Merge tag 'for-linus-5.15b-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen fixes from Juergen Gross:

 - The first hunk of a Xen swiotlb fixup series fixing multiple minor
   issues and doing some small cleanups

 - Some further Xen related fixes avoiding WARN() splats when running as
   Xen guests or dom0

 - A Kconfig fix allowing the pvcalls frontend to be built as a module

* tag 'for-linus-5.15b-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  swiotlb-xen: drop DEFAULT_NSLABS
  swiotlb-xen: arrange to have buffer info logged
  swiotlb-xen: drop leftover __ref
  swiotlb-xen: limit init retries
  swiotlb-xen: suppress certain init retries
  swiotlb-xen: maintain slab count properly
  swiotlb-xen: fix late init retry
  swiotlb-xen: avoid double free
  xen/pvcalls: backend can be a module
  xen: fix usage of pmd_populate in mremap for pv guests
  xen: reset legacy rtc flag for PV domU
  PM: base: power: don't try to use non-existing RTC for storing data
  xen/balloon: use a kernel thread instead a workqueue

Author: torvalds

arch/x86/xen/enlighten_pv.c

@@ -1214,6 +1214,11 @@ static void __init xen_dom0_set_legacy_features(void)
 	x86_platform.legacy.rtc = 1;
 }
 
+static void __init xen_domu_set_legacy_features(void)
+{
+	x86_platform.legacy.rtc = 0;
+}
+
 /* First C function to be called on Xen boot */
 asmlinkage __visible void __init xen_start_kernel(void)
 {
@@ -1359,6 +1364,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
 		add_preferred_console("xenboot", 0, NULL);
 		if (pci_xen)
 			x86_init.pci.arch_init = pci_xen_init;
+		x86_platform.set_legacy_features =
+				xen_domu_set_legacy_features;
 	} else {
 		const struct dom0_vga_console_info *info =
 			(void *)((char *)xen_start_info +

arch/x86/xen/mmu_pv.c

@@ -1518,14 +1518,17 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
 	if (pinned) {
 		struct page *page = pfn_to_page(pfn);
 
-		if (static_branch_likely(&xen_struct_pages_ready))
+		pinned = false;
+		if (static_branch_likely(&xen_struct_pages_ready)) {
+			pinned = PagePinned(page);
 			SetPagePinned(page);
+		}
 
 		xen_mc_batch();
 
 		__set_pfn_prot(pfn, PAGE_KERNEL_RO);
 
-		if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
+		if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned)
 			__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
 
 		xen_mc_issue(PARAVIRT_LAZY_MMU);

drivers/base/power/trace.c

@@ -13,6 +13,7 @@
 #include <linux/export.h>
 #include <linux/rtc.h>
 #include <linux/suspend.h>
+#include <linux/init.h>
 
 #include <linux/mc146818rtc.h>
 
@@ -165,6 +166,9 @@ void generate_pm_trace(const void *tracedata, unsigned int user)
 	const char *file = *(const char **)(tracedata + 2);
 	unsigned int user_hash_value, file_hash_value;
 
+	if (!x86_platform.legacy.rtc)
+		return;
+
 	user_hash_value = user % USERHASH;
 	file_hash_value = hash_string(lineno, file, FILEHASH);
 	set_magic_time(user_hash_value, file_hash_value, dev_hash_value);
@@ -267,6 +271,9 @@ static struct notifier_block pm_trace_nb = {
 
 static int __init early_resume_init(void)
 {
+	if (!x86_platform.legacy.rtc)
+		return 0;
+
 	hash_value_early_read = read_magic_time();
 	register_pm_notifier(&pm_trace_nb);
 	return 0;
@@ -277,6 +284,9 @@ static int __init late_resume_init(void)
 	unsigned int val = hash_value_early_read;
 	unsigned int user, file, dev;
 
+	if (!x86_platform.legacy.rtc)
+		return 0;
+
 	user = val % USERHASH;
 	val = val / USERHASH;
 	file = val % FILEHASH;

drivers/xen/Kconfig

@@ -214,7 +214,7 @@ config XEN_PVCALLS_FRONTEND
 	  implements them.
 
 config XEN_PVCALLS_BACKEND
-	bool "XEN PV Calls backend driver"
+	tristate "XEN PV Calls backend driver"
 	depends on INET && XEN && XEN_BACKEND
 	help
 	  Experimental backend for the Xen PV Calls protocol

drivers/xen/balloon.c

@@ -43,6 +43,8 @@
 #include <linux/sched.h>
 #include <linux/cred.h>
 #include <linux/errno.h>
+#include <linux/freezer.h>
+#include <linux/kthread.h>
 #include <linux/mm.h>
 #include <linux/memblock.h>
 #include <linux/pagemap.h>
@@ -115,7 +117,7 @@ static struct ctl_table xen_root[] = {
 #define EXTENT_ORDER (fls(XEN_PFN_PER_PAGE) - 1)
 
 /*
- * balloon_process() state:
+ * balloon_thread() state:
  *
  * BP_DONE: done or nothing to do,
  * BP_WAIT: wait to be rescheduled,
@@ -130,6 +132,8 @@ enum bp_state {
 	BP_ECANCELED
 };
 
+/* Main waiting point for xen-balloon thread. */
+static DECLARE_WAIT_QUEUE_HEAD(balloon_thread_wq);
 
 static DEFINE_MUTEX(balloon_mutex);
 
@@ -144,10 +148,6 @@ static xen_pfn_t frame_list[PAGE_SIZE / sizeof(xen_pfn_t)];
 static LIST_HEAD(ballooned_pages);
 static DECLARE_WAIT_QUEUE_HEAD(balloon_wq);
 
-/* Main work function, always executed in process context. */
-static void balloon_process(struct work_struct *work);
-static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
-
 /* When ballooning out (allocating memory to return to Xen) we don't really
    want the kernel to try too hard since that can trigger the oom killer. */
 #define GFP_BALLOON \
@@ -366,7 +366,7 @@ static void xen_online_page(struct page *page, unsigned int order)
 static int xen_memory_notifier(struct notifier_block *nb, unsigned long val, void *v)
 {
 	if (val == MEM_ONLINE)
-		schedule_delayed_work(&balloon_worker, 0);
+		wake_up(&balloon_thread_wq);
 
 	return NOTIFY_OK;
 }
@@ -491,18 +491,43 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 }
 
 /*
- * As this is a work item it is guaranteed to run as a single instance only.
+ * Stop waiting if either state is not BP_EAGAIN and ballooning action is
+ * needed, or if the credit has changed while state is BP_EAGAIN.
+ */
+static bool balloon_thread_cond(enum bp_state state, long credit)
+{
+	if (state != BP_EAGAIN)
+		credit = 0;
+
+	return current_credit() != credit || kthread_should_stop();
+}
+
+/*
+ * As this is a kthread it is guaranteed to run as a single instance only.
  * We may of course race updates of the target counts (which are protected
  * by the balloon lock), or with changes to the Xen hard limit, but we will
  * recover from these in time.
  */
-static void balloon_process(struct work_struct *work)
+static int balloon_thread(void *unused)
 {
 	enum bp_state state = BP_DONE;
 	long credit;
+	unsigned long timeout;
+
+	set_freezable();
+	for (;;) {
+		if (state == BP_EAGAIN)
+			timeout = balloon_stats.schedule_delay * HZ;
+		else
+			timeout = 3600 * HZ;
+		credit = current_credit();
 
+		wait_event_interruptible_timeout(balloon_thread_wq,
+				 balloon_thread_cond(state, credit), timeout);
+
+		if (kthread_should_stop())
+			return 0;
 
-	do {
 		mutex_lock(&balloon_mutex);
 
 		credit = current_credit();
@@ -529,20 +554,15 @@ static void balloon_process(struct work_struct *work)
 		mutex_unlock(&balloon_mutex);
 
 		cond_resched();
-
-	} while (credit && state == BP_DONE);
-
-	/* Schedule more work if there is some still to be done. */
-	if (state == BP_EAGAIN)
-		schedule_delayed_work(&balloon_worker, balloon_stats.schedule_delay * HZ);
+	}
 }
 
 /* Resets the Xen limit, sets new target, and kicks off processing. */
 void balloon_set_new_target(unsigned long target)
 {
 	/* No need for lock. Not read-modify-write updates. */
 	balloon_stats.target_pages = target;
-	schedule_delayed_work(&balloon_worker, 0);
+	wake_up(&balloon_thread_wq);
 }
 EXPORT_SYMBOL_GPL(balloon_set_new_target);
 
@@ -647,7 +667,7 @@ void free_xenballooned_pages(int nr_pages, struct page **pages)
 
 	/* The balloon may be too large now. Shrink it if needed. */
 	if (current_credit())
-		schedule_delayed_work(&balloon_worker, 0);
+		wake_up(&balloon_thread_wq);
 
 	mutex_unlock(&balloon_mutex);
 }
@@ -679,6 +699,8 @@ static void __init balloon_add_region(unsigned long start_pfn,
 
 static int __init balloon_init(void)
 {
+	struct task_struct *task;
+
 	if (!xen_domain())
 		return -ENODEV;
 
@@ -722,6 +744,12 @@ static int __init balloon_init(void)
 	}
 #endif
 
+	task = kthread_run(balloon_thread, NULL, "xen-balloon");
+	if (IS_ERR(task)) {
+		pr_err("xen-balloon thread could not be started, ballooning will not work!\n");
+		return PTR_ERR(task);
+	}
+
 	/* Init the xen-balloon driver. */
 	xen_balloon_init();
 

drivers/xen/swiotlb-xen.c

@@ -106,27 +106,26 @@ static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr)
 
 static int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
 {
-	int i, rc;
-	int dma_bits;
+	int rc;
+	unsigned int order = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT);
+	unsigned int i, dma_bits = order + PAGE_SHIFT;
 	dma_addr_t dma_handle;
 	phys_addr_t p = virt_to_phys(buf);
 
-	dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;
+	BUILD_BUG_ON(IO_TLB_SEGSIZE & (IO_TLB_SEGSIZE - 1));
+	BUG_ON(nslabs % IO_TLB_SEGSIZE);
 
 	i = 0;
 	do {
-		int slabs = min(nslabs - i, (unsigned long)IO_TLB_SEGSIZE);
-
 		do {
 			rc = xen_create_contiguous_region(
-				p + (i << IO_TLB_SHIFT),
-				get_order(slabs << IO_TLB_SHIFT),
+				p + (i << IO_TLB_SHIFT), order,
 				dma_bits, &dma_handle);
 		} while (rc && dma_bits++ < MAX_DMA_BITS);
 		if (rc)
 			return rc;
 
-		i += slabs;
+		i += IO_TLB_SEGSIZE;
 	} while (i < nslabs);
 	return 0;
 }
@@ -153,9 +152,7 @@ static const char *xen_swiotlb_error(enum xen_swiotlb_err err)
 	return "";
 }
 
-#define DEFAULT_NSLABS		ALIGN(SZ_64M >> IO_TLB_SHIFT, IO_TLB_SEGSIZE)
-
-int __ref xen_swiotlb_init(void)
+int xen_swiotlb_init(void)
 {
 	enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
 	unsigned long bytes = swiotlb_size_or_default();
@@ -185,7 +182,7 @@ int __ref xen_swiotlb_init(void)
 		order--;
 	}
 	if (!start)
-		goto error;
+		goto exit;
 	if (order != get_order(bytes)) {
 		pr_warn("Warning: only able to allocate %ld MB for software IO TLB\n",
 			(PAGE_SIZE << order) >> 20);
@@ -208,15 +205,15 @@ int __ref xen_swiotlb_init(void)
 	swiotlb_set_max_segment(PAGE_SIZE);
 	return 0;
 error:
-	if (repeat--) {
+	if (nslabs > 1024 && repeat--) {
 		/* Min is 2MB */
-		nslabs = max(1024UL, (nslabs >> 1));
-		pr_info("Lowering to %luMB\n",
-			(nslabs << IO_TLB_SHIFT) >> 20);
+		nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE));
+		bytes = nslabs << IO_TLB_SHIFT;
+		pr_info("Lowering to %luMB\n", bytes >> 20);
 		goto retry;
 	}
+exit:
 	pr_err("%s (rc:%d)\n", xen_swiotlb_error(m_ret), rc);
-	free_pages((unsigned long)start, order);
 	return rc;
 }
 
@@ -244,17 +241,17 @@ void __init xen_swiotlb_init_early(void)
 	rc = xen_swiotlb_fixup(start, nslabs);
 	if (rc) {
 		memblock_free(__pa(start), PAGE_ALIGN(bytes));
-		if (repeat--) {
+		if (nslabs > 1024 && repeat--) {
 			/* Min is 2MB */
-			nslabs = max(1024UL, (nslabs >> 1));
+			nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE));
 			bytes = nslabs << IO_TLB_SHIFT;
 			pr_info("Lowering to %luMB\n", bytes >> 20);
 			goto retry;
 		}
 		panic("%s (rc:%d)", xen_swiotlb_error(XEN_SWIOTLB_EFIXUP), rc);
 	}
 
-	if (swiotlb_init_with_tbl(start, nslabs, false))
+	if (swiotlb_init_with_tbl(start, nslabs, true))
 		panic("Cannot allocate SWIOTLB buffer");
 	swiotlb_set_max_segment(PAGE_SIZE);
 }