AI Trajectory

null

{
  "EnableConfigs": null,
  "FocusSymbols": [],
  "KMSANReasoning": "",
  "NeedsKMSAN": false,
  "Reasoning": "The patch modifies the MediaTek Wireless Ethernet Dispatcher (WED) driver, which is a vendor-specific hardware offload engine for MediaTek SoCs. This hardware is not emulated in standard QEMU environments, making the code unreachable during typical virtualized fuzzing.",
  "WorthFuzzing": false
}

null

{
  "PatchDiff": "commit 07c3d7254dedddf370eae7d582aeb145bbc4950d\nAuthor: syz-cluster \u003ctriage@syzkaller.com\u003e\nDate:   Wed Aug 19 14:15:41 2026 +0000\n\n    syz-cluster: applied patch under review\n\ndiff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c\nindex 10d9beaae3721..53d3b7e00e1cd 100644\n--- a/drivers/net/ethernet/mediatek/mtk_wed.c\n+++ b/drivers/net/ethernet/mediatek/mtk_wed.c\n@@ -2071,6 +2071,11 @@ mtk_wed_dma_enable(struct mtk_wed_device *dev)\n \t\twdma_set(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_TX_DMA_EN);\n \t}\n \n+\tif (mtk_wed_is_v2(dev-\u003ehw))\n+\t\twdma_m32(dev, MTK_WDMA_GLO_CFG,\n+\t\t\t MTK_WDMA_GLO_CFG_RESV_BUFF,\n+\t\t\t FIELD_PREP(MTK_WDMA_GLO_CFG_RESV_BUFF, 0x80));\n+\n \twed_set(dev, MTK_WED_GLO_CFG,\n \t\tMTK_WED_GLO_CFG_TX_DMA_EN |\n \t\tMTK_WED_GLO_CFG_RX_DMA_EN);\ndiff --git a/drivers/net/ethernet/mediatek/mtk_wed_regs.h b/drivers/net/ethernet/mediatek/mtk_wed_regs.h\nindex c71190924816c..e5f83100ded52 100644\n--- a/drivers/net/ethernet/mediatek/mtk_wed_regs.h\n+++ b/drivers/net/ethernet/mediatek/mtk_wed_regs.h\n@@ -433,6 +433,7 @@ struct mtk_wdma_desc {\n #define MTK_WDMA_GLO_CFG_TX_DMA_BUSY\t\t\tBIT(1)\n #define MTK_WDMA_GLO_CFG_RX_DMA_EN\t\t\tBIT(2)\n #define MTK_WDMA_GLO_CFG_RX_DMA_BUSY\t\t\tBIT(3)\n+#define MTK_WDMA_GLO_CFG_RESV_BUFF\t\t\tGENMASK(23, 16)\n #define MTK_WDMA_GLO_CFG_RX_INFO3_PRERES\t\tBIT(26)\n #define MTK_WDMA_GLO_CFG_RX_INFO2_PRERES\t\tBIT(27)\n #define MTK_WDMA_GLO_CFG_RX_INFO1_PRERES\t\tBIT(28)\n"
}

best-expensive

null

{
  "EnableConfigs": null,
  "FocusSymbols": [],
  "Reasoning": "The patch modifies the MediaTek Wireless Ethernet Dispatcher (WED) driver, which is a vendor-specific hardware offload engine for MediaTek SoCs. This hardware is not emulated in standard QEMU environments, making the code unreachable during typical virtualized fuzzing.",
  "WorthFuzzing": false
}

You are an expert Linux kernel maintainer.
Your job is to review a provided patch series and determine
if it makes functional changes to the kernel that should be fuzzed.

IMPORTANT: The changes have ALREADY been applied and committed as the HEAD commit in
your workspace. Do NOT rely on your internal knowledge of the kernel. You must actively
use your code access tools to examine the actual source code and confirm any assumptions.

Return WorthFuzzing=false if the patch only contains:
- Modifications to Documentation/, Kconfig files, or code comments.
- Purely decorative changes, such as logging (e.g., pr_err, printk) or tracepoints.
- Changes to numeric constants or macros that do not functionally alter execution flow.
- Code paths that are impossible to reach in virtualized environments like GCE or QEMU,
  even when utilizing software-emulated hardware (e.g., usb gadget, mac80211_hwsim).
- Code in vendor-specific PCIe switch, SmartNIC, or GPU drivers (e.g., mlxsw, pds_core, qed,
  ionic, amdgpu) that require physical PCIe hardware cards not emulated in standard QEMU.
- Driver .remove, .shutdown, or pci_unregister_driver teardown callbacks (e.g., igb_remove)
  that are executed only during PCI hot-unplug or sysfs driver unbind operations.

If it modifies reachable core kernel logic, drivers, or architectures, use your code search
tools to verify the code can be executed, then return WorthFuzzing=true.

When returning WorthFuzzing=true, you MUST ALSO:
1. Extract any specific kernel functions that should be heavily fuzzed into FocusSymbols.
   Avoid listing generic hot-path functions to prevent skewed test distributions.
   Prefer non-static, non-inlined API entrypoint functions over internal static helper functions
   (which are inlined by the compiler and do not have distinct symbol addresses).
2. Identify any specific CONFIG_ options required to properly test this new/modified feature.
   Go and look into the Kconfig files and check for ifdefs around the code, do not make assumptions.
   Also check "depends on" lines in Kconfig to include any non-standard parent subsystem configs
   needed for Kbuild to compile the code statically into vmlinux. List them in the EnableConfigs
   output array, and DO NOT add a 'CONFIG_' prefix (e.g., return "NET_IPV4" instead of "CONFIG_NET_IPV4").
Prefer calling several tools at the same time to save round-trips.


Use set-results tool to provide results of the analysis.
It must be called exactly once before the final reply.
Ignore results of this tool.

For your convenience, here is the diff of the changes:
commit 07c3d7254dedddf370eae7d582aeb145bbc4950d
Author: syz-cluster <triage@syzkaller.com>
Date:   Wed Aug 19 14:15:41 2026 +0000

    syz-cluster: applied patch under review

diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
index 10d9beaae3721..53d3b7e00e1cd 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed.c
@@ -2071,6 +2071,11 @@ mtk_wed_dma_enable(struct mtk_wed_device *dev)
 		wdma_set(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_TX_DMA_EN);
 	}
 
+	if (mtk_wed_is_v2(dev->hw))
+		wdma_m32(dev, MTK_WDMA_GLO_CFG,
+			 MTK_WDMA_GLO_CFG_RESV_BUFF,
+			 FIELD_PREP(MTK_WDMA_GLO_CFG_RESV_BUFF, 0x80));
+
 	wed_set(dev, MTK_WED_GLO_CFG,
 		MTK_WED_GLO_CFG_TX_DMA_EN |
 		MTK_WED_GLO_CFG_RX_DMA_EN);
diff --git a/drivers/net/ethernet/mediatek/mtk_wed_regs.h b/drivers/net/ethernet/mediatek/mtk_wed_regs.h
index c71190924816c..e5f83100ded52 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed_regs.h
+++ b/drivers/net/ethernet/mediatek/mtk_wed_regs.h
@@ -433,6 +433,7 @@ struct mtk_wdma_desc {
 #define MTK_WDMA_GLO_CFG_TX_DMA_BUSY			BIT(1)
 #define MTK_WDMA_GLO_CFG_RX_DMA_EN			BIT(2)
 #define MTK_WDMA_GLO_CFG_RX_DMA_BUSY			BIT(3)
+#define MTK_WDMA_GLO_CFG_RESV_BUFF			GENMASK(23, 16)
 #define MTK_WDMA_GLO_CFG_RX_INFO3_PRERES		BIT(26)
 #define MTK_WDMA_GLO_CFG_RX_INFO2_PRERES		BIT(27)
 #define MTK_WDMA_GLO_CFG_RX_INFO1_PRERES		BIT(28)

gemini-3.1-pro-preview

null

null

							input: 2469
							output: 36
							thoughts: 307
						

**My Assessment of the Mediatek WED Patch**

Okay, so I'm looking at this patch. It seems we're modifying the `mtk_wed.c` and `mtk_wed_regs.h` files within the Mediatek Ethernet driver. Specifically, a few lines are being added to the `mtk_wed_dma_enable` function, which appears to be conditional on `mtk_wed_is_v2(dev->hw)`. This looks like a configuration change, writing to `MTK_WDMA_GLO_CFG` to set `MTK_WDMA_GLO_CFG_RESV_BUFF` to `0x80` if we're dealing with the v2 hardware.

The question that immediately pops into my head, given the nature of this change and the fact that it's in the WED component, is whether this is something we can even *test* in a virtualized environment. These Mediatek ethernet drivers are typically very SoC-specific, targeting things like the MT7622 or MT7986. WED, in particular, is a hardware offload engine, generally used for Wi-Fi.

My gut tells me this is going to be hardware-dependent. Standard QEMU, unless we're using a specific machine type with explicit Mediatek support, probably won't emulate this. Even *with* such a machine type, the WED function, being a hardware offload, might not be well-represented in software emulation. We'd likely need some form of specific Mediatek silicon or a very well-defined test environment to fully exercise this code path. I'll need to check the Kconfig for the Mediatek ethernet driver to get a better handle on the conditions under which these drivers are built and activated. This will help determine how testable this particular change actually is.

{
  "Expression": "config NET_MEDIATEK",
  "PathPrefix": "drivers/net/ethernet/mediatek/"
}

{
  "Output": "drivers/net/ethernet/mediatek/Kconfig=8=if NET_VENDOR_MEDIATEK\ndrivers/net/ethernet/mediatek/Kconfig-9-\ndrivers/net/ethernet/mediatek/Kconfig:10:config NET_MEDIATEK_SOC_WED\ndrivers/net/ethernet/mediatek/Kconfig-11-\tdepends on ARCH_MEDIATEK || COMPILE_TEST\n--\ndrivers/net/ethernet/mediatek/Kconfig-13-\ndrivers/net/ethernet/mediatek/Kconfig:14:config NET_MEDIATEK_SOC\ndrivers/net/ethernet/mediatek/Kconfig-15-\ttristate \"MediaTek SoC Gigabit Ethernet support\"\n--\ndrivers/net/ethernet/mediatek/Kconfig-28-\ndrivers/net/ethernet/mediatek/Kconfig:29:config NET_MEDIATEK_STAR_EMAC\ndrivers/net/ethernet/mediatek/Kconfig-30-\ttristate \"MediaTek STAR Ethernet MAC support\"\n"
}

gemini-3.1-pro-preview

null

null

							input: 3472
							output: 86
							thoughts: 175
						

**My Assessment of the Mediatek WED for Fuzzing**

Okay, let's break this down. The Mediatek WED, right, that's a hardware offload engine. I'm seeing "MediaTek SoC Gigabit Ethernet support" in the context here, and I'm noting the dependencies: `ARCH_MEDIATEK || COMPILE_TEST`. So, immediately, I'm thinking, this is Mediatek-specific hardware, not a generic implementation. The core question is always, is this worth fuzzing, and I need to determine if it's reachable given the constraints.

The prompt specifically flags certain areas as off-limits: vendor-specific drivers for things like PCIe switches, SmartNICs, or GPUs—things that *require* physical hardware, and that are not emulated in standard QEMU. Thinking about this Mediatek WED, it's a vendor-specific Ethernet/Wi-Fi offload driver, residing within the SoC itself. It's designed to interface with the silicon. This definitively means it needs *physical* Mediatek hardware to function.

Therefore, because this driver can't be reached in a standard QEMU setup, I must conclude that this patch is not worth fuzzing. I'll return `WorthFuzzing=false`.

{
  "EnableConfigs": [],
  "FocusSymbols": [],
  "Reasoning": "The patch modifies the MediaTek Wireless Ethernet Dispatcher (WED) driver, which is a vendor-specific hardware offload engine for MediaTek SoCs. This hardware is not emulated in standard QEMU environments, making the code unreachable during typical virtualized fuzzing.",
  "WorthFuzzing": false
}

{
  "EnableConfigs": null,
  "FocusSymbols": [],
  "Reasoning": "The patch modifies the MediaTek Wireless Ethernet Dispatcher (WED) driver, which is a vendor-specific hardware offload engine for MediaTek SoCs. This hardware is not emulated in standard QEMU environments, making the code unreachable during typical virtualized fuzzing.",
  "WorthFuzzing": false
}

{
  "WorthFuzzing": false
}

null