Commit 0815d5cc authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'for-linus-6.9-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip 

Pull xen updates from Juergen Gross:

 - Xen event channel handling fix for a regression with a rare kernel
   config and some added hardening

 - better support of running Xen dom0 in PVH mode

 - a cleanup for the xen grant-dma-iommu driver

* tag 'for-linus-6.9-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/events: increment refcnt only if event channel is refcounted
  xen/evtchn: avoid WARN() when unbinding an event channel
  x86/xen: attempt to inflate the memory balloon on PVH
  xen/grant-dma-iommu: Convert to platform remove callback returning void
parents b3603fcb d277f9d8

arch/x86/include/asm/xen/hypervisor.h

+5 −0
Original line number Diff line number Diff line
@@ -62,6 +62,11 @@ void xen_arch_unregister_cpu(int num); 
#ifdef CONFIG_PVH

void __init xen_pvh_init(struct boot_params *boot_params);

void __init mem_map_via_hcall(struct boot_params *boot_params_p);

#ifdef CONFIG_XEN_PVH

void __init xen_reserve_extra_memory(struct boot_params *bootp);

#else

static inline void xen_reserve_extra_memory(struct boot_params *bootp) { }

#endif

#endif



/* Lazy mode for batching updates / context switch */

arch/x86/platform/pvh/enlighten.c

+3 −0
Original line number Diff line number Diff line
@@ -75,6 +75,9 @@ static void __init init_pvh_bootparams(bool xen_guest) 
	} else

		xen_raw_printk("Warning: Can fit ISA range into e820\n");



	if (xen_guest)

		xen_reserve_extra_memory(&pvh_bootparams);



	pvh_bootparams.hdr.cmd_line_ptr =

		pvh_start_info.cmdline_paddr;

arch/x86/xen/enlighten.c

+32 −0
Original line number Diff line number Diff line
@@ -6,6 +6,7 @@ 
#include <linux/console.h>

#include <linux/cpu.h>

#include <linux/kexec.h>

#include <linux/memblock.h>

#include <linux/slab.h>

#include <linux/panic_notifier.h>
@@ -350,3 +351,34 @@ void xen_arch_unregister_cpu(int num) 
}

EXPORT_SYMBOL(xen_arch_unregister_cpu);

#endif



/* Amount of extra memory space we add to the e820 ranges */

struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;



void __init xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns)

{

	unsigned int i;



	/*

	 * No need to check for zero size, should happen rarely and will only

	 * write a new entry regarded to be unused due to zero size.

	 */

	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {

		/* Add new region. */

		if (xen_extra_mem[i].n_pfns == 0) {

			xen_extra_mem[i].start_pfn = start_pfn;

			xen_extra_mem[i].n_pfns = n_pfns;

			break;

		}

		/* Append to existing region. */

		if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns ==

		    start_pfn) {

			xen_extra_mem[i].n_pfns += n_pfns;

			break;

		}

	}

	if (i == XEN_EXTRA_MEM_MAX_REGIONS)

		printk(KERN_WARNING "Warning: not enough extra memory regions\n");



	memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));

}

arch/x86/xen/enlighten_pvh.c

+68 −0
Original line number Diff line number Diff line 
// SPDX-License-Identifier: GPL-2.0

#include <linux/acpi.h>

#include <linux/export.h>

#include <linux/mm.h>



#include <xen/hvc-console.h>
@@ -73,3 +74,70 @@ void __init mem_map_via_hcall(struct boot_params *boot_params_p) 
	}

	boot_params_p->e820_entries = memmap.nr_entries;

}



/*

 * Reserve e820 UNUSABLE regions to inflate the memory balloon.

 *

 * On PVH dom0 the host memory map is used, RAM regions available to dom0 are

 * located as the same place as in the native memory map, but since dom0 gets

 * less memory than the total amount of host RAM the ranges that can't be

 * populated are converted from RAM -> UNUSABLE.  Use such regions (up to the

 * ratio signaled in EXTRA_MEM_RATIO) in order to inflate the balloon driver at

 * boot.  Doing so prevents the guest (even if just temporary) from using holes

 * in the memory map in order to map grants or foreign addresses, and

 * hopefully limits the risk of a clash with a device MMIO region.  Ideally the

 * hypervisor should notify us which memory ranges are suitable for creating

 * foreign mappings, but that's not yet implemented.

 */

void __init xen_reserve_extra_memory(struct boot_params *bootp)

{

	unsigned int i, ram_pages = 0, extra_pages;



	for (i = 0; i < bootp->e820_entries; i++) {

		struct boot_e820_entry *e = &bootp->e820_table[i];



		if (e->type != E820_TYPE_RAM)

			continue;

		ram_pages += PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr);

	}



	/* Max amount of extra memory. */

	extra_pages = EXTRA_MEM_RATIO * ram_pages;



	/*

	 * Convert UNUSABLE ranges to RAM and reserve them for foreign mapping

	 * purposes.

	 */

	for (i = 0; i < bootp->e820_entries && extra_pages; i++) {

		struct boot_e820_entry *e = &bootp->e820_table[i];

		unsigned long pages;



		if (e->type != E820_TYPE_UNUSABLE)

			continue;



		pages = min(extra_pages,

			PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr));



		if (pages != (PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr))) {

			struct boot_e820_entry *next;



			if (bootp->e820_entries ==

			    ARRAY_SIZE(bootp->e820_table))

				/* No space left to split - skip region. */

				continue;



			/* Split entry. */

			next = e + 1;

			memmove(next, e,

				(bootp->e820_entries - i) * sizeof(*e));

			bootp->e820_entries++;

			next->addr = PAGE_ALIGN(e->addr) + PFN_PHYS(pages);

			e->size = next->addr - e->addr;

			next->size -= e->size;

		}

		e->type = E820_TYPE_RAM;

		extra_pages -= pages;



		xen_add_extra_mem(PFN_UP(e->addr), pages);

	}

}

arch/x86/xen/setup.c

+0 −44
Original line number Diff line number Diff line
@@ -38,9 +38,6 @@ 


#define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024)



/* Amount of extra memory space we add to the e820 ranges */

struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;



/* Number of pages released from the initial allocation. */

unsigned long xen_released_pages;
@@ -64,18 +61,6 @@ static struct { 
} xen_remap_buf __initdata __aligned(PAGE_SIZE);

static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY;



/*

 * The maximum amount of extra memory compared to the base size.  The

 * main scaling factor is the size of struct page.  At extreme ratios

 * of base:extra, all the base memory can be filled with page

 * structures for the extra memory, leaving no space for anything

 * else.

 *

 * 10x seems like a reasonable balance between scaling flexibility and

 * leaving a practically usable system.

 */

#define EXTRA_MEM_RATIO		(10)



static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB);



static void __init xen_parse_512gb(void)
@@ -96,35 +81,6 @@ static void __init xen_parse_512gb(void) 
	xen_512gb_limit = val;

}



static void __init xen_add_extra_mem(unsigned long start_pfn,

				     unsigned long n_pfns)

{

	int i;



	/*

	 * No need to check for zero size, should happen rarely and will only

	 * write a new entry regarded to be unused due to zero size.

	 */

	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {

		/* Add new region. */

		if (xen_extra_mem[i].n_pfns == 0) {

			xen_extra_mem[i].start_pfn = start_pfn;

			xen_extra_mem[i].n_pfns = n_pfns;

			break;

		}

		/* Append to existing region. */

		if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns ==

		    start_pfn) {

			xen_extra_mem[i].n_pfns += n_pfns;

			break;

		}

	}

	if (i == XEN_EXTRA_MEM_MAX_REGIONS)

		printk(KERN_WARNING "Warning: not enough extra memory regions\n");



	memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));

}



static void __init xen_del_extra_mem(unsigned long start_pfn,

				     unsigned long n_pfns)

{