FAILED: patch "[PATCH] octeontx2-pf: Fix the use of GFP_KERNEL in atomic context on" failed to apply to 5.15-stable tree

The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

Possible dependencies:

55ba18dc62de ("octeontx2-pf: Fix the use of GFP_KERNEL in atomic context on rt") 4af1b64f80fb ("octeontx2-pf: Fix lmtst ID used in aura free")

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 55ba18dc62deff5910c0fa64486dea1ff20832ff Mon Sep 17 00:00:00 2001
From: Kevin Hao <[email protected]>
Date: Wed, 18 Jan 2023 15:13:00 +0800
Subject: [PATCH] octeontx2-pf: Fix the use of GFP_KERNEL in atomic context on
rt

The commit 4af1b64f80fb ("octeontx2-pf: Fix lmtst ID used in aura free") uses the get/put_cpu() to protect the usage of percpu pointer in ->aura_freeptr() callback, but it also unnecessarily disable the preemption for the blockable memory allocation. The commit 87b93b678e95 ("octeontx2-pf: Avoid use of GFP_KERNEL in atomic context") tried to fix these sleep inside atomic warnings. But it only fix the one for the non-rt kernel. For the rt kernel, we still get the similar warnings like below.

  BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:46
  in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1, name: swapper/0
  preempt_count: 1, expected: 0
  RCU nest depth: 0, expected: 0
  3 locks held by swapper/0/1:
   #0: ffff800009fc5fe8 (rtnl_mutex){+.+.}-{3:3}, at: rtnl_lock+0x24/0x30
   #1: ffff000100c276c0 (&mbox->lock){+.+.}-{3:3}, at: otx2_init_hw_resources+0x8c/0x3a4
   #2: ffffffbfef6537e0 (&cpu_rcache->lock){+.+.}-{2:2}, at: alloc_iova_fast+0x1ac/0x2ac
  Preemption disabled at:
  [<ffff800008b1908c>] otx2_rq_aura_pool_init+0x14c/0x284
  CPU: 20 PID: 1 Comm: swapper/0 Tainted: G        W          6.2.0-rc3-rt1-yocto-preempt-rt #1
  Hardware name: Marvell OcteonTX CN96XX board (DT)
  Call trace:
   dump_backtrace.part.0+0xe8/0xf4
   show_stack+0x20/0x30
   dump_stack_lvl+0x9c/0xd8
   dump_stack+0x18/0x34
   __might_resched+0x188/0x224
   rt_spin_lock+0x64/0x110
   alloc_iova_fast+0x1ac/0x2ac
   iommu_dma_alloc_iova+0xd4/0x110
   __iommu_dma_map+0x80/0x144
   iommu_dma_map_page+0xe8/0x260
   dma_map_page_attrs+0xb4/0xc0
   __otx2_alloc_rbuf+0x90/0x150
   otx2_rq_aura_pool_init+0x1c8/0x284
   otx2_init_hw_resources+0xe4/0x3a4
   otx2_open+0xf0/0x610
   __dev_open+0x104/0x224
   __dev_change_flags+0x1e4/0x274
   dev_change_flags+0x2c/0x7c
   ic_open_devs+0x124/0x2f8
   ip_auto_config+0x180/0x42c
   do_one_initcall+0x90/0x4dc
   do_basic_setup+0x10c/0x14c
   kernel_init_freeable+0x10c/0x13c
   kernel_init+0x2c/0x140
   ret_from_fork+0x10/0x20

Of course, we can shuffle the get/put_cpu() to only wrap the invocation of ->aura_freeptr() as what commit 87b93b678e95 does. But there are only two ->aura_freeptr() callbacks, otx2_aura_freeptr() and cn10k_aura_freeptr(). There is no usage of perpcu variable in the otx2_aura_freeptr() at all, so the get/put_cpu() seems redundant to it. We can move the get/put_cpu() into the corresponding callback which really has the percpu variable usage and avoid the sprinkling of get/put_cpu() in several places.

index 497b777b6a34..8a41ad8ca04f 100644
@@ -1012,7 +1012,6 @@ static void otx2_pool_refill_task(struct work_struct *work)
 	rbpool = cq->rbpool;
 	free_ptrs = cq->pool_ptrs;
 
-	get_cpu();
 	while (cq->pool_ptrs) {
 		if (otx2_alloc_rbuf(pfvf, rbpool, &bufptr)) {
 			/* Schedule a WQ if we fails to free atleast half of the

@@ -1032,7 +1031,6 @@ static void otx2_pool_refill_task(struct work_struct *work)
 		pfvf->hw_ops->aura_freeptr(pfvf, qidx, bufptr + OTX2_HEAD_ROOM);
 		cq->pool_ptrs--;
 	}
-	put_cpu();
 	cq->refill_task_sched = false;
 }
 

@@ -1387,9 +1385,7 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf)
 			err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
 			if (err)
 				goto err_mem;
-			get_cpu();
 			pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);
-			put_cpu();
 			sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr;
 		}
 	}

@@ -1435,21 +1431,18 @@ int otx2_rq_aura_pool_init(struct otx2_nic *pfvf)
 	if (err)
 		goto fail;
 
-	get_cpu();
 	/* Allocate pointers and free them to aura/pool */
 	for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) {
 		pool = &pfvf->qset.pool[pool_id];
 		for (ptr = 0; ptr < num_ptrs; ptr++) {
 			err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
 			if (err)
-				goto err_mem;
+				return -ENOMEM;
 			pfvf->hw_ops->aura_freeptr(pfvf, pool_id,
 						   bufptr + OTX2_HEAD_ROOM);
 		}
 	}
-err_mem:
-	put_cpu();
-	return err ? -ENOMEM : 0;
+	return 0;
 fail:
 	otx2_mbox_reset(&pfvf->mbox.mbox, 0);
 	otx2_aura_pool_free(pfvf);

index 5bee3c3a7ce4..3d22cc6a2804 100644
@@ -736,8 +736,10 @@ static inline void cn10k_aura_freeptr(void *dev, int aura, u64 buf)
 	u64 ptrs[2];
 
 	ptrs[1] = buf;
+	get_cpu();
 	/* Free only one buffer at time during init and teardown */
 	__cn10k_aura_freeptr(pfvf, aura, ptrs, 2);
+	put_cpu();
 }
 
 /* Alloc pointer from pool/aura */