timeout_us = 100;
+		const unsigned int timeout_ms = 4;
+		struct reg_and_bit rb;
+
+		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
+		if (!i915_mmio_reg_offset(rb.reg))
+			continue;
+
+		intel_uncore_write_fw(uncore, rb.reg, rb.bit);
+		if (__intel_wait_for_register_fw(uncore,
+						 rb.reg, rb.bit, 0,
+						 timeout_us, timeout_ms,
+						 NULL))
+			drm_err_ratelimited(&gt->i915->drm,
+					    "%s TLB invalidation did not complete in %ums!\n",
+					    engine->name, timeout_ms);
+	}
+
+	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
+	mutex_unlock(&gt->tlb_invalidate_lock);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 9157c7411f603..d9a1168172ae3 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -77,4 +77,6 @@ static inline bool intel_gt_is_wedged(const struct intel_gt *gt)
 void intel_gt_info_print(const struct intel_gt_info *info,
 			 struct drm_printer *p);
 
+void intel_gt_invalidate_tlbs(struct intel_gt *gt);
+
 #endif /* __INTEL_GT_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index 6d39a4a11bf39..78c061614d8bb 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -36,6 +36,8 @@ struct intel_gt {
 
 	struct intel_uc uc;
 
+	struct mutex tlb_invalidate_lock;
+
 	struct intel_gt_timelines {
 		spinlock_t lock; /* protects active_list */
 		struct list_head active_list;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index ce8c91c5fdd3b..12488996a7f4f 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2639,6 +2639,12 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING	(1 << 28)
 #define   GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT	(1 << 24)
 
+#define GEN8_RTCR	_MMIO(0x4260)
+#define GEN8_M1TCR	_MMIO(0x4264)
+#define GEN8_M2TCR	_MMIO(0x4268)
+#define GEN8_BTCR	_MMIO(0x426c)
+#define GEN8_VTCR	_MMIO(0x4270)
+
 #if 0
 #define PRB0_TAIL	_MMIO(0x2030)
 #define PRB0_HEAD	_MMIO(0x2034)
@@ -2728,6 +2734,11 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   FAULT_VA_HIGH_BITS		(0xf << 0)
 #define   FAULT_GTT_SEL			(1 << 4)
 
+#define GEN12_GFX_TLB_INV_CR	_MMIO(0xced8)
+#define GEN12_VD_TLB_INV_CR	_MMIO(0xcedc)
+#define GEN12_VE_TLB_INV_CR	_MMIO(0xcee0)
+#define GEN12_BLT_TLB_INV_CR	_MMIO(0xcee4)
+
 #define GEN12_AUX_ERR_DBG		_MMIO(0x43f4)
 
 #define FPGA_DBG		_MMIO(0x42300)
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index caa9b041616b0..50a86fd89d005 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -439,6 +439,9 @@ int i915_vma_bind(struct i915_vma *vma,
 		vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags);
 	}
 
+	if (vma->obj)
+		set_bit(I915_BO_WAS_BOUND_BIT, &vma->obj->flags);
+
 	atomic_or(bind_flags, &vma->flags);
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 97ded2a59cf4c..01849840ac560 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -694,7 +694,8 @@ void intel_uncore_forcewake_get__locked(struct intel_uncore *uncore,
 }
 
 static void __intel_uncore_forcewake_put(struct intel_uncore *uncore,
-					 enum forcewake_domains fw_domains)
+					 enum forcewake_domains fw_domains,
+					 bool delayed)
 {
 	struct intel_uncore_forcewake_domain *domain;
 	unsigned int tmp;
@@ -709,7 +710,11 @@ static void __intel_uncore_forcewake_put(struct intel_uncore *uncore,
 			continue;
 		}
 
-		uncore->funcs.force_wake_put(uncore, domain->mask);
+		if (delayed &&
+		    !(domain->uncore->fw_domains_timer & domain->mask))
+			fw_domain_arm_timer(domain);
+		else
+			uncore->funcs.force_wake_put(uncore, domain->mask);
 	}
 }
 
@@ -730,7 +735,20 @@ void intel_uncore_forcewake_put(struct intel_uncore *uncore,
 		return;
 
 	spin_lock_irqsave(&uncore->lock, irqflags);
-	__intel_uncore_forcewake_put(uncore, fw_domains);
+	__intel_uncore_forcewake_put(uncore, fw_domains, false);
+	spin_unlock_irqrestore(&uncore->lock, irqflags);
+}
+
+void intel_uncore_forcewake_put_delayed(struct intel_uncore *uncore,
+					enum forcewake_domains fw_domains)
+{
+	unsigned long irqflags;
+
+	if (!uncore->funcs.force_wake_put)
+		return;
+
+	spin_lock_irqsave(&uncore->lock, irqflags);
+	__intel_uncore_forcewake_put(uncore, fw_domains, true);
 	spin_unlock_irqrestore(&uncore->lock, irqflags);
 }
 
@@ -772,7 +790,7 @@ void intel_uncore_forcewake_put__locked(struct intel_uncore *uncore,
 	if (!uncore->funcs.force_wake_put)
 		return;
 
-	__intel_uncore_forcewake_put(uncore, fw_domains);
+	__intel_uncore_forcewake_put(uncore, fw_domains, false);
 }
 
 void assert_forcewakes_inactive(struct intel_uncore *uncore)
diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h
index c4b22d9d0b451..034f04e0de8b7 100644
--- a/drivers/gpu/drm/i915/intel_uncore.h
+++ b/drivers/gpu/drm/i915/intel_uncore.h
@@ -211,6 +211,8 @@ void intel_uncore_forcewake_get(struct intel_uncore *uncore,
 				enum forcewake_domains domains);
 void intel_uncore_forcewake_put(struct intel_uncore *uncore,
 				enum forcewake_domains domains);
+void intel_uncore_forcewake_put_delayed(struct intel_uncore *uncore,
+					enum forcewake_domains domains);
 void intel_uncore_forcewake_flush(struct intel_uncore *uncore,
 				  enum forcewake_domains fw_domains);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 1523b51a7284c..ad208a5f4ebe5 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1088,15 +1088,14 @@ extern int vmw_execbuf_fence_commands(struct drm_file *file_priv,
 				      struct vmw_private *dev_priv,
 				      struct vmw_fence_obj **p_fence,
 				      uint32_t *p_handle);
-extern void vmw_execbuf_copy_fence_user(struct vmw_private *dev_priv,
+extern int vmw_execbuf_copy_fence_user(struct vmw_private *dev_priv,
 					struct vmw_fpriv *vmw_fp,
 					int ret,
 					struct drm_vmw_fence_rep __user
 					*user_fence_rep,
 					struct vmw_fence_obj *fence,
 					uint32_t fence_handle,
-					int32_t out_fence_fd,
-					struct sync_file *sync_file);
+					int32_t out_fence_fd);
 bool vmw_cmd_describe(const void *buf, u32 *size, char const **cmd);
 
 /**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 83e1b54eb8647..739cbc77d8867 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -3816,17 +3816,17 @@ int vmw_execbuf_fence_commands(struct drm_file *file_priv,
  * Also if copying fails, user-space will be unable to signal the fence object
  * so we wait for it immediately, and then unreference the user-space reference.
  */
-void
+int
 vmw_execbuf_copy_fence_user(struct vmw_private *dev_priv,
 			    struct vmw_fpriv *vmw_fp, int ret,
 			    struct drm_vmw_fence_rep __user *user_fence_rep,
 			    struct vmw_fence_obj *fence, uint32_t fence_handle,
-			    int32_t out_fence_fd, struct sync_file *sync_file)
+			    int32_t out_fence_fd)
 {
 	struct drm_vmw_fence_rep fence_rep;
 
 	if (user_fence_rep == NULL)
-		return;
+		return 0;
 
 	memset(&fence_rep, 0, sizeof(fence_rep));
 
@@ -3854,20 +3854,14 @@ vmw_execbuf_copy_fence_user(struct vmw_private *dev_priv,
 	 * handle.
 	 */
 	if (unlikely(ret != 0) && (fence_rep.error == 0)) {
-		if (sync_file)
-			fput(sync_file->file);
-
-		if (fence_rep.fd != -1) {
-			put_unused_fd(fence_rep.fd);
-			fence_rep.fd = -1;
-		}
-
 		ttm_ref_object_base_unref(vmw_fp->tfile, fence_handle,
 					  TTM_REF_USAGE);
 		VMW_DEBUG_USER("Fence copy error. Syncing.\n");
 		(void) vmw_fence_obj_wait(fence, false, false,
 					  VMW_FENCE_WAIT_TIMEOUT);
 	}
+
+	return ret ? -EFAULT : 0;
 }
 
 /**
@@ -4209,16 +4203,23 @@ int vmw_execbuf_process(struct drm_file *file_priv,
 
 			(void) vmw_fence_obj_wait(fence, false, false,
 						  VMW_FENCE_WAIT_TIMEOUT);
+		}
+	}
+
+	ret = vmw_execbuf_copy_fence_user(dev_priv, vmw_fpriv(file_priv), ret,
+				    user_fence_rep, fence, handle, out_fence_fd);
+
+	if (sync_file) {
+		if (ret) {
+			/* usercopy of fence failed, put the file object */
+			fput(sync_file->file);
+			put_unused_fd(out_fence_fd);
 		} else {
 			/* Link the fence with the FD created earlier */
 			fd_install(out_fence_fd, sync_file->file);
 		}
 	}
 
-	vmw_execbuf_copy_fence_user(dev_priv, vmw_fpriv(file_priv), ret,
-				    user_fence_rep, fence, handle, out_fence_fd,
-				    sync_file);
-
 	/* Don't unreference when handing fence out */
 	if (unlikely(out_fence != NULL)) {
 		*out_fence = fence;
@@ -4236,7 +4237,7 @@ int vmw_execbuf_process(struct drm_file *file_priv,
 	 */
 	vmw_validation_unref_lists(&val_ctx);
 
-	return 0;
+	return ret;
 
 out_unlock_binding:
 	mutex_unlock(&dev_priv->binding_mutex);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 0f8d293971576..8bc41ec97d71a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -1171,7 +1171,7 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data,
 	}
 
 	vmw_execbuf_copy_fence_user(dev_priv, vmw_fp, 0, user_fence_rep, fence,
-				    handle, -1, NULL);
+				    handle, -1);
 	vmw_fence_obj_unreference(&fence);
 	return 0;
 out_no_create:
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 312ed0881a99b..e58112997c881 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -2479,7 +2479,7 @@ void vmw_kms_helper_validation_finish(struct vmw_private *dev_priv,
 	if (file_priv)
 		vmw_execbuf_copy_fence_user(dev_priv, vmw_fpriv(file_priv),
 					    ret, user_fence_rep, fence,
-					    handle, -1, NULL);
+					    handle, -1);
 	if (out_fence)
 		*out_fence = fence;
 	else
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index d04994840b87d..bb3ba614fb174 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1850,6 +1850,14 @@ struct bnx2x {
 
 	/* Vxlan/Geneve related information */
 	u16 udp_tunnel_ports[BNX2X_UDP_PORT_MAX];
+
+#define FW_CAP_INVALIDATE_VF_FP_HSI	BIT(0)
+	u32 fw_cap;
+
+	u32 fw_major;
+	u32 fw_minor;
+	u32 fw_rev;
+	u32 fw_eng;
 };
 
 /* Tx queues may be less or equal to Rx queues */
@@ -2526,5 +2534,6 @@ void bnx2x_register_phc(struct bnx2x *bp);
  * Meant for implicit re-load flows.
  */
 int bnx2x_vlan_reconfigure_vid(struct bnx2x *bp);
-
+int bnx2x_init_firmware(struct bnx2x *bp);
+void bnx2x_release_firmware(struct bnx2x *bp);
 #endif /* bnx2x.h */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index b5d954cb409ae..41ebbb2c7d3ac 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -2364,10 +2364,8 @@ int bnx2x_compare_fw_ver(struct bnx2x *bp, u32 load_code, bool print_err)
 	if (load_code != FW_MSG_CODE_DRV_LOAD_COMMON_CHIP &&
 	    load_code != FW_MSG_CODE_DRV_LOAD_COMMON) {
 		/* build my FW version dword */
-		u32 my_fw = (BCM_5710_FW_MAJOR_VERSION) +
-			(BCM_5710_FW_MINOR_VERSION << 8) +
-			(BCM_5710_FW_REVISION_VERSION << 16) +
-			(BCM_5710_FW_ENGINEERING_VERSION << 24);
+		u32 my_fw = (bp->fw_major) + (bp->fw_minor << 8) +
+				(bp->fw_rev << 16) + (bp->fw_eng << 24);
 
 		/* read loaded FW from chip */
 		u32 loaded_fw = REG_RD(bp, XSEM_REG_PRAM);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
index 3f8435208bf49..a84d015da5dfa 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
@@ -241,6 +241,8 @@
 	IRO[221].m2))
 #define XSTORM_VF_TO_PF_OFFSET(funcId) \
 	(IRO[48].base + ((funcId) * IRO[48].m1))
+#define XSTORM_ETH_FUNCTION_INFO_FP_HSI_VALID_E2_OFFSET(fid)	\
+	(IRO[386].base + ((fid) * IRO[386].m1))
 #define COMMON_ASM_INVALID_ASSERT_OPCODE 0x0
 
 /* eth hsi version */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
index 622fadc50316e..611efee758340 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
@@ -3024,7 +3024,8 @@ struct afex_stats {
 
 #define BCM_5710_FW_MAJOR_VERSION			7
 #define BCM_5710_FW_MINOR_VERSION			13
-#define BCM_5710_FW_REVISION_VERSION		15
+#define BCM_5710_FW_REVISION_VERSION		21
+#define BCM_5710_FW_REVISION_VERSION_V15	15
 #define BCM_5710_FW_ENGINEERING_VERSION		0
 #define BCM_5710_FW_COMPILE_FLAGS			1
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 28069b2908625..9a86367a26369 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -74,9 +74,19 @@
 	__stringify(BCM_5710_FW_MINOR_VERSION) "."	\
 	__stringify(BCM_5710_FW_REVISION_VERSION) "."	\
 	__stringify(BCM_5710_FW_ENGINEERING_VERSION)
+
+#define FW_FILE_VERSION_V15				\
+	__stringify(BCM_5710_FW_MAJOR_VERSION) "."      \
+	__stringify(BCM_5710_FW_MINOR_VERSION) "."	\
+	__stringify(BCM_5710_FW_REVISION_VERSION_V15) "."	\
+	__stringify(BCM_5710_FW_ENGINEERING_VERSION)
+
 #define FW_FILE_NAME_E1		"bnx2x/bnx2x-e1-" FW_FILE_VERSION ".fw"
 #define FW_FILE_NAME_E1H	"bnx2x/bnx2x-e1h-" FW_FILE_VERSION ".fw"
 #define FW_FILE_NAME_E2		"bnx2x/bnx2x-e2-" FW_FILE_VERSION ".fw"
+#define FW_FILE_NAME_E1_V15	"bnx2x/bnx2x-e1-" FW_FILE_VERSION_V15 ".fw"
+#define FW_FILE_NAME_E1H_V15	"bnx2x/bnx2x-e1h-" FW_FILE_VERSION_V15 ".fw"
+#define FW_FILE_NAME_E2_V15	"bnx2x/bnx2x-e2-" FW_FILE_VERSION_V15 ".fw"
 
 /* Time in jiffies before concluding the transmitter is hung */
 #define TX_TIMEOUT		(5*HZ)
@@ -747,9 +757,7 @@ static int bnx2x_mc_assert(struct bnx2x *bp)
 		  CHIP_IS_E1(bp) ? "everest1" :
 		  CHIP_IS_E1H(bp) ? "everest1h" :
 		  CHIP_IS_E2(bp) ? "everest2" : "everest3",
-		  BCM_5710_FW_MAJOR_VERSION,
-		  BCM_5710_FW_MINOR_VERSION,
-		  BCM_5710_FW_REVISION_VERSION);
+		  bp->fw_major, bp->fw_minor, bp->fw_rev);
 
 	return rc;
 }
@@ -12355,6 +12363,15 @@ static int bnx2x_init_bp(struct bnx2x *bp)
 
 	bnx2x_read_fwinfo(bp);
 
+	if (IS_PF(bp)) {
+		rc = bnx2x_init_firmware(bp);
+
+		if (rc) {
+			bnx2x_free_mem_bp(bp);
+			return rc;
+		}
+	}
+
 	func = BP_FUNC(bp);
 
 	/* need to reset chip if undi was active */
@@ -12367,6 +12384,7 @@ static int bnx2x_init_bp(struct bnx2x *bp)
 
 		rc = bnx2x_prev_unload(bp);
 		if (rc) {
+			bnx2x_release_firmware(bp);
 			bnx2x_free_mem_bp(bp);
 			return rc;
 		}
@@ -13366,16 +13384,11 @@ static int bnx2x_check_firmware(struct bnx2x *bp)
 	/* Check FW version */
 	offset = be32_to_cpu(fw_hdr->fw_version.offset);
 	fw_ver = firmware->data + offset;
-	if ((fw_ver[0] != BCM_5710_FW_MAJOR_VERSION) ||
-	    (fw_ver[1] != BCM_5710_FW_MINOR_VERSION) ||
-	    (fw_ver[2] != BCM_5710_FW_REVISION_VERSION) ||
-	    (fw_ver[3] != BCM_5710_FW_ENGINEERING_VERSION)) {
+	if (fw_ver[0] != bp->fw_major || fw_ver[1] != bp->fw_minor ||
+	    fw_ver[2] != bp->fw_rev || fw_ver[3] != bp->fw_eng) {
 		BNX2X_ERR("Bad FW version:%d.%d.%d.%d. Should be %d.%d.%d.%d\n",
-		       fw_ver[0], fw_ver[1], fw_ver[2], fw_ver[3],
-		       BCM_5710_FW_MAJOR_VERSION,
-		       BCM_5710_FW_MINOR_VERSION,
-		       BCM_5710_FW_REVISION_VERSION,
-		       BCM_5710_FW_ENGINEERING_VERSION);
+			  fw_ver[0], fw_ver[1], fw_ver[2], fw_ver[3],
+			  bp->fw_major, bp->fw_minor, bp->fw_rev, bp->fw_eng);
 		return -EINVAL;
 	}
 
@@ -13453,34 +13466,51 @@ do {									\
 	     (u8 *)bp->arr, len);					\
 } while (0)
 
-static int bnx2x_init_firmware(struct bnx2x *bp)
+int bnx2x_init_firmware(struct bnx2x *bp)
 {
-	const char *fw_file_name;
+	const char *fw_file_name, *fw_file_name_v15;
 	struct bnx2x_fw_file_hdr *fw_hdr;
 	int rc;
 
 	if (bp->firmware)
 		return 0;
 
-	if (CHIP_IS_E1(bp))
+	if (CHIP_IS_E1(bp)) {
 		fw_file_name = FW_FILE_NAME_E1;
-	else if (CHIP_IS_E1H(bp))
+		fw_file_name_v15 = FW_FILE_NAME_E1_V15;
+	} else if (CHIP_IS_E1H(bp)) {
 		fw_file_name = FW_FILE_NAME_E1H;
-	else if (!CHIP_IS_E1x(bp))
+		fw_file_name_v15 = FW_FILE_NAME_E1H_V15;
+	} else if (!CHIP_IS_E1x(bp)) {
 		fw_file_name = FW_FILE_NAME_E2;
-	else {
+		fw_file_name_v15 = FW_FILE_NAME_E2_V15;
+	} else {
 		BNX2X_ERR("Unsupported chip revision\n");
 		return -EINVAL;
 	}
+
 	BNX2X_DEV_INFO("Loading %s\n", fw_file_name);
 
 	rc = request_firmware(&bp->firmware, fw_file_name, &bp->pdev->dev);
 	if (rc) {
-		BNX2X_ERR("Can't load firmware file %s\n",
-			  fw_file_name);
-		goto request_firmware_exit;
+		BNX2X_DEV_INFO("Trying to load older fw %s\n", fw_file_name_v15);
+
+		/* try to load prev version */
+		rc = request_firmware(&bp->firmware, fw_file_name_v15, &bp->pdev->dev);
+
+		if (rc)
+			goto request_firmware_exit;
+
+		bp->fw_rev = BCM_5710_FW_REVISION_VERSION_V15;
+	} else {
+		bp->fw_cap |= FW_CAP_INVALIDATE_VF_FP_HSI;
+		bp->fw_rev = BCM_5710_FW_REVISION_VERSION;
 	}
 
+	bp->fw_major = BCM_5710_FW_MAJOR_VERSION;
+	bp->fw_minor = BCM_5710_FW_MINOR_VERSION;
+	bp->fw_eng = BCM_5710_FW_ENGINEERING_VERSION;
+
 	rc = bnx2x_check_firmware(bp);
 	if (rc) {
 		BNX2X_ERR("Corrupt firmware file %s\n", fw_file_name);
@@ -13536,7 +13566,7 @@ request_firmware_exit:
 	return rc;
 }
 
-static void bnx2x_release_firmware(struct bnx2x *bp)
+void bnx2x_release_firmware(struct bnx2x *bp)
 {
 	kfree(bp->init_ops_offsets);
 	kfree(bp->init_ops);
@@ -14053,6 +14083,7 @@ static int bnx2x_init_one(struct pci_dev *pdev,
 	return 0;
 
 init_one_freemem:
+	bnx2x_release_firmware(bp);
 	bnx2x_free_mem_bp(bp);
 
 init_one_exit:
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 03eb0179ec008..08437eaacbb96 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -758,9 +758,18 @@ static void bnx2x_vf_igu_reset(struct bnx2x *bp, struct bnx2x_virtf *vf)
 
 void bnx2x_vf_enable_access(struct bnx2x *bp, u8 abs_vfid)
 {
+	u16 abs_fid;
+
+	abs_fid = FW_VF_HANDLE(abs_vfid);
+
 	/* set the VF-PF association in the FW */
-	storm_memset_vf_to_pf(bp, FW_VF_HANDLE(abs_vfid), BP_FUNC(bp));
-	storm_memset_func_en(bp, FW_VF_HANDLE(abs_vfid), 1);
+	storm_memset_vf_to_pf(bp, abs_fid, BP_FUNC(bp));
+	storm_memset_func_en(bp, abs_fid, 1);
+
+	/* Invalidate fp_hsi version for vfs */
+	if (bp->fw_cap & FW_CAP_INVALIDATE_VF_FP_HSI)
+		REG_WR8(bp, BAR_XSTRORM_INTMEM +
+			    XSTORM_ETH_FUNCTION_INFO_FP_HSI_VALID_E2_OFFSET(abs_fid), 0);
 
 	/* clear vf errors*/
 	bnx2x_vf_semi_clear_err(bp, abs_vfid);
diff --git a/fs/select.c b/fs/select.c
index 945896d0ac9e7..5edffee1162c2 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -458,9 +458,11 @@ get_max:
 	return max;
 }
 
-#define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR)
-#define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR)
-#define POLLEX_SET (EPOLLPRI)
+#define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR |\
+			EPOLLNVAL)
+#define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR |\
+			 EPOLLNVAL)
+#define POLLEX_SET (EPOLLPRI | EPOLLNVAL)
 
 static inline void wait_key_set(poll_table *wait, unsigned long in,
 				unsigned long out, unsigned long bit,
@@ -527,6 +529,7 @@ static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 					break;
 				if (!(bit & all_bits))
 					continue;
+				mask = EPOLLNVAL;
 				f = fdget(i);
 				if (f.file) {
 					wait_key_set(wait, in, out, bit,
@@ -534,34 +537,34 @@ static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 					mask = vfs_poll(f.file, wait);
 
 					fdput(f);
-					if ((mask & POLLIN_SET) && (in & bit)) {
-						res_in |= bit;
-						retval++;
-						wait->_qproc = NULL;
-					}
-					if ((mask & POLLOUT_SET) && (out & bit)) {
-						res_out |= bit;
-						retval++;
-						wait->_qproc = NULL;
-					}
-					if ((mask & POLLEX_SET) && (ex & bit)) {
-						res_ex |= bit;
-						retval++;
-						wait->_qproc = NULL;
-					}
-					/* got something, stop busy polling */
-					if (retval) {
-						can_busy_loop = false;
-						busy_flag = 0;
-
-					/*
-					 * only remember a returned
-					 * POLL_BUSY_LOOP if we asked for it
-					 */
-					} else if (busy_flag & mask)
-						can_busy_loop = true;
-
 				}
+				if ((mask & POLLIN_SET) && (in & bit)) {
+					res_in |= bit;
+					retval++;
+					wait->_qproc = NULL;
+				}
+				if ((mask & POLLOUT_SET) && (out & bit)) {
+					res_out |= bit;
+					retval++;
+					wait->_qproc = NULL;
+				}
+				if ((mask & POLLEX_SET) && (ex & bit)) {
+					res_ex |= bit;
+					retval++;
+					wait->_qproc = NULL;
+				}
+				/* got something, stop busy polling */
+				if (retval) {
+					can_busy_loop = false;
+					busy_flag = 0;
+
+				/*
+				 * only remember a returned
+				 * POLL_BUSY_LOOP if we asked for it
+				 */
+				} else if (busy_flag & mask)
+					can_busy_loop = true;
+
 			}
 			if (res_in)
 				*rinp = res_in;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b74e7ace4376b..844c35803739e 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1581,10 +1581,11 @@ static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp,
 						  struct rcu_data *rdp)
 {
 	rcu_lockdep_assert_cblist_protected(rdp);
-	if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) ||
-	    !raw_spin_trylock_rcu_node(rnp))
+	if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) || !raw_spin_trylock_rcu_node(rnp))
 		return;
-	WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
+	// The grace period cannot end while we hold the rcu_node lock.
+	if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))
+		WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
 	raw_spin_unlock_rcu_node(rnp);
 }