Merge tag 'perf-urgent-for-mingo-5.1-20190329' of...

Merge tag 'perf-urgent-for-mingo-5.1-20190329' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/urgent fixes from Arnaldo:

Core libraries:
  Jiri Olsa:
  - Fix max perf_event_attr.precise_ip detection.

  Kan Liang:
  - Fix parser error for uncore event alias

  Wei Lin:
  - Fixup ordering of kernel maps after obtaining the main kernel map address.

Intel PT:
  Adrian Hunter:
  - Fix TSC slip where A TSC packet can slip past MTC packets so that the
    timestamp appears to go backwards.

  - Fixes for exported-sql-viewer GUI conversion to python3.

ARM coresight:
  Solomon Tan:
  - Fix the build by adding a missing case value for enumeration value introduced
    in newer library, that now is the required one.

tool headers:
  Arnaldo Carvalho de Melo:
  - Syncronize kernel headers with the kernel, getting new io_uring and
    pidfd_send_signal syscalls so that 'perf trace' can handle them.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

arch/arm/Kconfig

@@ -596,6 +596,7 @@ config ARCH_DAVINCI
 	select HAVE_IDE
 	select PM_GENERIC_DOMAINS if PM
 	select PM_GENERIC_DOMAINS_OF if PM && OF
+	select REGMAP_MMIO
 	select RESET_CONTROLLER
 	select SPARSE_IRQ
 	select USE_OF

arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts

@@ -93,7 +93,7 @@ i2s_alt2: i2s_alt2 {
 };
 
 &hdmi {
-	hpd-gpios = <&gpio 46 GPIO_ACTIVE_LOW>;
+	hpd-gpios = <&gpio 46 GPIO_ACTIVE_HIGH>;
 };
 
 &pwm {

arch/arm/boot/dts/imx6dl-yapp4-common.dtsi

@@ -114,9 +114,9 @@ phy_port3: phy@2 {
 			reg = <2>;
 		};
 
-		switch@0 {
+		switch@10 {
 			compatible = "qca,qca8334";
-			reg = <0>;
+			reg = <10>;
 
 			switch_ports: ports {
 				#address-cells = <1>;
@@ -125,7 +125,7 @@ switch_ports: ports {
 				ethphy0: port@0 {
 					reg = <0>;
 					label = "cpu";
-					phy-mode = "rgmii";
+					phy-mode = "rgmii-id";
 					ethernet = <&fec>;
 
 					fixed-link {

arch/arm/boot/dts/imx6qdl-icore-rqs.dtsi

@@ -264,7 +264,7 @@ &usdhc3 {
 	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
 	vmcc-supply = <&reg_sd3_vmmc>;
 	cd-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
-	bus-witdh = <4>;
+	bus-width = <4>;
 	no-1-8-v;
 	status = "okay";
 };
@@ -275,7 +275,7 @@ &usdhc4 {
 	pinctrl-1 = <&pinctrl_usdhc4_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc4_200mhz>;
 	vmcc-supply = <&reg_sd4_vmmc>;
-	bus-witdh = <8>;
+	bus-width = <8>;
 	no-1-8-v;
 	non-removable;
 	status = "okay";

arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi

@@ -91,6 +91,7 @@ &fec {
 	pinctrl-0 = <&pinctrl_enet>;
 	phy-handle = <&ethphy>;
 	phy-mode = "rgmii";
+	phy-reset-duration = <10>; /* in msecs */
 	phy-reset-gpios = <&gpio3 23 GPIO_ACTIVE_LOW>;
 	phy-supply = <&vdd_eth_io_reg>;
 	status = "disabled";

arch/arm/boot/dts/imx6ull-pinfunc-snvs.h

-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2016 Freescale Semiconductor, Inc.
  * Copyright (C) 2017 NXP

arch/arm/boot/dts/ste-nomadik-nhk15.dts

@@ -213,12 +213,13 @@ spi {
 		gpio-sck = <&gpio0 5 GPIO_ACTIVE_HIGH>;
 		gpio-mosi = <&gpio0 4 GPIO_ACTIVE_HIGH>;
 		/*
-		 * It's not actually active high, but the frameworks assume
-		 * the polarity of the passed-in GPIO is "normal" (active
-		 * high) then actively drives the line low to select the
-		 * chip.
+		 * This chipselect is active high. Just setting the flags
+		 * to GPIO_ACTIVE_HIGH is not enough for the SPI DT bindings,
+		 * it will be ignored, only the special "spi-cs-high" flag
+		 * really counts.
 		 */
 		cs-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>;
+		spi-cs-high;
 		num-chipselects = <1>;
 
 		/*

arch/arm/configs/imx_v4_v5_defconfig

@@ -170,6 +170,9 @@ CONFIG_IMX_SDMA=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_IIO=y
 CONFIG_FSL_MX25_ADC=y
+CONFIG_PWM=y
+CONFIG_PWM_IMX1=y
+CONFIG_PWM_IMX27=y
 CONFIG_EXT4_FS=y
 # CONFIG_DNOTIFY is not set
 CONFIG_VFAT_FS=y

arch/arm/configs/imx_v6_v7_defconfig

@@ -398,7 +398,7 @@ CONFIG_MAG3110=y
 CONFIG_MPL3115=y
 CONFIG_PWM=y
 CONFIG_PWM_FSL_FTM=y
-CONFIG_PWM_IMX=y
+CONFIG_PWM_IMX27=y
 CONFIG_NVMEM_IMX_OCOTP=y
 CONFIG_NVMEM_VF610_OCOTP=y
 CONFIG_TEE=y

arch/arm/mach-imx/cpuidle-imx6q.c

@@ -16,30 +16,23 @@
 #include "cpuidle.h"
 #include "hardware.h"
 
-static atomic_t master = ATOMIC_INIT(0);
-static DEFINE_SPINLOCK(master_lock);
+static int num_idle_cpus = 0;
+static DEFINE_SPINLOCK(cpuidle_lock);
 
 static int imx6q_enter_wait(struct cpuidle_device *dev,
 			    struct cpuidle_driver *drv, int index)
 {
-	if (atomic_inc_return(&master) == num_online_cpus()) {
-		/*
-		 * With this lock, we prevent other cpu to exit and enter
-		 * this function again and become the master.
-		 */
-		if (!spin_trylock(&master_lock))
-			goto idle;
+	spin_lock(&cpuidle_lock);
+	if (++num_idle_cpus == num_online_cpus())
 		imx6_set_lpm(WAIT_UNCLOCKED);
-		cpu_do_idle();
-		imx6_set_lpm(WAIT_CLOCKED);
-		spin_unlock(&master_lock);
-		goto done;
-	}
+	spin_unlock(&cpuidle_lock);
 
-idle:
 	cpu_do_idle();
-done:
-	atomic_dec(&master);
+
+	spin_lock(&cpuidle_lock);
+	if (num_idle_cpus-- == num_online_cpus())
+		imx6_set_lpm(WAIT_CLOCKED);
+	spin_unlock(&cpuidle_lock);
 
 	return index;
 }

arch/arm/mach-imx/mach-imx51.c

@@ -59,6 +59,7 @@ static void __init imx51_m4if_setup(void)
 		return;
 
 	m4if_base = of_iomap(np, 0);
+	of_node_put(np);
 	if (!m4if_base) {
 		pr_err("Unable to map M4IF registers\n");
 		return;

arch/arm64/Kconfig.platforms

@@ -27,6 +27,7 @@ config ARCH_BCM2835
 	bool "Broadcom BCM2835 family"
 	select TIMER_OF
 	select GPIOLIB
+	select MFD_CORE
 	select PINCTRL
 	select PINCTRL_BCM2835
 	select ARM_AMBA

arch/arm64/boot/dts/nvidia/tegra186.dtsi

@@ -321,7 +321,6 @@ sdmmc4: sdhci@3460000 {
 		nvidia,default-trim = <0x9>;
 		nvidia,dqs-trim = <63>;
 		mmc-hs400-1_8v;
-		supports-cqe;
 		status = "disabled";
 	};
 

arch/arm64/boot/dts/renesas/r8a774c0.dtsi

@@ -2,7 +2,7 @@
 /*
  * Device Tree Source for the RZ/G2E (R8A774C0) SoC
  *
- * Copyright (C) 2018 Renesas Electronics Corp.
+ * Copyright (C) 2018-2019 Renesas Electronics Corp.
  */
 
 #include <dt-bindings/clock/r8a774c0-cpg-mssr.h>
@@ -1150,9 +1150,8 @@ scif5: serial@e6f30000 {
 				 <&cpg CPG_CORE R8A774C0_CLK_S3D1C>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
-			dmas = <&dmac1 0x5b>, <&dmac1 0x5a>,
-			       <&dmac2 0x5b>, <&dmac2 0x5a>;
-			dma-names = "tx", "rx", "tx", "rx";
+			dmas = <&dmac0 0x5b>, <&dmac0 0x5a>;
+			dma-names = "tx", "rx";
 			power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>;
 			resets = <&cpg 202>;
 			status = "disabled";

arch/arm64/boot/dts/renesas/r8a77990.dtsi

@@ -2,7 +2,7 @@
 /*
  * Device Tree Source for the R-Car E3 (R8A77990) SoC
  *
- * Copyright (C) 2018 Renesas Electronics Corp.
+ * Copyright (C) 2018-2019 Renesas Electronics Corp.
  */
 
 #include <dt-bindings/clock/r8a77990-cpg-mssr.h>
@@ -1067,9 +1067,8 @@ scif5: serial@e6f30000 {
 				 <&cpg CPG_CORE R8A77990_CLK_S3D1C>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
-			dmas = <&dmac1 0x5b>, <&dmac1 0x5a>,
-			       <&dmac2 0x5b>, <&dmac2 0x5a>;
-			dma-names = "tx", "rx", "tx", "rx";
+			dmas = <&dmac0 0x5b>, <&dmac0 0x5a>;
+			dma-names = "tx", "rx";
 			power-domains = <&sysc R8A77990_PD_ALWAYS_ON>;
 			resets = <&cpg 202>;
 			status = "disabled";

arch/s390/include/asm/ap.h

@@ -360,4 +360,15 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
 	return reg1;
 }
 
+/*
+ * Interface to tell the AP bus code that a configuration
+ * change has happened. The bus code should at least do
+ * an ap bus resource rescan.
+ */
+#if IS_ENABLED(CONFIG_ZCRYPT)
+void ap_bus_cfg_chg(void);
+#else
+static inline void ap_bus_cfg_chg(void){};
+#endif
+
 #endif /* _ASM_S390_AP_H_ */

arch/s390/include/asm/elf.h

@@ -252,11 +252,14 @@ do {								\
 
 /*
  * Cache aliasing on the latest machines calls for a mapping granularity
- * of 512KB. For 64-bit processes use a 512KB alignment and a randomization
- * of up to 1GB. For 31-bit processes the virtual address space is limited,
- * use no alignment and limit the randomization to 8MB.
+ * of 512KB for the anonymous mapping base. For 64-bit processes use a
+ * 512KB alignment and a randomization of up to 1GB. For 31-bit processes
+ * the virtual address space is limited, use no alignment and limit the
+ * randomization to 8MB.
+ * For the additional randomization of the program break use 32MB for
+ * 64-bit and 8MB for 31-bit.
  */
-#define BRK_RND_MASK	(is_compat_task() ? 0x7ffUL : 0x3ffffUL)
+#define BRK_RND_MASK	(is_compat_task() ? 0x7ffUL : 0x1fffUL)
 #define MMAP_RND_MASK	(is_compat_task() ? 0x7ffUL : 0x3ff80UL)
 #define MMAP_ALIGN_MASK	(is_compat_task() ? 0 : 0x7fUL)
 #define STACK_RND_MASK	MMAP_RND_MASK

arch/s390/include/asm/lowcore.h

@@ -91,52 +91,53 @@ struct lowcore {
 	__u64	hardirq_timer;			/* 0x02e8 */
 	__u64	softirq_timer;			/* 0x02f0 */
 	__u64	steal_timer;			/* 0x02f8 */
-	__u64	last_update_timer;		/* 0x0300 */
-	__u64	last_update_clock;		/* 0x0308 */
-	__u64	int_clock;			/* 0x0310 */
-	__u64	mcck_clock;			/* 0x0318 */
-	__u64	clock_comparator;		/* 0x0320 */
-	__u64	boot_clock[2];			/* 0x0328 */
+	__u64	avg_steal_timer;		/* 0x0300 */
+	__u64	last_update_timer;		/* 0x0308 */
+	__u64	last_update_clock;		/* 0x0310 */
+	__u64	int_clock;			/* 0x0318*/
+	__u64	mcck_clock;			/* 0x0320 */
+	__u64	clock_comparator;		/* 0x0328 */
+	__u64	boot_clock[2];			/* 0x0330 */
 
 	/* Current process. */
-	__u64	current_task;			/* 0x0338 */
-	__u64	kernel_stack;			/* 0x0340 */
+	__u64	current_task;			/* 0x0340 */
+	__u64	kernel_stack;			/* 0x0348 */
 
 	/* Interrupt, DAT-off and restartstack. */
-	__u64	async_stack;			/* 0x0348 */
-	__u64	nodat_stack;			/* 0x0350 */
-	__u64	restart_stack;			/* 0x0358 */
+	__u64	async_stack;			/* 0x0350 */
+	__u64	nodat_stack;			/* 0x0358 */
+	__u64	restart_stack;			/* 0x0360 */
 
 	/* Restart function and parameter. */
-	__u64	restart_fn;			/* 0x0360 */
-	__u64	restart_data;			/* 0x0368 */
-	__u64	restart_source;			/* 0x0370 */
+	__u64	restart_fn;			/* 0x0368 */
+	__u64	restart_data;			/* 0x0370 */
+	__u64	restart_source;			/* 0x0378 */
 
 	/* Address space pointer. */
-	__u64	kernel_asce;			/* 0x0378 */
-	__u64	user_asce;			/* 0x0380 */
-	__u64	vdso_asce;			/* 0x0388 */
+	__u64	kernel_asce;			/* 0x0380 */
+	__u64	user_asce;			/* 0x0388 */
+	__u64	vdso_asce;			/* 0x0390 */
 
 	/*
 	 * The lpp and current_pid fields form a
 	 * 64-bit value that is set as program
 	 * parameter with the LPP instruction.
 	 */
-	__u32	lpp;				/* 0x0390 */
-	__u32	current_pid;			/* 0x0394 */
+	__u32	lpp;				/* 0x0398 */
+	__u32	current_pid;			/* 0x039c */
 
 	/* SMP info area */
-	__u32	cpu_nr;				/* 0x0398 */
-	__u32	softirq_pending;		/* 0x039c */
-	__u32	preempt_count;			/* 0x03a0 */
-	__u32	spinlock_lockval;		/* 0x03a4 */
-	__u32	spinlock_index;			/* 0x03a8 */
-	__u32	fpu_flags;			/* 0x03ac */
-	__u64	percpu_offset;			/* 0x03b0 */
-	__u64	vdso_per_cpu_data;		/* 0x03b8 */
-	__u64	machine_flags;			/* 0x03c0 */
-	__u64	gmap;				/* 0x03c8 */
-	__u8	pad_0x03d0[0x0400-0x03d0];	/* 0x03d0 */
+	__u32	cpu_nr;				/* 0x03a0 */
+	__u32	softirq_pending;		/* 0x03a4 */
+	__u32	preempt_count;			/* 0x03a8 */
+	__u32	spinlock_lockval;		/* 0x03ac */
+	__u32	spinlock_index;			/* 0x03b0 */
+	__u32	fpu_flags;			/* 0x03b4 */
+	__u64	percpu_offset;			/* 0x03b8 */
+	__u64	vdso_per_cpu_data;		/* 0x03c0 */
+	__u64	machine_flags;			/* 0x03c8 */
+	__u64	gmap;				/* 0x03d0 */
+	__u8	pad_0x03d8[0x0400-0x03d8];	/* 0x03d8 */
 
 	/* br %r1 trampoline */
 	__u16	br_r1_trampoline;		/* 0x0400 */

arch/s390/kernel/perf_cpum_cf_diag.c

@@ -196,23 +196,30 @@ static void cf_diag_perf_event_destroy(struct perf_event *event)
  */
 static int __hw_perf_event_init(struct perf_event *event)
 {
-	struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
 	struct perf_event_attr *attr = &event->attr;
+	struct cpu_cf_events *cpuhw;
 	enum cpumf_ctr_set i;
 	int err = 0;
 
-	debug_sprintf_event(cf_diag_dbg, 5,
-			    "%s event %p cpu %d authorized %#x\n", __func__,
-			    event, event->cpu, cpuhw->info.auth_ctl);
+	debug_sprintf_event(cf_diag_dbg, 5, "%s event %p cpu %d\n", __func__,
+			    event, event->cpu);
 
 	event->hw.config = attr->config;
 	event->hw.config_base = 0;
-	local64_set(&event->count, 0);
 
-	/* Add all authorized counter sets to config_base */
+	/* Add all authorized counter sets to config_base. The
+	 * the hardware init function is either called per-cpu or just once
+	 * for all CPUS (event->cpu == -1).  This depends on the whether
+	 * counting is started for all CPUs or on a per workload base where
+	 * the perf event moves from one CPU to another CPU.
+	 * Checking the authorization on any CPU is fine as the hardware
+	 * applies the same authorization settings to all CPUs.
+	 */
+	cpuhw = &get_cpu_var(cpu_cf_events);
 	for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i)
 		if (cpuhw->info.auth_ctl & cpumf_ctr_ctl[i])
 			event->hw.config_base |= cpumf_ctr_ctl[i];
+	put_cpu_var(cpu_cf_events);
 
 	/* No authorized counter sets, nothing to count/sample */
 	if (!event->hw.config_base) {

arch/s390/kernel/smp.c

@@ -266,7 +266,8 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
 	lc->percpu_offset = __per_cpu_offset[cpu];
 	lc->kernel_asce = S390_lowcore.kernel_asce;
 	lc->machine_flags = S390_lowcore.machine_flags;
-	lc->user_timer = lc->system_timer = lc->steal_timer = 0;
+	lc->user_timer = lc->system_timer =
+		lc->steal_timer = lc->avg_steal_timer = 0;
 	__ctl_store(lc->cregs_save_area, 0, 15);
 	save_access_regs((unsigned int *) lc->access_regs_save_area);
 	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,

arch/s390/kernel/vtime.c

@@ -124,7 +124,7 @@ static void account_system_index_scaled(struct task_struct *p, u64 cputime,
  */
 static int do_account_vtime(struct task_struct *tsk)
 {
-	u64 timer, clock, user, guest, system, hardirq, softirq, steal;
+	u64 timer, clock, user, guest, system, hardirq, softirq;
 
 	timer = S390_lowcore.last_update_timer;
 	clock = S390_lowcore.last_update_clock;
@@ -182,12 +182,6 @@ static int do_account_vtime(struct task_struct *tsk)
 	if (softirq)
 		account_system_index_scaled(tsk, softirq, CPUTIME_SOFTIRQ);
 
-	steal = S390_lowcore.steal_timer;
-	if ((s64) steal > 0) {
-		S390_lowcore.steal_timer = 0;
-		account_steal_time(cputime_to_nsecs(steal));
-	}
-
 	return virt_timer_forward(user + guest + system + hardirq + softirq);
 }
 
@@ -213,8 +207,19 @@ void vtime_task_switch(struct task_struct *prev)
  */
 void vtime_flush(struct task_struct *tsk)
 {
+	u64 steal, avg_steal;
+
 	if (do_account_vtime(tsk))
 		virt_timer_expire();
+
+	steal = S390_lowcore.steal_timer;
+	avg_steal = S390_lowcore.avg_steal_timer / 2;
+	if ((s64) steal > 0) {
+		S390_lowcore.steal_timer = 0;
+		account_steal_time(steal);
+		avg_steal += steal;
+	}
+	S390_lowcore.avg_steal_timer = avg_steal;
 }
 
 /*

drivers/s390/cio/chsc.c

@@ -24,6 +24,7 @@
 #include <asm/crw.h>
 #include <asm/isc.h>
 #include <asm/ebcdic.h>
+#include <asm/ap.h>
 
 #include "css.h"
 #include "cio.h"
@@ -586,6 +587,15 @@ static void chsc_process_sei_scm_avail(struct chsc_sei_nt0_area *sei_area)
 			      " failed (rc=%d).\n", ret);
 }
 
+static void chsc_process_sei_ap_cfg_chg(struct chsc_sei_nt0_area *sei_area)
+{
+	CIO_CRW_EVENT(3, "chsc: ap config changed\n");
+	if (sei_area->rs != 5)
+		return;
+
+	ap_bus_cfg_chg();
+}
+
 static void chsc_process_sei_nt2(struct chsc_sei_nt2_area *sei_area)
 {
 	switch (sei_area->cc) {
@@ -612,6 +622,9 @@ static void chsc_process_sei_nt0(struct chsc_sei_nt0_area *sei_area)
 	case 2: /* i/o resource accessibility */
 		chsc_process_sei_res_acc(sei_area);
 		break;
+	case 3: /* ap config changed */
+		chsc_process_sei_ap_cfg_chg(sei_area);
+		break;
 	case 7: /* channel-path-availability information */
 		chsc_process_sei_chp_avail(sei_area);
 		break;

drivers/s390/cio/vfio_ccw_drv.c

@@ -72,20 +72,24 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work)
 {
 	struct vfio_ccw_private *private;
 	struct irb *irb;
+	bool is_final;
 
 	private = container_of(work, struct vfio_ccw_private, io_work);
 	irb = &private->irb;
 
+	is_final = !(scsw_actl(&irb->scsw) &
+		     (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT));
 	if (scsw_is_solicited(&irb->scsw)) {
 		cp_update_scsw(&private->cp, &irb->scsw);
-		cp_free(&private->cp);
+		if (is_final)
+			cp_free(&private->cp);
 	}
 	memcpy(private->io_region->irb_area, irb, sizeof(*irb));
 
 	if (private->io_trigger)
 		eventfd_signal(private->io_trigger, 1);
 
-	if (private->mdev)
+	if (private->mdev && is_final)
 		private->state = VFIO_CCW_STATE_IDLE;
 }
 

drivers/s390/crypto/ap_bus.c

@@ -810,11 +810,18 @@ static int ap_device_remove(struct device *dev)
 	struct ap_device *ap_dev = to_ap_dev(dev);
 	struct ap_driver *ap_drv = ap_dev->drv;
 
+	/* prepare ap queue device removal */
 	if (is_queue_dev(dev))
-		ap_queue_remove(to_ap_queue(dev));
+		ap_queue_prepare_remove(to_ap_queue(dev));
+
+	/* driver's chance to clean up gracefully */
 	if (ap_drv->remove)
 		ap_drv->remove(ap_dev);
 
+	/* now do the ap queue device remove */
+	if (is_queue_dev(dev))
+		ap_queue_remove(to_ap_queue(dev));
+
 	/* Remove queue/card from list of active queues/cards */
 	spin_lock_bh(&ap_list_lock);
 	if (is_card_dev(dev))
@@ -860,6 +867,16 @@ void ap_bus_force_rescan(void)
 }
 EXPORT_SYMBOL(ap_bus_force_rescan);
 
+/*
+* A config change has happened, force an ap bus rescan.
+*/
+void ap_bus_cfg_chg(void)
+{
+	AP_DBF(DBF_INFO, "%s config change, forcing bus rescan\n", __func__);
+
+	ap_bus_force_rescan();
+}
+
 /*
  * hex2bitmap() - parse hex mask string and set bitmap.
  * Valid strings are "0x012345678" with at least one valid hex number.

drivers/s390/crypto/ap_bus.h

@@ -91,6 +91,7 @@ enum ap_state {
 	AP_STATE_WORKING,
 	AP_STATE_QUEUE_FULL,
 	AP_STATE_SUSPEND_WAIT,
+	AP_STATE_REMOVE,	/* about to be removed from driver */
 	AP_STATE_UNBOUND,	/* momentary not bound to a driver */
 	AP_STATE_BORKED,	/* broken */
 	NR_AP_STATES
@@ -252,6 +253,7 @@ void ap_bus_force_rescan(void);
 
 void ap_queue_init_reply(struct ap_queue *aq, struct ap_message *ap_msg);
 struct ap_queue *ap_queue_create(ap_qid_t qid, int device_type);
+void ap_queue_prepare_remove(struct ap_queue *aq);
 void ap_queue_remove(struct ap_queue *aq);
 void ap_queue_suspend(struct ap_device *ap_dev);
 void ap_queue_resume(struct ap_device *ap_dev);

drivers/s390/crypto/ap_queue.c

@@ -420,6 +420,10 @@ static ap_func_t *ap_jumptable[NR_AP_STATES][NR_AP_EVENTS] = {
 		[AP_EVENT_POLL] = ap_sm_suspend_read,
 		[AP_EVENT_TIMEOUT] = ap_sm_nop,
 	},
+	[AP_STATE_REMOVE] = {
+		[AP_EVENT_POLL] = ap_sm_nop,
+		[AP_EVENT_TIMEOUT] = ap_sm_nop,
+	},
 	[AP_STATE_UNBOUND] = {
 		[AP_EVENT_POLL] = ap_sm_nop,
 		[AP_EVENT_TIMEOUT] = ap_sm_nop,
@@ -740,18 +744,31 @@ void ap_flush_queue(struct ap_queue *aq)
 }
 EXPORT_SYMBOL(ap_flush_queue);
 
-void ap_queue_remove(struct ap_queue *aq)
+void ap_queue_prepare_remove(struct ap_queue *aq)
 {
-	ap_flush_queue(aq);
+	spin_lock_bh(&aq->lock);
+	/* flush queue */
+	__ap_flush_queue(aq);
+	/* set REMOVE state to prevent new messages are queued in */
+	aq->state = AP_STATE_REMOVE;
 	del_timer_sync(&aq->timeout);
+	spin_unlock_bh(&aq->lock);
+}
 
-	/* reset with zero, also clears irq registration */
+void ap_queue_remove(struct ap_queue *aq)
+{
+	/*
+	 * all messages have been flushed and the state is
+	 * AP_STATE_REMOVE. Now reset with zero which also
+	 * clears the irq registration and move the state
+	 * to AP_STATE_UNBOUND to signal that this queue
+	 * is not used by any driver currently.
+	 */
 	spin_lock_bh(&aq->lock);
 	ap_zapq(aq->qid);
 	aq->state = AP_STATE_UNBOUND;
 	spin_unlock_bh(&aq->lock);
 }
-EXPORT_SYMBOL(ap_queue_remove);
 
 void ap_queue_reinit_state(struct ap_queue *aq)
 {
@@ -760,4 +777,3 @@ void ap_queue_reinit_state(struct ap_queue *aq)
 	ap_wait(ap_sm_event(aq, AP_EVENT_POLL));
 	spin_unlock_bh(&aq->lock);
 }
-EXPORT_SYMBOL(ap_queue_reinit_state);

drivers/s390/crypto/zcrypt_api.c

@@ -586,6 +586,7 @@ static inline bool zcrypt_check_queue(struct ap_perms *perms, int queue)
 
 static inline struct zcrypt_queue *zcrypt_pick_queue(struct zcrypt_card *zc,
 						     struct zcrypt_queue *zq,
+						     struct module **pmod,
 						     unsigned int weight)
 {
 	if (!zq || !try_module_get(zq->queue->ap_dev.drv->driver.owner))
@@ -595,15 +596,15 @@ static inline struct zcrypt_queue *zcrypt_pick_queue(struct zcrypt_card *zc,
 	atomic_add(weight, &zc->load);
 	atomic_add(weight, &zq->load);
 	zq->request_count++;
+	*pmod = zq->queue->ap_dev.drv->driver.owner;
 	return zq;
 }
 
 static inline void zcrypt_drop_queue(struct zcrypt_card *zc,
 				     struct zcrypt_queue *zq,
+				     struct module *mod,
 				     unsigned int weight)
 {
-	struct module *mod = zq->queue->ap_dev.drv->driver.owner;
-
 	zq->request_count--;
 	atomic_sub(weight, &zc->load);
 	atomic_sub(weight, &zq->load);
@@ -653,6 +654,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms,
 	unsigned int weight, pref_weight;
 	unsigned int func_code;
 	int qid = 0, rc = -ENODEV;
+	struct module *mod;
 
 	trace_s390_zcrypt_req(mex, TP_ICARSAMODEXPO);
 
@@ -706,7 +708,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms,
 			pref_weight = weight;
 		}
 	}
-	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
@@ -718,7 +720,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms,
 	rc = pref_zq->ops->rsa_modexpo(pref_zq, mex);
 
 	spin_lock(&zcrypt_list_lock);
-	zcrypt_drop_queue(pref_zc, pref_zq, weight);
+	zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 out:
@@ -735,6 +737,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms,
 	unsigned int weight, pref_weight;
 	unsigned int func_code;
 	int qid = 0, rc = -ENODEV;
+	struct module *mod;
 
 	trace_s390_zcrypt_req(crt, TP_ICARSACRT);
 
@@ -788,7 +791,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms,
 			pref_weight = weight;
 		}
 	}
-	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
@@ -800,7 +803,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms,
 	rc = pref_zq->ops->rsa_modexpo_crt(pref_zq, crt);
 
 	spin_lock(&zcrypt_list_lock);
-	zcrypt_drop_queue(pref_zc, pref_zq, weight);
+	zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 out:
@@ -819,6 +822,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms,
 	unsigned int func_code;
 	unsigned short *domain;
 	int qid = 0, rc = -ENODEV;
+	struct module *mod;
 
 	trace_s390_zcrypt_req(xcRB, TB_ZSECSENDCPRB);
 
@@ -865,7 +869,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms,
 			pref_weight = weight;
 		}
 	}
-	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
@@ -881,7 +885,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms,
 	rc = pref_zq->ops->send_cprb(pref_zq, xcRB, &ap_msg);
 
 	spin_lock(&zcrypt_list_lock);
-	zcrypt_drop_queue(pref_zc, pref_zq, weight);
+	zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 out:
@@ -932,6 +936,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms,
 	unsigned int func_code;
 	struct ap_message ap_msg;
 	int qid = 0, rc = -ENODEV;
+	struct module *mod;
 
 	trace_s390_zcrypt_req(xcrb, TP_ZSENDEP11CPRB);
 
@@ -1000,7 +1005,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms,
 			pref_weight = weight;
 		}
 	}
-	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
@@ -1012,7 +1017,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms,
 	rc = pref_zq->ops->send_ep11_cprb(pref_zq, xcrb, &ap_msg);
 
 	spin_lock(&zcrypt_list_lock);
-	zcrypt_drop_queue(pref_zc, pref_zq, weight);
+	zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 out_free:
@@ -1033,6 +1038,7 @@ static long zcrypt_rng(char *buffer)
 	struct ap_message ap_msg;
 	unsigned int domain;
 	int qid = 0, rc = -ENODEV;
+	struct module *mod;
 
 	trace_s390_zcrypt_req(buffer, TP_HWRNGCPRB);
 
@@ -1064,7 +1070,7 @@ static long zcrypt_rng(char *buffer)
 			pref_weight = weight;
 		}
 	}
-	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
@@ -1076,7 +1082,7 @@ static long zcrypt_rng(char *buffer)
 	rc = pref_zq->ops->rng(pref_zq, buffer, &ap_msg);
 
 	spin_lock(&zcrypt_list_lock);
-	zcrypt_drop_queue(pref_zc, pref_zq, weight);
+	zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 out:

drivers/soc/bcm/bcm2835-power.c

@@ -150,7 +150,12 @@ struct bcm2835_power {
 
 static int bcm2835_asb_enable(struct bcm2835_power *power, u32 reg)
 {
-	u64 start = ktime_get_ns();
+	u64 start;
+
+	if (!reg)
+		return 0;
+
+	start = ktime_get_ns();
 
 	/* Enable the module's async AXI bridges. */
 	ASB_WRITE(reg, ASB_READ(reg) & ~ASB_REQ_STOP);
@@ -165,7 +170,12 @@ static int bcm2835_asb_enable(struct bcm2835_power *power, u32 reg)
 
 static int bcm2835_asb_disable(struct bcm2835_power *power, u32 reg)
 {
-	u64 start = ktime_get_ns();
+	u64 start;
+
+	if (!reg)
+		return 0;
+
+	start = ktime_get_ns();
 
 	/* Enable the module's async AXI bridges. */
 	ASB_WRITE(reg, ASB_READ(reg) | ASB_REQ_STOP);
@@ -475,7 +485,7 @@ static int bcm2835_power_pd_power_off(struct generic_pm_domain *domain)
 	}
 }
 
-static void
+static int
 bcm2835_init_power_domain(struct bcm2835_power *power,
 			  int pd_xlate_index, const char *name)
 {
@@ -483,6 +493,17 @@ bcm2835_init_power_domain(struct bcm2835_power *power,
 	struct bcm2835_power_domain *dom = &power->domains[pd_xlate_index];
 
 	dom->clk = devm_clk_get(dev->parent, name);
+	if (IS_ERR(dom->clk)) {
+		int ret = PTR_ERR(dom->clk);
+
+		if (ret == -EPROBE_DEFER)
+			return ret;
+
+		/* Some domains don't have a clk, so make sure that we
+		 * don't deref an error pointer later.
+		 */
+		dom->clk = NULL;
+	}
 
 	dom->base.name = name;
 	dom->base.power_on = bcm2835_power_pd_power_on;
@@ -495,6 +516,8 @@ bcm2835_init_power_domain(struct bcm2835_power *power,
 	pm_genpd_init(&dom->base, NULL, true);
 
 	power->pd_xlate.domains[pd_xlate_index] = &dom->base;
+
+	return 0;
 }
 
 /** bcm2835_reset_reset - Resets a block that has a reset line in the
@@ -592,7 +615,7 @@ static int bcm2835_power_probe(struct platform_device *pdev)
 		{ BCM2835_POWER_DOMAIN_IMAGE_PERI, BCM2835_POWER_DOMAIN_CAM0 },
 		{ BCM2835_POWER_DOMAIN_IMAGE_PERI, BCM2835_POWER_DOMAIN_CAM1 },
 	};
-	int ret, i;
+	int ret = 0, i;
 	u32 id;
 
 	power = devm_kzalloc(dev, sizeof(*power), GFP_KERNEL);
@@ -619,8 +642,11 @@ static int bcm2835_power_probe(struct platform_device *pdev)
 
 	power->pd_xlate.num_domains = ARRAY_SIZE(power_domain_names);
 
-	for (i = 0; i < ARRAY_SIZE(power_domain_names); i++)
-		bcm2835_init_power_domain(power, i, power_domain_names[i]);
+	for (i = 0; i < ARRAY_SIZE(power_domain_names); i++) {
+		ret = bcm2835_init_power_domain(power, i, power_domain_names[i]);
+		if (ret)
+			goto fail;
+	}
 
 	for (i = 0; i < ARRAY_SIZE(domain_deps); i++) {
 		pm_genpd_add_subdomain(&power->domains[domain_deps[i].parent].base,
@@ -634,12 +660,21 @@ static int bcm2835_power_probe(struct platform_device *pdev)
 
 	ret = devm_reset_controller_register(dev, &power->reset);
 	if (ret)
-		return ret;
+		goto fail;
 
 	of_genpd_add_provider_onecell(dev->parent->of_node, &power->pd_xlate);
 
 	dev_info(dev, "Broadcom BCM2835 power domains driver");
 	return 0;
+
+fail:
+	for (i = 0; i < ARRAY_SIZE(power_domain_names); i++) {
+		struct generic_pm_domain *dom = &power->domains[i].base;
+
+		if (dom->name)
+			pm_genpd_remove(dom);
+	}
+	return ret;
 }
 
 static int bcm2835_power_remove(struct platform_device *pdev)

fs/afs/fsclient.c

@@ -1515,8 +1515,8 @@ static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr)
 
 	xdr_encode_AFS_StoreStatus(&bp, attr);
 
-	*bp++ = 0;				/* position of start of write */
-	*bp++ = 0;
+	*bp++ = htonl(attr->ia_size >> 32);	/* position of start of write */
+	*bp++ = htonl((u32) attr->ia_size);
 	*bp++ = 0;				/* size of write */
 	*bp++ = 0;
 	*bp++ = htonl(attr->ia_size >> 32);	/* new file length */
@@ -1564,7 +1564,7 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr)
 
 	xdr_encode_AFS_StoreStatus(&bp, attr);
 
-	*bp++ = 0;				/* position of start of write */
+	*bp++ = htonl(attr->ia_size);		/* position of start of write */
 	*bp++ = 0;				/* size of write */
 	*bp++ = htonl(attr->ia_size);		/* new file length */
 

fs/afs/yfsclient.c

@@ -1514,7 +1514,7 @@ static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr)
 	bp = xdr_encode_u32(bp, 0); /* RPC flags */
 	bp = xdr_encode_YFSFid(bp, &vnode->fid);
 	bp = xdr_encode_YFS_StoreStatus(bp, attr);
-	bp = xdr_encode_u64(bp, 0);		/* position of start of write */
+	bp = xdr_encode_u64(bp, attr->ia_size);	/* position of start of write */
 	bp = xdr_encode_u64(bp, 0);		/* size of write */
 	bp = xdr_encode_u64(bp, attr->ia_size);	/* new file length */
 	yfs_check_req(call, bp);

tools/arch/alpha/include/uapi/asm/mman.h

@@ -27,8 +27,6 @@
 #define MAP_NONBLOCK	0x40000
 #define MAP_NORESERVE	0x10000
 #define MAP_POPULATE	0x20000
-#define MAP_PRIVATE	0x02
-#define MAP_SHARED	0x01
 #define MAP_STACK	0x80000
 #define PROT_EXEC	0x4
 #define PROT_GROWSDOWN	0x01000000

tools/arch/mips/include/uapi/asm/mman.h

@@ -28,8 +28,6 @@
 #define MAP_NONBLOCK	0x20000
 #define MAP_NORESERVE	0x0400
 #define MAP_POPULATE	0x10000
-#define MAP_PRIVATE	0x002
-#define MAP_SHARED	0x001
 #define MAP_STACK	0x40000
 #define PROT_EXEC	0x04
 #define PROT_GROWSDOWN	0x01000000

tools/arch/parisc/include/uapi/asm/mman.h

@@ -27,8 +27,6 @@
 #define MAP_NONBLOCK	0x20000
 #define MAP_NORESERVE	0x4000
 #define MAP_POPULATE	0x10000
-#define MAP_PRIVATE	0x02
-#define MAP_SHARED	0x01
 #define MAP_STACK	0x40000
 #define PROT_EXEC	0x4
 #define PROT_GROWSDOWN	0x01000000

tools/arch/powerpc/include/uapi/asm/kvm.h

@@ -463,10 +463,12 @@ struct kvm_ppc_cpu_char {
 #define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED	(1ULL << 58)
 #define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF	(1ULL << 57)
 #define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS	(1ULL << 56)
+#define KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST	(1ull << 54)
 
 #define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY	(1ULL << 63)
 #define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR		(1ULL << 62)
 #define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ULL << 61)
+#define KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE	(1ull << 58)
 
 /* Per-vcpu XICS interrupt controller state */
 #define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)

tools/arch/x86/include/asm/cpufeatures.h

@@ -344,6 +344,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */

tools/arch/xtensa/include/uapi/asm/mman.h

@@ -27,8 +27,6 @@
 #define MAP_NONBLOCK	0x20000
 #define MAP_NORESERVE	0x0400
 #define MAP_POPULATE	0x10000
-#define MAP_PRIVATE	0x002
-#define MAP_SHARED	0x001
 #define MAP_STACK	0x40000
 #define PROT_EXEC	0x4
 #define PROT_GROWSDOWN	0x01000000

tools/build/feature/test-libopencsd.c

@@ -4,9 +4,9 @@
 /*
  * Check OpenCSD library version is sufficient to provide required features
  */
-#define OCSD_MIN_VER ((0 << 16) | (10 << 8) | (0))
+#define OCSD_MIN_VER ((0 << 16) | (11 << 8) | (0))
 #if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER)
-#error "OpenCSD >= 0.10.0 is required"
+#error "OpenCSD >= 0.11.0 is required"
 #endif
 
 int main(void)

tools/include/uapi/asm-generic/mman-common-tools.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+#define __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+
+#include <asm-generic/mman-common.h>
+
+/* We need this because we need to have tools/include/uapi/ included in the tools
+ * header search path to get access to stuff that is not yet in the system's
+ * copy of the files in that directory, but since this cset:
+ *
+ *     746c9398f5ac ("arch: move common mmap flags to linux/mman.h")
+ *
+ * We end up making sys/mman.h, that is in the system headers, to not find the
+ * MAP_SHARED and MAP_PRIVATE defines because they are not anymore in our copy
+ * of asm-generic/mman-common.h. So we define them here and include this header
+ * from each of the per arch mman.h headers.
+ */
+#ifndef MAP_SHARED
+#define MAP_SHARED	0x01		/* Share changes */
+#define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+#endif
+#endif // __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H

tools/include/uapi/asm-generic/mman-common.h

@@ -15,9 +15,7 @@
 #define PROT_GROWSDOWN	0x01000000	/* mprotect flag: extend change to start of growsdown vma */
 #define PROT_GROWSUP	0x02000000	/* mprotect flag: extend change to end of growsup vma */
 
-#define MAP_SHARED	0x01		/* Share changes */
-#define MAP_PRIVATE	0x02		/* Changes are private */
-#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+/* 0x01 - 0x03 are defined in linux/mman.h */
 #define MAP_TYPE	0x0f		/* Mask for type of mapping */
 #define MAP_FIXED	0x10		/* Interpret addr exactly */
 #define MAP_ANONYMOUS	0x20		/* don't use a file */

tools/include/uapi/asm-generic/mman.h

@@ -2,7 +2,7 @@
 #ifndef __ASM_GENERIC_MMAN_H
 #define __ASM_GENERIC_MMAN_H
 
-#include <asm-generic/mman-common.h>
+#include <asm-generic/mman-common-tools.h>
 
 #define MAP_GROWSDOWN	0x0100		/* stack-like segment */
 #define MAP_DENYWRITE	0x0800		/* ETXTBSY */

tools/include/uapi/asm-generic/unistd.h

@@ -824,8 +824,17 @@ __SYSCALL(__NR_futex_time64, sys_futex)
 __SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
 #endif
 
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
+
 #undef __NR_syscalls
-#define __NR_syscalls 424
+#define __NR_syscalls 428
 
 /*
  * 32 bit systems traditionally used different

tools/include/uapi/drm/i915_drm.h

@@ -1486,9 +1486,73 @@ struct drm_i915_gem_context_param {
 #define   I915_CONTEXT_MAX_USER_PRIORITY	1023 /* inclusive */
 #define   I915_CONTEXT_DEFAULT_PRIORITY		0
 #define   I915_CONTEXT_MIN_USER_PRIORITY	-1023 /* inclusive */
+	/*
+	 * When using the following param, value should be a pointer to
+	 * drm_i915_gem_context_param_sseu.
+	 */
+#define I915_CONTEXT_PARAM_SSEU		0x7
 	__u64 value;
 };
 
+/**
+ * Context SSEU programming
+ *
+ * It may be necessary for either functional or performance reason to configure
+ * a context to run with a reduced number of SSEU (where SSEU stands for Slice/
+ * Sub-slice/EU).
+ *
+ * This is done by configuring SSEU configuration using the below
+ * @struct drm_i915_gem_context_param_sseu for every supported engine which
+ * userspace intends to use.
+ *
+ * Not all GPUs or engines support this functionality in which case an error
+ * code -ENODEV will be returned.
+ *
+ * Also, flexibility of possible SSEU configuration permutations varies between
+ * GPU generations and software imposed limitations. Requesting such a
+ * combination will return an error code of -EINVAL.
+ *
+ * NOTE: When perf/OA is active the context's SSEU configuration is ignored in
+ * favour of a single global setting.
+ */
+struct drm_i915_gem_context_param_sseu {
+	/*
+	 * Engine class & instance to be configured or queried.
+	 */
+	__u16 engine_class;
+	__u16 engine_instance;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * Mask of slices to enable for the context. Valid values are a subset
+	 * of the bitmask value returned for I915_PARAM_SLICE_MASK.
+	 */
+	__u64 slice_mask;
+
+	/*
+	 * Mask of subslices to enable for the context. Valid values are a
+	 * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
+	 */
+	__u64 subslice_mask;
+
+	/*
+	 * Minimum/Maximum number of EUs to enable per subslice for the
+	 * context. min_eus_per_subslice must be inferior or equal to
+	 * max_eus_per_subslice.
+	 */
+	__u16 min_eus_per_subslice;
+	__u16 max_eus_per_subslice;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 rsvd;
+};
+
 enum drm_i915_oa_format {
 	I915_OA_FORMAT_A13 = 1,	    /* HSW only */
 	I915_OA_FORMAT_A29,	    /* HSW only */

tools/include/uapi/linux/fcntl.h

@@ -41,6 +41,7 @@
 #define F_SEAL_SHRINK	0x0002	/* prevent file from shrinking */
 #define F_SEAL_GROW	0x0004	/* prevent file from growing */
 #define F_SEAL_WRITE	0x0008	/* prevent writes */
+#define F_SEAL_FUTURE_WRITE	0x0010  /* prevent future writes while mapped */
 /* (1U << 31) is reserved for signed error codes */
 
 /*

tools/include/uapi/linux/mman.h

@@ -12,6 +12,10 @@
 #define OVERCOMMIT_ALWAYS		1
 #define OVERCOMMIT_NEVER		2
 
+#define MAP_SHARED	0x01		/* Share changes */
+#define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+
 /*
  * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
  * size other than the default is desired.  See hugetlb_encode.h.

tools/perf/Makefile.perf

@@ -481,8 +481,8 @@ $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_t
 mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c
 mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh
 
-$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
-	$(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
+$(mmap_flags_array): $(linux_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
+	$(Q)$(SHELL) '$(mmap_flags_tbl)' $(linux_uapi_dir) $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
 
 mount_flags_array := $(beauty_outdir)/mount_flags_array.c
 mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh

tools/perf/arch/x86/entry/syscalls/syscall_64.tbl

@@ -345,6 +345,10 @@
 334	common	rseq			__x64_sys_rseq
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
+424	common	pidfd_send_signal	__x64_sys_pidfd_send_signal
+425	common	io_uring_setup		__x64_sys_io_uring_setup
+426	common	io_uring_enter		__x64_sys_io_uring_enter
+427	common	io_uring_register	__x64_sys_io_uring_register
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

tools/perf/check-headers.sh

@@ -103,7 +103,7 @@ done
 # diff with extra ignore lines
 check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
 check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
-check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"'
+check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
 check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
 
 # diff non-symmetric files

tools/perf/scripts/python/exported-sql-viewer.py

@@ -107,6 +107,7 @@ import os
 from PySide.QtCore import *
 from PySide.QtGui import *
 from PySide.QtSql import *
+pyside_version_1 = True
 from decimal import *
 from ctypes import *
 from multiprocessing import Process, Array, Value, Event
@@ -1526,6 +1527,19 @@ def BranchDataPrep(query):
 			" (" + dsoname(query.value(15)) + ")")
 	return data
 
+def BranchDataPrepWA(query):
+	data = []
+	data.append(query.value(0))
+	# Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+	data.append("{:>19}".format(query.value(1)))
+	for i in xrange(2, 8):
+		data.append(query.value(i))
+	data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
+			" (" + dsoname(query.value(11)) + ")" + " -> " +
+			tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
+			" (" + dsoname(query.value(15)) + ")")
+	return data
+
 # Branch data model
 
 class BranchModel(TreeModel):
@@ -1553,7 +1567,11 @@ class BranchModel(TreeModel):
 			" AND evsel_id = " + str(self.event_id) +
 			" ORDER BY samples.id"
 			" LIMIT " + str(glb_chunk_sz))
-		self.fetcher = SQLFetcher(glb, sql, BranchDataPrep, self.AddSample)
+		if pyside_version_1 and sys.version_info[0] == 3:
+			prep = BranchDataPrepWA
+		else:
+			prep = BranchDataPrep
+		self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample)
 		self.fetcher.done.connect(self.Update)
 		self.fetcher.Fetch(glb_chunk_sz)
 
@@ -2079,14 +2097,6 @@ def IsSelectable(db, table, sql = ""):
 		return False
 	return True
 
-# SQL data preparation
-
-def SQLTableDataPrep(query, count):
-	data = []
-	for i in xrange(count):
-		data.append(query.value(i))
-	return data
-
 # SQL table data model item
 
 class SQLTableItem():
@@ -2110,7 +2120,7 @@ class SQLTableModel(TableModel):
 		self.more = True
 		self.populated = 0
 		self.column_headers = column_headers
-		self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): SQLTableDataPrep(x, y), self.AddSample)
+		self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): self.SQLTableDataPrep(x, y), self.AddSample)
 		self.fetcher.done.connect(self.Update)
 		self.fetcher.Fetch(glb_chunk_sz)
 
@@ -2154,6 +2164,12 @@ class SQLTableModel(TableModel):
 	def columnHeader(self, column):
 		return self.column_headers[column]
 
+	def SQLTableDataPrep(self, query, count):
+		data = []
+		for i in xrange(count):
+			data.append(query.value(i))
+		return data
+
 # SQL automatic table data model
 
 class SQLAutoTableModel(SQLTableModel):
@@ -2182,8 +2198,32 @@ class SQLAutoTableModel(SQLTableModel):
 			QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'")
 			while query.next():
 				column_headers.append(query.value(0))
+		if pyside_version_1 and sys.version_info[0] == 3:
+			if table_name == "samples_view":
+				self.SQLTableDataPrep = self.samples_view_DataPrep
+			if table_name == "samples":
+				self.SQLTableDataPrep = self.samples_DataPrep
 		super(SQLAutoTableModel, self).__init__(glb, sql, column_headers, parent)
 
+	def samples_view_DataPrep(self, query, count):
+		data = []
+		data.append(query.value(0))
+		# Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+		data.append("{:>19}".format(query.value(1)))
+		for i in xrange(2, count):
+			data.append(query.value(i))
+		return data
+
+	def samples_DataPrep(self, query, count):
+		data = []
+		for i in xrange(9):
+			data.append(query.value(i))
+		# Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+		data.append("{:>19}".format(query.value(9)))
+		for i in xrange(10, count):
+			data.append(query.value(i))
+		return data
+
 # Base class for custom ResizeColumnsToContents
 
 class ResizeColumnsToContentsBase(QObject):
@@ -2868,9 +2908,13 @@ class LibXED():
 		ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0)
 		if not ok:
 			return 0, ""
+		if sys.version_info[0] == 2:
+			result = inst.buffer.value
+		else:
+			result = inst.buffer.value.decode()
 		# Return instruction length and the disassembled instruction text
 		# For now, assume the length is in byte 166
-		return inst.xedd[166], inst.buffer.value
+		return inst.xedd[166], result
 
 def TryOpen(file_name):
 	try:
@@ -2886,9 +2930,14 @@ def Is64Bit(f):
 	header = f.read(7)
 	f.seek(pos)
 	magic = header[0:4]
-	eclass = ord(header[4])
-	encoding = ord(header[5])
-	version = ord(header[6])
+	if sys.version_info[0] == 2:
+		eclass = ord(header[4])
+		encoding = ord(header[5])
+		version = ord(header[6])
+	else:
+		eclass = header[4]
+		encoding = header[5]
+		version = header[6]
 	if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1:
 		result = True if eclass == 2 else False
 	return result

tools/perf/trace/beauty/mmap_flags.sh

 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-if [ $# -ne 2 ] ; then
+if [ $# -ne 3 ] ; then
 	[ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/`
+	linux_header_dir=tools/include/uapi/linux
 	header_dir=tools/include/uapi/asm-generic
 	arch_header_dir=tools/arch/${hostarch}/include/uapi/asm
 else
-	header_dir=$1
-	arch_header_dir=$2
+	linux_header_dir=$1
+	header_dir=$2
+	arch_header_dir=$3
 fi
 
+linux_mman=${linux_header_dir}/mman.h
 arch_mman=${arch_header_dir}/mman.h
 
 # those in egrep -vw are flags, we want just the bits
@@ -20,6 +23,11 @@ egrep -q $regex ${arch_mman} && \
 (egrep $regex ${arch_mman} | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+egrep -q $regex ${linux_mman} && \
+(egrep $regex ${linux_mman} | \
+	egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
 ([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) &&
 (egrep $regex ${header_dir}/mman-common.h | \
 	egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \

tools/perf/util/cs-etm-decoder/cs-etm-decoder.c

@@ -387,6 +387,7 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
 		break;
 	case OCSD_INSTR_ISB:
 	case OCSD_INSTR_DSB_DMB:
+	case OCSD_INSTR_WFI_WFE:
 	case OCSD_INSTR_OTHER:
 	default:
 		packet->last_instr_taken_branch = false;

tools/perf/util/evlist.c

@@ -231,35 +231,6 @@ void perf_evlist__set_leader(struct perf_evlist *evlist)
 	}
 }
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *pattr)
-{
-	struct perf_event_attr attr = {
-		.type		= PERF_TYPE_HARDWARE,
-		.config		= PERF_COUNT_HW_CPU_CYCLES,
-		.exclude_kernel	= 1,
-		.precise_ip	= 3,
-	};
-
-	event_attr_init(&attr);
-
-	/*
-	 * Unnamed union member, not supported as struct member named
-	 * initializer in older compilers such as gcc 4.4.7
-	 */
-	attr.sample_period = 1;
-
-	while (attr.precise_ip != 0) {
-		int fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
-		if (fd != -1) {
-			close(fd);
-			break;
-		}
-		--attr.precise_ip;
-	}
-
-	pattr->precise_ip = attr.precise_ip;
-}
-
 int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise)
 {
 	struct perf_evsel *evsel = perf_evsel__new_cycles(precise);

tools/perf/util/evlist.h

@@ -315,8 +315,6 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
-
 struct perf_evsel *
 perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 

tools/perf/util/evsel.c

@@ -295,7 +295,6 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise)
 	if (!precise)
 		goto new_event;
 
-	perf_event_attr__set_max_precise_ip(&attr);
 	/*
 	 * Now let the usual logic to set up the perf_event_attr defaults
 	 * to kick in when we return and before perf_evsel__open() is called.
@@ -305,6 +304,8 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise)
 	if (evsel == NULL)
 		goto out;
 
+	evsel->precise_max = true;
+
 	/* use asprintf() because free(evsel) assumes name is allocated */
 	if (asprintf(&evsel->name, "cycles%s%s%.*s",
 		     (attr.precise_ip || attr.exclude_kernel) ? ":" : "",
@@ -1083,7 +1084,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	}
 
 	if (evsel->precise_max)
-		perf_event_attr__set_max_precise_ip(attr);
+		attr->precise_ip = 3;
 
 	if (opts->all_user) {
 		attr->exclude_kernel = 1;
@@ -1749,6 +1750,59 @@ static bool ignore_missing_thread(struct perf_evsel *evsel,
 	return true;
 }
 
+static void display_attr(struct perf_event_attr *attr)
+{
+	if (verbose >= 2) {
+		fprintf(stderr, "%.60s\n", graph_dotted_line);
+		fprintf(stderr, "perf_event_attr:\n");
+		perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL);
+		fprintf(stderr, "%.60s\n", graph_dotted_line);
+	}
+}
+
+static int perf_event_open(struct perf_evsel *evsel,
+			   pid_t pid, int cpu, int group_fd,
+			   unsigned long flags)
+{
+	int precise_ip = evsel->attr.precise_ip;
+	int fd;
+
+	while (1) {
+		pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
+			  pid, cpu, group_fd, flags);
+
+		fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags);
+		if (fd >= 0)
+			break;
+
+		/*
+		 * Do quick precise_ip fallback if:
+		 *  - there is precise_ip set in perf_event_attr
+		 *  - maximum precise is requested
+		 *  - sys_perf_event_open failed with ENOTSUP error,
+		 *    which is associated with wrong precise_ip
+		 */
+		if (!precise_ip || !evsel->precise_max || (errno != ENOTSUP))
+			break;
+
+		/*
+		 * We tried all the precise_ip values, and it's
+		 * still failing, so leave it to standard fallback.
+		 */
+		if (!evsel->attr.precise_ip) {
+			evsel->attr.precise_ip = precise_ip;
+			break;
+		}
+
+		pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP);
+		evsel->attr.precise_ip--;
+		pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip);
+		display_attr(&evsel->attr);
+	}
+
+	return fd;
+}
+
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 		     struct thread_map *threads)
 {
@@ -1824,12 +1878,7 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
 
-	if (verbose >= 2) {
-		fprintf(stderr, "%.60s\n", graph_dotted_line);
-		fprintf(stderr, "perf_event_attr:\n");
-		perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL);
-		fprintf(stderr, "%.60s\n", graph_dotted_line);
-	}
+	display_attr(&evsel->attr);
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
@@ -1841,13 +1890,10 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
-			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
-				  pid, cpus->map[cpu], group_fd, flags);
-
 			test_attr__ready();
 
-			fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
-						 group_fd, flags);
+			fd = perf_event_open(evsel, pid, cpus->map[cpu],
+					     group_fd, flags);
 
 			FD(evsel, cpu, thread) = fd;
 

tools/perf/util/intel-pt-decoder/intel-pt-decoder.c

@@ -251,19 +251,15 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 		if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d))
 			decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n /
 						decoder->tsc_ctc_ratio_d;
-
-		/*
-		 * Allow for timestamps appearing to backwards because a TSC
-		 * packet has slipped past a MTC packet, so allow 2 MTC ticks
-		 * or ...
-		 */
-		decoder->tsc_slip = multdiv(2 << decoder->mtc_shift,
-					decoder->tsc_ctc_ratio_n,
-					decoder->tsc_ctc_ratio_d);
 	}
-	/* ... or 0x100 paranoia */
-	if (decoder->tsc_slip < 0x100)
-		decoder->tsc_slip = 0x100;
+
+	/*
+	 * A TSC packet can slip past MTC packets so that the timestamp appears
+	 * to go backwards. One estimate is that can be up to about 40 CPU
+	 * cycles, which is certainly less than 0x1000 TSC ticks, but accept
+	 * slippage an order of magnitude more to be on the safe side.
+	 */
+	decoder->tsc_slip = 0x10000;
 
 	intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift);
 	intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n);

tools/perf/util/machine.c

@@ -1421,6 +1421,20 @@ static void machine__set_kernel_mmap(struct machine *machine,
 		machine->vmlinux_map->end = ~0ULL;
 }
 
+static void machine__update_kernel_mmap(struct machine *machine,
+				     u64 start, u64 end)
+{
+	struct map *map = machine__kernel_map(machine);
+
+	map__get(map);
+	map_groups__remove(&machine->kmaps, map);
+
+	machine__set_kernel_mmap(machine, start, end);
+
+	map_groups__insert(&machine->kmaps, map);
+	map__put(map);
+}
+
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
@@ -1453,17 +1467,11 @@ int machine__create_kernel_maps(struct machine *machine)
 			goto out_put;
 		}
 
-		/* we have a real start address now, so re-order the kmaps */
-		map = machine__kernel_map(machine);
-
-		map__get(map);
-		map_groups__remove(&machine->kmaps, map);
-
-		/* assume it's the last in the kmaps */
-		machine__set_kernel_mmap(machine, addr, ~0ULL);
-
-		map_groups__insert(&machine->kmaps, map);
-		map__put(map);
+		/*
+		 * we have a real start address now, so re-order the kmaps
+		 * assume it's the last in the kmaps
+		 */
+		machine__update_kernel_mmap(machine, addr, ~0ULL);
 	}
 
 	if (machine__create_extra_kernel_maps(machine, kernel))
@@ -1599,7 +1607,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (strstr(kernel->long_name, "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
-		machine__set_kernel_mmap(machine, event->mmap.start,
+		machine__update_kernel_mmap(machine, event->mmap.start,
 					 event->mmap.start + event->mmap.len);
 
 		/*

tools/perf/util/pmu.c

@@ -732,10 +732,20 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 
 		if (!is_arm_pmu_core(name)) {
 			pname = pe->pmu ? pe->pmu : "cpu";
+
+			/*
+			 * uncore alias may be from different PMU
+			 * with common prefix
+			 */
+			if (pmu_is_uncore(name) &&
+			    !strncmp(pname, name, strlen(pname)))
+				goto new_alias;
+
 			if (strcmp(pname, name))
 				continue;
 		}
 
+new_alias:
 		/* need type casts to override 'const' */
 		__perf_pmu__new_alias(head, NULL, (char *)pe->name,
 				(char *)pe->desc, (char *)pe->event,