rtw88: pci: Rearrange the memory usage for skb in RX ISR

Testing with RTL8822BE hardware, when available memory is low, we
frequently see a kernel panic and system freeze.

First, rtw_pci_rx_isr encounters a memory allocation failure (trimmed):

rx routine starvation
WARNING: CPU: 7 PID: 9871 at drivers/net/wireless/realtek/rtw88/pci.c:822 rtw_pci_rx_isr.constprop.25+0x35a/0x370 [rtwpci]
[ 2356.580313] RIP: 0010:rtw_pci_rx_isr.constprop.25+0x35a/0x370 [rtwpci]

Then we see a variety of different error conditions and kernel panics,
such as this one (trimmed):

rtw_pci 0000:02:00.0: pci bus timeout, check dma status
skbuff: skb_over_panic: text:00000000091b6e66 len:415 put:415 head:00000000d2880c6f data:000000007a02b1ea tail:0x1df end:0xc0 dev:<NULL>
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:105!
invalid opcode: 0000 [#1] SMP NOPTI
RIP: 0010:skb_panic+0x43/0x45

When skb allocation fails and the "rx routine starvation" is hit, the
function returns immediately without updating the RX ring. At this
point, the RX ring may continue referencing an old skb which was already
handed off to ieee80211_rx_irqsafe(). When it comes to be used again,
bad things happen.

This patch allocates a new, data-sized skb first in RX ISR. After
copying the data in, we pass it to the upper layers. However, if skb
allocation fails, we effectively drop the frame. In both cases, the
original, full size ring skb is reused.

In addition, to fixing the kernel crash, the RX routine should now
generally behave better under low memory conditions.

Buglink: https://bugzilla.kernel.org/show_bug.cgi?id=204053
Signed-off-by: Jian-Hong Pan <jian-hong@endlessm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>

diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index 353871c27779847974db2e61438c4aa56fa6358f..5da9e9e440241eaee24e3333391d90a80d10a491 100644 (file)
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -765,6 +765,7 @@ static void rtw_pci_rx_isr(struct rtw_dev *rtwdev, struct rtw_pci *rtwpci,
        u32 pkt_offset;
        u32 pkt_desc_sz = chip->rx_pkt_desc_sz;
        u32 buf_desc_sz = chip->rx_buf_desc_sz;
+       u32 new_len;
        u8 *rx_desc;
        dma_addr_t dma;
 
@@ -792,40 +793,34 @@ static void rtw_pci_rx_isr(struct rtw_dev *rtwdev, struct rtw_pci *rtwpci,
                pkt_offset = pkt_desc_sz + pkt_stat.drv_info_sz +
                             pkt_stat.shift;
 
-               if (pkt_stat.is_c2h) {
-                       /* keep rx_desc, halmac needs it */
-                       skb_put(skb, pkt_stat.pkt_len + pkt_offset);
+               /* allocate a new skb for this frame,
+                * discard the frame if none available
+                */
+               new_len = pkt_stat.pkt_len + pkt_offset;
+               new = dev_alloc_skb(new_len);
+               if (WARN_ONCE(!new, "rx routine starvation\n"))
+                       goto next_rp;
+
+               /* put the DMA data including rx_desc from phy to new skb */
+               skb_put_data(new, skb->data, new_len);
 
-                       /* pass offset for further operation */
-                       *((u32 *)skb->cb) = pkt_offset;
-                       skb_queue_tail(&rtwdev->c2h_queue, skb);
+               if (pkt_stat.is_c2h) {
+                        /* pass rx_desc & offset for further operation */
+                       *((u32 *)new->cb) = pkt_offset;
+                       skb_queue_tail(&rtwdev->c2h_queue, new);
                        ieee80211_queue_work(rtwdev->hw, &rtwdev->c2h_work);
                } else {
-                       /* remove rx_desc, maybe use skb_pull? */
-                       skb_put(skb, pkt_stat.pkt_len);
-                       skb_reserve(skb, pkt_offset);
-
-                       /* alloc a smaller skb to mac80211 */
-                       new = dev_alloc_skb(pkt_stat.pkt_len);
-                       if (!new) {
-                               new = skb;
-                       } else {
-                               skb_put_data(new, skb->data, skb->len);
-                               dev_kfree_skb_any(skb);
-                       }
-                       /* TODO: merge into rx.c */
-                       rtw_rx_stats(rtwdev, pkt_stat.vif, skb);
+                       /* remove rx_desc */
+                       skb_pull(new, pkt_offset);
+
+                       rtw_rx_stats(rtwdev, pkt_stat.vif, new);
                        memcpy(new->cb, &rx_status, sizeof(rx_status));
                        ieee80211_rx_irqsafe(rtwdev->hw, new);
                }
 
-               /* skb delivered to mac80211, alloc a new one in rx ring */
-               new = dev_alloc_skb(RTK_PCI_RX_BUF_SIZE);
-               if (WARN(!new, "rx routine starvation\n"))
-                       return;
-
-               ring->buf[cur_rp] = new;
-               rtw_pci_reset_rx_desc(rtwdev, new, ring, cur_rp, buf_desc_sz);
+next_rp:
+               /* new skb delivered to mac80211, re-enable original skb DMA */
+               rtw_pci_reset_rx_desc(rtwdev, skb, ring, cur_rp, buf_desc_sz);
 
                /* host read next element in ring */
                if (++cur_rp >= ring->r.len)