#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/pagemap.h>
+#include <linux/pci.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/uio.h>
/* The Kernel specific component of the struct vmci_queue structure. */
struct vmci_queue_kern_if {
- struct page **page;
- struct page **header_page;
- void *va;
struct mutex __mutex; /* Protects the queue. */
struct mutex *mutex; /* Shared by producer and consumer queues. */
- bool host;
- size_t num_pages;
- bool mapped;
+ size_t num_pages; /* Number of pages incl. header. */
+ bool host; /* Host or guest? */
+ union {
+ struct {
+ dma_addr_t *pas;
+ void **vas;
+ } g; /* Used by the guest. */
+ struct {
+ struct page **page;
+ struct page **header_page;
+ } h; /* Used by the host. */
+ } u;
};
/*
struct vmci_queue *queue = q;
if (queue) {
- u64 i = DIV_ROUND_UP(size, PAGE_SIZE);
+ u64 i;
- if (queue->kernel_if->mapped) {
- vunmap(queue->kernel_if->va);
- queue->kernel_if->va = NULL;
+ /* Given size does not include header, so add in a page here. */
+ for (i = 0; i < DIV_ROUND_UP(size, PAGE_SIZE) + 1; i++) {
+ dma_free_coherent(&vmci_pdev->dev, PAGE_SIZE,
+ queue->kernel_if->u.g.vas[i],
+ queue->kernel_if->u.g.pas[i]);
}
- while (i)
- __free_page(queue->kernel_if->page[--i]);
-
- vfree(queue->q_header);
+ vfree(queue);
}
}
/*
- * Allocates kernel VA space of specified size, plus space for the
- * queue structure/kernel interface and the queue header. Allocates
- * physical pages for the queue data pages.
- *
- * PAGE m: struct vmci_queue_header (struct vmci_queue->q_header)
- * PAGE m+1: struct vmci_queue
- * PAGE m+1+q: struct vmci_queue_kern_if (struct vmci_queue->kernel_if)
- * PAGE n-size: Data pages (struct vmci_queue->kernel_if->page[])
+ * Allocates kernel queue pages of specified size with IOMMU mappings,
+ * plus space for the queue structure/kernel interface and the queue
+ * header.
*/
static void *qp_alloc_queue(u64 size, u32 flags)
{
u64 i;
struct vmci_queue *queue;
- struct vmci_queue_header *q_header;
- const u64 num_data_pages = DIV_ROUND_UP(size, PAGE_SIZE);
- const uint queue_size =
- PAGE_SIZE +
- sizeof(*queue) + sizeof(*(queue->kernel_if)) +
- num_data_pages * sizeof(*(queue->kernel_if->page));
-
- q_header = vmalloc(queue_size);
- if (!q_header)
+ const size_t num_pages = DIV_ROUND_UP(size, PAGE_SIZE) + 1;
+ const size_t pas_size = num_pages * sizeof(*queue->kernel_if->u.g.pas);
+ const size_t vas_size = num_pages * sizeof(*queue->kernel_if->u.g.vas);
+ const size_t queue_size =
+ sizeof(*queue) + sizeof(*queue->kernel_if) +
+ pas_size + vas_size;
+
+ queue = vmalloc(queue_size);
+ if (!queue)
return NULL;
- queue = (void *)q_header + PAGE_SIZE;
- queue->q_header = q_header;
+ queue->q_header = NULL;
queue->saved_header = NULL;
queue->kernel_if = (struct vmci_queue_kern_if *)(queue + 1);
- queue->kernel_if->header_page = NULL; /* Unused in guest. */
- queue->kernel_if->page = (struct page **)(queue->kernel_if + 1);
+ queue->kernel_if->mutex = NULL;
+ queue->kernel_if->num_pages = num_pages;
+ queue->kernel_if->u.g.pas = (dma_addr_t *)(queue->kernel_if + 1);
+ queue->kernel_if->u.g.vas =
+ (void **)((u8 *)queue->kernel_if->u.g.pas + pas_size);
queue->kernel_if->host = false;
- queue->kernel_if->va = NULL;
- queue->kernel_if->mapped = false;
-
- for (i = 0; i < num_data_pages; i++) {
- queue->kernel_if->page[i] = alloc_pages(GFP_KERNEL, 0);
- if (!queue->kernel_if->page[i])
- goto fail;
- }
- if (vmci_qp_pinned(flags)) {
- queue->kernel_if->va =
- vmap(queue->kernel_if->page, num_data_pages, VM_MAP,
- PAGE_KERNEL);
- if (!queue->kernel_if->va)
- goto fail;
-
- queue->kernel_if->mapped = true;
+ for (i = 0; i < num_pages; i++) {
+ queue->kernel_if->u.g.vas[i] =
+ dma_alloc_coherent(&vmci_pdev->dev, PAGE_SIZE,
+ &queue->kernel_if->u.g.pas[i],
+ GFP_KERNEL);
+ if (!queue->kernel_if->u.g.vas[i]) {
+ /* Size excl. the header. */
+ qp_free_queue(queue, i * PAGE_SIZE);
+ return NULL;
+ }
}
- return (void *)queue;
+ /* Queue header is the first page. */
+ queue->q_header = queue->kernel_if->u.g.vas[0];
- fail:
- qp_free_queue(queue, i * PAGE_SIZE);
- return NULL;
+ return queue;
}
/*
size_t bytes_copied = 0;
while (bytes_copied < size) {
- u64 page_index = (queue_offset + bytes_copied) / PAGE_SIZE;
- size_t page_offset =
+ const u64 page_index =
+ (queue_offset + bytes_copied) / PAGE_SIZE;
+ const size_t page_offset =
(queue_offset + bytes_copied) & (PAGE_SIZE - 1);
void *va;
size_t to_copy;
- if (!kernel_if->mapped)
- va = kmap(kernel_if->page[page_index]);
+ if (kernel_if->host)
+ va = kmap(kernel_if->u.h.page[page_index]);
else
- va = (void *)((u8 *)kernel_if->va +
- (page_index * PAGE_SIZE));
+ va = kernel_if->u.g.vas[page_index + 1];
+ /* Skip header. */
if (size - bytes_copied > PAGE_SIZE - page_offset)
/* Enough payload to fill up from this page. */
err = memcpy_fromiovec((u8 *)va + page_offset,
iov, to_copy);
if (err != 0) {
- kunmap(kernel_if->page[page_index]);
+ if (kernel_if->host)
+ kunmap(kernel_if->u.h.page[page_index]);
return VMCI_ERROR_INVALID_ARGS;
}
} else {
}
bytes_copied += to_copy;
- if (!kernel_if->mapped)
- kunmap(kernel_if->page[page_index]);
+ if (kernel_if->host)
+ kunmap(kernel_if->u.h.page[page_index]);
}
return VMCI_SUCCESS;
size_t bytes_copied = 0;
while (bytes_copied < size) {
- u64 page_index = (queue_offset + bytes_copied) / PAGE_SIZE;
- size_t page_offset =
+ const u64 page_index =
+ (queue_offset + bytes_copied) / PAGE_SIZE;
+ const size_t page_offset =
(queue_offset + bytes_copied) & (PAGE_SIZE - 1);
void *va;
size_t to_copy;
- if (!kernel_if->mapped)
- va = kmap(kernel_if->page[page_index]);
+ if (kernel_if->host)
+ va = kmap(kernel_if->u.h.page[page_index]);
else
- va = (void *)((u8 *)kernel_if->va +
- (page_index * PAGE_SIZE));
+ va = kernel_if->u.g.vas[page_index + 1];
+ /* Skip header. */
if (size - bytes_copied > PAGE_SIZE - page_offset)
/* Enough payload to fill up this page. */
err = memcpy_toiovec(iov, (u8 *)va + page_offset,
to_copy);
if (err != 0) {
- kunmap(kernel_if->page[page_index]);
+ if (kernel_if->host)
+ kunmap(kernel_if->u.h.page[page_index]);
return VMCI_ERROR_INVALID_ARGS;
}
} else {
}
bytes_copied += to_copy;
- if (!kernel_if->mapped)
- kunmap(kernel_if->page[page_index]);
+ if (kernel_if->host)
+ kunmap(kernel_if->u.h.page[page_index]);
}
return VMCI_SUCCESS;
return VMCI_ERROR_NO_MEM;
}
- produce_ppns[0] = page_to_pfn(vmalloc_to_page(produce_q->q_header));
- for (i = 1; i < num_produce_pages; i++) {
+ for (i = 0; i < num_produce_pages; i++) {
unsigned long pfn;
produce_ppns[i] =
- page_to_pfn(produce_q->kernel_if->page[i - 1]);
+ produce_q->kernel_if->u.g.pas[i] >> PAGE_SHIFT;
pfn = produce_ppns[i];
/* Fail allocation if PFN isn't supported by hypervisor. */
goto ppn_error;
}
- consume_ppns[0] = page_to_pfn(vmalloc_to_page(consume_q->q_header));
- for (i = 1; i < num_consume_pages; i++) {
+ for (i = 0; i < num_consume_pages; i++) {
unsigned long pfn;
consume_ppns[i] =
- page_to_pfn(consume_q->kernel_if->page[i - 1]);
+ consume_q->kernel_if->u.g.pas[i] >> PAGE_SHIFT;
pfn = consume_ppns[i];
/* Fail allocation if PFN isn't supported by hypervisor. */
const size_t num_pages = DIV_ROUND_UP(size, PAGE_SIZE) + 1;
const size_t queue_size = sizeof(*queue) + sizeof(*(queue->kernel_if));
const size_t queue_page_size =
- num_pages * sizeof(*queue->kernel_if->page);
+ num_pages * sizeof(*queue->kernel_if->u.h.page);
queue = kzalloc(queue_size + queue_page_size, GFP_KERNEL);
if (queue) {
queue->q_header = NULL;
queue->saved_header = NULL;
- queue->kernel_if =
- (struct vmci_queue_kern_if *)((u8 *)queue +
- sizeof(*queue));
+ queue->kernel_if = (struct vmci_queue_kern_if *)(queue + 1);
queue->kernel_if->host = true;
queue->kernel_if->mutex = NULL;
queue->kernel_if->num_pages = num_pages;
- queue->kernel_if->header_page =
+ queue->kernel_if->u.h.header_page =
(struct page **)((u8 *)queue + queue_size);
- queue->kernel_if->page = &queue->kernel_if->header_page[1];
- queue->kernel_if->va = NULL;
- queue->kernel_if->mapped = false;
+ queue->kernel_if->u.h.page =
+ &queue->kernel_if->u.h.header_page[1];
}
return queue;
current->mm,
(uintptr_t) produce_uva,
produce_q->kernel_if->num_pages,
- 1, 0, produce_q->kernel_if->header_page, NULL);
+ 1, 0,
+ produce_q->kernel_if->u.h.header_page, NULL);
if (retval < produce_q->kernel_if->num_pages) {
pr_warn("get_user_pages(produce) failed (retval=%d)", retval);
- qp_release_pages(produce_q->kernel_if->header_page, retval,
- false);
+ qp_release_pages(produce_q->kernel_if->u.h.header_page,
+ retval, false);
err = VMCI_ERROR_NO_MEM;
goto out;
}
current->mm,
(uintptr_t) consume_uva,
consume_q->kernel_if->num_pages,
- 1, 0, consume_q->kernel_if->header_page, NULL);
+ 1, 0,
+ consume_q->kernel_if->u.h.header_page, NULL);
if (retval < consume_q->kernel_if->num_pages) {
pr_warn("get_user_pages(consume) failed (retval=%d)", retval);
- qp_release_pages(consume_q->kernel_if->header_page, retval,
- false);
- qp_release_pages(produce_q->kernel_if->header_page,
+ qp_release_pages(consume_q->kernel_if->u.h.header_page,
+ retval, false);
+ qp_release_pages(produce_q->kernel_if->u.h.header_page,
produce_q->kernel_if->num_pages, false);
err = VMCI_ERROR_NO_MEM;
}
static void qp_host_unregister_user_memory(struct vmci_queue *produce_q,
struct vmci_queue *consume_q)
{
- qp_release_pages(produce_q->kernel_if->header_page,
+ qp_release_pages(produce_q->kernel_if->u.h.header_page,
produce_q->kernel_if->num_pages, true);
- memset(produce_q->kernel_if->header_page, 0,
- sizeof(*produce_q->kernel_if->header_page) *
+ memset(produce_q->kernel_if->u.h.header_page, 0,
+ sizeof(*produce_q->kernel_if->u.h.header_page) *
produce_q->kernel_if->num_pages);
- qp_release_pages(consume_q->kernel_if->header_page,
+ qp_release_pages(consume_q->kernel_if->u.h.header_page,
consume_q->kernel_if->num_pages, true);
- memset(consume_q->kernel_if->header_page, 0,
- sizeof(*consume_q->kernel_if->header_page) *
+ memset(consume_q->kernel_if->u.h.header_page, 0,
+ sizeof(*consume_q->kernel_if->u.h.header_page) *
consume_q->kernel_if->num_pages);
}
if (produce_q->q_header != consume_q->q_header)
return VMCI_ERROR_QUEUEPAIR_MISMATCH;
- if (produce_q->kernel_if->header_page == NULL ||
- *produce_q->kernel_if->header_page == NULL)
+ if (produce_q->kernel_if->u.h.header_page == NULL ||
+ *produce_q->kernel_if->u.h.header_page == NULL)
return VMCI_ERROR_UNAVAILABLE;
- headers[0] = *produce_q->kernel_if->header_page;
- headers[1] = *consume_q->kernel_if->header_page;
+ headers[0] = *produce_q->kernel_if->u.h.header_page;
+ headers[1] = *consume_q->kernel_if->u.h.header_page;
produce_q->q_header = vmap(headers, 2, VM_MAP, PAGE_KERNEL);
if (produce_q->q_header != NULL) {
if (result < VMCI_SUCCESS)
return result;
- /*
- * Preemptively load in the headers if non-blocking to
- * prevent blocking later.
- */
- if (entry->qp.flags & VMCI_QPFLAG_NONBLOCK) {
- result = qp_host_map_queues(entry->produce_q,
- entry->consume_q);
- if (result < VMCI_SUCCESS) {
- qp_host_unregister_user_memory(
- entry->produce_q,
- entry->consume_q);
- return result;
- }
- }
-
entry->state = VMCIQPB_ATTACHED_MEM;
} else {
entry->state = VMCIQPB_ATTACHED_NO_MEM;
return VMCI_ERROR_UNAVAILABLE;
} else {
- /*
- * For non-blocking queue pairs, we cannot rely on
- * enqueue/dequeue to map in the pages on the
- * host-side, since it may block, so we make an
- * attempt here.
- */
-
- if (flags & VMCI_QPFLAG_NONBLOCK) {
- result =
- qp_host_map_queues(entry->produce_q,
- entry->consume_q);
- if (result < VMCI_SUCCESS)
- return result;
-
- entry->qp.flags |= flags &
- (VMCI_QPFLAG_NONBLOCK | VMCI_QPFLAG_PINNED);
- }
-
/* The host side has successfully attached to a queue pair. */
entry->state = VMCIQPB_ATTACHED_MEM;
}
* Since non-blocking isn't yet implemented on the host personality we
* have no reason to acquire a spin lock. So to avoid the use of an
* unnecessary lock only acquire the mutex if we can block.
- * Note: It is assumed that QPFLAG_PINNED implies QPFLAG_NONBLOCK. Therefore
- * we can use the same locking function for access to both the queue
- * and the queue headers as it is the same logic. Assert this behvior.
*/
static void qp_lock(const struct vmci_qp *qpair)
{
- if (vmci_can_block(qpair->flags))
- qp_acquire_queue_mutex(qpair->produce_q);
+ qp_acquire_queue_mutex(qpair->produce_q);
}
/*
* Helper routine that unlocks the queue pair after calling
- * qp_lock. Respects non-blocking and pinning flags.
+ * qp_lock.
*/
static void qp_unlock(const struct vmci_qp *qpair)
{
- if (vmci_can_block(qpair->flags))
- qp_release_queue_mutex(qpair->produce_q);
+ qp_release_queue_mutex(qpair->produce_q);
}
/*
* currently not mapped, it will be attempted to do so.
*/
static int qp_map_queue_headers(struct vmci_queue *produce_q,
- struct vmci_queue *consume_q,
- bool can_block)
+ struct vmci_queue *consume_q)
{
int result;
if (NULL == produce_q->q_header || NULL == consume_q->q_header) {
- if (can_block)
- result = qp_host_map_queues(produce_q, consume_q);
- else
- result = VMCI_ERROR_QUEUEPAIR_NOT_READY;
-
+ result = qp_host_map_queues(produce_q, consume_q);
if (result < VMCI_SUCCESS)
return (produce_q->saved_header &&
consume_q->saved_header) ?
{
int result;
- result = qp_map_queue_headers(qpair->produce_q, qpair->consume_q,
- vmci_can_block(qpair->flags));
+ result = qp_map_queue_headers(qpair->produce_q, qpair->consume_q);
if (result == VMCI_SUCCESS) {
*produce_q_header = qpair->produce_q->q_header;
*consume_q_header = qpair->consume_q->q_header;
{
unsigned int generation;
- if (qpair->flags & VMCI_QPFLAG_NONBLOCK)
- return false;
-
qpair->blocked++;
generation = qpair->generation;
qp_unlock(qpair);
const u64 produce_q_size,
const void *buf,
size_t buf_size,
- vmci_memcpy_to_queue_func memcpy_to_queue,
- bool can_block)
+ vmci_memcpy_to_queue_func memcpy_to_queue)
{
s64 free_space;
u64 tail;
size_t written;
ssize_t result;
- result = qp_map_queue_headers(produce_q, consume_q, can_block);
+ result = qp_map_queue_headers(produce_q, consume_q);
if (unlikely(result != VMCI_SUCCESS))
return result;
void *buf,
size_t buf_size,
vmci_memcpy_from_queue_func memcpy_from_queue,
- bool update_consumer,
- bool can_block)
+ bool update_consumer)
{
s64 buf_ready;
u64 head;
size_t read;
ssize_t result;
- result = qp_map_queue_headers(produce_q, consume_q, can_block);
+ result = qp_map_queue_headers(produce_q, consume_q);
if (unlikely(result != VMCI_SUCCESS))
return result;
route = vmci_guest_code_active() ?
VMCI_ROUTE_AS_GUEST : VMCI_ROUTE_AS_HOST;
- /* If NONBLOCK or PINNED is set, we better be the guest personality. */
- if ((!vmci_can_block(flags) || vmci_qp_pinned(flags)) &&
- VMCI_ROUTE_AS_GUEST != route) {
- pr_devel("Not guest personality w/ NONBLOCK OR PINNED set");
+ if (flags & (VMCI_QPFLAG_NONBLOCK | VMCI_QPFLAG_PINNED)) {
+ pr_devel("NONBLOCK OR PINNED set");
return VMCI_ERROR_INVALID_ARGS;
}
- /*
- * Limit the size of pinned QPs and check sanity.
- *
- * Pinned pages implies non-blocking mode. Mutexes aren't acquired
- * when the NONBLOCK flag is set in qpair code; and also should not be
- * acquired when the PINNED flagged is set. Since pinning pages
- * implies we want speed, it makes no sense not to have NONBLOCK
- * set if PINNED is set. Hence enforce this implication.
- */
- if (vmci_qp_pinned(flags)) {
- if (vmci_can_block(flags)) {
- pr_err("Attempted to enable pinning w/o non-blocking");
- return VMCI_ERROR_INVALID_ARGS;
- }
-
- if (produce_qsize + consume_qsize > VMCI_MAX_PINNED_QP_MEMORY)
- return VMCI_ERROR_NO_RESOURCES;
- }
-
my_qpair = kzalloc(sizeof(*my_qpair), GFP_KERNEL);
if (!my_qpair)
return VMCI_ERROR_NO_MEM;
qpair->consume_q,
qpair->produce_q_size,
buf, buf_size,
- qp_memcpy_to_queue,
- vmci_can_block(qpair->flags));
+ qp_memcpy_to_queue);
if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
!qp_wait_for_ready_queue(qpair))
qpair->consume_q,
qpair->consume_q_size,
buf, buf_size,
- qp_memcpy_from_queue, true,
- vmci_can_block(qpair->flags));
+ qp_memcpy_from_queue, true);
if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
!qp_wait_for_ready_queue(qpair))
qpair->consume_q,
qpair->consume_q_size,
buf, buf_size,
- qp_memcpy_from_queue, false,
- vmci_can_block(qpair->flags));
+ qp_memcpy_from_queue, false);
if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
!qp_wait_for_ready_queue(qpair))
qpair->consume_q,
qpair->produce_q_size,
iov, iov_size,
- qp_memcpy_to_queue_iov,
- vmci_can_block(qpair->flags));
+ qp_memcpy_to_queue_iov);
if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
!qp_wait_for_ready_queue(qpair))
qpair->consume_q_size,
iov, iov_size,
qp_memcpy_from_queue_iov,
- true, vmci_can_block(qpair->flags));
+ true);
if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
!qp_wait_for_ready_queue(qpair))
qpair->consume_q_size,
iov, iov_size,
qp_memcpy_from_queue_iov,
- false, vmci_can_block(qpair->flags));
+ false);
if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
!qp_wait_for_ready_queue(qpair))
projects / firefly-linux-kernel-4.4.55.git / blobdiff