linux/drivers/iommu/s390-iommu.c

798 lines
19 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 14:07:57 +00:00
// SPDX-License-Identifier: GPL-2.0
/*
* IOMMU API for s390 PCI devices
*
* Copyright IBM Corp. 2015
* Author(s): Gerald Schaefer <gerald.schaefer@de.ibm.com>
*/
#include <linux/pci.h>
#include <linux/iommu.h>
#include <linux/iommu-helper.h>
#include <linux/sizes.h>
#include <linux/rculist.h>
#include <linux/rcupdate.h>
#include <asm/pci_dma.h>
#include "dma-iommu.h"
static const struct iommu_ops s390_iommu_ops;
static struct kmem_cache *dma_region_table_cache;
static struct kmem_cache *dma_page_table_cache;
static u64 s390_iommu_aperture;
static u32 s390_iommu_aperture_factor = 1;
struct s390_domain {
struct iommu_domain domain;
struct list_head devices;
struct zpci_iommu_ctrs ctrs;
unsigned long *dma_table;
spinlock_t list_lock;
struct rcu_head rcu;
};
static inline unsigned int calc_rtx(dma_addr_t ptr)
{
return ((unsigned long)ptr >> ZPCI_RT_SHIFT) & ZPCI_INDEX_MASK;
}
static inline unsigned int calc_sx(dma_addr_t ptr)
{
return ((unsigned long)ptr >> ZPCI_ST_SHIFT) & ZPCI_INDEX_MASK;
}
static inline unsigned int calc_px(dma_addr_t ptr)
{
return ((unsigned long)ptr >> PAGE_SHIFT) & ZPCI_PT_MASK;
}
static inline void set_pt_pfaa(unsigned long *entry, phys_addr_t pfaa)
{
*entry &= ZPCI_PTE_FLAG_MASK;
*entry |= (pfaa & ZPCI_PTE_ADDR_MASK);
}
static inline void set_rt_sto(unsigned long *entry, phys_addr_t sto)
{
*entry &= ZPCI_RTE_FLAG_MASK;
*entry |= (sto & ZPCI_RTE_ADDR_MASK);
*entry |= ZPCI_TABLE_TYPE_RTX;
}
static inline void set_st_pto(unsigned long *entry, phys_addr_t pto)
{
*entry &= ZPCI_STE_FLAG_MASK;
*entry |= (pto & ZPCI_STE_ADDR_MASK);
*entry |= ZPCI_TABLE_TYPE_SX;
}
static inline void validate_rt_entry(unsigned long *entry)
{
*entry &= ~ZPCI_TABLE_VALID_MASK;
*entry &= ~ZPCI_TABLE_OFFSET_MASK;
*entry |= ZPCI_TABLE_VALID;
*entry |= ZPCI_TABLE_LEN_RTX;
}
static inline void validate_st_entry(unsigned long *entry)
{
*entry &= ~ZPCI_TABLE_VALID_MASK;
*entry |= ZPCI_TABLE_VALID;
}
static inline void invalidate_pt_entry(unsigned long *entry)
{
WARN_ON_ONCE((*entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_INVALID);
*entry &= ~ZPCI_PTE_VALID_MASK;
*entry |= ZPCI_PTE_INVALID;
}
static inline void validate_pt_entry(unsigned long *entry)
{
WARN_ON_ONCE((*entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID);
*entry &= ~ZPCI_PTE_VALID_MASK;
*entry |= ZPCI_PTE_VALID;
}
static inline void entry_set_protected(unsigned long *entry)
{
*entry &= ~ZPCI_TABLE_PROT_MASK;
*entry |= ZPCI_TABLE_PROTECTED;
}
static inline void entry_clr_protected(unsigned long *entry)
{
*entry &= ~ZPCI_TABLE_PROT_MASK;
*entry |= ZPCI_TABLE_UNPROTECTED;
}
static inline int reg_entry_isvalid(unsigned long entry)
{
return (entry & ZPCI_TABLE_VALID_MASK) == ZPCI_TABLE_VALID;
}
static inline int pt_entry_isvalid(unsigned long entry)
{
return (entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID;
}
static inline unsigned long *get_rt_sto(unsigned long entry)
{
if ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_RTX)
return phys_to_virt(entry & ZPCI_RTE_ADDR_MASK);
else
return NULL;
}
static inline unsigned long *get_st_pto(unsigned long entry)
{
if ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_SX)
return phys_to_virt(entry & ZPCI_STE_ADDR_MASK);
else
return NULL;
}
static int __init dma_alloc_cpu_table_caches(void)
{
dma_region_table_cache = kmem_cache_create("PCI_DMA_region_tables",
ZPCI_TABLE_SIZE,
ZPCI_TABLE_ALIGN,
0, NULL);
if (!dma_region_table_cache)
return -ENOMEM;
dma_page_table_cache = kmem_cache_create("PCI_DMA_page_tables",
ZPCI_PT_SIZE,
ZPCI_PT_ALIGN,
0, NULL);
if (!dma_page_table_cache) {
kmem_cache_destroy(dma_region_table_cache);
return -ENOMEM;
}
return 0;
}
static unsigned long *dma_alloc_cpu_table(gfp_t gfp)
{
unsigned long *table, *entry;
table = kmem_cache_alloc(dma_region_table_cache, gfp);
if (!table)
return NULL;
for (entry = table; entry < table + ZPCI_TABLE_ENTRIES; entry++)
*entry = ZPCI_TABLE_INVALID;
return table;
}
static void dma_free_cpu_table(void *table)
{
kmem_cache_free(dma_region_table_cache, table);
}
static void dma_free_page_table(void *table)
{
kmem_cache_free(dma_page_table_cache, table);
}
static void dma_free_seg_table(unsigned long entry)
{
unsigned long *sto = get_rt_sto(entry);
int sx;
for (sx = 0; sx < ZPCI_TABLE_ENTRIES; sx++)
if (reg_entry_isvalid(sto[sx]))
dma_free_page_table(get_st_pto(sto[sx]));
dma_free_cpu_table(sto);
}
static void dma_cleanup_tables(unsigned long *table)
{
int rtx;
if (!table)
return;
for (rtx = 0; rtx < ZPCI_TABLE_ENTRIES; rtx++)
if (reg_entry_isvalid(table[rtx]))
dma_free_seg_table(table[rtx]);
dma_free_cpu_table(table);
}
static unsigned long *dma_alloc_page_table(gfp_t gfp)
{
unsigned long *table, *entry;
table = kmem_cache_alloc(dma_page_table_cache, gfp);
if (!table)
return NULL;
for (entry = table; entry < table + ZPCI_PT_ENTRIES; entry++)
*entry = ZPCI_PTE_INVALID;
return table;
}
static unsigned long *dma_get_seg_table_origin(unsigned long *rtep, gfp_t gfp)
{
unsigned long old_rte, rte;
unsigned long *sto;
rte = READ_ONCE(*rtep);
if (reg_entry_isvalid(rte)) {
sto = get_rt_sto(rte);
} else {
sto = dma_alloc_cpu_table(gfp);
if (!sto)
return NULL;
set_rt_sto(&rte, virt_to_phys(sto));
validate_rt_entry(&rte);
entry_clr_protected(&rte);
old_rte = cmpxchg(rtep, ZPCI_TABLE_INVALID, rte);
if (old_rte != ZPCI_TABLE_INVALID) {
/* Somone else was faster, use theirs */
dma_free_cpu_table(sto);
sto = get_rt_sto(old_rte);
}
}
return sto;
}
static unsigned long *dma_get_page_table_origin(unsigned long *step, gfp_t gfp)
{
unsigned long old_ste, ste;
unsigned long *pto;
ste = READ_ONCE(*step);
if (reg_entry_isvalid(ste)) {
pto = get_st_pto(ste);
} else {
pto = dma_alloc_page_table(gfp);
if (!pto)
return NULL;
set_st_pto(&ste, virt_to_phys(pto));
validate_st_entry(&ste);
entry_clr_protected(&ste);
old_ste = cmpxchg(step, ZPCI_TABLE_INVALID, ste);
if (old_ste != ZPCI_TABLE_INVALID) {
/* Somone else was faster, use theirs */
dma_free_page_table(pto);
pto = get_st_pto(old_ste);
}
}
return pto;
}
static unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr, gfp_t gfp)
{
unsigned long *sto, *pto;
unsigned int rtx, sx, px;
rtx = calc_rtx(dma_addr);
sto = dma_get_seg_table_origin(&rto[rtx], gfp);
if (!sto)
return NULL;
sx = calc_sx(dma_addr);
pto = dma_get_page_table_origin(&sto[sx], gfp);
if (!pto)
return NULL;
px = calc_px(dma_addr);
return &pto[px];
}
static void dma_update_cpu_trans(unsigned long *ptep, phys_addr_t page_addr, int flags)
{
unsigned long pte;
pte = READ_ONCE(*ptep);
if (flags & ZPCI_PTE_INVALID) {
invalidate_pt_entry(&pte);
} else {
set_pt_pfaa(&pte, page_addr);
validate_pt_entry(&pte);
}
if (flags & ZPCI_TABLE_PROTECTED)
entry_set_protected(&pte);
else
entry_clr_protected(&pte);
xchg(ptep, pte);
}
static struct s390_domain *to_s390_domain(struct iommu_domain *dom)
{
return container_of(dom, struct s390_domain, domain);
}
static bool s390_iommu_capable(struct device *dev, enum iommu_cap cap)
{
struct zpci_dev *zdev = to_zpci_dev(dev);
switch (cap) {
case IOMMU_CAP_CACHE_COHERENCY:
return true;
case IOMMU_CAP_DEFERRED_FLUSH:
return zdev->pft != PCI_FUNC_TYPE_ISM;
default:
return false;
}
}
static struct iommu_domain *s390_domain_alloc_paging(struct device *dev)
{
struct s390_domain *s390_domain;
s390_domain = kzalloc(sizeof(*s390_domain), GFP_KERNEL);
if (!s390_domain)
return NULL;
s390_domain->dma_table = dma_alloc_cpu_table(GFP_KERNEL);
if (!s390_domain->dma_table) {
kfree(s390_domain);
return NULL;
}
2022-10-25 11:56:54 +00:00
s390_domain->domain.geometry.force_aperture = true;
s390_domain->domain.geometry.aperture_start = 0;
s390_domain->domain.geometry.aperture_end = ZPCI_TABLE_SIZE_RT - 1;
spin_lock_init(&s390_domain->list_lock);
INIT_LIST_HEAD_RCU(&s390_domain->devices);
return &s390_domain->domain;
}
static void s390_iommu_rcu_free_domain(struct rcu_head *head)
{
struct s390_domain *s390_domain = container_of(head, struct s390_domain, rcu);
dma_cleanup_tables(s390_domain->dma_table);
kfree(s390_domain);
}
static void s390_domain_free(struct iommu_domain *domain)
{
struct s390_domain *s390_domain = to_s390_domain(domain);
rcu_read_lock();
WARN_ON(!list_empty(&s390_domain->devices));
rcu_read_unlock();
call_rcu(&s390_domain->rcu, s390_iommu_rcu_free_domain);
}
static void s390_iommu_detach_device(struct iommu_domain *domain,
struct device *dev)
{
struct s390_domain *s390_domain = to_s390_domain(domain);
struct zpci_dev *zdev = to_zpci_dev(dev);
unsigned long flags;
spin_lock_irqsave(&s390_domain->list_lock, flags);
list_del_rcu(&zdev->iommu_list);
spin_unlock_irqrestore(&s390_domain->list_lock, flags);
zpci_unregister_ioat(zdev, 0);
zdev->s390_domain = NULL;
zdev->dma_table = NULL;
}
static int s390_iommu_attach_device(struct iommu_domain *domain,
struct device *dev)
{
struct s390_domain *s390_domain = to_s390_domain(domain);
struct zpci_dev *zdev = to_zpci_dev(dev);
unsigned long flags;
u8 status;
2022-10-25 11:56:54 +00:00
int cc;
if (!zdev)
return -ENODEV;
2022-10-25 11:56:54 +00:00
if (WARN_ON(domain->geometry.aperture_start > zdev->end_dma ||
domain->geometry.aperture_end < zdev->start_dma))
return -EINVAL;
if (zdev->s390_domain)
s390_iommu_detach_device(&zdev->s390_domain->domain, dev);
cc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
virt_to_phys(s390_domain->dma_table), &status);
/*
* If the device is undergoing error recovery the reset code
* will re-establish the new domain.
*/
if (cc && status != ZPCI_PCI_ST_FUNC_NOT_AVAIL)
return -EIO;
2022-10-25 11:56:54 +00:00
zdev->dma_table = s390_domain->dma_table;
zdev->s390_domain = s390_domain;
2022-10-25 11:56:54 +00:00
spin_lock_irqsave(&s390_domain->list_lock, flags);
list_add_rcu(&zdev->iommu_list, &s390_domain->devices);
spin_unlock_irqrestore(&s390_domain->list_lock, flags);
return 0;
}
2022-10-25 11:56:54 +00:00
static void s390_iommu_get_resv_regions(struct device *dev,
struct list_head *list)
{
struct zpci_dev *zdev = to_zpci_dev(dev);
struct iommu_resv_region *region;
if (zdev->start_dma) {
region = iommu_alloc_resv_region(0, zdev->start_dma, 0,
IOMMU_RESV_RESERVED, GFP_KERNEL);
if (!region)
return;
list_add_tail(&region->list, list);
}
if (zdev->end_dma < ZPCI_TABLE_SIZE_RT - 1) {
region = iommu_alloc_resv_region(zdev->end_dma + 1,
ZPCI_TABLE_SIZE_RT - zdev->end_dma - 1,
0, IOMMU_RESV_RESERVED, GFP_KERNEL);
if (!region)
return;
list_add_tail(&region->list, list);
}
}
static struct iommu_device *s390_iommu_probe_device(struct device *dev)
{
struct zpci_dev *zdev;
if (!dev_is_pci(dev))
return ERR_PTR(-ENODEV);
zdev = to_zpci_dev(dev);
2022-10-25 11:56:54 +00:00
if (zdev->start_dma > zdev->end_dma ||
zdev->start_dma > ZPCI_TABLE_SIZE_RT - 1)
return ERR_PTR(-EINVAL);
if (zdev->end_dma > ZPCI_TABLE_SIZE_RT - 1)
zdev->end_dma = ZPCI_TABLE_SIZE_RT - 1;
iommu/dma: Allow a single FQ in addition to per-CPU FQs In some virtualized environments, including s390 paged memory guests, IOTLB flushes are used to update IOMMU shadow tables. Due to this, they are much more expensive than in typical bare metal environments or non-paged s390 guests. In addition they may parallelize poorly in virtualized environments. This changes the trade off for flushing IOVAs such that minimizing the number of IOTLB flushes trumps any benefit of cheaper queuing operations or increased paralellism. In this scenario per-CPU flush queues pose several problems. Firstly per-CPU memory is often quite limited prohibiting larger queues. Secondly collecting IOVAs per-CPU but flushing via a global timeout reduces the number of IOVAs flushed for each timeout especially on s390 where PCI interrupts may not be bound to a specific CPU. Let's introduce a single flush queue mode that reuses the same queue logic but only allocates a single global queue. This mode is selected by dma-iommu if a newly introduced .shadow_on_flush flag is set in struct dev_iommu. As a first user the s390 IOMMU driver sets this flag during probe_device. With the unchanged small FQ size and timeouts this setting is worse than per-CPU queues but a follow up patch will make the FQ size and timeout variable. Together this allows the common IOVA flushing code to more closely resemble the global flush behavior used on s390's previous internal DMA API implementation. Link: https://lore.kernel.org/all/9a466109-01c5-96b0-bf03-304123f435ee@arm.com/ Acked-by: Robin Murphy <robin.murphy@arm.com> Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com> #s390 Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com> Link: https://lore.kernel.org/r/20230928-dma_iommu-v13-5-9e5fc4dacc36@linux.ibm.com Signed-off-by: Joerg Roedel <jroedel@suse.de>
2023-09-28 14:31:39 +00:00
if (zdev->tlb_refresh)
dev->iommu->shadow_on_flush = 1;
return &zdev->iommu_dev;
}
static void s390_iommu_release_device(struct device *dev)
{
struct zpci_dev *zdev = to_zpci_dev(dev);
/*
* release_device is expected to detach any domain currently attached
* to the device, but keep it attached to other devices in the group.
*/
if (zdev)
s390_iommu_detach_device(&zdev->s390_domain->domain, dev);
}
static int zpci_refresh_all(struct zpci_dev *zdev)
{
return zpci_refresh_trans((u64)zdev->fh << 32, zdev->start_dma,
zdev->end_dma - zdev->start_dma + 1);
}
static void s390_iommu_flush_iotlb_all(struct iommu_domain *domain)
{
struct s390_domain *s390_domain = to_s390_domain(domain);
struct zpci_dev *zdev;
rcu_read_lock();
list_for_each_entry_rcu(zdev, &s390_domain->devices, iommu_list) {
atomic64_inc(&s390_domain->ctrs.global_rpcits);
zpci_refresh_all(zdev);
}
rcu_read_unlock();
}
static void s390_iommu_iotlb_sync(struct iommu_domain *domain,
struct iommu_iotlb_gather *gather)
{
struct s390_domain *s390_domain = to_s390_domain(domain);
size_t size = gather->end - gather->start + 1;
struct zpci_dev *zdev;
/* If gather was never added to there is nothing to flush */
if (!gather->end)
return;
rcu_read_lock();
list_for_each_entry_rcu(zdev, &s390_domain->devices, iommu_list) {
atomic64_inc(&s390_domain->ctrs.sync_rpcits);
zpci_refresh_trans((u64)zdev->fh << 32, gather->start,
size);
}
rcu_read_unlock();
}
static int s390_iommu_iotlb_sync_map(struct iommu_domain *domain,
unsigned long iova, size_t size)
{
struct s390_domain *s390_domain = to_s390_domain(domain);
struct zpci_dev *zdev;
int ret = 0;
rcu_read_lock();
list_for_each_entry_rcu(zdev, &s390_domain->devices, iommu_list) {
if (!zdev->tlb_refresh)
continue;
atomic64_inc(&s390_domain->ctrs.sync_map_rpcits);
ret = zpci_refresh_trans((u64)zdev->fh << 32,
iova, size);
/*
* let the hypervisor discover invalidated entries
* allowing it to free IOVAs and unpin pages
*/
if (ret == -ENOMEM) {
ret = zpci_refresh_all(zdev);
if (ret)
break;
}
}
rcu_read_unlock();
return ret;
}
static int s390_iommu_validate_trans(struct s390_domain *s390_domain,
phys_addr_t pa, dma_addr_t dma_addr,
unsigned long nr_pages, int flags,
gfp_t gfp)
{
phys_addr_t page_addr = pa & PAGE_MASK;
unsigned long *entry;
unsigned long i;
int rc;
for (i = 0; i < nr_pages; i++) {
entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr,
gfp);
if (unlikely(!entry)) {
rc = -ENOMEM;
goto undo_cpu_trans;
}
dma_update_cpu_trans(entry, page_addr, flags);
page_addr += PAGE_SIZE;
dma_addr += PAGE_SIZE;
}
return 0;
undo_cpu_trans:
while (i-- > 0) {
dma_addr -= PAGE_SIZE;
entry = dma_walk_cpu_trans(s390_domain->dma_table,
dma_addr, gfp);
if (!entry)
break;
dma_update_cpu_trans(entry, 0, ZPCI_PTE_INVALID);
}
return rc;
}
static int s390_iommu_invalidate_trans(struct s390_domain *s390_domain,
dma_addr_t dma_addr, unsigned long nr_pages)
{
unsigned long *entry;
unsigned long i;
int rc = 0;
for (i = 0; i < nr_pages; i++) {
entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr,
GFP_ATOMIC);
if (unlikely(!entry)) {
rc = -EINVAL;
break;
}
dma_update_cpu_trans(entry, 0, ZPCI_PTE_INVALID);
dma_addr += PAGE_SIZE;
}
return rc;
}
static int s390_iommu_map_pages(struct iommu_domain *domain,
unsigned long iova, phys_addr_t paddr,
size_t pgsize, size_t pgcount,
int prot, gfp_t gfp, size_t *mapped)
{
struct s390_domain *s390_domain = to_s390_domain(domain);
size_t size = pgcount << __ffs(pgsize);
int flags = ZPCI_PTE_VALID, rc = 0;
if (pgsize != SZ_4K)
return -EINVAL;
if (iova < s390_domain->domain.geometry.aperture_start ||
(iova + size - 1) > s390_domain->domain.geometry.aperture_end)
return -EINVAL;
if (!IS_ALIGNED(iova | paddr, pgsize))
return -EINVAL;
if (!(prot & IOMMU_WRITE))
flags |= ZPCI_TABLE_PROTECTED;
rc = s390_iommu_validate_trans(s390_domain, paddr, iova,
pgcount, flags, gfp);
if (!rc) {
*mapped = size;
atomic64_add(pgcount, &s390_domain->ctrs.mapped_pages);
}
return rc;
}
static phys_addr_t s390_iommu_iova_to_phys(struct iommu_domain *domain,
dma_addr_t iova)
{
struct s390_domain *s390_domain = to_s390_domain(domain);
unsigned long *rto, *sto, *pto;
unsigned long ste, pte, rte;
unsigned int rtx, sx, px;
phys_addr_t phys = 0;
if (iova < domain->geometry.aperture_start ||
iova > domain->geometry.aperture_end)
return 0;
rtx = calc_rtx(iova);
sx = calc_sx(iova);
px = calc_px(iova);
rto = s390_domain->dma_table;
rte = READ_ONCE(rto[rtx]);
if (reg_entry_isvalid(rte)) {
sto = get_rt_sto(rte);
ste = READ_ONCE(sto[sx]);
if (reg_entry_isvalid(ste)) {
pto = get_st_pto(ste);
pte = READ_ONCE(pto[px]);
if (pt_entry_isvalid(pte))
phys = pte & ZPCI_PTE_ADDR_MASK;
}
}
return phys;
}
static size_t s390_iommu_unmap_pages(struct iommu_domain *domain,
unsigned long iova,
size_t pgsize, size_t pgcount,
struct iommu_iotlb_gather *gather)
{
struct s390_domain *s390_domain = to_s390_domain(domain);
size_t size = pgcount << __ffs(pgsize);
int rc;
if (WARN_ON(iova < s390_domain->domain.geometry.aperture_start ||
(iova + size - 1) > s390_domain->domain.geometry.aperture_end))
return 0;
rc = s390_iommu_invalidate_trans(s390_domain, iova, pgcount);
if (rc)
return 0;
iommu_iotlb_gather_add_range(gather, iova, size);
atomic64_add(pgcount, &s390_domain->ctrs.unmapped_pages);
return size;
}
struct zpci_iommu_ctrs *zpci_get_iommu_ctrs(struct zpci_dev *zdev)
{
if (!zdev || !zdev->s390_domain)
return NULL;
return &zdev->s390_domain->ctrs;
}
int zpci_init_iommu(struct zpci_dev *zdev)
{
u64 aperture_size;
int rc = 0;
rc = iommu_device_sysfs_add(&zdev->iommu_dev, NULL, NULL,
"s390-iommu.%08x", zdev->fid);
if (rc)
goto out_err;
rc = iommu_device_register(&zdev->iommu_dev, &s390_iommu_ops, NULL);
if (rc)
goto out_sysfs;
zdev->start_dma = PAGE_ALIGN(zdev->start_dma);
aperture_size = min3(s390_iommu_aperture,
ZPCI_TABLE_SIZE_RT - zdev->start_dma,
zdev->end_dma - zdev->start_dma + 1);
zdev->end_dma = zdev->start_dma + aperture_size - 1;
return 0;
out_sysfs:
iommu_device_sysfs_remove(&zdev->iommu_dev);
out_err:
return rc;
}
void zpci_destroy_iommu(struct zpci_dev *zdev)
{
iommu_device_unregister(&zdev->iommu_dev);
iommu_device_sysfs_remove(&zdev->iommu_dev);
}
static int __init s390_iommu_setup(char *str)
{
if (!strcmp(str, "strict")) {
pr_warn("s390_iommu=strict deprecated; use iommu.strict=1 instead\n");
iommu_set_dma_strict();
}
return 1;
}
__setup("s390_iommu=", s390_iommu_setup);
static int __init s390_iommu_aperture_setup(char *str)
{
if (kstrtou32(str, 10, &s390_iommu_aperture_factor))
s390_iommu_aperture_factor = 1;
return 1;
}
__setup("s390_iommu_aperture=", s390_iommu_aperture_setup);
static int __init s390_iommu_init(void)
{
int rc;
iommu_dma_forcedac = true;
s390_iommu_aperture = (u64)virt_to_phys(high_memory);
if (!s390_iommu_aperture_factor)
s390_iommu_aperture = ULONG_MAX;
else
s390_iommu_aperture *= s390_iommu_aperture_factor;
rc = dma_alloc_cpu_table_caches();
if (rc)
return rc;
return rc;
}
subsys_initcall(s390_iommu_init);
static const struct iommu_ops s390_iommu_ops = {
.capable = s390_iommu_capable,
.domain_alloc_paging = s390_domain_alloc_paging,
.probe_device = s390_iommu_probe_device,
.release_device = s390_iommu_release_device,
.device_group = generic_device_group,
.pgsize_bitmap = SZ_4K,
2022-10-25 11:56:54 +00:00
.get_resv_regions = s390_iommu_get_resv_regions,
.default_domain_ops = &(const struct iommu_domain_ops) {
.attach_dev = s390_iommu_attach_device,
.map_pages = s390_iommu_map_pages,
.unmap_pages = s390_iommu_unmap_pages,
.flush_iotlb_all = s390_iommu_flush_iotlb_all,
.iotlb_sync = s390_iommu_iotlb_sync,
.iotlb_sync_map = s390_iommu_iotlb_sync_map,
.iova_to_phys = s390_iommu_iova_to_phys,
.free = s390_domain_free,
}
};