From 37f49e37ab4cb5d0bc4c60eb5c6d4dd57db767bb Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 07:44:59 +0000
Subject: [PATCH] gmac get mac form eeprom

---
 kernel/arch/x86/kernel/hpet.c | 1041 ++++++++++++++++++++++++++++-----------------------------
 1 files changed, 518 insertions(+), 523 deletions(-)

diff --git a/kernel/arch/x86/kernel/hpet.c b/kernel/arch/x86/kernel/hpet.c
index 1e3f1f1..574df24 100644
--- a/kernel/arch/x86/kernel/hpet.c
+++ b/kernel/arch/x86/kernel/hpet.c
@@ -1,35 +1,45 @@
-#include <linux/clocksource.h>
+// SPDX-License-Identifier: GPL-2.0-only
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
-#include <linux/irq.h>
 #include <linux/export.h>
 #include <linux/delay.h>
-#include <linux/errno.h>
-#include <linux/i8253.h>
-#include <linux/slab.h>
 #include <linux/hpet.h>
-#include <linux/init.h>
 #include <linux/cpu.h>
-#include <linux/pm.h>
-#include <linux/io.h>
+#include <linux/irq.h>
 
-#include <asm/cpufeature.h>
-#include <asm/irqdomain.h>
-#include <asm/fixmap.h>
 #include <asm/hpet.h>
 #include <asm/time.h>
+#include <asm/mwait.h>
+
+#undef  pr_fmt
+#define pr_fmt(fmt) "hpet: " fmt
+
+enum hpet_mode {
+	HPET_MODE_UNUSED,
+	HPET_MODE_LEGACY,
+	HPET_MODE_CLOCKEVT,
+	HPET_MODE_DEVICE,
+};
+
+struct hpet_channel {
+	struct clock_event_device	evt;
+	unsigned int			num;
+	unsigned int			cpu;
+	unsigned int			irq;
+	unsigned int			in_use;
+	enum hpet_mode			mode;
+	unsigned int			boot_cfg;
+	char				name[10];
+};
+
+struct hpet_base {
+	unsigned int			nr_channels;
+	unsigned int			nr_clockevents;
+	unsigned int			boot_cfg;
+	struct hpet_channel		*channels;
+};
 
 #define HPET_MASK			CLOCKSOURCE_MASK(32)
-
-/* FSEC = 10^-15
-   NSEC = 10^-9 */
-#define FSEC_PER_NSEC			1000000L
-
-#define HPET_DEV_USED_BIT		2
-#define HPET_DEV_USED			(1 << HPET_DEV_USED_BIT)
-#define HPET_DEV_VALID			0x8
-#define HPET_DEV_FSB_CAP		0x1000
-#define HPET_DEV_PERI_CAP		0x2000
 
 #define HPET_MIN_CYCLES			128
 #define HPET_MIN_PROG_DELTA		(HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1))
@@ -42,22 +52,25 @@
 bool					hpet_msi_disable;
 
 #ifdef CONFIG_PCI_MSI
-static unsigned int			hpet_num_timers;
+static DEFINE_PER_CPU(struct hpet_channel *, cpu_hpet_channel);
+static struct irq_domain		*hpet_domain;
 #endif
+
 static void __iomem			*hpet_virt_address;
 
-struct hpet_dev {
-	struct clock_event_device	evt;
-	unsigned int			num;
-	int				cpu;
-	unsigned int			irq;
-	unsigned int			flags;
-	char				name[10];
-};
+static struct hpet_base			hpet_base;
 
-static inline struct hpet_dev *EVT_TO_HPET_DEV(struct clock_event_device *evtdev)
+static bool				hpet_legacy_int_enabled;
+static unsigned long			hpet_freq;
+
+bool					boot_hpet_disable;
+bool					hpet_force_user;
+static bool				hpet_verbose;
+
+static inline
+struct hpet_channel *clockevent_to_channel(struct clock_event_device *evt)
 {
-	return container_of(evtdev, struct hpet_dev, evt);
+	return container_of(evt, struct hpet_channel, evt);
 }
 
 inline unsigned int hpet_readl(unsigned int a)
@@ -70,13 +83,9 @@
 	writel(d, hpet_virt_address + a);
 }
 
-#ifdef CONFIG_X86_64
-#include <asm/pgtable.h>
-#endif
-
 static inline void hpet_set_mapping(void)
 {
-	hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
+	hpet_virt_address = ioremap(hpet_address, HPET_MMAP_SIZE);
 }
 
 static inline void hpet_clear_mapping(void)
@@ -88,10 +97,6 @@
 /*
  * HPET command line enable / disable
  */
-bool boot_hpet_disable;
-bool hpet_force_user;
-static bool hpet_verbose;
-
 static int __init hpet_setup(char *str)
 {
 	while (str) {
@@ -123,13 +128,8 @@
 	return !boot_hpet_disable && hpet_address;
 }
 
-/*
- * HPET timer interrupt enable / disable
- */
-static bool hpet_legacy_int_enabled;
-
 /**
- * is_hpet_enabled - check whether the hpet timer interrupt is enabled
+ * is_hpet_enabled - Check whether the legacy HPET timer interrupt is enabled
  */
 int is_hpet_enabled(void)
 {
@@ -139,32 +139,36 @@
 
 static void _hpet_print_config(const char *function, int line)
 {
-	u32 i, timers, l, h;
-	printk(KERN_INFO "hpet: %s(%d):\n", function, line);
-	l = hpet_readl(HPET_ID);
-	h = hpet_readl(HPET_PERIOD);
-	timers = ((l & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT) + 1;
-	printk(KERN_INFO "hpet: ID: 0x%x, PERIOD: 0x%x\n", l, h);
-	l = hpet_readl(HPET_CFG);
-	h = hpet_readl(HPET_STATUS);
-	printk(KERN_INFO "hpet: CFG: 0x%x, STATUS: 0x%x\n", l, h);
+	u32 i, id, period, cfg, status, channels, l, h;
+
+	pr_info("%s(%d):\n", function, line);
+
+	id = hpet_readl(HPET_ID);
+	period = hpet_readl(HPET_PERIOD);
+	pr_info("ID: 0x%x, PERIOD: 0x%x\n", id, period);
+
+	cfg = hpet_readl(HPET_CFG);
+	status = hpet_readl(HPET_STATUS);
+	pr_info("CFG: 0x%x, STATUS: 0x%x\n", cfg, status);
+
 	l = hpet_readl(HPET_COUNTER);
 	h = hpet_readl(HPET_COUNTER+4);
-	printk(KERN_INFO "hpet: COUNTER_l: 0x%x, COUNTER_h: 0x%x\n", l, h);
+	pr_info("COUNTER_l: 0x%x, COUNTER_h: 0x%x\n", l, h);
 
-	for (i = 0; i < timers; i++) {
+	channels = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT) + 1;
+
+	for (i = 0; i < channels; i++) {
 		l = hpet_readl(HPET_Tn_CFG(i));
 		h = hpet_readl(HPET_Tn_CFG(i)+4);
-		printk(KERN_INFO "hpet: T%d: CFG_l: 0x%x, CFG_h: 0x%x\n",
-		       i, l, h);
+		pr_info("T%d: CFG_l: 0x%x, CFG_h: 0x%x\n", i, l, h);
+
 		l = hpet_readl(HPET_Tn_CMP(i));
 		h = hpet_readl(HPET_Tn_CMP(i)+4);
-		printk(KERN_INFO "hpet: T%d: CMP_l: 0x%x, CMP_h: 0x%x\n",
-		       i, l, h);
+		pr_info("T%d: CMP_l: 0x%x, CMP_h: 0x%x\n", i, l, h);
+
 		l = hpet_readl(HPET_Tn_ROUTE(i));
 		h = hpet_readl(HPET_Tn_ROUTE(i)+4);
-		printk(KERN_INFO "hpet: T%d ROUTE_l: 0x%x, ROUTE_h: 0x%x\n",
-		       i, l, h);
+		pr_info("T%d ROUTE_l: 0x%x, ROUTE_h: 0x%x\n", i, l, h);
 	}
 }
 
@@ -175,31 +179,20 @@
 } while (0)
 
 /*
- * When the hpet driver (/dev/hpet) is enabled, we need to reserve
+ * When the HPET driver (/dev/hpet) is enabled, we need to reserve
  * timer 0 and timer 1 in case of RTC emulation.
  */
 #ifdef CONFIG_HPET
 
-static void hpet_reserve_msi_timers(struct hpet_data *hd);
-
-static void hpet_reserve_platform_timers(unsigned int id)
+static void __init hpet_reserve_platform_timers(void)
 {
-	struct hpet __iomem *hpet = hpet_virt_address;
-	struct hpet_timer __iomem *timer = &hpet->hpet_timers[2];
-	unsigned int nrtimers, i;
 	struct hpet_data hd;
-
-	nrtimers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT) + 1;
+	unsigned int i;
 
 	memset(&hd, 0, sizeof(hd));
 	hd.hd_phys_address	= hpet_address;
-	hd.hd_address		= hpet;
-	hd.hd_nirqs		= nrtimers;
-	hpet_reserve_timer(&hd, 0);
-
-#ifdef CONFIG_HPET_EMULATE_RTC
-	hpet_reserve_timer(&hd, 1);
-#endif
+	hd.hd_address		= hpet_virt_address;
+	hd.hd_nirqs		= hpet_base.nr_channels;
 
 	/*
 	 * NOTE that hd_irq[] reflects IOAPIC input pins (LEGACY_8254
@@ -209,30 +202,52 @@
 	hd.hd_irq[0] = HPET_LEGACY_8254;
 	hd.hd_irq[1] = HPET_LEGACY_RTC;
 
-	for (i = 2; i < nrtimers; timer++, i++) {
-		hd.hd_irq[i] = (readl(&timer->hpet_config) &
-			Tn_INT_ROUTE_CNF_MASK) >> Tn_INT_ROUTE_CNF_SHIFT;
+	for (i = 0; i < hpet_base.nr_channels; i++) {
+		struct hpet_channel *hc = hpet_base.channels + i;
+
+		if (i >= 2)
+			hd.hd_irq[i] = hc->irq;
+
+		switch (hc->mode) {
+		case HPET_MODE_UNUSED:
+		case HPET_MODE_DEVICE:
+			hc->mode = HPET_MODE_DEVICE;
+			break;
+		case HPET_MODE_CLOCKEVT:
+		case HPET_MODE_LEGACY:
+			hpet_reserve_timer(&hd, hc->num);
+			break;
+		}
 	}
 
-	hpet_reserve_msi_timers(&hd);
-
 	hpet_alloc(&hd);
-
 }
+
+static void __init hpet_select_device_channel(void)
+{
+	int i;
+
+	for (i = 0; i < hpet_base.nr_channels; i++) {
+		struct hpet_channel *hc = hpet_base.channels + i;
+
+		/* Associate the first unused channel to /dev/hpet */
+		if (hc->mode == HPET_MODE_UNUSED) {
+			hc->mode = HPET_MODE_DEVICE;
+			return;
+		}
+	}
+}
+
 #else
-static void hpet_reserve_platform_timers(unsigned int id) { }
+static inline void hpet_reserve_platform_timers(void) { }
+static inline void hpet_select_device_channel(void) {}
 #endif
 
-/*
- * Common hpet info
- */
-static unsigned long hpet_freq;
-
-static struct clock_event_device hpet_clockevent;
-
+/* Common HPET functions */
 static void hpet_stop_counter(void)
 {
 	u32 cfg = hpet_readl(HPET_CFG);
+
 	cfg &= ~HPET_CFG_ENABLE;
 	hpet_writel(cfg, HPET_CFG);
 }
@@ -246,6 +261,7 @@
 static void hpet_start_counter(void)
 {
 	unsigned int cfg = hpet_readl(HPET_CFG);
+
 	cfg |= HPET_CFG_ENABLE;
 	hpet_writel(cfg, HPET_CFG);
 }
@@ -277,24 +293,9 @@
 	hpet_legacy_int_enabled = true;
 }
 
-static void hpet_legacy_clockevent_register(void)
+static int hpet_clkevt_set_state_periodic(struct clock_event_device *evt)
 {
-	/* Start HPET legacy interrupts */
-	hpet_enable_legacy_int();
-
-	/*
-	 * Start hpet with the boot cpu mask and make it
-	 * global after the IO_APIC has been initialized.
-	 */
-	hpet_clockevent.cpumask = cpumask_of(boot_cpu_data.cpu_index);
-	clockevents_config_and_register(&hpet_clockevent, hpet_freq,
-					HPET_MIN_PROG_DELTA, 0x7FFFFFFF);
-	global_clock_event = &hpet_clockevent;
-	printk(KERN_DEBUG "hpet clockevent registered\n");
-}
-
-static int hpet_set_periodic(struct clock_event_device *evt, int timer)
-{
+	unsigned int channel = clockevent_to_channel(evt)->num;
 	unsigned int cfg, cmp, now;
 	uint64_t delta;
 
@@ -303,11 +304,11 @@
 	delta >>= evt->shift;
 	now = hpet_readl(HPET_COUNTER);
 	cmp = now + (unsigned int)delta;
-	cfg = hpet_readl(HPET_Tn_CFG(timer));
+	cfg = hpet_readl(HPET_Tn_CFG(channel));
 	cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL |
 	       HPET_TN_32BIT;
-	hpet_writel(cfg, HPET_Tn_CFG(timer));
-	hpet_writel(cmp, HPET_Tn_CMP(timer));
+	hpet_writel(cfg, HPET_Tn_CFG(channel));
+	hpet_writel(cmp, HPET_Tn_CMP(channel));
 	udelay(1);
 	/*
 	 * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL
@@ -316,52 +317,55 @@
 	 * (See AMD-8111 HyperTransport I/O Hub Data Sheet,
 	 * Publication # 24674)
 	 */
-	hpet_writel((unsigned int)delta, HPET_Tn_CMP(timer));
+	hpet_writel((unsigned int)delta, HPET_Tn_CMP(channel));
 	hpet_start_counter();
 	hpet_print_config();
 
 	return 0;
 }
 
-static int hpet_set_oneshot(struct clock_event_device *evt, int timer)
+static int hpet_clkevt_set_state_oneshot(struct clock_event_device *evt)
 {
+	unsigned int channel = clockevent_to_channel(evt)->num;
 	unsigned int cfg;
 
-	cfg = hpet_readl(HPET_Tn_CFG(timer));
+	cfg = hpet_readl(HPET_Tn_CFG(channel));
 	cfg &= ~HPET_TN_PERIODIC;
 	cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
-	hpet_writel(cfg, HPET_Tn_CFG(timer));
+	hpet_writel(cfg, HPET_Tn_CFG(channel));
 
 	return 0;
 }
 
-static int hpet_shutdown(struct clock_event_device *evt, int timer)
+static int hpet_clkevt_set_state_shutdown(struct clock_event_device *evt)
 {
+	unsigned int channel = clockevent_to_channel(evt)->num;
 	unsigned int cfg;
 
-	cfg = hpet_readl(HPET_Tn_CFG(timer));
+	cfg = hpet_readl(HPET_Tn_CFG(channel));
 	cfg &= ~HPET_TN_ENABLE;
-	hpet_writel(cfg, HPET_Tn_CFG(timer));
+	hpet_writel(cfg, HPET_Tn_CFG(channel));
 
 	return 0;
 }
 
-static int hpet_resume(struct clock_event_device *evt)
+static int hpet_clkevt_legacy_resume(struct clock_event_device *evt)
 {
 	hpet_enable_legacy_int();
 	hpet_print_config();
 	return 0;
 }
 
-static int hpet_next_event(unsigned long delta,
-			   struct clock_event_device *evt, int timer)
+static int
+hpet_clkevt_set_next_event(unsigned long delta, struct clock_event_device *evt)
 {
+	unsigned int channel = clockevent_to_channel(evt)->num;
 	u32 cnt;
 	s32 res;
 
 	cnt = hpet_readl(HPET_COUNTER);
 	cnt += (u32) delta;
-	hpet_writel(cnt, HPET_Tn_CMP(timer));
+	hpet_writel(cnt, HPET_Tn_CMP(channel));
 
 	/*
 	 * HPETs are a complete disaster. The compare register is
@@ -390,360 +394,250 @@
 	return res < HPET_MIN_CYCLES ? -ETIME : 0;
 }
 
-static int hpet_legacy_shutdown(struct clock_event_device *evt)
+static void hpet_init_clockevent(struct hpet_channel *hc, unsigned int rating)
 {
-	return hpet_shutdown(evt, 0);
+	struct clock_event_device *evt = &hc->evt;
+
+	evt->rating		= rating;
+	evt->irq		= hc->irq;
+	evt->name		= hc->name;
+	evt->cpumask		= cpumask_of(hc->cpu);
+	evt->set_state_oneshot	= hpet_clkevt_set_state_oneshot;
+	evt->set_next_event	= hpet_clkevt_set_next_event;
+	evt->set_state_shutdown	= hpet_clkevt_set_state_shutdown;
+
+	evt->features = CLOCK_EVT_FEAT_ONESHOT;
+	if (hc->boot_cfg & HPET_TN_PERIODIC) {
+		evt->features		|= CLOCK_EVT_FEAT_PERIODIC;
+		evt->set_state_periodic	= hpet_clkevt_set_state_periodic;
+	}
 }
 
-static int hpet_legacy_set_oneshot(struct clock_event_device *evt)
+static void __init hpet_legacy_clockevent_register(struct hpet_channel *hc)
 {
-	return hpet_set_oneshot(evt, 0);
-}
+	/*
+	 * Start HPET with the boot CPU's cpumask and make it global after
+	 * the IO_APIC has been initialized.
+	 */
+	hc->cpu = boot_cpu_data.cpu_index;
+	strncpy(hc->name, "hpet", sizeof(hc->name));
+	hpet_init_clockevent(hc, 50);
 
-static int hpet_legacy_set_periodic(struct clock_event_device *evt)
-{
-	return hpet_set_periodic(evt, 0);
-}
+	hc->evt.tick_resume	= hpet_clkevt_legacy_resume;
 
-static int hpet_legacy_resume(struct clock_event_device *evt)
-{
-	return hpet_resume(evt);
-}
+	/*
+	 * Legacy horrors and sins from the past. HPET used periodic mode
+	 * unconditionally forever on the legacy channel 0. Removing the
+	 * below hack and using the conditional in hpet_init_clockevent()
+	 * makes at least Qemu and one hardware machine fail to boot.
+	 * There are two issues which cause the boot failure:
+	 *
+	 * #1 After the timer delivery test in IOAPIC and the IOAPIC setup
+	 *    the next interrupt is not delivered despite the HPET channel
+	 *    being programmed correctly. Reprogramming the HPET after
+	 *    switching to IOAPIC makes it work again. After fixing this,
+	 *    the next issue surfaces:
+	 *
+	 * #2 Due to the unconditional periodic mode availability the Local
+	 *    APIC timer calibration can hijack the global clockevents
+	 *    event handler without causing damage. Using oneshot at this
+	 *    stage makes if hang because the HPET does not get
+	 *    reprogrammed due to the handler hijacking. Duh, stupid me!
+	 *
+	 * Both issues require major surgery and especially the kick HPET
+	 * again after enabling IOAPIC results in really nasty hackery.
+	 * This 'assume periodic works' magic has survived since HPET
+	 * support got added, so it's questionable whether this should be
+	 * fixed. Both Qemu and the failing hardware machine support
+	 * periodic mode despite the fact that both don't advertise it in
+	 * the configuration register and both need that extra kick after
+	 * switching to IOAPIC. Seems to be a feature...
+	 */
+	hc->evt.features		|= CLOCK_EVT_FEAT_PERIODIC;
+	hc->evt.set_state_periodic	= hpet_clkevt_set_state_periodic;
 
-static int hpet_legacy_next_event(unsigned long delta,
-			struct clock_event_device *evt)
-{
-	return hpet_next_event(delta, evt, 0);
-}
+	/* Start HPET legacy interrupts */
+	hpet_enable_legacy_int();
 
-/*
- * The hpet clock event device
- */
-static struct clock_event_device hpet_clockevent = {
-	.name			= "hpet",
-	.features		= CLOCK_EVT_FEAT_PERIODIC |
-				  CLOCK_EVT_FEAT_ONESHOT,
-	.set_state_periodic	= hpet_legacy_set_periodic,
-	.set_state_oneshot	= hpet_legacy_set_oneshot,
-	.set_state_shutdown	= hpet_legacy_shutdown,
-	.tick_resume		= hpet_legacy_resume,
-	.set_next_event		= hpet_legacy_next_event,
-	.irq			= 0,
-	.rating			= 50,
-};
+	clockevents_config_and_register(&hc->evt, hpet_freq,
+					HPET_MIN_PROG_DELTA, 0x7FFFFFFF);
+	global_clock_event = &hc->evt;
+	pr_debug("Clockevent registered\n");
+}
 
 /*
  * HPET MSI Support
  */
 #ifdef CONFIG_PCI_MSI
 
-static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev);
-static struct hpet_dev	*hpet_devs;
-static struct irq_domain *hpet_domain;
-
 void hpet_msi_unmask(struct irq_data *data)
 {
-	struct hpet_dev *hdev = irq_data_get_irq_handler_data(data);
+	struct hpet_channel *hc = irq_data_get_irq_handler_data(data);
 	unsigned int cfg;
 
-	/* unmask it */
-	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
+	cfg = hpet_readl(HPET_Tn_CFG(hc->num));
 	cfg |= HPET_TN_ENABLE | HPET_TN_FSB;
-	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
+	hpet_writel(cfg, HPET_Tn_CFG(hc->num));
 }
 
 void hpet_msi_mask(struct irq_data *data)
 {
-	struct hpet_dev *hdev = irq_data_get_irq_handler_data(data);
+	struct hpet_channel *hc = irq_data_get_irq_handler_data(data);
 	unsigned int cfg;
 
-	/* mask it */
-	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
+	cfg = hpet_readl(HPET_Tn_CFG(hc->num));
 	cfg &= ~(HPET_TN_ENABLE | HPET_TN_FSB);
-	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
+	hpet_writel(cfg, HPET_Tn_CFG(hc->num));
 }
 
-void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg)
+void hpet_msi_write(struct hpet_channel *hc, struct msi_msg *msg)
 {
-	hpet_writel(msg->data, HPET_Tn_ROUTE(hdev->num));
-	hpet_writel(msg->address_lo, HPET_Tn_ROUTE(hdev->num) + 4);
+	hpet_writel(msg->data, HPET_Tn_ROUTE(hc->num));
+	hpet_writel(msg->address_lo, HPET_Tn_ROUTE(hc->num) + 4);
 }
 
-void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg)
+static int hpet_clkevt_msi_resume(struct clock_event_device *evt)
 {
-	msg->data = hpet_readl(HPET_Tn_ROUTE(hdev->num));
-	msg->address_lo = hpet_readl(HPET_Tn_ROUTE(hdev->num) + 4);
-	msg->address_hi = 0;
-}
-
-static int hpet_msi_shutdown(struct clock_event_device *evt)
-{
-	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-
-	return hpet_shutdown(evt, hdev->num);
-}
-
-static int hpet_msi_set_oneshot(struct clock_event_device *evt)
-{
-	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-
-	return hpet_set_oneshot(evt, hdev->num);
-}
-
-static int hpet_msi_set_periodic(struct clock_event_device *evt)
-{
-	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-
-	return hpet_set_periodic(evt, hdev->num);
-}
-
-static int hpet_msi_resume(struct clock_event_device *evt)
-{
-	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-	struct irq_data *data = irq_get_irq_data(hdev->irq);
+	struct hpet_channel *hc = clockevent_to_channel(evt);
+	struct irq_data *data = irq_get_irq_data(hc->irq);
 	struct msi_msg msg;
 
 	/* Restore the MSI msg and unmask the interrupt */
 	irq_chip_compose_msi_msg(data, &msg);
-	hpet_msi_write(hdev, &msg);
+	hpet_msi_write(hc, &msg);
 	hpet_msi_unmask(data);
 	return 0;
 }
 
-static int hpet_msi_next_event(unsigned long delta,
-				struct clock_event_device *evt)
+static irqreturn_t hpet_msi_interrupt_handler(int irq, void *data)
 {
-	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-	return hpet_next_event(delta, evt, hdev->num);
-}
+	struct hpet_channel *hc = data;
+	struct clock_event_device *evt = &hc->evt;
 
-static irqreturn_t hpet_interrupt_handler(int irq, void *data)
-{
-	struct hpet_dev *dev = (struct hpet_dev *)data;
-	struct clock_event_device *hevt = &dev->evt;
-
-	if (!hevt->event_handler) {
-		printk(KERN_INFO "Spurious HPET timer interrupt on HPET timer %d\n",
-				dev->num);
+	if (!evt->event_handler) {
+		pr_info("Spurious interrupt HPET channel %d\n", hc->num);
 		return IRQ_HANDLED;
 	}
 
-	hevt->event_handler(hevt);
+	evt->event_handler(evt);
 	return IRQ_HANDLED;
 }
 
-static int hpet_setup_irq(struct hpet_dev *dev)
+static int hpet_setup_msi_irq(struct hpet_channel *hc)
 {
-
-	if (request_irq(dev->irq, hpet_interrupt_handler,
+	if (request_irq(hc->irq, hpet_msi_interrupt_handler,
 			IRQF_TIMER | IRQF_NOBALANCING,
-			dev->name, dev))
+			hc->name, hc))
 		return -1;
 
-	disable_irq(dev->irq);
-	irq_set_affinity(dev->irq, cpumask_of(dev->cpu));
-	enable_irq(dev->irq);
+	disable_irq(hc->irq);
+	irq_set_affinity(hc->irq, cpumask_of(hc->cpu));
+	enable_irq(hc->irq);
 
-	printk(KERN_DEBUG "hpet: %s irq %d for MSI\n",
-			 dev->name, dev->irq);
+	pr_debug("%s irq %u for MSI\n", hc->name, hc->irq);
 
 	return 0;
 }
 
-/* This should be called in specific @cpu */
-static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu)
+/* Invoked from the hotplug callback on @cpu */
+static void init_one_hpet_msi_clockevent(struct hpet_channel *hc, int cpu)
 {
-	struct clock_event_device *evt = &hdev->evt;
+	struct clock_event_device *evt = &hc->evt;
 
-	WARN_ON(cpu != smp_processor_id());
-	if (!(hdev->flags & HPET_DEV_VALID))
-		return;
+	hc->cpu = cpu;
+	per_cpu(cpu_hpet_channel, cpu) = hc;
+	hpet_setup_msi_irq(hc);
 
-	hdev->cpu = cpu;
-	per_cpu(cpu_hpet_dev, cpu) = hdev;
-	evt->name = hdev->name;
-	hpet_setup_irq(hdev);
-	evt->irq = hdev->irq;
-
-	evt->rating = 110;
-	evt->features = CLOCK_EVT_FEAT_ONESHOT;
-	if (hdev->flags & HPET_DEV_PERI_CAP) {
-		evt->features |= CLOCK_EVT_FEAT_PERIODIC;
-		evt->set_state_periodic = hpet_msi_set_periodic;
-	}
-
-	evt->set_state_shutdown = hpet_msi_shutdown;
-	evt->set_state_oneshot = hpet_msi_set_oneshot;
-	evt->tick_resume = hpet_msi_resume;
-	evt->set_next_event = hpet_msi_next_event;
-	evt->cpumask = cpumask_of(hdev->cpu);
+	hpet_init_clockevent(hc, 110);
+	evt->tick_resume = hpet_clkevt_msi_resume;
 
 	clockevents_config_and_register(evt, hpet_freq, HPET_MIN_PROG_DELTA,
 					0x7FFFFFFF);
 }
 
-#ifdef CONFIG_HPET
-/* Reserve at least one timer for userspace (/dev/hpet) */
-#define RESERVE_TIMERS 1
-#else
-#define RESERVE_TIMERS 0
-#endif
-
-static void hpet_msi_capability_lookup(unsigned int start_timer)
+static struct hpet_channel *hpet_get_unused_clockevent(void)
 {
-	unsigned int id;
-	unsigned int num_timers;
-	unsigned int num_timers_used = 0;
-	int i, irq;
+	int i;
 
-	if (hpet_msi_disable)
+	for (i = 0; i < hpet_base.nr_channels; i++) {
+		struct hpet_channel *hc = hpet_base.channels + i;
+
+		if (hc->mode != HPET_MODE_CLOCKEVT || hc->in_use)
+			continue;
+		hc->in_use = 1;
+		return hc;
+	}
+	return NULL;
+}
+
+static int hpet_cpuhp_online(unsigned int cpu)
+{
+	struct hpet_channel *hc = hpet_get_unused_clockevent();
+
+	if (hc)
+		init_one_hpet_msi_clockevent(hc, cpu);
+	return 0;
+}
+
+static int hpet_cpuhp_dead(unsigned int cpu)
+{
+	struct hpet_channel *hc = per_cpu(cpu_hpet_channel, cpu);
+
+	if (!hc)
+		return 0;
+	free_irq(hc->irq, hc);
+	hc->in_use = 0;
+	per_cpu(cpu_hpet_channel, cpu) = NULL;
+	return 0;
+}
+
+static void __init hpet_select_clockevents(void)
+{
+	unsigned int i;
+
+	hpet_base.nr_clockevents = 0;
+
+	/* No point if MSI is disabled or CPU has an Always Runing APIC Timer */
+	if (hpet_msi_disable || boot_cpu_has(X86_FEATURE_ARAT))
 		return;
 
-	if (boot_cpu_has(X86_FEATURE_ARAT))
-		return;
-	id = hpet_readl(HPET_ID);
-
-	num_timers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT);
-	num_timers++; /* Value read out starts from 0 */
 	hpet_print_config();
 
 	hpet_domain = hpet_create_irq_domain(hpet_blockid);
 	if (!hpet_domain)
 		return;
 
-	hpet_devs = kcalloc(num_timers, sizeof(struct hpet_dev), GFP_KERNEL);
-	if (!hpet_devs)
-		return;
+	for (i = 0; i < hpet_base.nr_channels; i++) {
+		struct hpet_channel *hc = hpet_base.channels + i;
+		int irq;
 
-	hpet_num_timers = num_timers;
-
-	for (i = start_timer; i < num_timers - RESERVE_TIMERS; i++) {
-		struct hpet_dev *hdev = &hpet_devs[num_timers_used];
-		unsigned int cfg = hpet_readl(HPET_Tn_CFG(i));
-
-		/* Only consider HPET timer with MSI support */
-		if (!(cfg & HPET_TN_FSB_CAP))
+		if (hc->mode != HPET_MODE_UNUSED)
 			continue;
 
-		hdev->flags = 0;
-		if (cfg & HPET_TN_PERIODIC_CAP)
-			hdev->flags |= HPET_DEV_PERI_CAP;
-		sprintf(hdev->name, "hpet%d", i);
-		hdev->num = i;
+		/* Only consider HPET channel with MSI support */
+		if (!(hc->boot_cfg & HPET_TN_FSB_CAP))
+			continue;
 
-		irq = hpet_assign_irq(hpet_domain, hdev, hdev->num);
+		sprintf(hc->name, "hpet%d", i);
+
+		irq = hpet_assign_irq(hpet_domain, hc, hc->num);
 		if (irq <= 0)
 			continue;
 
-		hdev->irq = irq;
-		hdev->flags |= HPET_DEV_FSB_CAP;
-		hdev->flags |= HPET_DEV_VALID;
-		num_timers_used++;
-		if (num_timers_used == num_possible_cpus())
+		hc->irq = irq;
+		hc->mode = HPET_MODE_CLOCKEVT;
+
+		if (++hpet_base.nr_clockevents == num_possible_cpus())
 			break;
 	}
 
-	printk(KERN_INFO "HPET: %d timers in total, %d timers will be used for per-cpu timer\n",
-		num_timers, num_timers_used);
+	pr_info("%d channels of %d reserved for per-cpu timers\n",
+		hpet_base.nr_channels, hpet_base.nr_clockevents);
 }
 
-#ifdef CONFIG_HPET
-static void hpet_reserve_msi_timers(struct hpet_data *hd)
-{
-	int i;
-
-	if (!hpet_devs)
-		return;
-
-	for (i = 0; i < hpet_num_timers; i++) {
-		struct hpet_dev *hdev = &hpet_devs[i];
-
-		if (!(hdev->flags & HPET_DEV_VALID))
-			continue;
-
-		hd->hd_irq[hdev->num] = hdev->irq;
-		hpet_reserve_timer(hd, hdev->num);
-	}
-}
-#endif
-
-static struct hpet_dev *hpet_get_unused_timer(void)
-{
-	int i;
-
-	if (!hpet_devs)
-		return NULL;
-
-	for (i = 0; i < hpet_num_timers; i++) {
-		struct hpet_dev *hdev = &hpet_devs[i];
-
-		if (!(hdev->flags & HPET_DEV_VALID))
-			continue;
-		if (test_and_set_bit(HPET_DEV_USED_BIT,
-			(unsigned long *)&hdev->flags))
-			continue;
-		return hdev;
-	}
-	return NULL;
-}
-
-struct hpet_work_struct {
-	struct delayed_work work;
-	struct completion complete;
-};
-
-static void hpet_work(struct work_struct *w)
-{
-	struct hpet_dev *hdev;
-	int cpu = smp_processor_id();
-	struct hpet_work_struct *hpet_work;
-
-	hpet_work = container_of(w, struct hpet_work_struct, work.work);
-
-	hdev = hpet_get_unused_timer();
-	if (hdev)
-		init_one_hpet_msi_clockevent(hdev, cpu);
-
-	complete(&hpet_work->complete);
-}
-
-static int hpet_cpuhp_online(unsigned int cpu)
-{
-	struct hpet_work_struct work;
-
-	INIT_DELAYED_WORK_ONSTACK(&work.work, hpet_work);
-	init_completion(&work.complete);
-	/* FIXME: add schedule_work_on() */
-	schedule_delayed_work_on(cpu, &work.work, 0);
-	wait_for_completion(&work.complete);
-	destroy_delayed_work_on_stack(&work.work);
-	return 0;
-}
-
-static int hpet_cpuhp_dead(unsigned int cpu)
-{
-	struct hpet_dev *hdev = per_cpu(cpu_hpet_dev, cpu);
-
-	if (!hdev)
-		return 0;
-	free_irq(hdev->irq, hdev);
-	hdev->flags &= ~HPET_DEV_USED;
-	per_cpu(cpu_hpet_dev, cpu) = NULL;
-	return 0;
-}
 #else
 
-static void hpet_msi_capability_lookup(unsigned int start_timer)
-{
-	return;
-}
-
-#ifdef CONFIG_HPET
-static void hpet_reserve_msi_timers(struct hpet_data *hd)
-{
-	return;
-}
-#endif
+static inline void hpet_select_clockevents(void) { }
 
 #define hpet_cpuhp_online	NULL
 #define hpet_cpuhp_dead		NULL
@@ -757,10 +651,10 @@
 /*
  * Reading the HPET counter is a very slow operation. If a large number of
  * CPUs are trying to access the HPET counter simultaneously, it can cause
- * massive delay and slow down system performance dramatically. This may
+ * massive delays and slow down system performance dramatically. This may
  * happen when HPET is the default clock source instead of TSC. For a
  * really large system with hundreds of CPUs, the slowdown may be so
- * severe that it may actually crash the system because of a NMI watchdog
+ * severe, that it can actually crash the system because of a NMI watchdog
  * soft lockup, for example.
  *
  * If multiple CPUs are trying to access the HPET counter at the same time,
@@ -769,10 +663,9 @@
  *
  * This special feature is only enabled on x86-64 systems. It is unlikely
  * that 32-bit x86 systems will have enough CPUs to require this feature
- * with its associated locking overhead. And we also need 64-bit atomic
- * read.
+ * with its associated locking overhead. We also need 64-bit atomic read.
  *
- * The lock and the hpet value are stored together and can be read in a
+ * The lock and the HPET value are stored together and can be read in a
  * single atomic 64-bit read. It is explicitly assumed that arch_spinlock_t
  * is 32 bits in size.
  */
@@ -861,15 +754,40 @@
 	.resume		= hpet_resume_counter,
 };
 
-static int hpet_clocksource_register(void)
+/*
+ * AMD SB700 based systems with spread spectrum enabled use a SMM based
+ * HPET emulation to provide proper frequency setting.
+ *
+ * On such systems the SMM code is initialized with the first HPET register
+ * access and takes some time to complete. During this time the config
+ * register reads 0xffffffff. We check for max 1000 loops whether the
+ * config register reads a non-0xffffffff value to make sure that the
+ * HPET is up and running before we proceed any further.
+ *
+ * A counting loop is safe, as the HPET access takes thousands of CPU cycles.
+ *
+ * On non-SB700 based machines this check is only done once and has no
+ * side effects.
+ */
+static bool __init hpet_cfg_working(void)
 {
-	u64 start, now;
-	u64 t1;
+	int i;
 
-	/* Start the counter */
+	for (i = 0; i < 1000; i++) {
+		if (hpet_readl(HPET_CFG) != 0xFFFFFFFF)
+			return true;
+	}
+
+	pr_warn("Config register invalid. Disabling HPET\n");
+	return false;
+}
+
+static bool __init hpet_counting(void)
+{
+	u64 start, now, t1;
+
 	hpet_restart_counter();
 
-	/* Verify whether hpet counter works */
 	t1 = hpet_readl(HPET_COUNTER);
 	start = rdtsc();
 
@@ -880,72 +798,124 @@
 	 * 1 GHz == 200us
 	 */
 	do {
-		rep_nop();
+		if (t1 != hpet_readl(HPET_COUNTER))
+			return true;
 		now = rdtsc();
 	} while ((now - start) < 200000UL);
 
-	if (t1 == hpet_readl(HPET_COUNTER)) {
-		printk(KERN_WARNING
-		       "HPET counter not counting. HPET disabled\n");
-		return -ENODEV;
-	}
-
-	clocksource_register_hz(&clocksource_hpet, (u32)hpet_freq);
-	return 0;
+	pr_warn("Counter not counting. HPET disabled\n");
+	return false;
 }
 
-static u32 *hpet_boot_cfg;
+static bool __init mwait_pc10_supported(void)
+{
+	unsigned int eax, ebx, ecx, mwait_substates;
+
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return false;
+
+	if (!cpu_feature_enabled(X86_FEATURE_MWAIT))
+		return false;
+
+	if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
+		return false;
+
+	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates);
+
+	return (ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) &&
+	       (ecx & CPUID5_ECX_INTERRUPT_BREAK) &&
+	       (mwait_substates & (0xF << 28));
+}
+
+/*
+ * Check whether the system supports PC10. If so force disable HPET as that
+ * stops counting in PC10. This check is overbroad as it does not take any
+ * of the following into account:
+ *
+ *	- ACPI tables
+ *	- Enablement of intel_idle
+ *	- Command line arguments which limit intel_idle C-state support
+ *
+ * That's perfectly fine. HPET is a piece of hardware designed by committee
+ * and the only reasons why it is still in use on modern systems is the
+ * fact that it is impossible to reliably query TSC and CPU frequency via
+ * CPUID or firmware.
+ *
+ * If HPET is functional it is useful for calibrating TSC, but this can be
+ * done via PMTIMER as well which seems to be the last remaining timer on
+ * X86/INTEL platforms that has not been completely wreckaged by feature
+ * creep.
+ *
+ * In theory HPET support should be removed altogether, but there are older
+ * systems out there which depend on it because TSC and APIC timer are
+ * dysfunctional in deeper C-states.
+ *
+ * It's only 20 years now that hardware people have been asked to provide
+ * reliable and discoverable facilities which can be used for timekeeping
+ * and per CPU timer interrupts.
+ *
+ * The probability that this problem is going to be solved in the
+ * forseeable future is close to zero, so the kernel has to be cluttered
+ * with heuristics to keep up with the ever growing amount of hardware and
+ * firmware trainwrecks. Hopefully some day hardware people will understand
+ * that the approach of "This can be fixed in software" is not sustainable.
+ * Hope dies last...
+ */
+static bool __init hpet_is_pc10_damaged(void)
+{
+	unsigned long long pcfg;
+
+	/* Check whether PC10 substates are supported */
+	if (!mwait_pc10_supported())
+		return false;
+
+	/* Check whether PC10 is enabled in PKG C-state limit */
+	rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, pcfg);
+	if ((pcfg & 0xF) < 8)
+		return false;
+
+	if (hpet_force_user) {
+		pr_warn("HPET force enabled via command line, but dysfunctional in PC10.\n");
+		return false;
+	}
+
+	pr_info("HPET dysfunctional in PC10. Force disabled.\n");
+	boot_hpet_disable = true;
+	return true;
+}
 
 /**
  * hpet_enable - Try to setup the HPET timer. Returns 1 on success.
  */
 int __init hpet_enable(void)
 {
-	u32 hpet_period, cfg, id;
+	u32 hpet_period, cfg, id, irq;
+	unsigned int i, channels;
+	struct hpet_channel *hc;
 	u64 freq;
-	unsigned int i, last;
 
 	if (!is_hpet_capable())
+		return 0;
+
+	if (hpet_is_pc10_damaged())
 		return 0;
 
 	hpet_set_mapping();
 	if (!hpet_virt_address)
 		return 0;
 
+	/* Validate that the config register is working */
+	if (!hpet_cfg_working())
+		goto out_nohpet;
+
 	/*
 	 * Read the period and check for a sane value:
 	 */
 	hpet_period = hpet_readl(HPET_PERIOD);
-
-	/*
-	 * AMD SB700 based systems with spread spectrum enabled use a
-	 * SMM based HPET emulation to provide proper frequency
-	 * setting. The SMM code is initialized with the first HPET
-	 * register access and takes some time to complete. During
-	 * this time the config register reads 0xffffffff. We check
-	 * for max. 1000 loops whether the config register reads a non
-	 * 0xffffffff value to make sure that HPET is up and running
-	 * before we go further. A counting loop is safe, as the HPET
-	 * access takes thousands of CPU cycles. On non SB700 based
-	 * machines this check is only done once and has no side
-	 * effects.
-	 */
-	for (i = 0; hpet_readl(HPET_CFG) == 0xFFFFFFFF; i++) {
-		if (i == 1000) {
-			printk(KERN_WARNING
-			       "HPET config register value = 0xFFFFFFFF. "
-			       "Disabling HPET\n");
-			goto out_nohpet;
-		}
-	}
-
 	if (hpet_period < HPET_MIN_PERIOD || hpet_period > HPET_MAX_PERIOD)
 		goto out_nohpet;
 
-	/*
-	 * The period is a femto seconds value. Convert it to a
-	 * frequency.
-	 */
+	/* The period is a femtoseconds value. Convert it to a frequency. */
 	freq = FSEC_PER_SEC;
 	do_div(freq, hpet_period);
 	hpet_freq = freq;
@@ -957,71 +927,97 @@
 	id = hpet_readl(HPET_ID);
 	hpet_print_config();
 
-	last = (id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT;
+	/* This is the HPET channel number which is zero based */
+	channels = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT) + 1;
 
-#ifdef CONFIG_HPET_EMULATE_RTC
 	/*
 	 * The legacy routing mode needs at least two channels, tick timer
 	 * and the rtc emulation channel.
 	 */
-	if (!last)
+	if (IS_ENABLED(CONFIG_HPET_EMULATE_RTC) && channels < 2)
 		goto out_nohpet;
-#endif
 
+	hc = kcalloc(channels, sizeof(*hc), GFP_KERNEL);
+	if (!hc) {
+		pr_warn("Disabling HPET.\n");
+		goto out_nohpet;
+	}
+	hpet_base.channels = hc;
+	hpet_base.nr_channels = channels;
+
+	/* Read, store and sanitize the global configuration */
 	cfg = hpet_readl(HPET_CFG);
-	hpet_boot_cfg = kmalloc_array(last + 2, sizeof(*hpet_boot_cfg),
-				      GFP_KERNEL);
-	if (hpet_boot_cfg)
-		*hpet_boot_cfg = cfg;
-	else
-		pr_warn("HPET initial state will not be saved\n");
+	hpet_base.boot_cfg = cfg;
 	cfg &= ~(HPET_CFG_ENABLE | HPET_CFG_LEGACY);
 	hpet_writel(cfg, HPET_CFG);
 	if (cfg)
-		pr_warn("Unrecognized bits %#x set in global cfg\n", cfg);
+		pr_warn("Global config: Unknown bits %#x\n", cfg);
 
-	for (i = 0; i <= last; ++i) {
+	/* Read, store and sanitize the per channel configuration */
+	for (i = 0; i < channels; i++, hc++) {
+		hc->num = i;
+
 		cfg = hpet_readl(HPET_Tn_CFG(i));
-		if (hpet_boot_cfg)
-			hpet_boot_cfg[i + 1] = cfg;
+		hc->boot_cfg = cfg;
+		irq = (cfg & Tn_INT_ROUTE_CNF_MASK) >> Tn_INT_ROUTE_CNF_SHIFT;
+		hc->irq = irq;
+
 		cfg &= ~(HPET_TN_ENABLE | HPET_TN_LEVEL | HPET_TN_FSB);
 		hpet_writel(cfg, HPET_Tn_CFG(i));
+
 		cfg &= ~(HPET_TN_PERIODIC | HPET_TN_PERIODIC_CAP
 			 | HPET_TN_64BIT_CAP | HPET_TN_32BIT | HPET_TN_ROUTE
 			 | HPET_TN_FSB | HPET_TN_FSB_CAP);
 		if (cfg)
-			pr_warn("Unrecognized bits %#x set in cfg#%u\n",
-				cfg, i);
+			pr_warn("Channel #%u config: Unknown bits %#x\n", i, cfg);
 	}
 	hpet_print_config();
 
-	if (hpet_clocksource_register())
+	/*
+	 * Validate that the counter is counting. This needs to be done
+	 * after sanitizing the config registers to properly deal with
+	 * force enabled HPETs.
+	 */
+	if (!hpet_counting())
 		goto out_nohpet;
 
+	clocksource_register_hz(&clocksource_hpet, (u32)hpet_freq);
+
 	if (id & HPET_ID_LEGSUP) {
-		hpet_legacy_clockevent_register();
+		hpet_legacy_clockevent_register(&hpet_base.channels[0]);
+		hpet_base.channels[0].mode = HPET_MODE_LEGACY;
+		if (IS_ENABLED(CONFIG_HPET_EMULATE_RTC))
+			hpet_base.channels[1].mode = HPET_MODE_LEGACY;
 		return 1;
 	}
 	return 0;
 
 out_nohpet:
+	kfree(hpet_base.channels);
+	hpet_base.channels = NULL;
+	hpet_base.nr_channels = 0;
 	hpet_clear_mapping();
 	hpet_address = 0;
 	return 0;
 }
 
 /*
- * Needs to be late, as the reserve_timer code calls kalloc !
+ * The late initialization runs after the PCI quirks have been invoked
+ * which might have detected a system on which the HPET can be enforced.
  *
- * Not a problem on i386 as hpet_enable is called from late_time_init,
- * but on x86_64 it is necessary !
+ * Also, the MSI machinery is not working yet when the HPET is initialized
+ * early.
+ *
+ * If the HPET is enabled, then:
+ *
+ *  1) Reserve one channel for /dev/hpet if CONFIG_HPET=y
+ *  2) Reserve up to num_possible_cpus() channels as per CPU clockevents
+ *  3) Setup /dev/hpet if CONFIG_HPET=y
+ *  4) Register hotplug callbacks when clockevents are available
  */
 static __init int hpet_late_init(void)
 {
 	int ret;
-
-	if (boot_hpet_disable)
-		return -ENODEV;
 
 	if (!hpet_address) {
 		if (!force_hpet_address)
@@ -1034,21 +1030,14 @@
 	if (!hpet_virt_address)
 		return -ENODEV;
 
-	if (hpet_readl(HPET_ID) & HPET_ID_LEGSUP)
-		hpet_msi_capability_lookup(2);
-	else
-		hpet_msi_capability_lookup(0);
-
-	hpet_reserve_platform_timers(hpet_readl(HPET_ID));
+	hpet_select_device_channel();
+	hpet_select_clockevents();
+	hpet_reserve_platform_timers();
 	hpet_print_config();
 
-	if (hpet_msi_disable)
+	if (!hpet_base.nr_clockevents)
 		return 0;
 
-	if (boot_cpu_has(X86_FEATURE_ARAT))
-		return 0;
-
-	/* This notifier should be called after workqueue is ready */
 	ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "x86/hpet:online",
 				hpet_cpuhp_online, NULL);
 	if (ret)
@@ -1067,47 +1056,47 @@
 
 void hpet_disable(void)
 {
-	if (is_hpet_capable() && hpet_virt_address) {
-		unsigned int cfg = hpet_readl(HPET_CFG), id, last;
+	unsigned int i;
+	u32 cfg;
 
-		if (hpet_boot_cfg)
-			cfg = *hpet_boot_cfg;
-		else if (hpet_legacy_int_enabled) {
-			cfg &= ~HPET_CFG_LEGACY;
-			hpet_legacy_int_enabled = false;
-		}
-		cfg &= ~HPET_CFG_ENABLE;
-		hpet_writel(cfg, HPET_CFG);
+	if (!is_hpet_capable() || !hpet_virt_address)
+		return;
 
-		if (!hpet_boot_cfg)
-			return;
+	/* Restore boot configuration with the enable bit cleared */
+	cfg = hpet_base.boot_cfg;
+	cfg &= ~HPET_CFG_ENABLE;
+	hpet_writel(cfg, HPET_CFG);
 
-		id = hpet_readl(HPET_ID);
-		last = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT);
+	/* Restore the channel boot configuration */
+	for (i = 0; i < hpet_base.nr_channels; i++)
+		hpet_writel(hpet_base.channels[i].boot_cfg, HPET_Tn_CFG(i));
 
-		for (id = 0; id <= last; ++id)
-			hpet_writel(hpet_boot_cfg[id + 1], HPET_Tn_CFG(id));
-
-		if (*hpet_boot_cfg & HPET_CFG_ENABLE)
-			hpet_writel(*hpet_boot_cfg, HPET_CFG);
-	}
+	/* If the HPET was enabled at boot time, reenable it */
+	if (hpet_base.boot_cfg & HPET_CFG_ENABLE)
+		hpet_writel(hpet_base.boot_cfg, HPET_CFG);
 }
 
 #ifdef CONFIG_HPET_EMULATE_RTC
 
-/* HPET in LegacyReplacement Mode eats up RTC interrupt line. When, HPET
+/*
+ * HPET in LegacyReplacement mode eats up the RTC interrupt line. When HPET
  * is enabled, we support RTC interrupt functionality in software.
+ *
  * RTC has 3 kinds of interrupts:
- * 1) Update Interrupt - generate an interrupt, every sec, when RTC clock
- *    is updated
- * 2) Alarm Interrupt - generate an interrupt at a specific time of day
- * 3) Periodic Interrupt - generate periodic interrupt, with frequencies
- *    2Hz-8192Hz (2Hz-64Hz for non-root user) (all freqs in powers of 2)
- * (1) and (2) above are implemented using polling at a frequency of
- * 64 Hz. The exact frequency is a tradeoff between accuracy and interrupt
- * overhead. (DEFAULT_RTC_INT_FREQ)
- * For (3), we use interrupts at 64Hz or user specified periodic
- * frequency, whichever is higher.
+ *
+ *  1) Update Interrupt - generate an interrupt, every second, when the
+ *     RTC clock is updated
+ *  2) Alarm Interrupt - generate an interrupt at a specific time of day
+ *  3) Periodic Interrupt - generate periodic interrupt, with frequencies
+ *     2Hz-8192Hz (2Hz-64Hz for non-root user) (all frequencies in powers of 2)
+ *
+ * (1) and (2) above are implemented using polling at a frequency of 64 Hz:
+ * DEFAULT_RTC_INT_FREQ.
+ *
+ * The exact frequency is a tradeoff between accuracy and interrupt overhead.
+ *
+ * For (3), we use interrupts at 64 Hz, or the user specified periodic frequency,
+ * if it's higher.
  */
 #include <linux/mc146818rtc.h>
 #include <linux/rtc.h>
@@ -1128,7 +1117,7 @@
 static rtc_irq_handler irq_handler;
 
 /*
- * Check that the hpet counter c1 is ahead of the c2
+ * Check that the HPET counter c1 is ahead of c2
  */
 static inline int hpet_cnt_ahead(u32 c1, u32 c2)
 {
@@ -1166,8 +1155,8 @@
 EXPORT_SYMBOL_GPL(hpet_unregister_irq_handler);
 
 /*
- * Timer 1 for RTC emulation. We use one shot mode, as periodic mode
- * is not supported by all HPET implementations for timer 1.
+ * Channel 1 for RTC emulation. We use one shot mode, as periodic mode
+ * is not supported by all HPET implementations for channel 1.
  *
  * hpet_rtc_timer_init() is called when the rtc is initialized.
  */
@@ -1180,10 +1169,11 @@
 		return 0;
 
 	if (!hpet_default_delta) {
+		struct clock_event_device *evt = &hpet_base.channels[0].evt;
 		uint64_t clc;
 
-		clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC;
-		clc >>= hpet_clockevent.shift + DEFAULT_RTC_SHIFT;
+		clc = (uint64_t) evt->mult * NSEC_PER_SEC;
+		clc >>= evt->shift + DEFAULT_RTC_SHIFT;
 		hpet_default_delta = clc;
 	}
 
@@ -1212,6 +1202,7 @@
 static void hpet_disable_rtc_channel(void)
 {
 	u32 cfg = hpet_readl(HPET_T1_CFG);
+
 	cfg &= ~HPET_TN_ENABLE;
 	hpet_writel(cfg, HPET_T1_CFG);
 }
@@ -1253,8 +1244,7 @@
 }
 EXPORT_SYMBOL_GPL(hpet_set_rtc_irq_bit);
 
-int hpet_set_alarm_time(unsigned char hrs, unsigned char min,
-			unsigned char sec)
+int hpet_set_alarm_time(unsigned char hrs, unsigned char min, unsigned char sec)
 {
 	if (!is_hpet_enabled())
 		return 0;
@@ -1274,15 +1264,18 @@
 	if (!is_hpet_enabled())
 		return 0;
 
-	if (freq <= DEFAULT_RTC_INT_FREQ)
+	if (freq <= DEFAULT_RTC_INT_FREQ) {
 		hpet_pie_limit = DEFAULT_RTC_INT_FREQ / freq;
-	else {
-		clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC;
+	} else {
+		struct clock_event_device *evt = &hpet_base.channels[0].evt;
+
+		clc = (uint64_t) evt->mult * NSEC_PER_SEC;
 		do_div(clc, freq);
-		clc >>= hpet_clockevent.shift;
+		clc >>= evt->shift;
 		hpet_pie_delta = clc;
 		hpet_pie_limit = 0;
 	}
+
 	return 1;
 }
 EXPORT_SYMBOL_GPL(hpet_set_periodic_freq);
@@ -1320,8 +1313,7 @@
 		if (hpet_rtc_flags & RTC_PIE)
 			hpet_pie_count += lost_ints;
 		if (printk_ratelimit())
-			printk(KERN_WARNING "hpet1: lost %d rtc interrupts\n",
-				lost_ints);
+			pr_warn("Lost %d RTC interrupts\n", lost_ints);
 	}
 }
 
@@ -1333,8 +1325,12 @@
 	hpet_rtc_timer_reinit();
 	memset(&curr_time, 0, sizeof(struct rtc_time));
 
-	if (hpet_rtc_flags & (RTC_UIE | RTC_AIE))
-		mc146818_get_time(&curr_time);
+	if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) {
+		if (unlikely(mc146818_get_time(&curr_time) < 0)) {
+			pr_err_ratelimited("unable to read current time from RTC\n");
+			return IRQ_HANDLED;
+		}
+	}
 
 	if (hpet_rtc_flags & RTC_UIE &&
 	    curr_time.tm_sec != hpet_prev_update_sec) {
@@ -1343,8 +1339,7 @@
 		hpet_prev_update_sec = curr_time.tm_sec;
 	}
 
-	if (hpet_rtc_flags & RTC_PIE &&
-	    ++hpet_pie_count >= hpet_pie_limit) {
+	if (hpet_rtc_flags & RTC_PIE && ++hpet_pie_count >= hpet_pie_limit) {
 		rtc_int_flag |= RTC_PF;
 		hpet_pie_count = 0;
 	}
@@ -1353,7 +1348,7 @@
 	    (curr_time.tm_sec == hpet_alarm_time.tm_sec) &&
 	    (curr_time.tm_min == hpet_alarm_time.tm_min) &&
 	    (curr_time.tm_hour == hpet_alarm_time.tm_hour))
-			rtc_int_flag |= RTC_AF;
+		rtc_int_flag |= RTC_AF;
 
 	if (rtc_int_flag) {
 		rtc_int_flag |= (RTC_IRQF | (RTC_NUM_INTS << 8));

--
Gitblit v1.6.2