x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

5 files changed, 413 insertions, 0 deletions

diff --git a/arch/microblaze/boot/.gitignore b/arch/microblaze/boot/.gitignore
new file mode 100644
index 000000000..11a9e229f
--- /dev/null
+++ b/arch/microblaze/boot/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+linux.bin*
+simpleImage.*
diff --git a/arch/microblaze/boot/Makefile b/arch/microblaze/boot/Makefile
new file mode 100644
index 000000000..2b42c370d
--- /dev/null
+++ b/arch/microblaze/boot/Makefile
@@ -0,0 +1,35 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# arch/microblaze/boot/Makefile
+#
+
+targets := linux.bin linux.bin.gz linux.bin.ub simpleImage.*
+
+OBJCOPYFLAGS := -R .note -R .comment -R .note.gnu.build-id -O binary
+
+$(obj)/linux.bin: vmlinux FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/linux.bin.ub: $(obj)/linux.bin FORCE
+	$(call if_changed,uimage)
+
+$(obj)/linux.bin.gz: $(obj)/linux.bin FORCE
+	$(call if_changed,gzip)
+
+quiet_cmd_strip = STRIP   $< $@$2
+	cmd_strip = $(STRIP) -K microblaze_start -K _end -K __log_buf \
+				-K _fdt_start $< -o $@$2
+
+UIMAGE_LOADADDR = $(CONFIG_KERNEL_BASE_ADDR)
+
+$(obj)/simpleImage.$(DTB): vmlinux FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/simpleImage.$(DTB).ub: $(obj)/simpleImage.$(DTB) FORCE
+	$(call if_changed,uimage)
+
+$(obj)/simpleImage.$(DTB).unstrip: vmlinux FORCE
+	$(call if_changed,copy)
+
+$(obj)/simpleImage.$(DTB).strip: vmlinux FORCE
+	$(call if_changed,strip)
diff --git a/arch/microblaze/boot/dts/Makefile b/arch/microblaze/boot/dts/Makefile
new file mode 100644
index 000000000..b84e2cbb2
--- /dev/null
+++ b/arch/microblaze/boot/dts/Makefile
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+
+dtb-y := system.dtb
+
+ifneq ($(DTB),)
+obj-y += linked_dtb.o
+
+# Ensure system.dtb exists
+$(obj)/linked_dtb.o: $(obj)/system.dtb
+
+# Generate system.dtb from $(DTB).dtb
+ifneq ($(DTB),system)
+$(obj)/system.dtb: $(obj)/$(DTB).dtb
+	$(call if_changed,copy)
+endif
+endif
+
+# Rule to build device tree blobs
+DTC_FLAGS := -p 1024
diff --git a/arch/microblaze/boot/dts/linked_dtb.S b/arch/microblaze/boot/dts/linked_dtb.S
new file mode 100644
index 000000000..23345af37
--- /dev/null
+++ b/arch/microblaze/boot/dts/linked_dtb.S
@@ -0,0 +1,2 @@
+.section __fdt_blob,"a"
+.incbin "arch/microblaze/boot/dts/system.dtb"
diff --git a/arch/microblaze/boot/dts/system.dts b/arch/microblaze/boot/dts/system.dts
new file mode 100644
index 000000000..22252451e
--- /dev/null
+++ b/arch/microblaze/boot/dts/system.dts
@@ -0,0 +1,353 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Device Tree Generator version: 1.1
+ *
+ * (C) Copyright 2007-2008 Xilinx, Inc.
+ * (C) Copyright 2007-2009 Michal Simek
+ *
+ * Michal SIMEK <monstr@monstr.eu>
+ *
+ * CAUTION: This file is automatically generated by libgen.
+ * Version: Xilinx EDK 10.1.03 EDK_K_SP3.6
+ *
+ * XPS project directory: Xilinx-ML505-ll_temac-sgdma-MMU-FDT-edk101
+ */
+
+/dts-v1/;
+/ {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	compatible = "xlnx,microblaze";
+	model = "testing";
+	DDR2_SDRAM: memory@90000000 {
+		device_type = "memory";
+		reg = < 0x90000000 0x10000000 >;
+	} ;
+	aliases {
+		ethernet0 = &Hard_Ethernet_MAC;
+		serial0 = &RS232_Uart_1;
+	} ;
+	chosen {
+		bootargs = "console=ttyUL0,115200 highres=on";
+		stdout-path = "/plb@0/serial@84000000";
+	} ;
+	cpus {
+		#address-cells = <1>;
+		#cpus = <0x1>;
+		#size-cells = <0>;
+		microblaze_0: cpu@0 {
+			clock-frequency = <125000000>;
+			compatible = "xlnx,microblaze-7.10.d";
+			d-cache-baseaddr = <0x90000000>;
+			d-cache-highaddr = <0x9fffffff>;
+			d-cache-line-size = <0x10>;
+			d-cache-size = <0x2000>;
+			device_type = "cpu";
+			i-cache-baseaddr = <0x90000000>;
+			i-cache-highaddr = <0x9fffffff>;
+			i-cache-line-size = <0x10>;
+			i-cache-size = <0x2000>;
+			model = "microblaze,7.10.d";
+			reg = <0>;
+			timebase-frequency = <125000000>;
+			xlnx,addr-tag-bits = <0xf>;
+			xlnx,allow-dcache-wr = <0x1>;
+			xlnx,allow-icache-wr = <0x1>;
+			xlnx,area-optimized = <0x0>;
+			xlnx,cache-byte-size = <0x2000>;
+			xlnx,d-lmb = <0x1>;
+			xlnx,d-opb = <0x0>;
+			xlnx,d-plb = <0x1>;
+			xlnx,data-size = <0x20>;
+			xlnx,dcache-addr-tag = <0xf>;
+			xlnx,dcache-always-used = <0x1>;
+			xlnx,dcache-byte-size = <0x2000>;
+			xlnx,dcache-line-len = <0x4>;
+			xlnx,dcache-use-fsl = <0x1>;
+			xlnx,debug-enabled = <0x1>;
+			xlnx,div-zero-exception = <0x1>;
+			xlnx,dopb-bus-exception = <0x0>;
+			xlnx,dynamic-bus-sizing = <0x1>;
+			xlnx,edge-is-positive = <0x1>;
+			xlnx,family = "virtex5";
+			xlnx,endianness = <0x1>;
+			xlnx,fpu-exception = <0x1>;
+			xlnx,fsl-data-size = <0x20>;
+			xlnx,fsl-exception = <0x0>;
+			xlnx,fsl-links = <0x0>;
+			xlnx,i-lmb = <0x1>;
+			xlnx,i-opb = <0x0>;
+			xlnx,i-plb = <0x1>;
+			xlnx,icache-always-used = <0x1>;
+			xlnx,icache-line-len = <0x4>;
+			xlnx,icache-use-fsl = <0x1>;
+			xlnx,ill-opcode-exception = <0x1>;
+			xlnx,instance = "microblaze_0";
+			xlnx,interconnect = <0x1>;
+			xlnx,interrupt-is-edge = <0x0>;
+			xlnx,iopb-bus-exception = <0x0>;
+			xlnx,mmu-dtlb-size = <0x4>;
+			xlnx,mmu-itlb-size = <0x2>;
+			xlnx,mmu-tlb-access = <0x3>;
+			xlnx,mmu-zones = <0x10>;
+			xlnx,number-of-pc-brk = <0x1>;
+			xlnx,number-of-rd-addr-brk = <0x0>;
+			xlnx,number-of-wr-addr-brk = <0x0>;
+			xlnx,opcode-0x0-illegal = <0x1>;
+			xlnx,pvr = <0x2>;
+			xlnx,pvr-user1 = <0x0>;
+			xlnx,pvr-user2 = <0x0>;
+			xlnx,reset-msr = <0x0>;
+			xlnx,sco = <0x0>;
+			xlnx,unaligned-exceptions = <0x1>;
+			xlnx,use-barrel = <0x1>;
+			xlnx,use-dcache = <0x1>;
+			xlnx,use-div = <0x1>;
+			xlnx,use-ext-brk = <0x1>;
+			xlnx,use-ext-nm-brk = <0x1>;
+			xlnx,use-extended-fsl-instr = <0x0>;
+			xlnx,use-fpu = <0x2>;
+			xlnx,use-hw-mul = <0x2>;
+			xlnx,use-icache = <0x1>;
+			xlnx,use-interrupt = <0x1>;
+			xlnx,use-mmu = <0x3>;
+			xlnx,use-msr-instr = <0x1>;
+			xlnx,use-pcmp-instr = <0x1>;
+		} ;
+	} ;
+	mb_plb: plb@0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "xlnx,plb-v46-1.03.a", "xlnx,plb-v46-1.00.a", "simple-bus";
+		ranges ;
+		FLASH: flash@a0000000 {
+			bank-width = <2>;
+			compatible = "xlnx,xps-mch-emc-2.00.a", "cfi-flash";
+			reg = < 0xa0000000 0x2000000 >;
+			xlnx,family = "virtex5";
+			xlnx,include-datawidth-matching-0 = <0x1>;
+			xlnx,include-datawidth-matching-1 = <0x0>;
+			xlnx,include-datawidth-matching-2 = <0x0>;
+			xlnx,include-datawidth-matching-3 = <0x0>;
+			xlnx,include-negedge-ioregs = <0x0>;
+			xlnx,include-plb-ipif = <0x1>;
+			xlnx,include-wrbuf = <0x1>;
+			xlnx,max-mem-width = <0x10>;
+			xlnx,mch-native-dwidth = <0x20>;
+			xlnx,mch-plb-clk-period-ps = <0x1f40>;
+			xlnx,mch-splb-awidth = <0x20>;
+			xlnx,mch0-accessbuf-depth = <0x10>;
+			xlnx,mch0-protocol = <0x0>;
+			xlnx,mch0-rddatabuf-depth = <0x10>;
+			xlnx,mch1-accessbuf-depth = <0x10>;
+			xlnx,mch1-protocol = <0x0>;
+			xlnx,mch1-rddatabuf-depth = <0x10>;
+			xlnx,mch2-accessbuf-depth = <0x10>;
+			xlnx,mch2-protocol = <0x0>;
+			xlnx,mch2-rddatabuf-depth = <0x10>;
+			xlnx,mch3-accessbuf-depth = <0x10>;
+			xlnx,mch3-protocol = <0x0>;
+			xlnx,mch3-rddatabuf-depth = <0x10>;
+			xlnx,mem0-width = <0x10>;
+			xlnx,mem1-width = <0x20>;
+			xlnx,mem2-width = <0x20>;
+			xlnx,mem3-width = <0x20>;
+			xlnx,num-banks-mem = <0x1>;
+			xlnx,num-channels = <0x0>;
+			xlnx,priority-mode = <0x0>;
+			xlnx,synch-mem-0 = <0x0>;
+			xlnx,synch-mem-1 = <0x0>;
+			xlnx,synch-mem-2 = <0x0>;
+			xlnx,synch-mem-3 = <0x0>;
+			xlnx,synch-pipedelay-0 = <0x2>;
+			xlnx,synch-pipedelay-1 = <0x2>;
+			xlnx,synch-pipedelay-2 = <0x2>;
+			xlnx,synch-pipedelay-3 = <0x2>;
+			xlnx,tavdv-ps-mem-0 = <0x1adb0>;
+			xlnx,tavdv-ps-mem-1 = <0x3a98>;
+			xlnx,tavdv-ps-mem-2 = <0x3a98>;
+			xlnx,tavdv-ps-mem-3 = <0x3a98>;
+			xlnx,tcedv-ps-mem-0 = <0x1adb0>;
+			xlnx,tcedv-ps-mem-1 = <0x3a98>;
+			xlnx,tcedv-ps-mem-2 = <0x3a98>;
+			xlnx,tcedv-ps-mem-3 = <0x3a98>;
+			xlnx,thzce-ps-mem-0 = <0x88b8>;
+			xlnx,thzce-ps-mem-1 = <0x1b58>;
+			xlnx,thzce-ps-mem-2 = <0x1b58>;
+			xlnx,thzce-ps-mem-3 = <0x1b58>;
+			xlnx,thzoe-ps-mem-0 = <0x1b58>;
+			xlnx,thzoe-ps-mem-1 = <0x1b58>;
+			xlnx,thzoe-ps-mem-2 = <0x1b58>;
+			xlnx,thzoe-ps-mem-3 = <0x1b58>;
+			xlnx,tlzwe-ps-mem-0 = <0x88b8>;
+			xlnx,tlzwe-ps-mem-1 = <0x0>;
+			xlnx,tlzwe-ps-mem-2 = <0x0>;
+			xlnx,tlzwe-ps-mem-3 = <0x0>;
+			xlnx,twc-ps-mem-0 = <0x2af8>;
+			xlnx,twc-ps-mem-1 = <0x3a98>;
+			xlnx,twc-ps-mem-2 = <0x3a98>;
+			xlnx,twc-ps-mem-3 = <0x3a98>;
+			xlnx,twp-ps-mem-0 = <0x11170>;
+			xlnx,twp-ps-mem-1 = <0x2ee0>;
+			xlnx,twp-ps-mem-2 = <0x2ee0>;
+			xlnx,twp-ps-mem-3 = <0x2ee0>;
+			xlnx,xcl0-linesize = <0x4>;
+			xlnx,xcl0-writexfer = <0x1>;
+			xlnx,xcl1-linesize = <0x4>;
+			xlnx,xcl1-writexfer = <0x1>;
+			xlnx,xcl2-linesize = <0x4>;
+			xlnx,xcl2-writexfer = <0x1>;
+			xlnx,xcl3-linesize = <0x4>;
+			xlnx,xcl3-writexfer = <0x1>;
+		} ;
+		Hard_Ethernet_MAC: xps-ll-temac@81c00000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "xlnx,compound";
+			ranges ;
+			ethernet@81c00000 {
+				compatible = "xlnx,xps-ll-temac-1.01.b", "xlnx,xps-ll-temac-1.00.a";
+				interrupt-parent = <&xps_intc_0>;
+				interrupts = < 5 2 >;
+				llink-connected = <&PIM3>;
+				local-mac-address = [ 00 0a 35 00 00 00 ];
+				reg = < 0x81c00000 0x40 >;
+				xlnx,bus2core-clk-ratio = <0x1>;
+				xlnx,phy-type = <0x1>;
+				xlnx,phyaddr = <0x1>;
+				xlnx,rxcsum = <0x0>;
+				xlnx,rxfifo = <0x1000>;
+				xlnx,temac-type = <0x0>;
+				xlnx,txcsum = <0x0>;
+				xlnx,txfifo = <0x1000>;
+			} ;
+		} ;
+		IIC_EEPROM: i2c@81600000 {
+			compatible = "xlnx,xps-iic-2.00.a";
+			interrupt-parent = <&xps_intc_0>;
+			interrupts = < 6 2 >;
+			reg = < 0x81600000 0x10000 >;
+			xlnx,clk-freq = <0x7735940>;
+			xlnx,family = "virtex5";
+			xlnx,gpo-width = <0x1>;
+			xlnx,iic-freq = <0x186a0>;
+			xlnx,scl-inertial-delay = <0x0>;
+			xlnx,sda-inertial-delay = <0x0>;
+			xlnx,ten-bit-adr = <0x0>;
+		} ;
+		LEDs_8Bit: gpio@81400000 {
+			compatible = "xlnx,xps-gpio-1.00.a";
+			interrupt-parent = <&xps_intc_0>;
+			interrupts = < 7 2 >;
+			reg = < 0x81400000 0x10000 >;
+			xlnx,all-inputs = <0x0>;
+			xlnx,all-inputs-2 = <0x0>;
+			xlnx,dout-default = <0x0>;
+			xlnx,dout-default-2 = <0x0>;
+			xlnx,family = "virtex5";
+			xlnx,gpio-width = <0x8>;
+			xlnx,interrupt-present = <0x1>;
+			xlnx,is-bidir = <0x1>;
+			xlnx,is-bidir-2 = <0x1>;
+			xlnx,is-dual = <0x0>;
+			xlnx,tri-default = <0xffffffff>;
+			xlnx,tri-default-2 = <0xffffffff>;
+			#gpio-cells = <2>;
+			gpio-controller;
+		} ;
+
+		gpio-leds {
+			compatible = "gpio-leds";
+
+			heartbeat {
+				label = "Heartbeat";
+				gpios = <&LEDs_8Bit 4 1>;
+				linux,default-trigger = "heartbeat";
+			};
+
+			yellow {
+				label = "Yellow";
+				gpios = <&LEDs_8Bit 5 1>;
+			};
+
+			red {
+				label = "Red";
+				gpios = <&LEDs_8Bit 6 1>;
+			};
+
+			green {
+				label = "Green";
+				gpios = <&LEDs_8Bit 7 1>;
+			};
+		} ;
+
+		gpio-restart {
+			compatible = "gpio-restart";
+			/*
+			 * FIXME: is this active low or active high?
+			 * the current flag (1) indicates active low.
+			 * delay measures are templates, should be adjusted
+			 * to datasheet or trial-and-error with real hardware.
+			 */
+			gpios = <&LEDs_8Bit 2 1>;
+			active-delay = <100>;
+			inactive-delay = <10>;
+			wait-delay = <100>;
+		};
+
+		RS232_Uart_1: serial@84000000 {
+			clock-frequency = <125000000>;
+			compatible = "xlnx,xps-uartlite-1.00.a";
+			current-speed = <115200>;
+			device_type = "serial";
+			interrupt-parent = <&xps_intc_0>;
+			interrupts = < 8 0 >;
+			port-number = <0>;
+			reg = < 0x84000000 0x10000 >;
+			xlnx,baudrate = <0x1c200>;
+			xlnx,data-bits = <0x8>;
+			xlnx,family = "virtex5";
+			xlnx,odd-parity = <0x0>;
+			xlnx,use-parity = <0x0>;
+		} ;
+		debug_module: debug@84400000 {
+			compatible = "xlnx,mdm-1.00.d";
+			reg = < 0x84400000 0x10000 >;
+			xlnx,family = "virtex5";
+			xlnx,interconnect = <0x1>;
+			xlnx,jtag-chain = <0x2>;
+			xlnx,mb-dbg-ports = <0x1>;
+			xlnx,uart-width = <0x8>;
+			xlnx,use-uart = <0x1>;
+			xlnx,write-fsl-ports = <0x0>;
+		} ;
+		mpmc@90000000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "xlnx,mpmc-4.02.a";
+			ranges ;
+			PIM3: sdma@84600180 {
+				compatible = "xlnx,ll-dma-1.00.a";
+				interrupt-parent = <&xps_intc_0>;
+				interrupts = < 2 2 1 2 >;
+				reg = < 0x84600180 0x80 >;
+			} ;
+		} ;
+		xps_intc_0: interrupt-controller@81800000 {
+			#interrupt-cells = <0x2>;
+			compatible = "xlnx,xps-intc-1.00.a";
+			interrupt-controller ;
+			reg = < 0x81800000 0x10000 >;
+			xlnx,kind-of-intr = <0x100>;
+			xlnx,num-intr-inputs = <0x9>;
+		} ;
+		xps_timer_1: timer@83c00000 {
+			compatible = "xlnx,xps-timer-1.00.a";
+			interrupt-parent = <&xps_intc_0>;
+			interrupts = < 3 2 >;
+			reg = < 0x83c00000 0x10000 >;
+			xlnx,count-width = <0x20>;
+			xlnx,one-timer-only = <0x0>;
+		} ;
+	} ;
+}  ;