Release 4.11 drivers/hv/hv_balloon.c
/*
* Copyright (c) 2012, Microsoft Corporation.
*
* Author:
* K. Y. Srinivasan <kys@microsoft.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for more
* details.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/jiffies.h>
#include <linux/mman.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/kthread.h>
#include <linux/completion.h>
#include <linux/memory_hotplug.h>
#include <linux/memory.h>
#include <linux/notifier.h>
#include <linux/percpu_counter.h>
#include <linux/hyperv.h>
/*
* We begin with definitions supporting the Dynamic Memory protocol
* with the host.
*
* Begin protocol definitions.
*/
/*
* Protocol versions. The low word is the minor version, the high word the major
* version.
*
* History:
* Initial version 1.0
* Changed to 0.1 on 2009/03/25
* Changes to 0.2 on 2009/05/14
* Changes to 0.3 on 2009/12/03
* Changed to 1.0 on 2011/04/05
*/
#define DYNMEM_MAKE_VERSION(Major, Minor) ((__u32)(((Major) << 16) | (Minor)))
#define DYNMEM_MAJOR_VERSION(Version) ((__u32)(Version) >> 16)
#define DYNMEM_MINOR_VERSION(Version) ((__u32)(Version) & 0xff)
enum {
DYNMEM_PROTOCOL_VERSION_1 = DYNMEM_MAKE_VERSION(0, 3),
DYNMEM_PROTOCOL_VERSION_2 = DYNMEM_MAKE_VERSION(1, 0),
DYNMEM_PROTOCOL_VERSION_3 = DYNMEM_MAKE_VERSION(2, 0),
DYNMEM_PROTOCOL_VERSION_WIN7 = DYNMEM_PROTOCOL_VERSION_1,
DYNMEM_PROTOCOL_VERSION_WIN8 = DYNMEM_PROTOCOL_VERSION_2,
DYNMEM_PROTOCOL_VERSION_WIN10 = DYNMEM_PROTOCOL_VERSION_3,
DYNMEM_PROTOCOL_VERSION_CURRENT = DYNMEM_PROTOCOL_VERSION_WIN10
};
/*
* Message Types
*/
enum dm_message_type {
/*
* Version 0.3
*/
DM_ERROR = 0,
DM_VERSION_REQUEST = 1,
DM_VERSION_RESPONSE = 2,
DM_CAPABILITIES_REPORT = 3,
DM_CAPABILITIES_RESPONSE = 4,
DM_STATUS_REPORT = 5,
DM_BALLOON_REQUEST = 6,
DM_BALLOON_RESPONSE = 7,
DM_UNBALLOON_REQUEST = 8,
DM_UNBALLOON_RESPONSE = 9,
DM_MEM_HOT_ADD_REQUEST = 10,
DM_MEM_HOT_ADD_RESPONSE = 11,
DM_VERSION_03_MAX = 11,
/*
* Version 1.0.
*/
DM_INFO_MESSAGE = 12,
DM_VERSION_1_MAX = 12
};
/*
* Structures defining the dynamic memory management
* protocol.
*/
union dm_version {
struct {
__u16 minor_version;
__u16 major_version;
};
__u32 version;
}
__packed;
union dm_caps {
struct {
__u64 balloon:1;
__u64 hot_add:1;
/*
* To support guests that may have alignment
* limitations on hot-add, the guest can specify
* its alignment requirements; a value of n
* represents an alignment of 2^n in mega bytes.
*/
__u64 hot_add_alignment:4;
__u64 reservedz:58;
}
cap_bits;
__u64 caps;
}
__packed;
union dm_mem_page_range {
struct {
/*
* The PFN number of the first page in the range.
* 40 bits is the architectural limit of a PFN
* number for AMD64.
*/
__u64 start_page:40;
/*
* The number of pages in the range.
*/
__u64 page_cnt:24;
}
finfo;
__u64 page_range;
}
__packed;
/*
* The header for all dynamic memory messages:
*
* type: Type of the message.
* size: Size of the message in bytes; including the header.
* trans_id: The guest is responsible for manufacturing this ID.
*/
struct dm_header {
__u16 type;
__u16 size;
__u32 trans_id;
}
__packed;
/*
* A generic message format for dynamic memory.
* Specific message formats are defined later in the file.
*/
struct dm_message {
struct dm_header hdr;
__u8 data[]; /* enclosed message */
}
__packed;
/*
* Specific message types supporting the dynamic memory protocol.
*/
/*
* Version negotiation message. Sent from the guest to the host.
* The guest is free to try different versions until the host
* accepts the version.
*
* dm_version: The protocol version requested.
* is_last_attempt: If TRUE, this is the last version guest will request.
* reservedz: Reserved field, set to zero.
*/
struct dm_version_request {
struct dm_header hdr;
union dm_version version;
__u32 is_last_attempt:1;
__u32 reservedz:31;
}
__packed;
/*
* Version response message; Host to Guest and indicates
* if the host has accepted the version sent by the guest.
*
* is_accepted: If TRUE, host has accepted the version and the guest
* should proceed to the next stage of the protocol. FALSE indicates that
* guest should re-try with a different version.
*
* reservedz: Reserved field, set to zero.
*/
struct dm_version_response {
struct dm_header hdr;
__u64 is_accepted:1;
__u64 reservedz:63;
}
__packed;
/*
* Message reporting capabilities. This is sent from the guest to the
* host.
*/
struct dm_capabilities {
struct dm_header hdr;
union dm_caps caps;
__u64 min_page_cnt;
__u64 max_page_number;
}
__packed;
/*
* Response to the capabilities message. This is sent from the host to the
* guest. This message notifies if the host has accepted the guest's
* capabilities. If the host has not accepted, the guest must shutdown
* the service.
*
* is_accepted: Indicates if the host has accepted guest's capabilities.
* reservedz: Must be 0.
*/
struct dm_capabilities_resp_msg {
struct dm_header hdr;
__u64 is_accepted:1;
__u64 reservedz:63;
}
__packed;
/*
* This message is used to report memory pressure from the guest.
* This message is not part of any transaction and there is no
* response to this message.
*
* num_avail: Available memory in pages.
* num_committed: Committed memory in pages.
* page_file_size: The accumulated size of all page files
* in the system in pages.
* zero_free: The nunber of zero and free pages.
* page_file_writes: The writes to the page file in pages.
* io_diff: An indicator of file cache efficiency or page file activity,
* calculated as File Cache Page Fault Count - Page Read Count.
* This value is in pages.
*
* Some of these metrics are Windows specific and fortunately
* the algorithm on the host side that computes the guest memory
* pressure only uses num_committed value.
*/
struct dm_status {
struct dm_header hdr;
__u64 num_avail;
__u64 num_committed;
__u64 page_file_size;
__u64 zero_free;
__u32 page_file_writes;
__u32 io_diff;
}
__packed;
/*
* Message to ask the guest to allocate memory - balloon up message.
* This message is sent from the host to the guest. The guest may not be
* able to allocate as much memory as requested.
*
* num_pages: number of pages to allocate.
*/
struct dm_balloon {
struct dm_header hdr;
__u32 num_pages;
__u32 reservedz;
}
__packed;
/*
* Balloon response message; this message is sent from the guest
* to the host in response to the balloon message.
*
* reservedz: Reserved; must be set to zero.
* more_pages: If FALSE, this is the last message of the transaction.
* if TRUE there will atleast one more message from the guest.
*
* range_count: The number of ranges in the range array.
*
* range_array: An array of page ranges returned to the host.
*
*/
struct dm_balloon_response {
struct dm_header hdr;
__u32 reservedz;
__u32 more_pages:1;
__u32 range_count:31;
union dm_mem_page_range range_array[];
}
__packed;
/*
* Un-balloon message; this message is sent from the host
* to the guest to give guest more memory.
*
* more_pages: If FALSE, this is the last message of the transaction.
* if TRUE there will atleast one more message from the guest.
*
* reservedz: Reserved; must be set to zero.
*
* range_count: The number of ranges in the range array.
*
* range_array: An array of page ranges returned to the host.
*
*/
struct dm_unballoon_request {
struct dm_header hdr;
__u32 more_pages:1;
__u32 reservedz:31;
__u32 range_count;
union dm_mem_page_range range_array[];
}
__packed;
/*
* Un-balloon response message; this message is sent from the guest
* to the host in response to an unballoon request.
*
*/
struct dm_unballoon_response {
struct dm_header hdr;
}
__packed;
/*
* Hot add request message. Message sent from the host to the guest.
*
* mem_range: Memory range to hot add.
*
* On Linux we currently don't support this since we cannot hot add
* arbitrary granularity of memory.
*/
struct dm_hot_add {
struct dm_header hdr;
union dm_mem_page_range range;
}
__packed;
/*
* Hot add response message.
* This message is sent by the guest to report the status of a hot add request.
* If page_count is less than the requested page count, then the host should
* assume all further hot add requests will fail, since this indicates that
* the guest has hit an upper physical memory barrier.
*
* Hot adds may also fail due to low resources; in this case, the guest must
* not complete this message until the hot add can succeed, and the host must
* not send a new hot add request until the response is sent.
* If VSC fails to hot add memory DYNMEM_NUMBER_OF_UNSUCCESSFUL_HOTADD_ATTEMPTS
* times it fails the request.
*
*
* page_count: number of pages that were successfully hot added.
*
* result: result of the operation 1: success, 0: failure.
*
*/
struct dm_hot_add_response {
struct dm_header hdr;
__u32 page_count;
__u32 result;
}
__packed;
/*
* Types of information sent from host to the guest.
*/
enum dm_info_type {
INFO_TYPE_MAX_PAGE_CNT = 0,
MAX_INFO_TYPE
};
/*
* Header for the information message.
*/
struct dm_info_header {
enum dm_info_type type;
__u32 data_size;
}
__packed;
/*
* This message is sent from the host to the guest to pass
* some relevant information (win8 addition).
*
* reserved: no used.
* info_size: size of the information blob.
* info: information blob.
*/
struct dm_info_msg {
struct dm_header hdr;
__u32 reserved;
__u32 info_size;
__u8 info[];
};
/*
* End protocol definitions.
*/
/*
* State to manage hot adding memory into the guest.
* The range start_pfn : end_pfn specifies the range
* that the host has asked us to hot add. The range
* start_pfn : ha_end_pfn specifies the range that we have
* currently hot added. We hot add in multiples of 128M
* chunks; it is possible that we may not be able to bring
* online all the pages in the region. The range
* covered_start_pfn:covered_end_pfn defines the pages that can
* be brough online.
*/
struct hv_hotadd_state {
struct list_head list;
unsigned long start_pfn;
unsigned long covered_start_pfn;
unsigned long covered_end_pfn;
unsigned long ha_end_pfn;
unsigned long end_pfn;
/*
* A list of gaps.
*/
struct list_head gap_list;
};
struct hv_hotadd_gap {
struct list_head list;
unsigned long start_pfn;
unsigned long end_pfn;
};
struct balloon_state {
__u32 num_pages;
struct work_struct wrk;
};
struct hot_add_wrk {
union dm_mem_page_range ha_page_range;
union dm_mem_page_range ha_region_range;
struct work_struct wrk;
};
static bool hot_add = true;
static bool do_hot_add;
/*
* Delay reporting memory pressure by
* the specified number of seconds.
*/
static uint pressure_report_delay = 45;
/*
* The last time we posted a pressure report to host.
*/
static unsigned long last_post_time;
module_param(hot_add, bool, (S_IRUGO | S_IWUSR));
MODULE_PARM_DESC(hot_add, "If set attempt memory hot_add");
module_param(pressure_report_delay, uint, (S_IRUGO | S_IWUSR));
MODULE_PARM_DESC(pressure_report_delay, "Delay in secs in reporting pressure");
static atomic_t trans_id = ATOMIC_INIT(0);
static int dm_ring_size = (5 * PAGE_SIZE);
/*
* Driver specific state.
*/
enum hv_dm_state {
DM_INITIALIZING = 0,
DM_INITIALIZED,
DM_BALLOON_UP,
DM_BALLOON_DOWN,
DM_HOT_ADD,
DM_INIT_ERROR
};
static __u8 recv_buffer[PAGE_SIZE];
static __u8 *send_buffer;
#define PAGES_IN_2M 512
#define HA_CHUNK (32 * 1024)
struct hv_dynmem_device {
struct hv_device *dev;
enum hv_dm_state state;
struct completion host_event;
struct completion config_event;
/*
* Number of pages we have currently ballooned out.
*/
unsigned int num_pages_ballooned;
unsigned int num_pages_onlined;
unsigned int num_pages_added;
/*
* State to manage the ballooning (up) operation.
*/
struct balloon_state balloon_wrk;
/*
* State to execute the "hot-add" operation.
*/
struct hot_add_wrk ha_wrk;
/*
* This state tracks if the host has specified a hot-add
* region.
*/
bool host_specified_ha_region;
/*
* State to synchronize hot-add.
*/
struct completion ol_waitevent;
bool ha_waiting;
/*
* This thread handles hot-add
* requests from the host as well as notifying
* the host with regards to memory pressure in
* the guest.
*/
struct task_struct *thread;
/*
* Protects ha_region_list, num_pages_onlined counter and individual
* regions from ha_region_list.
*/
spinlock_t ha_lock;
/*
* A list of hot-add regions.
*/
struct list_head ha_region_list;
/*
* We start with the highest version we can support
* and downgrade based on the host; we save here the
* next version to try.
*/
__u32 next_version;
/*
* The negotiated version agreed by host.
*/
__u32 version;
};
static struct hv_dynmem_device dm_device;
static void post_status(struct hv_dynmem_device *dm);
#ifdef CONFIG_MEMORY_HOTPLUG
static int hv_memory_notifier(struct notifier_block *nb, unsigned long val,
void *v)
{
struct memory_notify *mem = (struct memory_notify *)v;
unsigned long flags;
switch (val) {
case MEM_ONLINE:
spin_lock_irqsave(&dm_device.ha_lock, flags);
dm_device.num_pages_onlined += mem->nr_pages;
spin_unlock_irqrestore(&dm_device.ha_lock, flags);
/* Fall through */
case MEM_CANCEL_ONLINE:
if (dm_device.ha_waiting) {
dm_device.ha_waiting = false;
complete(&dm_device.ol_waitevent);
}
break;
case MEM_OFFLINE:
spin_lock_irqsave(&dm_device.ha_lock, flags);
dm_device.num_pages_onlined -= mem->nr_pages;
spin_unlock_irqrestore(&dm_device.ha_lock, flags);
break;
case MEM_GOING_ONLINE:
case MEM_GOING_OFFLINE:
case MEM_CANCEL_OFFLINE:
break;
}
return NOTIFY_OK;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Vitaly Kuznetsov | 78 | 54.17% | 5 | 83.33% |
| K. Y. Srinivasan | 66 | 45.83% | 1 | 16.67% |
| Total | 144 | 100.00% | 6 | 100.00% |
static struct notifier_block hv_memory_nb = {
.notifier_call = hv_memory_notifier,
.priority = 0
};
/* Check if the particular page is backed and can be onlined and online it. */
static void hv_page_online_one(struct hv_hotadd_state *has, struct page *pg)
{
unsigned long cur_start_pgp;
unsigned long cur_end_pgp;
struct hv_hotadd_gap *gap;
cur_start_pgp = (unsigned long)pfn_to_page(has->covered_start_pfn);
cur_end_pgp = (unsigned long)pfn_to_page(has->covered_end_pfn);
/* The page is not backed. */
if (((unsigned long)pg < cur_start_pgp) ||
((unsigned long)pg >= cur_end_pgp))
return;
/* Check for gaps. */
list_for_each_entry(gap, &has->gap_list, list) {
cur_start_pgp = (unsigned long)
pfn_to_page(gap->start_pfn);
cur_end_pgp = (unsigned long)
pfn_to_page(gap->end_pfn);
if (((unsigned long)pg >= cur_start_pgp) &&
((unsigned long)pg < cur_end_pgp)) {
return;
}
}
/* This frame is currently backed; online the page. */
__online_page_set_limits(pg);
__online_page_increment_counters(pg);
__online_page_free(pg);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Vitaly Kuznetsov | 157 | 100.00% | 1 | 100.00% |
| Total | 157 | 100.00% | 1 | 100.00% |
static void hv_bring_pgs_online(struct hv_hotadd_state *has,
unsigned long start_pfn, unsigned long size)
{
int i;
pr_debug("Online %lu pages starting at pfn 0x%lx\n", size, start_pfn);
for (i = 0; i < size; i++)
hv_page_online_one(has, pfn_to_page(start_pfn + i));
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| K. Y. Srinivasan | 37 | 66.07% | 1 | 25.00% |
| Alex Ng | 9 | 16.07% | 1 | 25.00% |
| Vitaly Kuznetsov | 9 | 16.07% | 1 | 25.00% |
| Wei Yongjun | 1 | 1.79% | 1 | 25.00% |
| Total | 56 | 100.00% | 4 | 100.00% |
static void hv_mem_hot_add(unsigned long start, unsigned long size,
unsigned long pfn_count,
struct hv_hotadd_state *has)
{
int ret = 0;
int i, nid;
unsigned long start_pfn;
unsigned long processed_pfn;
unsigned long total_pfn = pfn_count;
unsigned long flags;
for (i = 0; i < (size/HA_CHUNK); i++) {
start_pfn = start + (i * HA_CHUNK);
spin_lock_irqsave(&dm_device.ha_lock, flags);
has->ha_end_pfn += HA_CHUNK;
if (total_pfn > HA_CHUNK) {
processed_pfn = HA_CHUNK;
total_pfn -= HA_CHUNK;
} else {
processed_pfn = total_pfn;
total_pfn = 0;
}
has->covered_end_pfn += processed_pfn;
spin_unlock_irqrestore(&dm_device.ha_lock, flags);
init_completion(&dm_device.ol_waitevent);
dm_device.ha_waiting = !memhp_auto_online;
nid = memory_add_physaddr_to_nid(PFN_PHYS(start_pfn));
ret = add_memory(nid, PFN_PHYS((start_pfn)),
(HA_CHUNK << PAGE_SHIFT));
if (ret) {
pr_warn("hot_add memory failed error is %d\n", ret);
if (ret == -EEXIST) {
/*
* This error indicates that the error
* is not a transient failure. This is the
* case where the guest's physical address map
* precludes hot adding memory. Stop all further
* memory hot-add.
*/
do_hot_add = false;
}
spin_lock_irqsave(&dm_device.ha_lock, flags);
has->ha_end_pfn -= HA_CHUNK;
has->covered_end_pfn -= processed_pfn;
spin_unlock_irqrestore(&dm_device.ha_lock, flags);
break;
}
/*
* Wait for the memory block to be onlined when memory onlining
* is done outside of kernel (memhp_auto_online). Since the hot
* add has succeeded, it is ok to proceed even if the pages in
* the hot added region have not been "onlined" within the
* allowed time.
*/
if (dm_device.ha_waiting)
wait_for_completion_timeout(&dm_device.ol_waitevent,
5*HZ);
post_status(&dm_device);
}
return;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| K. Y. Srinivasan | 216 | 80.00% | 4 | 50.00% |
| Vitaly Kuznetsov | 53 | 19.63% | 3 | 37.50% |
| Alex Ng | 1 | 0.37% | 1 | 12.50% |
| Total | 270 | 100.00% | 8 | 100.00% |
static void hv_online_page(struct page *pg)
{
struct hv_hotadd_state *has;
unsigned long cur_start_pgp;
unsigned long cur_end_pgp;
unsigned long flags;
spin_lock_irqsave(&dm_device.ha_lock, flags);
list_for_each_entry(has, &dm_device.ha_region_list, list) {
cur_start_pgp = (unsigned long)
pfn_to_page(has->start_pfn);
cur_end_pgp = (unsigned long)pfn_to_page(has->end_pfn);
/* The page belongs to a different HAS. */
if (((unsigned long)pg < cur_start_pgp) ||
((unsigned long)pg >= cur_end_pgp))
continue;
hv_page_online_one(has, pg);
break;
}
spin_unlock_irqrestore(&dm_device.ha_lock, flags);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| K. Y. Srinivasan | 79 | 68.10% | 1 | 33.33% |
| Vitaly Kuznetsov | 37 | 31.90% | 2 | 66.67% |
| Total | 116 | 100.00% | 3 | 100.00% |
static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt)
{
struct hv_hotadd_state *has;
struct hv_hotadd_gap *gap;
unsigned long residual, new_inc;
int ret = 0;
unsigned long flags;
spin_lock_irqsave(&dm_device.ha_lock, flags);
list_for_each_entry(has, &dm_device.ha_region_list, list) {
/*
* If the pfn range we are dealing with is not in the current
* "hot add block", move on.
*/
if (start_pfn < has->start_pfn || start_pfn >= has->end_pfn)
continue;
/*
* If the current start pfn is not where the covered_end
* is, create a gap and update covered_end_pfn.
*/
if (has->covered_end_pfn != start_pfn) {
gap = kzalloc(sizeof(struct hv_hotadd_gap), GFP_ATOMIC);
if (!gap) {
ret = -ENOMEM;
break;
}
INIT_LIST_HEAD(&gap->list);
gap->start_pfn = has->covered_end_pfn;
gap->end_pfn = start_pfn;
list_add_tail(&gap->list, &has->gap_list);
has->covered_end_pfn = start_pfn;
}
/*
* If the current hot add-request extends beyond
* our current limit; extend it.
*/
if ((start_pfn + pfn_cnt) > has->end_pfn) {
residual = (start_pfn + pfn_cnt - has->end_pfn);
/*
* Extend the region by multiples of HA_CHUNK.
*/
new_inc = (residual / HA_CHUNK) * HA_CHUNK;
if (residual % HA_CHUNK)
new_inc += HA_CHUNK;
has->end_pfn += new_inc;
}
ret = 1;
break;
}
spin_unlock_irqrestore(&dm_device.ha_lock, flags);
return ret;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Vitaly Kuznetsov | 124 | 55.11% | 3 | 75.00% |
| K. Y. Srinivasan | 101 | 44.89% | 1 | 25.00% |
| Total | 225 | 100.00% | 4 | 100.00% |
static unsigned long handle_pg_range(unsigned long pg_start,
unsigned long pg_count)
{
unsigned long start_pfn = pg_start;
unsigned long pfn_cnt = pg_count;
unsigned long size;
struct hv_hotadd_state *has;
unsigned long pgs_ol = 0;
unsigned long old_covered_state;
unsigned long res = 0, flags;
pr_debug("Hot adding %lu pages starting at pfn 0x%lx.\n", pg_count,
pg_start);
spin_lock_irqsave(&dm_device.ha_lock, flags);
list_for_each_entry(has, &dm_device.ha_region_list, list) {
/*
* If the pfn range we are dealing with is not in the current
* "hot add block", move on.
*/
if (start_pfn < has->start_pfn || start_pfn >= has->end_pfn)
continue;
old_covered_state = has->covered_end_pfn;
if (start_pfn < has->ha_end_pfn) {
/*
* This is the case where we are backing pages
* in an already hot added region. Bring
* these pages online first.
*/
pgs_ol = has->ha_end_pfn - start_pfn;
if (pgs_ol > pfn_cnt)
pgs_ol = pfn_cnt;
has->covered_end_pfn += pgs_ol;
pfn_cnt -= pgs_ol;
/*
* Check if the corresponding memory block is already
* online by checking its last previously backed page.
* In case it is we need to bring rest (which was not
* backed previously) online too.
*/
if (start_pfn > has->start_pfn &&
!PageReserved(pfn_to_page(start_pfn - 1)))
hv_bring_pgs_online(has, start_pfn, pgs_ol);
}
if ((has->ha_end_pfn < has->end_pfn) && (pfn_cnt > 0)) {
/*
* We have some residual hot add range
* that needs to be hot added; hot add
* it now. Hot add a multiple of
* of HA_CHUNK that fully covers the pages
* we have.
*/
size = (has->end_pfn - has->ha_end_pfn);
if (pfn_cnt <= size) {
size = ((pfn_cnt / HA_CHUNK) * HA_CHUNK);
if (pfn_cnt % HA_CHUNK)
size += HA_CHUNK;
} else {
pfn_cnt = size;
}
spin_unlock_irqrestore(&dm_device.ha_lock, flags);
hv_mem_hot_add(has->ha_end_pfn, size, pfn_cnt, has);
spin_lock_irqsave(&dm_device.ha_lock, flags);
}
/*
* If we managed to online any pages that were given to us,
* we declare success.
*/
res = has->covered_end_pfn - old_covered_state;
break;
}
spin_unlock_irqrestore(&dm_device.ha_lock, flags);
return res;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| K. Y. Srinivasan | 200 | 66.89% | 1 | 16.67% |
| Vitaly Kuznetsov | 90 | 30.10% | 4 | 66.67% |
| Alex Ng | 9 | 3.01% | 1 | 16.67% |
| Total | 299 | 100.00% | 6 | 100.00% |
static unsigned long process_hot_add(unsigned long pg_start,
unsigned long pfn_cnt,
unsigned long rg_start,
unsigned long rg_size)
{
struct hv_hotadd_state *ha_region = NULL;
int covered;
unsigned long flags;
if (pfn_cnt == 0)
return 0;
if (!dm_device.host_specified_ha_region) {
covered = pfn_covered(pg_start, pfn_cnt);
if (covered < 0)
return 0;
if (covered)
goto do_pg_range;
}
/*
* If the host has specified a hot-add range; deal with it first.
*/
if (rg_size != 0) {
ha_region = kzalloc(sizeof(struct hv_hotadd_state), GFP_KERNEL);
if (!ha_region)
return 0;
INIT_LIST_HEAD(&ha_region->list);
INIT_LIST_HEAD(&ha_region->gap_list);
ha_region->start_pfn = rg_start;
ha_region->ha_end_pfn = rg_start;
ha_region->covered_start_pfn = pg_start;
ha_region->covered_end_pfn = pg_start;
ha_region->end_pfn = rg_start + rg_size;
spin_lock_irqsave(&dm_device.ha_lock, flags);
list_add_tail(&ha_region->list, &dm_device.ha_region_list);
spin_unlock_irqrestore(&dm_device.ha_lock, flags);
}
do_pg_range:
/*
* Process the page range specified; bringing them
* online if possible.
*/
return handle_pg_range(pg_start, pfn_cnt);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| K. Y. Srinivasan | 131 | 64.85% | 1 | 25.00% |
| Vitaly Kuznetsov | 71 | 35.15% | 3 | 75.00% |
| Total | 202 | 100.00% | 4 | 100.00% |
#endif
static void hot_add_req(struct work_struct *dummy)
{
struct dm_hot_add_response resp;
#ifdef CONFIG_MEMORY_HOTPLUG
unsigned long pg_start, pfn_cnt;
unsigned long rg_start, rg_sz;
#endif
struct hv_dynmem_device *dm = &dm_device;
memset(&resp, 0, sizeof(struct dm_hot_add_response));
resp.hdr.type = DM_MEM_HOT_ADD_RESPONSE;
resp.hdr.size = sizeof(struct dm_hot_add_response);
#ifdef CONFIG_MEMORY_HOTPLUG
pg_start = dm->ha_wrk.ha_page_range.finfo.start_page;
pfn_cnt = dm->ha_wrk.ha_page_range.finfo.page_cnt;
rg_start = dm->ha_wrk.ha_region_range.finfo.start_page;
rg_sz = dm->ha_wrk.ha_region_range.finfo.page_cnt;
if ((rg_start == 0) && (!dm->host_specified_ha_region)) {
unsigned long region_size;
unsigned long region_start;
/*
* The host has not specified the hot-add region.
* Based on the hot-add page range being specified,
* compute a hot-add region that can cover the pages
* that need to be hot-added while ensuring the alignment
* and size requirements of Linux as it relates to hot-add.
*/
region_start = pg_start;
region_size = (pfn_cnt / HA_CHUNK) * HA_CHUNK;
if (pfn_cnt % HA_CHUNK)
region_size += HA_CHUNK;
region_start = (pg_start / HA_CHUNK) * HA_CHUNK;
rg_start = region_start;
rg_sz = region_size;
}
if (do_hot_add)
resp.page_count = process_hot_add(pg_start, pfn_cnt,
rg_start, rg_sz);
dm->num_pages_added += resp.page_count;
#endif
/*
* The result field of the response structure has the
* following semantics:
*
* 1. If all or some pages hot-added: Guest should return success.
*
* 2. If no pages could be hot-added:
*
* If the guest returns success, then the host
* will not attempt any further hot-add operations. This
* signifies a permanent failure.
*
* If the guest returns failure, then this failure will be
* treated as a transient failure and the host may retry the
* hot-add operation after some delay.
*/
if (resp.page_count > 0)
resp.result = 1;
else if (!do_hot_add)
resp.result = 1;
else
resp.result = 0;
if (!do_hot_add || (resp.page_count == 0))
pr_info("Memory hot add failed\n");
dm->state = DM_INITIALIZED;
resp.hdr.trans_id = atomic_inc_return(&trans_id);
vmbus_sendpacket(dm->dev->channel, &resp,
sizeof(struct dm_hot_add_response),
(unsigned long)NULL,
VM_PKT_DATA_INBAND, 0);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| K. Y. Srinivasan | 312 | 97.50% | 5 | 83.33% |
| Vitaly Kuznetsov | 8 | 2.50% | 1 | 16.67% |
| Total | 320 | 100.00% | 6 | 100.00% |
static void process_info(struct hv_dynmem_device *dm, struct dm_info_msg *msg)
{
struct dm_info_header *info_hdr;
info_hdr = (struct dm_info_header *)msg->info;
switch (info_hdr->type) {
case INFO_TYPE_MAX_PAGE_CNT:
if (info_hdr->data_size == sizeof(__u64)) {
__u64 *max_page_count = (__u64 *)&info_hdr[1];
pr_info("INFO_TYPE_MAX_PAGE_CNT = %llu\n",
*max_page_count);
}
break;
default:
pr_info("Received Unknown type: %d\n", info_hdr->type);
}
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| K. Y. Srinivasan | 61 | 68.54% | 2 | 66.67% |
| Alex Ng | 28 | 31.46% | 1 | 33.33% |
| Total | 89 | 100.00% | 3 | 100.00% |
static unsigned long compute_balloon_floor(void)
{
unsigned long min_pages;
#define MB2PAGES(mb) ((mb) << (20 - PAGE_SHIFT))
/* Simple continuous piecewiese linear function:
* max MiB -> min MiB gradient
* 0 0
* 16 16
* 32 24
* 128 72 (1/2)
* 512 168 (1/4)
* 2048 360 (1/8)
* 8192 744 (1/16)
* 32768 1512 (1/32)
*/
if (totalram_pages < MB2PAGES(128))
min_pages = MB2PAGES(8)