Merge tag 'v5.15.129' into 5.15-main

This is the 5.15.129 stable release

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAmTvT7YACgkQONu9yGCS
# aT65pQ/+Ko+cSATQarGOACdQ6dEs1JwPnHkfnvroQedYVo/U2kmtjMCb84BNM7GQ
# u68xlJAG/SEhF5775iE5OT72dK/UdyNZtydGvNReJrdJ1wL7MAtaDzLEqr4W5RB8
# buRtcVofW4bi+kvAhGWnU7D0qT/ZdHYX64GKfAqf5/fR/p3ZVxB66VPI9VX5LKTa
# dE85Y7rLEApDlDTm/frhAiUijXYS27tJKuyqyWG/gRlCiZA6jeoaU90l5iU7jkPz
# LWwcRQ35PMNfpxSyOZdCx11a/zlHR+mw0l5+wxF+u6toWLH+kckWwWMoIKr/Il0H
# DZNPYMDn27uNKG+DHndY28/bwj7mAHgAtuTmHpdGfJa4/9zJRN6KDJQrtL+7O9wF
# eZTzMV7RpEZzVTyueUhOExaAy1zlap2QW5f8MLOQFGMrxD8oQYEprMkp2jcv4rst
# cVO2ayALcyrzWc9FdYwq4XpqL9rdG0LxqM6YQpCz77vBWlSpOseyyqfBX79r6eKk
# S2oNFYLgHBJDjOrsKoaHOmpej42/x4B2yktCmwzQdkNCtyBs/lqWfD+xr3yyiy2J
# h2p1+kzEpghHdIjqEG0sMW2NMSimScsCZzGoqYKLJ/LZRfC2BaFgkqxWpZtzku8K
# Ch8ITZSxEHHKCH+sF/LofhT4nJEGwUt0vIIZcHvtDxaFb32yris=
# =ruaG
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed Aug 30 16:18:30 2023 CEST
# gpg:                using RSA key 647F28654894E3BD457199BE38DBBDC86092693E
# gpg: Can't check signature: No public key

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 15
-SUBLEVEL = 128
+SUBLEVEL = 129
 EXTRAVERSION =
 NAME = Trick or Treat
 

arch/mips/include/asm/cpu-features.h

@@ -124,7 +124,24 @@
 #define cpu_has_tx39_cache	__opt(MIPS_CPU_TX39_CACHE)
 #endif
 #ifndef cpu_has_octeon_cache
-#define cpu_has_octeon_cache	0
+#define cpu_has_octeon_cache						\
+({									\
+	int __res;							\
+									\
+	switch (boot_cpu_type()) {					\
+	case CPU_CAVIUM_OCTEON:						\
+	case CPU_CAVIUM_OCTEON_PLUS:					\
+	case CPU_CAVIUM_OCTEON2:					\
+	case CPU_CAVIUM_OCTEON3:					\
+		__res = 1;						\
+		break;							\
+									\
+	default:							\
+		__res = 0;						\
+	}								\
+									\
+	__res;								\
+})
 #endif
 /* Don't override `cpu_has_fpu' to 1 or the "nofpu" option won't work.  */
 #ifndef cpu_has_fpu
@@ -351,7 +368,7 @@
 ({									\
 	int __res;							\
 									\
-	switch (current_cpu_type()) {					\
+	switch (boot_cpu_type()) {					\
 	case CPU_M14KC:							\
 	case CPU_74K:							\
 	case CPU_1074K:							\

arch/x86/include/asm/fpu/internal.h

@@ -416,8 +416,7 @@ DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
  * FPU state for a task MUST let the rest of the kernel know that the
  * FPU registers are no longer valid for this task.
  *
- * Either one of these invalidation functions is enough. Invalidate
- * a resource you control: CPU if using the CPU for something else
+ * Invalidate a resource you control: CPU if using the CPU for something else
  * (with preemption disabled), FPU for the current task, or a task that
  * is prevented from running by the current task.
  */

arch/x86/kernel/fpu/core.c

@@ -330,7 +330,7 @@ static void fpu_reset_fpstate(void)
 	struct fpu *fpu = &current->thread.fpu;
 
 	fpregs_lock();
-	fpu__drop(fpu);
+	__fpu_invalidate_fpregs_state(fpu);
 	/*
 	 * This does not change the actual hardware registers. It just
 	 * resets the memory image and sets TIF_NEED_FPU_LOAD so a

arch/x86/kernel/fpu/xstate.c

@@ -809,6 +809,13 @@ void __init fpu__init_system_xstate(void)
 		goto out_disable;
 	}
 
+	/*
+	 * CPU capabilities initialization runs before FPU init. So
+	 * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely
+	 * functional, set the feature bit so depending code works.
+	 */
+	setup_force_cpu_cap(X86_FEATURE_OSXSAVE);
+
 	print_xstate_offset_size();
 	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
 		xfeatures_mask_all,

arch/x86/kvm/mmu/tdp_mmu.c

@@ -10,7 +10,7 @@
 #include <asm/cmpxchg.h>
 #include <trace/events/kvm.h>
 
-static bool __read_mostly tdp_mmu_enabled = true;
+static bool __read_mostly tdp_mmu_enabled = false;
 module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644);
 
 /* Initializes the TDP MMU for the VM, if enabled. */

drivers/clk/clk-devres.c

@@ -205,18 +205,19 @@ EXPORT_SYMBOL(devm_clk_put);
 struct clk *devm_get_clk_from_child(struct device *dev,
 				    struct device_node *np, const char *con_id)
 {
-	struct clk **ptr, *clk;
+	struct devm_clk_state *state;
+	struct clk *clk;
 
-	ptr = devres_alloc(devm_clk_release, sizeof(*ptr), GFP_KERNEL);
-	if (!ptr)
+	state = devres_alloc(devm_clk_release, sizeof(*state), GFP_KERNEL);
+	if (!state)
 		return ERR_PTR(-ENOMEM);
 
 	clk = of_clk_get_by_name(np, con_id);
 	if (!IS_ERR(clk)) {
-		*ptr = clk;
-		devres_add(dev, ptr);
+		state->clk = clk;
+		devres_add(dev, state);
 	} else {
-		devres_free(ptr);
+		devres_free(state);
 	}
 
 	return clk;

drivers/dma-buf/sw_sync.c

@@ -191,6 +191,7 @@ static const struct dma_fence_ops timeline_fence_ops = {
  */
 static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
 {
+	LIST_HEAD(signalled);
 	struct sync_pt *pt, *next;
 
 	trace_sync_timeline(obj);
@@ -203,21 +204,20 @@ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
 		if (!timeline_fence_signaled(&pt->base))
 			break;
 
-		list_del_init(&pt->link);
+		dma_fence_get(&pt->base);
+
+		list_move_tail(&pt->link, &signalled);
 		rb_erase(&pt->node, &obj->pt_tree);
 
-		/*
-		 * A signal callback may release the last reference to this
-		 * fence, causing it to be freed. That operation has to be
-		 * last to avoid a use after free inside this loop, and must
-		 * be after we remove the fence from the timeline in order to
-		 * prevent deadlocking on timeline->lock inside
-		 * timeline_fence_release().
-		 */
 		dma_fence_signal_locked(&pt->base);
 	}
 
 	spin_unlock_irq(&obj->lock);
+
+	list_for_each_entry_safe(pt, next, &signalled, link) {
+		list_del_init(&pt->link);
+		dma_fence_put(&pt->base);
+	}
 }
 
 /**

drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c

@@ -3142,7 +3142,9 @@ void dcn10_wait_for_mpcc_disconnect(
 		if (pipe_ctx->stream_res.opp->mpcc_disconnect_pending[mpcc_inst]) {
 			struct hubp *hubp = get_hubp_by_inst(res_pool, mpcc_inst);
 
-			res_pool->mpc->funcs->wait_for_idle(res_pool->mpc, mpcc_inst);
+			if (pipe_ctx->stream_res.tg &&
+				pipe_ctx->stream_res.tg->funcs->is_tg_enabled(pipe_ctx->stream_res.tg))
+				res_pool->mpc->funcs->wait_for_idle(res_pool->mpc, mpcc_inst);
 			pipe_ctx->stream_res.opp->mpcc_disconnect_pending[mpcc_inst] = false;
 			hubp->funcs->set_blank(hubp, true);
 		}

drivers/gpu/drm/i915/i915_active.c

@@ -447,8 +447,11 @@ int i915_active_ref(struct i915_active *ref, u64 idx, struct dma_fence *fence)
 		}
 	} while (unlikely(is_barrier(active)));
 
-	if (!__i915_active_fence_set(active, fence))
+	fence = __i915_active_fence_set(active, fence);
+	if (!fence)
 		__i915_active_acquire(ref);
+	else
+		dma_fence_put(fence);
 
 out:
 	i915_active_release(ref);
@@ -467,13 +470,9 @@ __i915_active_set_fence(struct i915_active *ref,
 		return NULL;
 	}
 
-	rcu_read_lock();
 	prev = __i915_active_fence_set(active, fence);
-	if (prev)
-		prev = dma_fence_get_rcu(prev);
-	else
+	if (!prev)
 		__i915_active_acquire(ref);
-	rcu_read_unlock();
 
 	return prev;
 }
@@ -1040,10 +1039,11 @@ void i915_request_add_active_barriers(struct i915_request *rq)
  *
  * Records the new @fence as the last active fence along its timeline in
  * this active tracker, moving the tracking callbacks from the previous
- * fence onto this one. Returns the previous fence (if not already completed),
- * which the caller must ensure is executed before the new fence. To ensure
- * that the order of fences within the timeline of the i915_active_fence is
- * understood, it should be locked by the caller.
+ * fence onto this one. Gets and returns a reference to the previous fence
+ * (if not already completed), which the caller must put after making sure
+ * that it is executed before the new fence. To ensure that the order of
+ * fences within the timeline of the i915_active_fence is understood, it
+ * should be locked by the caller.
  */
 struct dma_fence *
 __i915_active_fence_set(struct i915_active_fence *active,
@@ -1052,7 +1052,23 @@ __i915_active_fence_set(struct i915_active_fence *active,
 	struct dma_fence *prev;
 	unsigned long flags;
 
-	if (fence == rcu_access_pointer(active->fence))
+	/*
+	 * In case of fences embedded in i915_requests, their memory is
+	 * SLAB_FAILSAFE_BY_RCU, then it can be reused right after release
+	 * by new requests.  Then, there is a risk of passing back a pointer
+	 * to a new, completely unrelated fence that reuses the same memory
+	 * while tracked under a different active tracker.  Combined with i915
+	 * perf open/close operations that build await dependencies between
+	 * engine kernel context requests and user requests from different
+	 * timelines, this can lead to dependency loops and infinite waits.
+	 *
+	 * As a countermeasure, we try to get a reference to the active->fence
+	 * first, so if we succeed and pass it back to our user then it is not
+	 * released and potentially reused by an unrelated request before the
+	 * user has a chance to set up an await dependency on it.
+	 */
+	prev = i915_active_fence_get(active);
+	if (fence == prev)
 		return fence;
 
 	GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags));
@@ -1061,27 +1077,56 @@ __i915_active_fence_set(struct i915_active_fence *active,
 	 * Consider that we have two threads arriving (A and B), with
 	 * C already resident as the active->fence.
 	 *
-	 * A does the xchg first, and so it sees C or NULL depending
-	 * on the timing of the interrupt handler. If it is NULL, the
-	 * previous fence must have been signaled and we know that
-	 * we are first on the timeline. If it is still present,
-	 * we acquire the lock on that fence and serialise with the interrupt
-	 * handler, in the process removing it from any future interrupt
-	 * callback. A will then wait on C before executing (if present).
-	 *
-	 * As B is second, it sees A as the previous fence and so waits for
-	 * it to complete its transition and takes over the occupancy for
-	 * itself -- remembering that it needs to wait on A before executing.
+	 * Both A and B have got a reference to C or NULL, depending on the
+	 * timing of the interrupt handler.  Let's assume that if A has got C
+	 * then it has locked C first (before B).
 	 *
 	 * Note the strong ordering of the timeline also provides consistent
 	 * nesting rules for the fence->lock; the inner lock is always the
 	 * older lock.
 	 */
 	spin_lock_irqsave(fence->lock, flags);
-	prev = xchg(__active_fence_slot(active), fence);
-	if (prev) {
-		GEM_BUG_ON(prev == fence);
+	if (prev)
 		spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING);
+
+	/*
+	 * A does the cmpxchg first, and so it sees C or NULL, as before, or
+	 * something else, depending on the timing of other threads and/or
+	 * interrupt handler.  If not the same as before then A unlocks C if
+	 * applicable and retries, starting from an attempt to get a new
+	 * active->fence.  Meanwhile, B follows the same path as A.
+	 * Once A succeeds with cmpxch, B fails again, retires, gets A from
+	 * active->fence, locks it as soon as A completes, and possibly
+	 * succeeds with cmpxchg.
+	 */
+	while (cmpxchg(__active_fence_slot(active), prev, fence) != prev) {
+		if (prev) {
+			spin_unlock(prev->lock);
+			dma_fence_put(prev);
+		}
+		spin_unlock_irqrestore(fence->lock, flags);
+
+		prev = i915_active_fence_get(active);
+		GEM_BUG_ON(prev == fence);
+
+		spin_lock_irqsave(fence->lock, flags);
+		if (prev)
+			spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING);
+	}
+
+	/*
+	 * If prev is NULL then the previous fence must have been signaled
+	 * and we know that we are first on the timeline.  If it is still
+	 * present then, having the lock on that fence already acquired, we
+	 * serialise with the interrupt handler, in the process of removing it
+	 * from any future interrupt callback.  A will then wait on C before
+	 * executing (if present).
+	 *
+	 * As B is second, it sees A as the previous fence and so waits for
+	 * it to complete its transition and takes over the occupancy for
+	 * itself -- remembering that it needs to wait on A before executing.
+	 */
+	if (prev) {
 		__list_del_entry(&active->cb.node);
 		spin_unlock(prev->lock); /* serialise with prev->cb_list */
 	}
@@ -1098,11 +1143,7 @@ int i915_active_fence_set(struct i915_active_fence *active,
 	int err = 0;
 
 	/* Must maintain timeline ordering wrt previous active requests */
-	rcu_read_lock();
 	fence = __i915_active_fence_set(active, &rq->fence);
-	if (fence) /* but the previous fence may not belong to that timeline! */
-		fence = dma_fence_get_rcu(fence);
-	rcu_read_unlock();
 	if (fence) {
 		err = i915_request_await_dma_fence(rq, fence);
 		dma_fence_put(fence);

drivers/gpu/drm/i915/i915_request.c

@@ -1596,6 +1596,8 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 							 &rq->dep,
 							 0);
 	}
+	if (prev)
+		i915_request_put(prev);
 
 	/*
 	 * Make sure that no request gazumped us - if it was allocated after

drivers/gpu/drm/vmwgfx/vmwgfx_drv.h

@@ -1685,4 +1685,16 @@ static inline bool vmw_has_fences(struct vmw_private *vmw)
 	return (vmw_fifo_caps(vmw) & SVGA_FIFO_CAP_FENCE) != 0;
 }
 
+static inline bool vmw_shadertype_is_valid(enum vmw_sm_type shader_model,
+					   u32 shader_type)
+{
+	SVGA3dShaderType max_allowed = SVGA3D_SHADERTYPE_PREDX_MAX;
+
+	if (shader_model >= VMW_SM_5)
+		max_allowed = SVGA3D_SHADERTYPE_MAX;
+	else if (shader_model >= VMW_SM_4)
+		max_allowed = SVGA3D_SHADERTYPE_DX10_MAX;
+	return shader_type >= SVGA3D_SHADERTYPE_MIN && shader_type < max_allowed;
+}
+
 #endif