From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions 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) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- drivers/clocksource/timer-sun5i.c | 377 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 377 insertions(+) create mode 100644 drivers/clocksource/timer-sun5i.c (limited to 'drivers/clocksource/timer-sun5i.c') diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c new file mode 100644 index 000000000..bcf155fb9 --- /dev/null +++ b/drivers/clocksource/timer-sun5i.c @@ -0,0 +1,377 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Allwinner SoCs hstimer driver. + * + * Copyright (C) 2013 Maxime Ripard + * + * Maxime Ripard + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define TIMER_IRQ_EN_REG 0x00 +#define TIMER_IRQ_EN(val) BIT(val) +#define TIMER_IRQ_ST_REG 0x04 +#define TIMER_CTL_REG(val, offset) (0x20 * (val) + 0x10 + (offset)) +#define TIMER_CTL_ENABLE BIT(0) +#define TIMER_CTL_RELOAD BIT(1) +#define TIMER_CTL_CLK_PRES(val) (((val) & 0x7) << 4) +#define TIMER_CTL_ONESHOT BIT(7) +#define TIMER_INTVAL_LO_REG(val, offset) (0x20 * (val) + 0x14 + (offset)) +#define TIMER_INTVAL_HI_REG(val, offset) (0x20 * (val) + 0x18 + (offset)) +#define TIMER_CNTVAL_LO_REG(val, offset) (0x20 * (val) + 0x1c + (offset)) +#define TIMER_CNTVAL_HI_REG(val, offset) (0x20 * (val) + 0x20 + (offset)) + +#define TIMER_SYNC_TICKS 3 + +/** + * struct sunxi_timer_quirks - Differences between SoC variants. + * + * @from_ctl_base_offset: offset applied from ctl register onwards + */ +struct sunxi_timer_quirks { + u32 from_ctl_base_offset; +}; + +struct sun5i_timer { + void __iomem *base; + struct clk *clk; + struct notifier_block clk_rate_cb; + u32 ticks_per_jiffy; + struct clocksource clksrc; + struct clock_event_device clkevt; + const struct sunxi_timer_quirks *quirks; +}; + +#define nb_to_sun5i_timer(x) \ + container_of(x, struct sun5i_timer, clk_rate_cb) +#define clksrc_to_sun5i_timer(x) \ + container_of(x, struct sun5i_timer, clksrc) +#define clkevt_to_sun5i_timer(x) \ + container_of(x, struct sun5i_timer, clkevt) + +/* + * When we disable a timer, we need to wait at least for 2 cycles of + * the timer source clock. We will use for that the clocksource timer + * that is already setup and runs at the same frequency than the other + * timers, and we never will be disabled. + */ +static void sun5i_clkevt_sync(struct sun5i_timer *ce) +{ + u32 offset = ce->quirks->from_ctl_base_offset; + u32 old = readl(ce->base + TIMER_CNTVAL_LO_REG(1, offset)); + + while ((old - readl(ce->base + TIMER_CNTVAL_LO_REG(1, offset))) < + TIMER_SYNC_TICKS) + cpu_relax(); +} + +static void sun5i_clkevt_time_stop(struct sun5i_timer *ce, u8 timer) +{ + u32 offset = ce->quirks->from_ctl_base_offset; + u32 val = readl(ce->base + TIMER_CTL_REG(timer, offset)); + + writel(val & ~TIMER_CTL_ENABLE, + ce->base + TIMER_CTL_REG(timer, offset)); + + sun5i_clkevt_sync(ce); +} + +static void sun5i_clkevt_time_setup(struct sun5i_timer *ce, u8 timer, u32 delay) +{ + u32 offset = ce->quirks->from_ctl_base_offset; + + writel(delay, ce->base + TIMER_INTVAL_LO_REG(timer, offset)); +} + +static void sun5i_clkevt_time_start(struct sun5i_timer *ce, u8 timer, bool periodic) +{ + u32 offset = ce->quirks->from_ctl_base_offset; + u32 val = readl(ce->base + TIMER_CTL_REG(timer, offset)); + + if (periodic) + val &= ~TIMER_CTL_ONESHOT; + else + val |= TIMER_CTL_ONESHOT; + + writel(val | TIMER_CTL_ENABLE | TIMER_CTL_RELOAD, + ce->base + TIMER_CTL_REG(timer, offset)); +} + +static int sun5i_clkevt_shutdown(struct clock_event_device *clkevt) +{ + struct sun5i_timer *ce = clkevt_to_sun5i_timer(clkevt); + + sun5i_clkevt_time_stop(ce, 0); + return 0; +} + +static int sun5i_clkevt_set_oneshot(struct clock_event_device *clkevt) +{ + struct sun5i_timer *ce = clkevt_to_sun5i_timer(clkevt); + + sun5i_clkevt_time_stop(ce, 0); + sun5i_clkevt_time_start(ce, 0, false); + return 0; +} + +static int sun5i_clkevt_set_periodic(struct clock_event_device *clkevt) +{ + struct sun5i_timer *ce = clkevt_to_sun5i_timer(clkevt); + + sun5i_clkevt_time_stop(ce, 0); + sun5i_clkevt_time_setup(ce, 0, ce->ticks_per_jiffy); + sun5i_clkevt_time_start(ce, 0, true); + return 0; +} + +static int sun5i_clkevt_next_event(unsigned long evt, + struct clock_event_device *clkevt) +{ + struct sun5i_timer *ce = clkevt_to_sun5i_timer(clkevt); + + sun5i_clkevt_time_stop(ce, 0); + sun5i_clkevt_time_setup(ce, 0, evt - TIMER_SYNC_TICKS); + sun5i_clkevt_time_start(ce, 0, false); + + return 0; +} + +static irqreturn_t sun5i_timer_interrupt(int irq, void *dev_id) +{ + struct sun5i_timer *ce = dev_id; + + writel(0x1, ce->base + TIMER_IRQ_ST_REG); + ce->clkevt.event_handler(&ce->clkevt); + + return IRQ_HANDLED; +} + +static u64 sun5i_clksrc_read(struct clocksource *clksrc) +{ + struct sun5i_timer *cs = clksrc_to_sun5i_timer(clksrc); + u32 offset = cs->quirks->from_ctl_base_offset; + + return ~readl(cs->base + TIMER_CNTVAL_LO_REG(1, offset)); +} + +static int sun5i_rate_cb(struct notifier_block *nb, + unsigned long event, void *data) +{ + struct clk_notifier_data *ndata = data; + struct sun5i_timer *cs = nb_to_sun5i_timer(nb); + + switch (event) { + case PRE_RATE_CHANGE: + clocksource_unregister(&cs->clksrc); + break; + + case POST_RATE_CHANGE: + clocksource_register_hz(&cs->clksrc, ndata->new_rate); + clockevents_update_freq(&cs->clkevt, ndata->new_rate); + cs->ticks_per_jiffy = DIV_ROUND_UP(ndata->new_rate, HZ); + break; + + default: + break; + } + + return NOTIFY_DONE; +} + +static int sun5i_setup_clocksource(struct platform_device *pdev, + unsigned long rate) +{ + struct sun5i_timer *cs = platform_get_drvdata(pdev); + u32 offset = cs->quirks->from_ctl_base_offset; + void __iomem *base = cs->base; + int ret; + + writel(~0, base + TIMER_INTVAL_LO_REG(1, offset)); + writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD, + base + TIMER_CTL_REG(1, offset)); + + cs->clksrc.name = pdev->dev.of_node->name; + cs->clksrc.rating = 340; + cs->clksrc.read = sun5i_clksrc_read; + cs->clksrc.mask = CLOCKSOURCE_MASK(32); + cs->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS; + cs->clksrc.owner = THIS_MODULE; + + ret = clocksource_register_hz(&cs->clksrc, rate); + if (ret) { + dev_err(&pdev->dev, "Couldn't register clock source.\n"); + return ret; + } + + return 0; +} + +static int sun5i_setup_clockevent(struct platform_device *pdev, + unsigned long rate, int irq) +{ + struct device *dev = &pdev->dev; + struct sun5i_timer *ce = platform_get_drvdata(pdev); + void __iomem *base = ce->base; + int ret; + u32 val; + + ce->clkevt.name = dev->of_node->name; + ce->clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; + ce->clkevt.set_next_event = sun5i_clkevt_next_event; + ce->clkevt.set_state_shutdown = sun5i_clkevt_shutdown; + ce->clkevt.set_state_periodic = sun5i_clkevt_set_periodic; + ce->clkevt.set_state_oneshot = sun5i_clkevt_set_oneshot; + ce->clkevt.tick_resume = sun5i_clkevt_shutdown; + ce->clkevt.rating = 340; + ce->clkevt.irq = irq; + ce->clkevt.cpumask = cpu_possible_mask; + ce->clkevt.owner = THIS_MODULE; + + /* Enable timer0 interrupt */ + val = readl(base + TIMER_IRQ_EN_REG); + writel(val | TIMER_IRQ_EN(0), base + TIMER_IRQ_EN_REG); + + clockevents_config_and_register(&ce->clkevt, rate, + TIMER_SYNC_TICKS, 0xffffffff); + + ret = devm_request_irq(dev, irq, sun5i_timer_interrupt, + IRQF_TIMER | IRQF_IRQPOLL, + "sun5i_timer0", ce); + if (ret) + return ret; + + return 0; +} + +static int sun5i_timer_probe(struct platform_device *pdev) +{ + const struct sunxi_timer_quirks *quirks; + struct device *dev = &pdev->dev; + struct sun5i_timer *st; + struct reset_control *rstc; + void __iomem *timer_base; + struct clk *clk; + unsigned long rate; + int irq, ret; + + st = devm_kzalloc(dev, sizeof(*st), GFP_KERNEL); + if (!st) + return -ENOMEM; + + platform_set_drvdata(pdev, st); + + timer_base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(timer_base)) { + dev_err(dev, "Can't map registers\n"); + return PTR_ERR(timer_base); + } + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + clk = devm_clk_get_enabled(dev, NULL); + if (IS_ERR(clk)) { + dev_err(dev, "Can't get timer clock\n"); + return PTR_ERR(clk); + } + + rate = clk_get_rate(clk); + if (!rate) { + dev_err(dev, "Couldn't get parent clock rate\n"); + return -EINVAL; + } + + quirks = of_device_get_match_data(&pdev->dev); + if (!quirks) { + dev_err(&pdev->dev, "Failed to determine the quirks to use\n"); + return -ENODEV; + } + + st->base = timer_base; + st->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ); + st->clk = clk; + st->clk_rate_cb.notifier_call = sun5i_rate_cb; + st->clk_rate_cb.next = NULL; + st->quirks = quirks; + + ret = devm_clk_notifier_register(dev, clk, &st->clk_rate_cb); + if (ret) { + dev_err(dev, "Unable to register clock notifier.\n"); + return ret; + } + + rstc = devm_reset_control_get_optional_exclusive(dev, NULL); + if (IS_ERR(rstc)) + return dev_err_probe(dev, PTR_ERR(rstc), + "failed to get reset\n"); + if (rstc) + reset_control_deassert(rstc); + + ret = sun5i_setup_clocksource(pdev, rate); + if (ret) + return ret; + + ret = sun5i_setup_clockevent(pdev, rate, irq); + if (ret) + goto err_unreg_clocksource; + + return 0; + +err_unreg_clocksource: + clocksource_unregister(&st->clksrc); + return ret; +} + +static void sun5i_timer_remove(struct platform_device *pdev) +{ + struct sun5i_timer *st = platform_get_drvdata(pdev); + + clocksource_unregister(&st->clksrc); +} + +static const struct sunxi_timer_quirks sun5i_sun7i_hstimer_quirks = { + .from_ctl_base_offset = 0x0, +}; + +static const struct sunxi_timer_quirks sun20i_d1_hstimer_quirks = { + .from_ctl_base_offset = 0x10, +}; + +static const struct of_device_id sun5i_timer_of_match[] = { + { + .compatible = "allwinner,sun5i-a13-hstimer", + .data = &sun5i_sun7i_hstimer_quirks, + }, + { + .compatible = "allwinner,sun7i-a20-hstimer", + .data = &sun5i_sun7i_hstimer_quirks, + }, + { + .compatible = "allwinner,sun20i-d1-hstimer", + .data = &sun20i_d1_hstimer_quirks, + }, + {}, +}; +MODULE_DEVICE_TABLE(of, sun5i_timer_of_match); + +static struct platform_driver sun5i_timer_driver = { + .probe = sun5i_timer_probe, + .remove = sun5i_timer_remove, + .driver = { + .name = "sun5i-timer", + .of_match_table = sun5i_timer_of_match, + .suppress_bind_attrs = true, + }, +}; +module_platform_driver(sun5i_timer_driver); -- cgit v1.3.1