linux-sg2042/drivers/fpga/dfl-afu-dma-region.c

415 lines
10 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Driver for FPGA Accelerated Function Unit (AFU) DMA Region Management
*
* Copyright (C) 2017-2018 Intel Corporation, Inc.
*
* Authors:
* Wu Hao <hao.wu@intel.com>
* Xiao Guangrong <guangrong.xiao@linux.intel.com>
*/
#include <linux/dma-mapping.h>
#include <linux/sched/signal.h>
#include <linux/uaccess.h>
mm: add account_locked_vm utility function locked_vm accounting is done roughly the same way in five places, so unify them in a helper. Include the helper's caller in the debug print to distinguish between callsites. Error codes stay the same, so user-visible behavior does too. The one exception is that the -EPERM case in tce_account_locked_vm is removed because Alexey has never seen it triggered. [daniel.m.jordan@oracle.com: v3] Link: http://lkml.kernel.org/r/20190529205019.20927-1-daniel.m.jordan@oracle.com [sfr@canb.auug.org.au: fix mm/util.c] Link: http://lkml.kernel.org/r/20190524175045.26897-1-daniel.m.jordan@oracle.com Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Acked-by: Alex Williamson <alex.williamson@redhat.com> Cc: Alan Tull <atull@kernel.org> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Christoph Lameter <cl@linux.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Moritz Fischer <mdf@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Steve Sistare <steven.sistare@oracle.com> Cc: Wu Hao <hao.wu@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-17 07:30:54 +08:00
#include <linux/mm.h>
#include "dfl-afu.h"
static void put_all_pages(struct page **pages, int npages)
{
int i;
for (i = 0; i < npages; i++)
if (pages[i])
put_page(pages[i]);
}
void afu_dma_region_init(struct dfl_feature_platform_data *pdata)
{
struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata);
afu->dma_regions = RB_ROOT;
}
/**
* afu_dma_pin_pages - pin pages of given dma memory region
* @pdata: feature device platform data
* @region: dma memory region to be pinned
*
* Pin all the pages of given dfl_afu_dma_region.
* Return 0 for success or negative error code.
*/
static int afu_dma_pin_pages(struct dfl_feature_platform_data *pdata,
struct dfl_afu_dma_region *region)
{
int npages = region->length >> PAGE_SHIFT;
struct device *dev = &pdata->dev->dev;
int ret, pinned;
mm: add account_locked_vm utility function locked_vm accounting is done roughly the same way in five places, so unify them in a helper. Include the helper's caller in the debug print to distinguish between callsites. Error codes stay the same, so user-visible behavior does too. The one exception is that the -EPERM case in tce_account_locked_vm is removed because Alexey has never seen it triggered. [daniel.m.jordan@oracle.com: v3] Link: http://lkml.kernel.org/r/20190529205019.20927-1-daniel.m.jordan@oracle.com [sfr@canb.auug.org.au: fix mm/util.c] Link: http://lkml.kernel.org/r/20190524175045.26897-1-daniel.m.jordan@oracle.com Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Acked-by: Alex Williamson <alex.williamson@redhat.com> Cc: Alan Tull <atull@kernel.org> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Christoph Lameter <cl@linux.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Moritz Fischer <mdf@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Steve Sistare <steven.sistare@oracle.com> Cc: Wu Hao <hao.wu@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-17 07:30:54 +08:00
ret = account_locked_vm(current->mm, npages, true);
if (ret)
return ret;
region->pages = kcalloc(npages, sizeof(struct page *), GFP_KERNEL);
if (!region->pages) {
ret = -ENOMEM;
goto unlock_vm;
}
mm/gup: change GUP fast to use flags rather than a write 'bool' To facilitate additional options to get_user_pages_fast() change the singular write parameter to be gup_flags. This patch does not change any functionality. New functionality will follow in subsequent patches. Some of the get_user_pages_fast() call sites were unchanged because they already passed FOLL_WRITE or 0 for the write parameter. NOTE: It was suggested to change the ordering of the get_user_pages_fast() arguments to ensure that callers were converted. This breaks the current GUP call site convention of having the returned pages be the final parameter. So the suggestion was rejected. Link: http://lkml.kernel.org/r/20190328084422.29911-4-ira.weiny@intel.com Link: http://lkml.kernel.org/r/20190317183438.2057-4-ira.weiny@intel.com Signed-off-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Mike Marshall <hubcap@omnibond.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Rich Felker <dalias@libc.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 08:17:11 +08:00
pinned = get_user_pages_fast(region->user_addr, npages, FOLL_WRITE,
region->pages);
if (pinned < 0) {
ret = pinned;
goto put_pages;
} else if (pinned != npages) {
ret = -EFAULT;
goto free_pages;
}
dev_dbg(dev, "%d pages pinned\n", pinned);
return 0;
put_pages:
put_all_pages(region->pages, pinned);
free_pages:
kfree(region->pages);
unlock_vm:
mm: add account_locked_vm utility function locked_vm accounting is done roughly the same way in five places, so unify them in a helper. Include the helper's caller in the debug print to distinguish between callsites. Error codes stay the same, so user-visible behavior does too. The one exception is that the -EPERM case in tce_account_locked_vm is removed because Alexey has never seen it triggered. [daniel.m.jordan@oracle.com: v3] Link: http://lkml.kernel.org/r/20190529205019.20927-1-daniel.m.jordan@oracle.com [sfr@canb.auug.org.au: fix mm/util.c] Link: http://lkml.kernel.org/r/20190524175045.26897-1-daniel.m.jordan@oracle.com Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Acked-by: Alex Williamson <alex.williamson@redhat.com> Cc: Alan Tull <atull@kernel.org> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Christoph Lameter <cl@linux.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Moritz Fischer <mdf@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Steve Sistare <steven.sistare@oracle.com> Cc: Wu Hao <hao.wu@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-17 07:30:54 +08:00
account_locked_vm(current->mm, npages, false);
return ret;
}
/**
* afu_dma_unpin_pages - unpin pages of given dma memory region
* @pdata: feature device platform data
* @region: dma memory region to be unpinned
*
* Unpin all the pages of given dfl_afu_dma_region.
* Return 0 for success or negative error code.
*/
static void afu_dma_unpin_pages(struct dfl_feature_platform_data *pdata,
struct dfl_afu_dma_region *region)
{
long npages = region->length >> PAGE_SHIFT;
struct device *dev = &pdata->dev->dev;
put_all_pages(region->pages, npages);
kfree(region->pages);
mm: add account_locked_vm utility function locked_vm accounting is done roughly the same way in five places, so unify them in a helper. Include the helper's caller in the debug print to distinguish between callsites. Error codes stay the same, so user-visible behavior does too. The one exception is that the -EPERM case in tce_account_locked_vm is removed because Alexey has never seen it triggered. [daniel.m.jordan@oracle.com: v3] Link: http://lkml.kernel.org/r/20190529205019.20927-1-daniel.m.jordan@oracle.com [sfr@canb.auug.org.au: fix mm/util.c] Link: http://lkml.kernel.org/r/20190524175045.26897-1-daniel.m.jordan@oracle.com Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Acked-by: Alex Williamson <alex.williamson@redhat.com> Cc: Alan Tull <atull@kernel.org> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Christoph Lameter <cl@linux.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Moritz Fischer <mdf@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Steve Sistare <steven.sistare@oracle.com> Cc: Wu Hao <hao.wu@intel.com> Cc: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-17 07:30:54 +08:00
account_locked_vm(current->mm, npages, false);
dev_dbg(dev, "%ld pages unpinned\n", npages);
}
/**
* afu_dma_check_continuous_pages - check if pages are continuous
* @region: dma memory region
*
* Return true if pages of given dma memory region have continuous physical
* address, otherwise return false.
*/
static bool afu_dma_check_continuous_pages(struct dfl_afu_dma_region *region)
{
int npages = region->length >> PAGE_SHIFT;
int i;
for (i = 0; i < npages - 1; i++)
if (page_to_pfn(region->pages[i]) + 1 !=
page_to_pfn(region->pages[i + 1]))
return false;
return true;
}
/**
* dma_region_check_iova - check if memory area is fully contained in the region
* @region: dma memory region
* @iova: address of the dma memory area
* @size: size of the dma memory area
*
* Compare the dma memory area defined by @iova and @size with given dma region.
* Return true if memory area is fully contained in the region, otherwise false.
*/
static bool dma_region_check_iova(struct dfl_afu_dma_region *region,
u64 iova, u64 size)
{
if (!size && region->iova != iova)
return false;
return (region->iova <= iova) &&
(region->length + region->iova >= iova + size);
}
/**
* afu_dma_region_add - add given dma region to rbtree
* @pdata: feature device platform data
* @region: dma region to be added
*
* Return 0 for success, -EEXIST if dma region has already been added.
*
* Needs to be called with pdata->lock heold.
*/
static int afu_dma_region_add(struct dfl_feature_platform_data *pdata,
struct dfl_afu_dma_region *region)
{
struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata);
struct rb_node **new, *parent = NULL;
dev_dbg(&pdata->dev->dev, "add region (iova = %llx)\n",
(unsigned long long)region->iova);
new = &afu->dma_regions.rb_node;
while (*new) {
struct dfl_afu_dma_region *this;
this = container_of(*new, struct dfl_afu_dma_region, node);
parent = *new;
if (dma_region_check_iova(this, region->iova, region->length))
return -EEXIST;
if (region->iova < this->iova)
new = &((*new)->rb_left);
else if (region->iova > this->iova)
new = &((*new)->rb_right);
else
return -EEXIST;
}
rb_link_node(&region->node, parent, new);
rb_insert_color(&region->node, &afu->dma_regions);
return 0;
}
/**
* afu_dma_region_remove - remove given dma region from rbtree
* @pdata: feature device platform data
* @region: dma region to be removed
*
* Needs to be called with pdata->lock heold.
*/
static void afu_dma_region_remove(struct dfl_feature_platform_data *pdata,
struct dfl_afu_dma_region *region)
{
struct dfl_afu *afu;
dev_dbg(&pdata->dev->dev, "del region (iova = %llx)\n",
(unsigned long long)region->iova);
afu = dfl_fpga_pdata_get_private(pdata);
rb_erase(&region->node, &afu->dma_regions);
}
/**
* afu_dma_region_destroy - destroy all regions in rbtree
* @pdata: feature device platform data
*
* Needs to be called with pdata->lock heold.
*/
void afu_dma_region_destroy(struct dfl_feature_platform_data *pdata)
{
struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata);
struct rb_node *node = rb_first(&afu->dma_regions);
struct dfl_afu_dma_region *region;
while (node) {
region = container_of(node, struct dfl_afu_dma_region, node);
dev_dbg(&pdata->dev->dev, "del region (iova = %llx)\n",
(unsigned long long)region->iova);
rb_erase(node, &afu->dma_regions);
if (region->iova)
dma_unmap_page(dfl_fpga_pdata_to_parent(pdata),
region->iova, region->length,
DMA_BIDIRECTIONAL);
if (region->pages)
afu_dma_unpin_pages(pdata, region);
node = rb_next(node);
kfree(region);
}
}
/**
* afu_dma_region_find - find the dma region from rbtree based on iova and size
* @pdata: feature device platform data
* @iova: address of the dma memory area
* @size: size of the dma memory area
*
* It finds the dma region from the rbtree based on @iova and @size:
* - if @size == 0, it finds the dma region which starts from @iova
* - otherwise, it finds the dma region which fully contains
* [@iova, @iova+size)
* If nothing is matched returns NULL.
*
* Needs to be called with pdata->lock held.
*/
struct dfl_afu_dma_region *
afu_dma_region_find(struct dfl_feature_platform_data *pdata, u64 iova, u64 size)
{
struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata);
struct rb_node *node = afu->dma_regions.rb_node;
struct device *dev = &pdata->dev->dev;
while (node) {
struct dfl_afu_dma_region *region;
region = container_of(node, struct dfl_afu_dma_region, node);
if (dma_region_check_iova(region, iova, size)) {
dev_dbg(dev, "find region (iova = %llx)\n",
(unsigned long long)region->iova);
return region;
}
if (iova < region->iova)
node = node->rb_left;
else if (iova > region->iova)
node = node->rb_right;
else
/* the iova region is not fully covered. */
break;
}
dev_dbg(dev, "region with iova %llx and size %llx is not found\n",
(unsigned long long)iova, (unsigned long long)size);
return NULL;
}
/**
* afu_dma_region_find_iova - find the dma region from rbtree by iova
* @pdata: feature device platform data
* @iova: address of the dma region
*
* Needs to be called with pdata->lock held.
*/
static struct dfl_afu_dma_region *
afu_dma_region_find_iova(struct dfl_feature_platform_data *pdata, u64 iova)
{
return afu_dma_region_find(pdata, iova, 0);
}
/**
* afu_dma_map_region - map memory region for dma
* @pdata: feature device platform data
* @user_addr: address of the memory region
* @length: size of the memory region
* @iova: pointer of iova address
*
* Map memory region defined by @user_addr and @length, and return dma address
* of the memory region via @iova.
* Return 0 for success, otherwise error code.
*/
int afu_dma_map_region(struct dfl_feature_platform_data *pdata,
u64 user_addr, u64 length, u64 *iova)
{
struct dfl_afu_dma_region *region;
int ret;
/*
* Check Inputs, only accept page-aligned user memory region with
* valid length.
*/
if (!PAGE_ALIGNED(user_addr) || !PAGE_ALIGNED(length) || !length)
return -EINVAL;
/* Check overflow */
if (user_addr + length < user_addr)
return -EINVAL;
region = kzalloc(sizeof(*region), GFP_KERNEL);
if (!region)
return -ENOMEM;
region->user_addr = user_addr;
region->length = length;
/* Pin the user memory region */
ret = afu_dma_pin_pages(pdata, region);
if (ret) {
dev_err(&pdata->dev->dev, "failed to pin memory region\n");
goto free_region;
}
/* Only accept continuous pages, return error else */
if (!afu_dma_check_continuous_pages(region)) {
dev_err(&pdata->dev->dev, "pages are not continuous\n");
ret = -EINVAL;
goto unpin_pages;
}
/* As pages are continuous then start to do DMA mapping */
region->iova = dma_map_page(dfl_fpga_pdata_to_parent(pdata),
region->pages[0], 0,
region->length,
DMA_BIDIRECTIONAL);
if (dma_mapping_error(dfl_fpga_pdata_to_parent(pdata), region->iova)) {
dev_err(&pdata->dev->dev, "failed to map for dma\n");
ret = -EFAULT;
goto unpin_pages;
}
*iova = region->iova;
mutex_lock(&pdata->lock);
ret = afu_dma_region_add(pdata, region);
mutex_unlock(&pdata->lock);
if (ret) {
dev_err(&pdata->dev->dev, "failed to add dma region\n");
goto unmap_dma;
}
return 0;
unmap_dma:
dma_unmap_page(dfl_fpga_pdata_to_parent(pdata),
region->iova, region->length, DMA_BIDIRECTIONAL);
unpin_pages:
afu_dma_unpin_pages(pdata, region);
free_region:
kfree(region);
return ret;
}
/**
* afu_dma_unmap_region - unmap dma memory region
* @pdata: feature device platform data
* @iova: dma address of the region
*
* Unmap dma memory region based on @iova.
* Return 0 for success, otherwise error code.
*/
int afu_dma_unmap_region(struct dfl_feature_platform_data *pdata, u64 iova)
{
struct dfl_afu_dma_region *region;
mutex_lock(&pdata->lock);
region = afu_dma_region_find_iova(pdata, iova);
if (!region) {
mutex_unlock(&pdata->lock);
return -EINVAL;
}
if (region->in_use) {
mutex_unlock(&pdata->lock);
return -EBUSY;
}
afu_dma_region_remove(pdata, region);
mutex_unlock(&pdata->lock);
dma_unmap_page(dfl_fpga_pdata_to_parent(pdata),
region->iova, region->length, DMA_BIDIRECTIONAL);
afu_dma_unpin_pages(pdata, region);
kfree(region);
return 0;
}