* [PATCH v3 08/11] powerpc/pseries/iommu: Update remove_dma_window() to accept property name
From: Leonardo Bras @ 2021-04-22 7:07 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras,
Leonardo Bras, Joel Stanley, Christophe Leroy,
Alexey Kardashevskiy, Nicolin Chen, Niklas Schnelle
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <20210422070721.463912-1-leobras.c@gmail.com>
Update remove_dma_window() so it can be used to remove DDW with a given
property name.
This enables the creation of new property names for DDW, so we can
have different usage for it, like indirect mapping.
Signed-off-by: Leonardo Bras <leobras.c@gmail.com>
---
arch/powerpc/platforms/pseries/iommu.c | 21 +++++++++++----------
1 file changed, 11 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 0147ccaf0be4..075c6e08f012 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -823,31 +823,32 @@ static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn);
}
-static void remove_ddw(struct device_node *np, bool remove_prop)
+static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_name)
{
struct property *win;
u32 ddw_avail[DDW_APPLICABLE_SIZE];
int ret = 0;
+ win = of_find_property(np, win_name, NULL);
+ if (!win)
+ return -EINVAL;
+
ret = of_property_read_u32_array(np, "ibm,ddw-applicable",
&ddw_avail[0], DDW_APPLICABLE_SIZE);
if (ret)
- return;
-
- win = of_find_property(np, DIRECT64_PROPNAME, NULL);
- if (!win)
- return;
+ return 0;
if (win->length >= sizeof(struct dynamic_dma_window_prop))
remove_dma_window(np, ddw_avail, win);
if (!remove_prop)
- return;
+ return 0;
ret = of_remove_property(np, win);
if (ret)
pr_warn("%pOF: failed to remove direct window property: %d\n",
np, ret);
+ return 0;
}
static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift)
@@ -900,7 +901,7 @@ static int find_existing_ddw_windows(void)
for_each_node_with_property(pdn, DIRECT64_PROPNAME) {
direct64 = of_get_property(pdn, DIRECT64_PROPNAME, &len);
if (!direct64 || len < sizeof(*direct64)) {
- remove_ddw(pdn, true);
+ remove_ddw(pdn, true, DIRECT64_PROPNAME);
continue;
}
@@ -1372,7 +1373,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
win64 = NULL;
out_del_win:
- remove_ddw(pdn, true);
+ remove_ddw(pdn, true, DIRECT64_PROPNAME);
out_failed:
if (default_win_removed)
@@ -1536,7 +1537,7 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
* we have to remove the property when releasing
* the device node.
*/
- remove_ddw(np, false);
+ remove_ddw(np, false, DIRECT64_PROPNAME);
if (pci && pci->table_group)
iommu_pseries_free_group(pci->table_group,
np->full_name);
--
2.30.2
^ permalink raw reply related
* [PATCH v3 09/11] powerpc/pseries/iommu: Find existing DDW with given property name
From: Leonardo Bras @ 2021-04-22 7:07 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras,
Leonardo Bras, Joel Stanley, Christophe Leroy,
Alexey Kardashevskiy, Nicolin Chen, Niklas Schnelle
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <20210422070721.463912-1-leobras.c@gmail.com>
At the moment pseries stores information about created directly mapped
DDW window in DIRECT64_PROPNAME.
With the objective of implementing indirect DMA mapping with DDW, it's
necessary to have another propriety name to make sure kexec'ing into older
kernels does not break, as it would if we reuse DIRECT64_PROPNAME.
In order to have this, find_existing_ddw_windows() needs to be able to
look for different property names.
Extract find_existing_ddw_windows() into find_existing_ddw_windows_named()
and calls it with current property name.
Signed-off-by: Leonardo Bras <leobras.c@gmail.com>
---
arch/powerpc/platforms/pseries/iommu.c | 25 +++++++++++++++----------
1 file changed, 15 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 075c6e08f012..3367233a5535 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -888,24 +888,21 @@ static struct direct_window *ddw_list_new_entry(struct device_node *pdn,
return window;
}
-static int find_existing_ddw_windows(void)
+static void find_existing_ddw_windows_named(const char *name)
{
int len;
struct device_node *pdn;
struct direct_window *window;
- const struct dynamic_dma_window_prop *direct64;
-
- if (!firmware_has_feature(FW_FEATURE_LPAR))
- return 0;
+ const struct dynamic_dma_window_prop *dma64;
- for_each_node_with_property(pdn, DIRECT64_PROPNAME) {
- direct64 = of_get_property(pdn, DIRECT64_PROPNAME, &len);
- if (!direct64 || len < sizeof(*direct64)) {
- remove_ddw(pdn, true, DIRECT64_PROPNAME);
+ for_each_node_with_property(pdn, name) {
+ dma64 = of_get_property(pdn, name, &len);
+ if (!dma64 || len < sizeof(*dma64)) {
+ remove_ddw(pdn, true, name);
continue;
}
- window = ddw_list_new_entry(pdn, direct64);
+ window = ddw_list_new_entry(pdn, dma64);
if (!window)
break;
@@ -913,6 +910,14 @@ static int find_existing_ddw_windows(void)
list_add(&window->list, &direct_window_list);
spin_unlock(&direct_window_list_lock);
}
+}
+
+static int find_existing_ddw_windows(void)
+{
+ if (!firmware_has_feature(FW_FEATURE_LPAR))
+ return 0;
+
+ find_existing_ddw_windows_named(DIRECT64_PROPNAME);
return 0;
}
--
2.30.2
^ permalink raw reply related
* [PATCH v3 10/11] powerpc/pseries/iommu: Make use of DDW for indirect mapping
From: Leonardo Bras @ 2021-04-22 7:07 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras,
Leonardo Bras, Joel Stanley, Christophe Leroy,
Alexey Kardashevskiy, Nicolin Chen, Niklas Schnelle
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <20210422070721.463912-1-leobras.c@gmail.com>
So far it's assumed possible to map the guest RAM 1:1 to the bus, which
works with a small number of devices. SRIOV changes it as the user can
configure hundreds VFs and since phyp preallocates TCEs and does not
allow IOMMU pages bigger than 64K, it has to limit the number of TCEs
per a PE to limit waste of physical pages.
As of today, if the assumed direct mapping is not possible, DDW creation
is skipped and the default DMA window "ibm,dma-window" is used instead.
By using DDW, indirect mapping can get more TCEs than available for the
default DMA window, and also get access to using much larger pagesizes
(16MB as implemented in qemu vs 4k from default DMA window), causing a
significant increase on the maximum amount of memory that can be IOMMU
mapped at the same time.
Indirect mapping will only be used if direct mapping is not a
possibility.
For indirect mapping, it's necessary to re-create the iommu_table with
the new DMA window parameters, so iommu_alloc() can use it.
Removing the default DMA window for using DDW with indirect mapping
is only allowed if there is no current IOMMU memory allocated in
the iommu_table. enable_ddw() is aborted otherwise.
Even though there won't be both direct and indirect mappings at the
same time, we can't reuse the DIRECT64_PROPNAME property name, or else
an older kexec()ed kernel can assume direct mapping, and skip
iommu_alloc(), causing undesirable behavior.
So a new property name DMA64_PROPNAME "linux,dma64-ddr-window-info"
was created to represent a DDW that does not allow direct mapping.
Signed-off-by: Leonardo Bras <leobras.c@gmail.com>
---
arch/powerpc/platforms/pseries/iommu.c | 87 +++++++++++++++++++++-----
1 file changed, 72 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 3367233a5535..50909cbc73f6 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -53,6 +53,7 @@ enum {
DDW_EXT_QUERY_OUT_SIZE = 2
};
+static phys_addr_t ddw_memory_hotplug_max(void);
#ifdef CONFIG_IOMMU_API
static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned long *tce,
enum dma_data_direction *direction, bool realmode);
@@ -380,6 +381,7 @@ static DEFINE_SPINLOCK(direct_window_list_lock);
/* protects initializing window twice for same device */
static DEFINE_MUTEX(direct_window_init_mutex);
#define DIRECT64_PROPNAME "linux,direct64-ddr-window-info"
+#define DMA64_PROPNAME "linux,dma64-ddr-window-info"
static int tce_clearrange_multi_pSeriesLP(unsigned long start_pfn,
unsigned long num_pfn, const void *arg)
@@ -918,6 +920,7 @@ static int find_existing_ddw_windows(void)
return 0;
find_existing_ddw_windows_named(DIRECT64_PROPNAME);
+ find_existing_ddw_windows_named(DMA64_PROPNAME);
return 0;
}
@@ -1207,10 +1210,13 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
struct device_node *dn;
u32 ddw_avail[DDW_APPLICABLE_SIZE];
struct direct_window *window;
+ const char *win_name;
struct property *win64 = NULL;
struct failed_ddw_pdn *fpdn;
- bool default_win_removed = false;
+ bool default_win_removed = false, direct_mapping = false;
bool pmem_present;
+ struct pci_dn *pci = PCI_DN(pdn);
+ struct iommu_table *tbl = pci->table_group->tables[0];
dn = of_find_node_by_type(NULL, "ibm,pmemory");
pmem_present = dn != NULL;
@@ -1218,8 +1224,12 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
mutex_lock(&direct_window_init_mutex);
- if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len))
- goto out_unlock;
+ if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len)) {
+ direct_mapping = (len >= max_ram_len);
+
+ mutex_unlock(&direct_window_init_mutex);
+ return direct_mapping;
+ }
/*
* If we already went through this for a previous function of
@@ -1298,7 +1308,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
goto out_failed;
}
/* verify the window * number of ptes will map the partition */
- /* check largest block * page size > max memory hotplug addr */
/*
* The "ibm,pmemory" can appear anywhere in the address space.
* Assuming it is still backed by page structs, try MAX_PHYSMEM_BITS
@@ -1320,6 +1329,17 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
1ULL << len,
query.largest_available_block,
1ULL << page_shift);
+
+ len = order_base_2(query.largest_available_block << page_shift);
+ win_name = DMA64_PROPNAME;
+ } else {
+ direct_mapping = true;
+ win_name = DIRECT64_PROPNAME;
+ }
+
+ /* DDW + IOMMU on single window may fail if there is any allocation */
+ if (default_win_removed && !direct_mapping && iommu_table_in_use(tbl)) {
+ dev_dbg(&dev->dev, "current IOMMU table in use, can't be replaced.\n");
goto out_failed;
}
@@ -1331,8 +1351,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
create.liobn, dn);
win_addr = ((u64)create.addr_hi << 32) | create.addr_lo;
- win64 = ddw_property_create(DIRECT64_PROPNAME, create.liobn, win_addr,
- page_shift, len);
+ win64 = ddw_property_create(win_name, create.liobn, win_addr, page_shift, len);
if (!win64) {
dev_info(&dev->dev,
"couldn't allocate property, property name, or value\n");
@@ -1350,12 +1369,47 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
if (!window)
goto out_del_prop;
- ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT,
- win64->value, tce_setrange_multi_pSeriesLP_walk);
- if (ret) {
- dev_info(&dev->dev, "failed to map direct window for %pOF: %d\n",
- dn, ret);
- goto out_del_list;
+ if (direct_mapping) {
+ /* DDW maps the whole partition, so enable direct DMA mapping */
+ ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT,
+ win64->value, tce_setrange_multi_pSeriesLP_walk);
+ if (ret) {
+ dev_info(&dev->dev, "failed to map direct window for %pOF: %d\n",
+ dn, ret);
+ goto out_del_list;
+ }
+ } else {
+ struct iommu_table *newtbl;
+ int i;
+
+ /* New table for using DDW instead of the default DMA window */
+ newtbl = iommu_pseries_alloc_table(pci->phb->node);
+ if (!newtbl) {
+ dev_dbg(&dev->dev, "couldn't create new IOMMU table\n");
+ goto out_del_list;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) {
+ const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
+
+ /* Look for MMIO32 */
+ if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM)
+ break;
+ }
+
+ _iommu_table_setparms(newtbl, pci->phb->bus->number, create.liobn, win_addr,
+ 1UL << len, page_shift, 0, &iommu_table_lpar_multi_ops);
+ iommu_init_table(newtbl, pci->phb->node, pci->phb->mem_resources[i].start,
+ pci->phb->mem_resources[i].end);
+
+ if (default_win_removed)
+ iommu_tce_table_put(tbl);
+ else
+ pci->table_group->tables[1] = tbl;
+
+ pci->table_group->tables[0] = newtbl;
+
+ set_iommu_table_base(&dev->dev, newtbl);
}
spin_lock(&direct_window_list_lock);
@@ -1398,10 +1452,10 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
* as RAM, then we failed to create a window to cover persistent
* memory and need to set the DMA limit.
*/
- if (pmem_present && win64 && (len == max_ram_len))
+ if (pmem_present && direct_mapping && len == max_ram_len)
dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + (1ULL << len);
- return win64;
+ return win64 && direct_mapping;
}
static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
@@ -1542,7 +1596,10 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
* we have to remove the property when releasing
* the device node.
*/
- remove_ddw(np, false, DIRECT64_PROPNAME);
+
+ if (remove_ddw(np, false, DIRECT64_PROPNAME))
+ remove_ddw(np, false, DMA64_PROPNAME);
+
if (pci && pci->table_group)
iommu_pseries_free_group(pci->table_group,
np->full_name);
--
2.30.2
^ permalink raw reply related
* [PATCH v3 11/11] powerpc/pseries/iommu: Rename "direct window" to "dma window"
From: Leonardo Bras @ 2021-04-22 7:07 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras,
Leonardo Bras, Joel Stanley, Christophe Leroy,
Alexey Kardashevskiy, Nicolin Chen, Niklas Schnelle
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <20210422070721.463912-1-leobras.c@gmail.com>
A previous change introduced the usage of DDW as a bigger indirect DMA
mapping when the DDW available size does not map the whole partition.
As most of the code that manipulates direct mappings was reused for
indirect mappings, it's necessary to rename all names and debug/info
messages to reflect that it can be used for both kinds of mapping.
This should cause no behavioural change, just adjust naming.
Signed-off-by: Leonardo Bras <leobras.c@gmail.com>
---
arch/powerpc/platforms/pseries/iommu.c | 93 +++++++++++++-------------
1 file changed, 48 insertions(+), 45 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 50909cbc73f6..f5d0a6f012da 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -355,7 +355,7 @@ struct dynamic_dma_window_prop {
__be32 window_shift; /* ilog2(tce_window_size) */
};
-struct direct_window {
+struct dma_win {
struct device_node *device;
const struct dynamic_dma_window_prop *prop;
struct list_head list;
@@ -375,11 +375,11 @@ struct ddw_create_response {
u32 addr_lo;
};
-static LIST_HEAD(direct_window_list);
+static LIST_HEAD(dma_win_list);
/* prevents races between memory on/offline and window creation */
-static DEFINE_SPINLOCK(direct_window_list_lock);
+static DEFINE_SPINLOCK(dma_win_list_lock);
/* protects initializing window twice for same device */
-static DEFINE_MUTEX(direct_window_init_mutex);
+static DEFINE_MUTEX(dma_win_init_mutex);
#define DIRECT64_PROPNAME "linux,direct64-ddr-window-info"
#define DMA64_PROPNAME "linux,dma64-ddr-window-info"
@@ -712,7 +712,10 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n",
dn);
- /* Find nearest ibm,dma-window, walking up the device tree */
+ /*
+ * Find nearest ibm,dma-window (default DMA window), walking up the
+ * device tree
+ */
for (pdn = dn; pdn != NULL; pdn = pdn->parent) {
dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
if (dma_window != NULL)
@@ -816,11 +819,11 @@ static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
ret = rtas_call(ddw_avail[DDW_REMOVE_PE_DMA_WIN], 1, 1, NULL, liobn);
if (ret)
- pr_warn("%pOF: failed to remove direct window: rtas returned "
+ pr_warn("%pOF: failed to remove DMA window: rtas returned "
"%d to ibm,remove-pe-dma-window(%x) %llx\n",
np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn);
else
- pr_debug("%pOF: successfully removed direct window: rtas returned "
+ pr_debug("%pOF: successfully removed DMA window: rtas returned "
"%d to ibm,remove-pe-dma-window(%x) %llx\n",
np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn);
}
@@ -848,37 +851,37 @@ static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_
ret = of_remove_property(np, win);
if (ret)
- pr_warn("%pOF: failed to remove direct window property: %d\n",
+ pr_warn("%pOF: failed to remove DMA window property: %d\n",
np, ret);
return 0;
}
static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift)
{
- struct direct_window *window;
- const struct dynamic_dma_window_prop *direct64;
+ struct dma_win *window;
+ const struct dynamic_dma_window_prop *dma64;
bool found = false;
- spin_lock(&direct_window_list_lock);
+ spin_lock(&dma_win_list_lock);
/* check if we already created a window and dupe that config if so */
- list_for_each_entry(window, &direct_window_list, list) {
+ list_for_each_entry(window, &dma_win_list, list) {
if (window->device == pdn) {
- direct64 = window->prop;
- *dma_addr = be64_to_cpu(direct64->dma_base);
- *window_shift = be32_to_cpu(direct64->window_shift);
+ dma64 = window->prop;
+ *dma_addr = be64_to_cpu(dma64->dma_base);
+ *window_shift = be32_to_cpu(dma64->window_shift);
found = true;
break;
}
}
- spin_unlock(&direct_window_list_lock);
+ spin_unlock(&dma_win_list_lock);
return found;
}
-static struct direct_window *ddw_list_new_entry(struct device_node *pdn,
- const struct dynamic_dma_window_prop *dma64)
+static struct dma_win *ddw_list_new_entry(struct device_node *pdn,
+ const struct dynamic_dma_window_prop *dma64)
{
- struct direct_window *window;
+ struct dma_win *window;
window = kzalloc(sizeof(*window), GFP_KERNEL);
if (!window)
@@ -894,7 +897,7 @@ static void find_existing_ddw_windows_named(const char *name)
{
int len;
struct device_node *pdn;
- struct direct_window *window;
+ struct dma_win *window;
const struct dynamic_dma_window_prop *dma64;
for_each_node_with_property(pdn, name) {
@@ -908,9 +911,9 @@ static void find_existing_ddw_windows_named(const char *name)
if (!window)
break;
- spin_lock(&direct_window_list_lock);
- list_add(&window->list, &direct_window_list);
- spin_unlock(&direct_window_list_lock);
+ spin_lock(&dma_win_list_lock);
+ list_add(&window->list, &dma_win_list);
+ spin_unlock(&dma_win_list_lock);
}
}
@@ -1209,7 +1212,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
u64 win_addr;
struct device_node *dn;
u32 ddw_avail[DDW_APPLICABLE_SIZE];
- struct direct_window *window;
+ struct dma_win *window;
const char *win_name;
struct property *win64 = NULL;
struct failed_ddw_pdn *fpdn;
@@ -1222,12 +1225,12 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
pmem_present = dn != NULL;
of_node_put(dn);
- mutex_lock(&direct_window_init_mutex);
+ mutex_lock(&dma_win_init_mutex);
if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len)) {
direct_mapping = (len >= max_ram_len);
- mutex_unlock(&direct_window_init_mutex);
+ mutex_unlock(&dma_win_init_mutex);
return direct_mapping;
}
@@ -1303,8 +1306,8 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
page_shift = iommu_get_page_shift(query.page_size);
if (!page_shift) {
- dev_dbg(&dev->dev, "no supported direct page size in mask %x",
- query.page_size);
+ dev_dbg(&dev->dev, "no supported page size in mask %x",
+ query.page_size);
goto out_failed;
}
/* verify the window * number of ptes will map the partition */
@@ -1360,7 +1363,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
ret = of_add_property(pdn, win64);
if (ret) {
- dev_err(&dev->dev, "unable to add dma window property for %pOF: %d",
+ dev_err(&dev->dev, "unable to add DMA window property for %pOF: %d",
pdn, ret);
goto out_free_prop;
}
@@ -1374,7 +1377,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT,
win64->value, tce_setrange_multi_pSeriesLP_walk);
if (ret) {
- dev_info(&dev->dev, "failed to map direct window for %pOF: %d\n",
+ dev_info(&dev->dev, "failed to map DMA window for %pOF: %d\n",
dn, ret);
goto out_del_list;
}
@@ -1412,9 +1415,9 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
set_iommu_table_base(&dev->dev, newtbl);
}
- spin_lock(&direct_window_list_lock);
- list_add(&window->list, &direct_window_list);
- spin_unlock(&direct_window_list_lock);
+ spin_lock(&dma_win_list_lock);
+ list_add(&window->list, &dma_win_list);
+ spin_unlock(&dma_win_list_lock);
dev->dev.archdata.dma_offset = win_addr;
goto out_unlock;
@@ -1445,7 +1448,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
list_add(&fpdn->list, &failed_ddw_pdn_list);
out_unlock:
- mutex_unlock(&direct_window_init_mutex);
+ mutex_unlock(&dma_win_init_mutex);
/*
* If we have persistent memory and the window size is only as big
@@ -1542,29 +1545,29 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
void *data)
{
- struct direct_window *window;
+ struct dma_win *window;
struct memory_notify *arg = data;
int ret = 0;
switch (action) {
case MEM_GOING_ONLINE:
- spin_lock(&direct_window_list_lock);
- list_for_each_entry(window, &direct_window_list, list) {
+ spin_lock(&dma_win_list_lock);
+ list_for_each_entry(window, &dma_win_list, list) {
ret |= tce_setrange_multi_pSeriesLP(arg->start_pfn,
arg->nr_pages, window->prop);
/* XXX log error */
}
- spin_unlock(&direct_window_list_lock);
+ spin_unlock(&dma_win_list_lock);
break;
case MEM_CANCEL_ONLINE:
case MEM_OFFLINE:
- spin_lock(&direct_window_list_lock);
- list_for_each_entry(window, &direct_window_list, list) {
+ spin_lock(&dma_win_list_lock);
+ list_for_each_entry(window, &dma_win_list, list) {
ret |= tce_clearrange_multi_pSeriesLP(arg->start_pfn,
arg->nr_pages, window->prop);
/* XXX log error */
}
- spin_unlock(&direct_window_list_lock);
+ spin_unlock(&dma_win_list_lock);
break;
default:
break;
@@ -1585,7 +1588,7 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
struct of_reconfig_data *rd = data;
struct device_node *np = rd->dn;
struct pci_dn *pci = PCI_DN(np);
- struct direct_window *window;
+ struct dma_win *window;
switch (action) {
case OF_RECONFIG_DETACH_NODE:
@@ -1604,15 +1607,15 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
iommu_pseries_free_group(pci->table_group,
np->full_name);
- spin_lock(&direct_window_list_lock);
- list_for_each_entry(window, &direct_window_list, list) {
+ spin_lock(&dma_win_list_lock);
+ list_for_each_entry(window, &dma_win_list, list) {
if (window->device == np) {
list_del(&window->list);
kfree(window);
break;
}
}
- spin_unlock(&direct_window_list_lock);
+ spin_unlock(&dma_win_list_lock);
break;
default:
err = NOTIFY_DONE;
--
2.30.2
^ permalink raw reply related
* Re: [PATCH v3 00/11] DDW + Indirect Mapping
From: Leonardo Bras @ 2021-04-22 7:19 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, Paul Mackerras,
Joel Stanley, Christophe Leroy, Alexey Kardashevskiy,
Nicolin Chen, Niklas Schnelle
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <20210422070721.463912-1-leobras.c@gmail.com>
Changes since v2:
- Some patches got removed from the series and sent by themselves,
- New tbl created for DDW + indirect mapping reserves MMIO32 space,
- Improved reserved area algorithm,
- Improved commit messages,
- Removed define for default DMA window prop name,
- Avoided some unnecessary renaming,
- Removed some unnecessary empty lines,
- Changed some code moving to forward declarations.
v2
Link: http://patchwork.ozlabs.org/project/linuxppc-dev/list/?series=201210&state=%2A&archive=both
On Thu, 2021-04-22 at 04:07 -0300, Leonardo Bras wrote:
> So far it's assumed possible to map the guest RAM 1:1 to the bus, which
> works with a small number of devices. SRIOV changes it as the user can
> configure hundreds VFs and since phyp preallocates TCEs and does not
> allow IOMMU pages bigger than 64K, it has to limit the number of TCEs
> per a PE to limit waste of physical pages.
>
> As of today, if the assumed direct mapping is not possible, DDW creation
> is skipped and the default DMA window "ibm,dma-window" is used instead.
>
> Using the DDW instead of the default DMA window may allow to expand the
> amount of memory that can be DMA-mapped, given the number of pages (TCEs)
> may stay the same (or increase) and the default DMA window offers only
> 4k-pages while DDW may offer larger pages (4k, 64k, 16M ...).
>
> Patch #1 replaces hard-coded 4K page size with a variable containing the
> correct page size for the window.
>
> Patch #2 introduces iommu_table_in_use(), and replace manual bit-field
> checking where it's used. It will be used for aborting enable_ddw() if
> there is any current iommu allocation and we are trying single window
> indirect mapping.
>
> Patch #3 introduces iommu_pseries_alloc_table() that will be helpful
> when indirect mapping needs to replace the iommu_table.
>
> Patch #4 adds helpers for adding DDWs in the list.
>
> Patch #5 refactors enable_ddw() so it returns if direct mapping is
> possible, instead of DMA offset. It helps for next patches on
> indirect DMA mapping and also allows DMA windows starting at 0x00.
>
> Patch #6 bring new helper to simplify enable_ddw(), allowing
> some reorganization for introducing indirect mapping DDW.
>
> Patch #7 adds new helper _iommu_table_setparms() and use it in other
> *setparams*() to fill iommu_table. It will also be used for creating a
> new iommu_table for indirect mapping.
>
> Patch #8 updates remove_dma_window() to accept different property names,
> so we can introduce a new property for indirect mapping.
>
> Patch #9 extracts find_existing_ddw_windows() into
> find_existing_ddw_windows_named(), and calls it by it's property name.
> This will be useful when the property for indirect mapping is created,
> so we can search the device-tree for both properties.
>
> Patch #10:
> Instead of destroying the created DDW if it doesn't map the whole
> partition, make use of it instead of the default DMA window as it improves
> performance. Also, update the iommu_table and re-generate the pools.
> It introduces a new property name for DDW with indirect DMA mapping.
>
> Patch #11:
> Does some renaming of 'direct window' to 'dma window', given the DDW
> created can now be also used in indirect mapping if direct mapping is not
> available.
>
> All patches were tested into an LPAR with an virtio-net interface that
> allows default DMA window and DDW to coexist.
>
> Leonardo Bras (11):
> powerpc/pseries/iommu: Replace hard-coded page shift
> powerpc/kernel/iommu: Add new iommu_table_in_use() helper
> powerpc/pseries/iommu: Add iommu_pseries_alloc_table() helper
> powerpc/pseries/iommu: Add ddw_list_new_entry() helper
> powerpc/pseries/iommu: Allow DDW windows starting at 0x00
> powerpc/pseries/iommu: Add ddw_property_create() and refactor
> enable_ddw()
> powerpc/pseries/iommu: Reorganize iommu_table_setparms*() with new
> helper
> powerpc/pseries/iommu: Update remove_dma_window() to accept property
> name
> powerpc/pseries/iommu: Find existing DDW with given property name
> powerpc/pseries/iommu: Make use of DDW for indirect mapping
> powerpc/pseries/iommu: Rename "direct window" to "dma window"
>
> arch/powerpc/include/asm/iommu.h | 1 +
> arch/powerpc/include/asm/tce.h | 8 -
> arch/powerpc/kernel/iommu.c | 65 ++--
> arch/powerpc/platforms/pseries/iommu.c | 504 +++++++++++++++----------
> 4 files changed, 338 insertions(+), 240 deletions(-)
>
^ permalink raw reply
* [PATCH 5/7] MIPS/octeon: simplify swiotlb initialization
From: Christoph Hellwig @ 2021-04-22 7:19 UTC (permalink / raw)
To: Konrad Rzeszutek Wilk
Cc: Juergen Gross, Tom Lendacky, Thomas Bogendoerfer, linux-mips,
iommu, Stefano Stabellini, xen-devel, Boris Ostrovsky,
linuxppc-dev
In-Reply-To: <20210422071921.1428607-1-hch@lst.de>
Just use swiotlb_adjust_size and swiotlb_init to initialize
swiotlb instead of doing a lot of manual work.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
arch/mips/cavium-octeon/dma-octeon.c | 16 ++--------------
arch/mips/include/asm/octeon/pci-octeon.h | 1 -
arch/mips/pci/pci-octeon.c | 2 +-
3 files changed, 3 insertions(+), 16 deletions(-)
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index 020b8ce5b8ff7c..6bc9ef5e3790ec 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -186,15 +186,12 @@ phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
return daddr;
}
-char *octeon_swiotlb;
-
void __init plat_swiotlb_setup(void)
{
phys_addr_t start, end;
phys_addr_t max_addr;
phys_addr_t addr_size;
size_t swiotlbsize;
- unsigned long swiotlb_nslabs;
u64 i;
max_addr = 0;
@@ -236,15 +233,6 @@ void __init plat_swiotlb_setup(void)
if (OCTEON_IS_OCTEON2() && max_addr >= 0x100000000ul)
swiotlbsize = 64 * (1<<20);
#endif
- swiotlb_nslabs = swiotlbsize >> IO_TLB_SHIFT;
- swiotlb_nslabs = ALIGN(swiotlb_nslabs, IO_TLB_SEGSIZE);
- swiotlbsize = swiotlb_nslabs << IO_TLB_SHIFT;
-
- octeon_swiotlb = memblock_alloc_low(swiotlbsize, PAGE_SIZE);
- if (!octeon_swiotlb)
- panic("%s: Failed to allocate %zu bytes align=%lx\n",
- __func__, swiotlbsize, PAGE_SIZE);
-
- if (swiotlb_init_with_tbl(octeon_swiotlb, swiotlbsize, 1) == -ENOMEM)
- panic("Cannot allocate SWIOTLB buffer");
+ swiotlb_adjust_size(swiotlbsize);
+ swiotlb_init(false);
}
diff --git a/arch/mips/include/asm/octeon/pci-octeon.h b/arch/mips/include/asm/octeon/pci-octeon.h
index b12d9a3fbfb6c0..a2f20a44fb6143 100644
--- a/arch/mips/include/asm/octeon/pci-octeon.h
+++ b/arch/mips/include/asm/octeon/pci-octeon.h
@@ -64,6 +64,5 @@ enum octeon_dma_bar_type {
extern enum octeon_dma_bar_type octeon_dma_bar_type;
void octeon_pci_dma_init(void);
-extern char *octeon_swiotlb;
#endif
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index fc29b85cfa926d..ff26cd9dc083f6 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -664,7 +664,7 @@ static int __init octeon_pci_setup(void)
/* BAR1 movable regions contiguous to cover the swiotlb */
octeon_bar1_pci_phys =
- virt_to_phys(octeon_swiotlb) & ~((1ull << 22) - 1);
+ io_tlb_default_mem->start & ~((1ull << 22) - 1);
for (index = 0; index < 32; index++) {
union cvmx_pci_bar1_indexx bar1_index;
--
2.30.1
^ permalink raw reply related
* [PATCH 3/7] swiotlb: use swiotlb_adjust_size in setup_io_tlb_npages
From: Christoph Hellwig @ 2021-04-22 7:19 UTC (permalink / raw)
To: Konrad Rzeszutek Wilk
Cc: Juergen Gross, Tom Lendacky, Thomas Bogendoerfer, linux-mips,
iommu, Stefano Stabellini, xen-devel, Boris Ostrovsky,
linuxppc-dev
In-Reply-To: <20210422071921.1428607-1-hch@lst.de>
Use the proper helper to do the proper alignment of the buffer size
to the requirements of the swiotlb allocator instead of open coding
the logic.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
kernel/dma/swiotlb.c | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 27461fd63e0330..93737d0932fbf2 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -76,11 +76,9 @@ static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT;
static int __init
setup_io_tlb_npages(char *str)
{
- if (isdigit(*str)) {
- /* avoid tail segment of size < IO_TLB_SEGSIZE */
- default_nslabs =
- ALIGN(simple_strtoul(str, &str, 0), IO_TLB_SEGSIZE);
- }
+ if (isdigit(*str))
+ swiotlb_adjust_size(
+ simple_strtoul(str, &str, 0) << IO_TLB_SHIFT);
if (*str == ',')
++str;
if (!strcmp(str, "force"))
--
2.30.1
^ permalink raw reply related
* cleanup and fix swiotlb sizing
From: Christoph Hellwig @ 2021-04-22 7:19 UTC (permalink / raw)
To: Konrad Rzeszutek Wilk
Cc: Juergen Gross, Tom Lendacky, Thomas Bogendoerfer, linux-mips,
iommu, Stefano Stabellini, xen-devel, Boris Ostrovsky,
linuxppc-dev
Hi all,
based on a report from Tom that overriding the default sizing provided
by the x86 SEV code on the command line doesn't work anymore, this series
cleans up how we handle default and command line sizes for the swiotlb
buffer and then fixes the recently introduced bug in a straight-forward
way.
Diffstat:
arch/mips/cavium-octeon/dma-octeon.c | 16 +--------------
arch/mips/include/asm/octeon/pci-octeon.h | 1
arch/mips/pci/pci-octeon.c | 2 -
arch/powerpc/platforms/pseries/svm.c | 13 ++----------
drivers/xen/swiotlb-xen.c | 2 -
include/linux/swiotlb.h | 2 -
kernel/dma/swiotlb.c | 32 +++++++++++++++---------------
7 files changed, 25 insertions(+), 43 deletions(-)
^ permalink raw reply
* [PATCH 4/7] powerpc/pseries: simplify svm_swiotlb_init
From: Christoph Hellwig @ 2021-04-22 7:19 UTC (permalink / raw)
To: Konrad Rzeszutek Wilk
Cc: Juergen Gross, Tom Lendacky, Thomas Bogendoerfer, linux-mips,
iommu, Stefano Stabellini, xen-devel, Boris Ostrovsky,
linuxppc-dev
In-Reply-To: <20210422071921.1428607-1-hch@lst.de>
The value returned by swiotlb_size_or_default is always properly
aligned now, so don't duplicate the work.
Signed-off-by: Christoph Hellwig <hch@lst.de>dddd
---
arch/powerpc/platforms/pseries/svm.c | 10 ++--------
1 file changed, 2 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c
index 4d281ff56ce96f..9187d2a1ed568d 100644
--- a/arch/powerpc/platforms/pseries/svm.c
+++ b/arch/powerpc/platforms/pseries/svm.c
@@ -43,20 +43,14 @@ machine_early_initcall(pseries, init_svm);
*/
void __init svm_swiotlb_init(void)
{
+ unsigned long bytes = swiotlb_size_or_default();
unsigned char *vstart;
- unsigned long bytes, io_tlb_nslabs;
-
- io_tlb_nslabs = (swiotlb_size_or_default() >> IO_TLB_SHIFT);
- io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
-
- bytes = io_tlb_nslabs << IO_TLB_SHIFT;
vstart = memblock_alloc(PAGE_ALIGN(bytes), PAGE_SIZE);
if (vstart && !swiotlb_init_with_tbl(vstart, bytes, false))
return;
- memblock_free_early(__pa(vstart),
- PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+ memblock_free_early(__pa(vstart), PAGE_ALIGN(bytes));
panic("SVM: Cannot allocate SWIOTLB buffer");
}
--
2.30.1
^ permalink raw reply related
* [PATCH 2/7] swiotlb: use swiotlb_size_or_default in swiotlb_init
From: Christoph Hellwig @ 2021-04-22 7:19 UTC (permalink / raw)
To: Konrad Rzeszutek Wilk
Cc: Juergen Gross, Tom Lendacky, Thomas Bogendoerfer, linux-mips,
iommu, Stefano Stabellini, xen-devel, Boris Ostrovsky,
linuxppc-dev
In-Reply-To: <20210422071921.1428607-1-hch@lst.de>
Use swiotlb_size_or_default to calculate the buffer size insted of
open coding it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
kernel/dma/swiotlb.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index c7b3dd86db7f56..27461fd63e0330 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -209,7 +209,7 @@ int __init swiotlb_init_with_tbl(char *tlb, size_t bytes, int verbose)
void __init
swiotlb_init(int verbose)
{
- size_t bytes = default_nslabs << IO_TLB_SHIFT;
+ size_t bytes = swiotlb_size_or_default();
void *tlb;
if (swiotlb_force == SWIOTLB_NO_FORCE)
--
2.30.1
^ permalink raw reply related
* [PATCH 7/7] swiotlb: don't override the command line in swiotlb_adjust_size
From: Christoph Hellwig @ 2021-04-22 7:19 UTC (permalink / raw)
To: Konrad Rzeszutek Wilk
Cc: Juergen Gross, Tom Lendacky, Thomas Bogendoerfer, linux-mips,
iommu, Stefano Stabellini, xen-devel, Boris Ostrovsky,
linuxppc-dev
In-Reply-To: <20210422071921.1428607-1-hch@lst.de>
When the user specified an explicit swiotlb size on the command line,
the achitecture code should not override it.
Fixes: 2cbc2776efe4 ("swiotlb: remove swiotlb_nr_tbl")
Reported-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
kernel/dma/swiotlb.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 87d06ddf4753f3..aef02a3825b494 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -106,7 +106,9 @@ void swiotlb_set_max_segment(unsigned int val)
unsigned long swiotlb_size_or_default(void)
{
- return swiotlb_default_size;
+ if (swiotlb_default_size)
+ return swiotlb_default_size;
+ return IO_TLB_DEFAULT_SIZE;
}
void __init swiotlb_adjust_size(unsigned long size)
@@ -116,6 +118,8 @@ void __init swiotlb_adjust_size(unsigned long size)
* architectures such as those supporting memory encryption to
* adjust/expand SWIOTLB size for their use.
*/
+ if (swiotlb_default_size)
+ return;
swiotlb_default_size = ALIGN(size, IO_TLB_SEGSIZE << IO_TLB_SHIFT);
pr_info("SWIOTLB bounce buffer size adjusted to %luMB",
swiotlb_default_size >> 20);
--
2.30.1
^ permalink raw reply related
* [PATCH 1/7] swiotlb: pass bytes instead of nslabs to swiotlb_init_with_tbl
From: Christoph Hellwig @ 2021-04-22 7:19 UTC (permalink / raw)
To: Konrad Rzeszutek Wilk
Cc: Juergen Gross, Tom Lendacky, Thomas Bogendoerfer, linux-mips,
iommu, Stefano Stabellini, xen-devel, Boris Ostrovsky,
linuxppc-dev
In-Reply-To: <20210422071921.1428607-1-hch@lst.de>
Pass the actual allocation size to swiotlb_init_with_tbl, which
simplifies things quite a bit.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
arch/mips/cavium-octeon/dma-octeon.c | 2 +-
arch/powerpc/platforms/pseries/svm.c | 3 +--
drivers/xen/swiotlb-xen.c | 2 +-
include/linux/swiotlb.h | 2 +-
kernel/dma/swiotlb.c | 10 +++++-----
5 files changed, 9 insertions(+), 10 deletions(-)
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index df70308db0e697..020b8ce5b8ff7c 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -245,6 +245,6 @@ void __init plat_swiotlb_setup(void)
panic("%s: Failed to allocate %zu bytes align=%lx\n",
__func__, swiotlbsize, PAGE_SIZE);
- if (swiotlb_init_with_tbl(octeon_swiotlb, swiotlb_nslabs, 1) == -ENOMEM)
+ if (swiotlb_init_with_tbl(octeon_swiotlb, swiotlbsize, 1) == -ENOMEM)
panic("Cannot allocate SWIOTLB buffer");
}
diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c
index 1d829e257996fb..4d281ff56ce96f 100644
--- a/arch/powerpc/platforms/pseries/svm.c
+++ b/arch/powerpc/platforms/pseries/svm.c
@@ -52,10 +52,9 @@ void __init svm_swiotlb_init(void)
bytes = io_tlb_nslabs << IO_TLB_SHIFT;
vstart = memblock_alloc(PAGE_ALIGN(bytes), PAGE_SIZE);
- if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, false))
+ if (vstart && !swiotlb_init_with_tbl(vstart, bytes, false))
return;
-
memblock_free_early(__pa(vstart),
PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
panic("SVM: Cannot allocate SWIOTLB buffer");
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 4c89afc0df6289..18d79f07b507ce 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -249,7 +249,7 @@ void __init xen_swiotlb_init_early(void)
panic("%s (rc:%d)", xen_swiotlb_error(XEN_SWIOTLB_EFIXUP), rc);
}
- if (swiotlb_init_with_tbl(start, nslabs, false))
+ if (swiotlb_init_with_tbl(start, bytes, false))
panic("Cannot allocate SWIOTLB buffer");
swiotlb_set_max_segment(PAGE_SIZE);
}
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 216854a5e5134b..d1d40ca5014b54 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -36,7 +36,7 @@ enum swiotlb_force {
#define IO_TLB_DEFAULT_SIZE (64UL<<20)
extern void swiotlb_init(int verbose);
-int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
+int swiotlb_init_with_tbl(char *tlb, size_t bytes, int verbose);
unsigned long swiotlb_size_or_default(void);
extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
extern int swiotlb_late_init_with_default_size(size_t default_size);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 0a5b6f7e75bce6..c7b3dd86db7f56 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -166,9 +166,9 @@ void __init swiotlb_update_mem_attributes(void)
memset(vaddr, 0, bytes);
}
-int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
+int __init swiotlb_init_with_tbl(char *tlb, size_t bytes, int verbose)
{
- unsigned long bytes = nslabs << IO_TLB_SHIFT, i;
+ unsigned long nslabs = bytes >> IO_TLB_SHIFT, i;
struct io_tlb_mem *mem;
size_t alloc_size;
@@ -209,17 +209,17 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
void __init
swiotlb_init(int verbose)
{
- size_t bytes = PAGE_ALIGN(default_nslabs << IO_TLB_SHIFT);
+ size_t bytes = default_nslabs << IO_TLB_SHIFT;
void *tlb;
if (swiotlb_force == SWIOTLB_NO_FORCE)
return;
/* Get IO TLB memory from the low pages */
- tlb = memblock_alloc_low(bytes, PAGE_SIZE);
+ tlb = memblock_alloc_low(PAGE_ALIGN(bytes), PAGE_SIZE);
if (!tlb)
goto fail;
- if (swiotlb_init_with_tbl(tlb, default_nslabs, verbose))
+ if (swiotlb_init_with_tbl(tlb, bytes, verbose))
goto fail_free_mem;
return;
--
2.30.1
^ permalink raw reply related
* [PATCH 6/7] swiotlb: replace default_nslabs with a byte value
From: Christoph Hellwig @ 2021-04-22 7:19 UTC (permalink / raw)
To: Konrad Rzeszutek Wilk
Cc: Juergen Gross, Tom Lendacky, Thomas Bogendoerfer, linux-mips,
iommu, Stefano Stabellini, xen-devel, Boris Ostrovsky,
linuxppc-dev
In-Reply-To: <20210422071921.1428607-1-hch@lst.de>
Replace the default_nslabs variable with one that stores the size in
bytes as that is what all the users actually expect.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
kernel/dma/swiotlb.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 93737d0932fbf2..87d06ddf4753f3 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -71,7 +71,7 @@ struct io_tlb_mem *io_tlb_default_mem;
*/
static unsigned int max_segment;
-static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT;
+static unsigned long swiotlb_default_size = IO_TLB_DEFAULT_SIZE;
static int __init
setup_io_tlb_npages(char *str)
@@ -106,7 +106,7 @@ void swiotlb_set_max_segment(unsigned int val)
unsigned long swiotlb_size_or_default(void)
{
- return default_nslabs << IO_TLB_SHIFT;
+ return swiotlb_default_size;
}
void __init swiotlb_adjust_size(unsigned long size)
@@ -116,9 +116,9 @@ void __init swiotlb_adjust_size(unsigned long size)
* architectures such as those supporting memory encryption to
* adjust/expand SWIOTLB size for their use.
*/
- size = ALIGN(size, IO_TLB_SIZE);
- default_nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
- pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20);
+ swiotlb_default_size = ALIGN(size, IO_TLB_SEGSIZE << IO_TLB_SHIFT);
+ pr_info("SWIOTLB bounce buffer size adjusted to %luMB",
+ swiotlb_default_size >> 20);
}
void swiotlb_print_info(void)
--
2.30.1
^ permalink raw reply related
* RE: [PATCH] powerpc: Initialize local variable fdt to NULL in elf64_load()
From: David Laight @ 2021-04-22 8:05 UTC (permalink / raw)
To: 'Daniel Axtens', Lakshmi Ramasubramanian, robh@kernel.org,
dan.carpenter@oracle.com
Cc: devicetree@vger.kernel.org, linuxppc-dev, kbuild-all@lists.01.org,
bauerman@linux.ibm.com, lkp@intel.com
In-Reply-To: <87r1j3ys8i.fsf@dja-thinkpad.axtens.net>
From: Daniel Axtens
> Sent: 22 April 2021 03:21
>
> > Hi Lakshmi,
> >
> >> On 4/15/21 12:14 PM, Lakshmi Ramasubramanian wrote:
> >>
> >> Sorry - missed copying device-tree and powerpc mailing lists.
> >>
> >>> There are a few "goto out;" statements before the local variable "fdt"
> >>> is initialized through the call to of_kexec_alloc_and_setup_fdt() in
> >>> elf64_load(). This will result in an uninitialized "fdt" being passed
> >>> to kvfree() in this function if there is an error before the call to
> >>> of_kexec_alloc_and_setup_fdt().
> >>>
> >>> Initialize the local variable "fdt" to NULL.
> >>>
> > I'm a huge fan of initialising local variables! But I'm struggling to
> > find the code path that will lead to an uninit fdt being returned...
>
> OK, so perhaps this was putting it too strongly. I have been bitten
> by uninitialised things enough in C that I may have taken a slightly
> overly-agressive view of fixing them in the source rather than the
> compiler. I do think compiler-level mitigations are better, and I take
> the point that we don't want to defeat compiler checking.
>
> (Does anyone - and by anyone I mean any large distro - compile with
> local variables inited by the compiler?)
There are compilers that initialise locals to zero for 'debug' builds
and leave the 'random' for optimised 'release' builds.
Lets not test what we are releasing!
I also think there is a new option to gcc (or clang?) to initialise
on-stack structures and arrays to ensure garbage isn't passed.
That seems to be a horrid performance hit!
Especially in userspace where large stack allocations are almost free.
Any auto-initialise ought to be with a semi-random value
(especially not zero) so that it is never right and doesn't
lead to lazy coding.
David
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
^ permalink raw reply
* [PATCH v5 00/16] Restricted DMA
From: Claire Chang @ 2021-04-22 8:14 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Frank Rowand, Konrad Rzeszutek Wilk,
boris.ostrovsky, jgross, Christoph Hellwig, Marek Szyprowski
Cc: heikki.krogerus, thomas.hellstrom, peterz, joonas.lahtinen,
dri-devel, chris, grant.likely, paulus, mingo, jxgao, sstabellini,
Saravana Kannan, xypron.glpk, Rafael J . Wysocki,
Bartosz Golaszewski, bskeggs, linux-pci, xen-devel,
Thierry Reding, intel-gfx, matthew.auld, linux-devicetree, daniel,
airlied, maarten.lankhorst, linuxppc-dev, jani.nikula,
Nicolas Boichat, rodrigo.vivi, bhelgaas, tientzu, Dan Williams,
Andy Shevchenko, nouveau, Greg KH, Randy Dunlap, lkml, tfiga,
list@263.net:IOMMU DRIVERS, Jim Quinlan, Robin Murphy, bauerman
This series implements mitigations for lack of DMA access control on
systems without an IOMMU, which could result in the DMA accessing the
system memory at unexpected times and/or unexpected addresses, possibly
leading to data leakage or corruption.
For example, we plan to use the PCI-e bus for Wi-Fi and that PCI-e bus is
not behind an IOMMU. As PCI-e, by design, gives the device full access to
system memory, a vulnerability in the Wi-Fi firmware could easily escalate
to a full system exploit (remote wifi exploits: [1a], [1b] that shows a
full chain of exploits; [2], [3]).
To mitigate the security concerns, we introduce restricted DMA. Restricted
DMA utilizes the existing swiotlb to bounce streaming DMA in and out of a
specially allocated region and does memory allocation from the same region.
The feature on its own provides a basic level of protection against the DMA
overwriting buffer contents at unexpected times. However, to protect
against general data leakage and system memory corruption, the system needs
to provide a way to restrict the DMA to a predefined memory region (this is
usually done at firmware level, e.g. MPU in ATF on some ARM platforms [4]).
[1a] https://googleprojectzero.blogspot.com/2017/04/over-air-exploiting-broadcoms-wi-fi_4.html
[1b] https://googleprojectzero.blogspot.com/2017/04/over-air-exploiting-broadcoms-wi-fi_11.html
[2] https://blade.tencent.com/en/advisories/qualpwn/
[3] https://www.bleepingcomputer.com/news/security/vulnerabilities-found-in-highly-popular-firmware-for-wifi-chips/
[4] https://github.com/ARM-software/arm-trusted-firmware/blob/master/plat/mediatek/mt8183/drivers/emi_mpu/emi_mpu.c#L132
v5:
Rebase on latest linux-next
v4:
- Fix spinlock bad magic
- Use rmem->name for debugfs entry
- Address the comments in v3
v3:
Using only one reserved memory region for both streaming DMA and memory
allocation.
https://lore.kernel.org/patchwork/cover/1360992/
v2:
Building on top of swiotlb.
https://lore.kernel.org/patchwork/cover/1280705/
v1:
Using dma_map_ops.
https://lore.kernel.org/patchwork/cover/1271660/
Claire Chang (16):
swiotlb: Fix the type of index
swiotlb: Refactor swiotlb init functions
swiotlb: Refactor swiotlb_create_debugfs
swiotlb: Add DMA_RESTRICTED_POOL
swiotlb: Add restricted DMA pool initialization
swiotlb: Add a new get_io_tlb_mem getter
swiotlb: Update is_swiotlb_buffer to add a struct device argument
swiotlb: Update is_swiotlb_active to add a struct device argument
swiotlb: Bounce data from/to restricted DMA pool if available
swiotlb: Move alloc_size to find_slots
swiotlb: Refactor swiotlb_tbl_unmap_single
dma-direct: Add a new wrapper __dma_direct_free_pages()
swiotlb: Add restricted DMA alloc/free support.
dma-direct: Allocate memory from restricted DMA pool if available
dt-bindings: of: Add restricted DMA pool
of: Add plumbing for restricted DMA pool
.../reserved-memory/reserved-memory.txt | 24 ++
drivers/gpu/drm/i915/gem/i915_gem_internal.c | 2 +-
drivers/gpu/drm/nouveau/nouveau_ttm.c | 2 +-
drivers/iommu/dma-iommu.c | 12 +-
drivers/of/address.c | 25 ++
drivers/of/device.c | 3 +
drivers/of/of_private.h | 5 +
drivers/pci/xen-pcifront.c | 2 +-
drivers/xen/swiotlb-xen.c | 2 +-
include/linux/device.h | 4 +
include/linux/swiotlb.h | 41 ++-
kernel/dma/Kconfig | 14 +
kernel/dma/direct.c | 57 +++--
kernel/dma/direct.h | 9 +-
kernel/dma/swiotlb.c | 242 +++++++++++++-----
15 files changed, 347 insertions(+), 97 deletions(-)
--
2.31.1.368.gbe11c130af-goog
^ permalink raw reply
* [PATCH v5 01/16] swiotlb: Fix the type of index
From: Claire Chang @ 2021-04-22 8:14 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Frank Rowand, Konrad Rzeszutek Wilk,
boris.ostrovsky, jgross, Christoph Hellwig, Marek Szyprowski
Cc: heikki.krogerus, thomas.hellstrom, peterz, joonas.lahtinen,
dri-devel, chris, grant.likely, paulus, mingo, jxgao, sstabellini,
Saravana Kannan, xypron.glpk, Rafael J . Wysocki,
Bartosz Golaszewski, bskeggs, linux-pci, xen-devel,
Thierry Reding, intel-gfx, matthew.auld, linux-devicetree, daniel,
airlied, maarten.lankhorst, linuxppc-dev, jani.nikula,
Nicolas Boichat, rodrigo.vivi, bhelgaas, tientzu, Dan Williams,
Andy Shevchenko, nouveau, Greg KH, Randy Dunlap, lkml, tfiga,
list@263.net:IOMMU DRIVERS, Jim Quinlan, Robin Murphy, bauerman
In-Reply-To: <20210422081508.3942748-1-tientzu@chromium.org>
Fix the type of index from unsigned int to int since find_slots() might
return -1.
Fixes: 0774983bc923 ("swiotlb: refactor swiotlb_tbl_map_single")
Signed-off-by: Claire Chang <tientzu@chromium.org>
---
kernel/dma/swiotlb.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 0a5b6f7e75bc..8635a57f88e9 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -499,7 +499,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
{
struct io_tlb_mem *mem = io_tlb_default_mem;
unsigned int offset = swiotlb_align_offset(dev, orig_addr);
- unsigned int index, i;
+ unsigned int i;
+ int index;
phys_addr_t tlb_addr;
if (!mem)
--
2.31.1.368.gbe11c130af-goog
^ permalink raw reply related
* [PATCH v5 02/16] swiotlb: Refactor swiotlb init functions
From: Claire Chang @ 2021-04-22 8:14 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Frank Rowand, Konrad Rzeszutek Wilk,
boris.ostrovsky, jgross, Christoph Hellwig, Marek Szyprowski
Cc: heikki.krogerus, thomas.hellstrom, peterz, joonas.lahtinen,
dri-devel, chris, grant.likely, paulus, mingo, jxgao, sstabellini,
Saravana Kannan, xypron.glpk, Rafael J . Wysocki,
Bartosz Golaszewski, bskeggs, linux-pci, xen-devel,
Thierry Reding, intel-gfx, matthew.auld, linux-devicetree, daniel,
airlied, maarten.lankhorst, linuxppc-dev, jani.nikula,
Nicolas Boichat, rodrigo.vivi, bhelgaas, tientzu, Dan Williams,
Andy Shevchenko, nouveau, Greg KH, Randy Dunlap, lkml, tfiga,
list@263.net:IOMMU DRIVERS, Jim Quinlan, Robin Murphy, bauerman
In-Reply-To: <20210422081508.3942748-1-tientzu@chromium.org>
Add a new function, swiotlb_init_io_tlb_mem, for the io_tlb_mem struct
initialization to make the code reusable.
Note that we now also call set_memory_decrypted in swiotlb_init_with_tbl.
Signed-off-by: Claire Chang <tientzu@chromium.org>
---
kernel/dma/swiotlb.c | 51 ++++++++++++++++++++++----------------------
1 file changed, 25 insertions(+), 26 deletions(-)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 8635a57f88e9..3f1adee35097 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -166,9 +166,30 @@ void __init swiotlb_update_mem_attributes(void)
memset(vaddr, 0, bytes);
}
-int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
+static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
+ unsigned long nslabs, bool late_alloc)
{
+ void *vaddr = phys_to_virt(start);
unsigned long bytes = nslabs << IO_TLB_SHIFT, i;
+
+ mem->nslabs = nslabs;
+ mem->start = start;
+ mem->end = mem->start + bytes;
+ mem->index = 0;
+ mem->late_alloc = late_alloc;
+ spin_lock_init(&mem->lock);
+ for (i = 0; i < mem->nslabs; i++) {
+ mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i);
+ mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
+ mem->slots[i].alloc_size = 0;
+ }
+
+ set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
+ memset(vaddr, 0, bytes);
+}
+
+int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
+{
struct io_tlb_mem *mem;
size_t alloc_size;
@@ -184,16 +205,8 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
if (!mem)
panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
__func__, alloc_size, PAGE_SIZE);
- mem->nslabs = nslabs;
- mem->start = __pa(tlb);
- mem->end = mem->start + bytes;
- mem->index = 0;
- spin_lock_init(&mem->lock);
- for (i = 0; i < mem->nslabs; i++) {
- mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i);
- mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
- mem->slots[i].alloc_size = 0;
- }
+
+ swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, false);
io_tlb_default_mem = mem;
if (verbose)
@@ -280,7 +293,6 @@ swiotlb_late_init_with_default_size(size_t default_size)
int
swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
{
- unsigned long bytes = nslabs << IO_TLB_SHIFT, i;
struct io_tlb_mem *mem;
if (swiotlb_force == SWIOTLB_NO_FORCE)
@@ -295,20 +307,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
if (!mem)
return -ENOMEM;
- mem->nslabs = nslabs;
- mem->start = virt_to_phys(tlb);
- mem->end = mem->start + bytes;
- mem->index = 0;
- mem->late_alloc = 1;
- spin_lock_init(&mem->lock);
- for (i = 0; i < mem->nslabs; i++) {
- mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i);
- mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
- mem->slots[i].alloc_size = 0;
- }
-
- set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT);
- memset(tlb, 0, bytes);
+ swiotlb_init_io_tlb_mem(mem, virt_to_phys(tlb), nslabs, true);
io_tlb_default_mem = mem;
swiotlb_print_info();
--
I'm not 100% sure if set_memory_decrypted is safe to call in
swiotlb_init_with_tbl, but I didn't hit any issue booting with this.
2.31.1.368.gbe11c130af-goog
^ permalink raw reply related
* [PATCH v5 03/16] swiotlb: Refactor swiotlb_create_debugfs
From: Claire Chang @ 2021-04-22 8:14 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Frank Rowand, Konrad Rzeszutek Wilk,
boris.ostrovsky, jgross, Christoph Hellwig, Marek Szyprowski
Cc: heikki.krogerus, thomas.hellstrom, peterz, joonas.lahtinen,
dri-devel, chris, grant.likely, paulus, mingo, jxgao, sstabellini,
Saravana Kannan, xypron.glpk, Rafael J . Wysocki,
Bartosz Golaszewski, bskeggs, linux-pci, xen-devel,
Thierry Reding, intel-gfx, matthew.auld, linux-devicetree, daniel,
airlied, maarten.lankhorst, linuxppc-dev, jani.nikula,
Nicolas Boichat, rodrigo.vivi, bhelgaas, tientzu, Dan Williams,
Andy Shevchenko, nouveau, Greg KH, Randy Dunlap, lkml, tfiga,
list@263.net:IOMMU DRIVERS, Jim Quinlan, Robin Murphy, bauerman
In-Reply-To: <20210422081508.3942748-1-tientzu@chromium.org>
Split the debugfs creation to make the code reusable for supporting
different bounce buffer pools, e.g. restricted DMA pool.
Signed-off-by: Claire Chang <tientzu@chromium.org>
---
kernel/dma/swiotlb.c | 18 ++++++++++++------
1 file changed, 12 insertions(+), 6 deletions(-)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 3f1adee35097..57a9adb920bf 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -660,18 +660,24 @@ EXPORT_SYMBOL_GPL(is_swiotlb_active);
#ifdef CONFIG_DEBUG_FS
-static int __init swiotlb_create_debugfs(void)
+static void swiotlb_create_debugfs(struct io_tlb_mem *mem, const char *name,
+ struct dentry *node)
{
- struct io_tlb_mem *mem = io_tlb_default_mem;
-
if (!mem)
- return 0;
- mem->debugfs = debugfs_create_dir("swiotlb", NULL);
+ return;
+
+ mem->debugfs = debugfs_create_dir(name, node);
debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs);
debugfs_create_ulong("io_tlb_used", 0400, mem->debugfs, &mem->used);
+}
+
+static int __init swiotlb_create_default_debugfs(void)
+{
+ swiotlb_create_debugfs(io_tlb_default_mem, "swiotlb", NULL);
+
return 0;
}
-late_initcall(swiotlb_create_debugfs);
+late_initcall(swiotlb_create_default_debugfs);
#endif
--
2.31.1.368.gbe11c130af-goog
^ permalink raw reply related
* [PATCH v5 04/16] swiotlb: Add DMA_RESTRICTED_POOL
From: Claire Chang @ 2021-04-22 8:14 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Frank Rowand, Konrad Rzeszutek Wilk,
boris.ostrovsky, jgross, Christoph Hellwig, Marek Szyprowski
Cc: heikki.krogerus, thomas.hellstrom, peterz, joonas.lahtinen,
dri-devel, chris, grant.likely, paulus, mingo, jxgao, sstabellini,
Saravana Kannan, xypron.glpk, Rafael J . Wysocki,
Bartosz Golaszewski, bskeggs, linux-pci, xen-devel,
Thierry Reding, intel-gfx, matthew.auld, linux-devicetree, daniel,
airlied, maarten.lankhorst, linuxppc-dev, jani.nikula,
Nicolas Boichat, rodrigo.vivi, bhelgaas, tientzu, Dan Williams,
Andy Shevchenko, nouveau, Greg KH, Randy Dunlap, lkml, tfiga,
list@263.net:IOMMU DRIVERS, Jim Quinlan, Robin Murphy, bauerman
In-Reply-To: <20210422081508.3942748-1-tientzu@chromium.org>
Add a new kconfig symbol, DMA_RESTRICTED_POOL, for restricted DMA pool.
Signed-off-by: Claire Chang <tientzu@chromium.org>
---
kernel/dma/Kconfig | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 77b405508743..3e961dc39634 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -80,6 +80,20 @@ config SWIOTLB
bool
select NEED_DMA_MAP_STATE
+config DMA_RESTRICTED_POOL
+ bool "DMA Restricted Pool"
+ depends on OF && OF_RESERVED_MEM
+ select SWIOTLB
+ help
+ This enables support for restricted DMA pools which provide a level of
+ DMA memory protection on systems with limited hardware protection
+ capabilities, such as those lacking an IOMMU.
+
+ For more information see
+ <Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt>
+ and <kernel/dma/swiotlb.c>.
+ If unsure, say "n".
+
#
# Should be selected if we can mmap non-coherent mappings to userspace.
# The only thing that is really required is a way to set an uncached bit
--
2.31.1.368.gbe11c130af-goog
^ permalink raw reply related
* [PATCH v5 05/16] swiotlb: Add restricted DMA pool initialization
From: Claire Chang @ 2021-04-22 8:14 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Frank Rowand, Konrad Rzeszutek Wilk,
boris.ostrovsky, jgross, Christoph Hellwig, Marek Szyprowski
Cc: heikki.krogerus, thomas.hellstrom, peterz, joonas.lahtinen,
dri-devel, chris, grant.likely, paulus, mingo, jxgao, sstabellini,
Saravana Kannan, xypron.glpk, Rafael J . Wysocki,
Bartosz Golaszewski, bskeggs, linux-pci, xen-devel,
Thierry Reding, intel-gfx, matthew.auld, linux-devicetree, daniel,
airlied, maarten.lankhorst, linuxppc-dev, jani.nikula,
Nicolas Boichat, rodrigo.vivi, bhelgaas, tientzu, Dan Williams,
Andy Shevchenko, nouveau, Greg KH, Randy Dunlap, lkml, tfiga,
list@263.net:IOMMU DRIVERS, Jim Quinlan, Robin Murphy, bauerman
In-Reply-To: <20210422081508.3942748-1-tientzu@chromium.org>
Add the initialization function to create restricted DMA pools from
matching reserved-memory nodes.
Signed-off-by: Claire Chang <tientzu@chromium.org>
---
include/linux/device.h | 4 +++
include/linux/swiotlb.h | 3 +-
kernel/dma/swiotlb.c | 80 +++++++++++++++++++++++++++++++++++++++++
3 files changed, 86 insertions(+), 1 deletion(-)
diff --git a/include/linux/device.h b/include/linux/device.h
index 38a2071cf776..4987608ea4ff 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -416,6 +416,7 @@ struct dev_links_info {
* @dma_pools: Dma pools (if dma'ble device).
* @dma_mem: Internal for coherent mem override.
* @cma_area: Contiguous memory area for dma allocations
+ * @dma_io_tlb_mem: Internal for swiotlb io_tlb_mem override.
* @archdata: For arch-specific additions.
* @of_node: Associated device tree node.
* @fwnode: Associated device node supplied by platform firmware.
@@ -521,6 +522,9 @@ struct device {
#ifdef CONFIG_DMA_CMA
struct cma *cma_area; /* contiguous memory area for dma
allocations */
+#endif
+#ifdef CONFIG_DMA_RESTRICTED_POOL
+ struct io_tlb_mem *dma_io_tlb_mem;
#endif
/* arch specific additions */
struct dev_archdata archdata;
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 216854a5e513..03ad6e3b4056 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -72,7 +72,8 @@ extern enum swiotlb_force swiotlb_force;
* range check to see if the memory was in fact allocated by this
* API.
* @nslabs: The number of IO TLB blocks (in groups of 64) between @start and
- * @end. This is command line adjustable via setup_io_tlb_npages.
+ * @end. For default swiotlb, this is command line adjustable via
+ * setup_io_tlb_npages.
* @used: The number of used IO TLB block.
* @list: The free list describing the number of free entries available
* from each index.
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 57a9adb920bf..ffbb8724e06c 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -39,6 +39,13 @@
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
#endif
+#ifdef CONFIG_DMA_RESTRICTED_POOL
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/slab.h>
+#endif
#include <asm/io.h>
#include <asm/dma.h>
@@ -681,3 +688,76 @@ static int __init swiotlb_create_default_debugfs(void)
late_initcall(swiotlb_create_default_debugfs);
#endif
+
+#ifdef CONFIG_DMA_RESTRICTED_POOL
+static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
+ struct device *dev)
+{
+ struct io_tlb_mem *mem = rmem->priv;
+ unsigned long nslabs = rmem->size >> IO_TLB_SHIFT;
+
+ if (dev->dma_io_tlb_mem)
+ return 0;
+
+ /* Since multiple devices can share the same pool, the private data,
+ * io_tlb_mem struct, will be initialized by the first device attached
+ * to it.
+ */
+ if (!mem) {
+ mem = kzalloc(struct_size(mem, slots, nslabs), GFP_KERNEL);
+ if (!mem)
+ return -ENOMEM;
+#ifdef CONFIG_ARM
+ if (!PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) {
+ kfree(mem);
+ return -EINVAL;
+ }
+#endif /* CONFIG_ARM */
+ swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, false);
+
+ rmem->priv = mem;
+ }
+
+#ifdef CONFIG_DEBUG_FS
+ if (!io_tlb_default_mem->debugfs)
+ io_tlb_default_mem->debugfs =
+ debugfs_create_dir("swiotlb", NULL);
+
+ swiotlb_create_debugfs(mem, rmem->name, io_tlb_default_mem->debugfs);
+#endif /* CONFIG_DEBUG_FS */
+
+ dev->dma_io_tlb_mem = mem;
+
+ return 0;
+}
+
+static void rmem_swiotlb_device_release(struct reserved_mem *rmem,
+ struct device *dev)
+{
+ if (dev)
+ dev->dma_io_tlb_mem = NULL;
+}
+
+static const struct reserved_mem_ops rmem_swiotlb_ops = {
+ .device_init = rmem_swiotlb_device_init,
+ .device_release = rmem_swiotlb_device_release,
+};
+
+static int __init rmem_swiotlb_setup(struct reserved_mem *rmem)
+{
+ unsigned long node = rmem->fdt_node;
+
+ if (of_get_flat_dt_prop(node, "reusable", NULL) ||
+ of_get_flat_dt_prop(node, "linux,cma-default", NULL) ||
+ of_get_flat_dt_prop(node, "linux,dma-default", NULL) ||
+ of_get_flat_dt_prop(node, "no-map", NULL))
+ return -EINVAL;
+
+ rmem->ops = &rmem_swiotlb_ops;
+ pr_info("Reserved memory: created device swiotlb memory pool at %pa, size %ld MiB\n",
+ &rmem->base, (unsigned long)rmem->size / SZ_1M);
+ return 0;
+}
+
+RESERVEDMEM_OF_DECLARE(dma, "restricted-dma-pool", rmem_swiotlb_setup);
+#endif /* CONFIG_DMA_RESTRICTED_POOL */
--
2.31.1.368.gbe11c130af-goog
^ permalink raw reply related
* [PATCH v5 06/16] swiotlb: Add a new get_io_tlb_mem getter
From: Claire Chang @ 2021-04-22 8:14 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Frank Rowand, Konrad Rzeszutek Wilk,
boris.ostrovsky, jgross, Christoph Hellwig, Marek Szyprowski
Cc: heikki.krogerus, thomas.hellstrom, peterz, joonas.lahtinen,
dri-devel, chris, grant.likely, paulus, mingo, jxgao, sstabellini,
Saravana Kannan, xypron.glpk, Rafael J . Wysocki,
Bartosz Golaszewski, bskeggs, linux-pci, xen-devel,
Thierry Reding, intel-gfx, matthew.auld, linux-devicetree, daniel,
airlied, maarten.lankhorst, linuxppc-dev, jani.nikula,
Nicolas Boichat, rodrigo.vivi, bhelgaas, tientzu, Dan Williams,
Andy Shevchenko, nouveau, Greg KH, Randy Dunlap, lkml, tfiga,
list@263.net:IOMMU DRIVERS, Jim Quinlan, Robin Murphy, bauerman
In-Reply-To: <20210422081508.3942748-1-tientzu@chromium.org>
Add a new getter, get_io_tlb_mem, to help select the io_tlb_mem struct.
The restricted DMA pool is preferred if available.
Signed-off-by: Claire Chang <tientzu@chromium.org>
---
include/linux/swiotlb.h | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 03ad6e3b4056..b469f04cca26 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -2,6 +2,7 @@
#ifndef __LINUX_SWIOTLB_H
#define __LINUX_SWIOTLB_H
+#include <linux/device.h>
#include <linux/dma-direction.h>
#include <linux/init.h>
#include <linux/types.h>
@@ -102,6 +103,16 @@ struct io_tlb_mem {
};
extern struct io_tlb_mem *io_tlb_default_mem;
+static inline struct io_tlb_mem *get_io_tlb_mem(struct device *dev)
+{
+#ifdef CONFIG_DMA_RESTRICTED_POOL
+ if (dev && dev->dma_io_tlb_mem)
+ return dev->dma_io_tlb_mem;
+#endif /* CONFIG_DMA_RESTRICTED_POOL */
+
+ return io_tlb_default_mem;
+}
+
static inline bool is_swiotlb_buffer(phys_addr_t paddr)
{
struct io_tlb_mem *mem = io_tlb_default_mem;
--
2.31.1.368.gbe11c130af-goog
^ permalink raw reply related
* [PATCH v5 07/16] swiotlb: Update is_swiotlb_buffer to add a struct device argument
From: Claire Chang @ 2021-04-22 8:14 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Frank Rowand, Konrad Rzeszutek Wilk,
boris.ostrovsky, jgross, Christoph Hellwig, Marek Szyprowski
Cc: heikki.krogerus, thomas.hellstrom, peterz, joonas.lahtinen,
dri-devel, chris, grant.likely, paulus, mingo, jxgao, sstabellini,
Saravana Kannan, xypron.glpk, Rafael J . Wysocki,
Bartosz Golaszewski, bskeggs, linux-pci, xen-devel,
Thierry Reding, intel-gfx, matthew.auld, linux-devicetree, daniel,
airlied, maarten.lankhorst, linuxppc-dev, jani.nikula,
Nicolas Boichat, rodrigo.vivi, bhelgaas, tientzu, Dan Williams,
Andy Shevchenko, nouveau, Greg KH, Randy Dunlap, lkml, tfiga,
list@263.net:IOMMU DRIVERS, Jim Quinlan, Robin Murphy, bauerman
In-Reply-To: <20210422081508.3942748-1-tientzu@chromium.org>
Update is_swiotlb_buffer to add a struct device argument. This will be
useful later to allow for restricted DMA pool.
Signed-off-by: Claire Chang <tientzu@chromium.org>
---
drivers/iommu/dma-iommu.c | 12 ++++++------
drivers/xen/swiotlb-xen.c | 2 +-
include/linux/swiotlb.h | 6 +++---
kernel/dma/direct.c | 6 +++---
kernel/dma/direct.h | 6 +++---
5 files changed, 16 insertions(+), 16 deletions(-)
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 7bcdd1205535..a5df35bfd150 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -504,7 +504,7 @@ static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr,
__iommu_dma_unmap(dev, dma_addr, size);
- if (unlikely(is_swiotlb_buffer(phys)))
+ if (unlikely(is_swiotlb_buffer(dev, phys)))
swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
}
@@ -575,7 +575,7 @@ static dma_addr_t __iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys,
}
iova = __iommu_dma_map(dev, phys, aligned_size, prot, dma_mask);
- if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(phys))
+ if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(dev, phys))
swiotlb_tbl_unmap_single(dev, phys, org_size, dir, attrs);
return iova;
}
@@ -781,7 +781,7 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev,
if (!dev_is_dma_coherent(dev))
arch_sync_dma_for_cpu(phys, size, dir);
- if (is_swiotlb_buffer(phys))
+ if (is_swiotlb_buffer(dev, phys))
swiotlb_sync_single_for_cpu(dev, phys, size, dir);
}
@@ -794,7 +794,7 @@ static void iommu_dma_sync_single_for_device(struct device *dev,
return;
phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
- if (is_swiotlb_buffer(phys))
+ if (is_swiotlb_buffer(dev, phys))
swiotlb_sync_single_for_device(dev, phys, size, dir);
if (!dev_is_dma_coherent(dev))
@@ -815,7 +815,7 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev,
if (!dev_is_dma_coherent(dev))
arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
- if (is_swiotlb_buffer(sg_phys(sg)))
+ if (is_swiotlb_buffer(dev, sg_phys(sg)))
swiotlb_sync_single_for_cpu(dev, sg_phys(sg),
sg->length, dir);
}
@@ -832,7 +832,7 @@ static void iommu_dma_sync_sg_for_device(struct device *dev,
return;
for_each_sg(sgl, sg, nelems, i) {
- if (is_swiotlb_buffer(sg_phys(sg)))
+ if (is_swiotlb_buffer(dev, sg_phys(sg)))
swiotlb_sync_single_for_device(dev, sg_phys(sg),
sg->length, dir);
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 4c89afc0df62..0c6ed09f8513 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -100,7 +100,7 @@ static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr)
* in our domain. Therefore _only_ check address within our domain.
*/
if (pfn_valid(PFN_DOWN(paddr)))
- return is_swiotlb_buffer(paddr);
+ return is_swiotlb_buffer(dev, paddr);
return 0;
}
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index b469f04cca26..2a6cca07540b 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -113,9 +113,9 @@ static inline struct io_tlb_mem *get_io_tlb_mem(struct device *dev)
return io_tlb_default_mem;
}
-static inline bool is_swiotlb_buffer(phys_addr_t paddr)
+static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr)
{
- struct io_tlb_mem *mem = io_tlb_default_mem;
+ struct io_tlb_mem *mem = get_io_tlb_mem(dev);
return mem && paddr >= mem->start && paddr < mem->end;
}
@@ -127,7 +127,7 @@ bool is_swiotlb_active(void);
void __init swiotlb_adjust_size(unsigned long size);
#else
#define swiotlb_force SWIOTLB_NO_FORCE
-static inline bool is_swiotlb_buffer(phys_addr_t paddr)
+static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr)
{
return false;
}
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index f737e3347059..84c9feb5474a 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -343,7 +343,7 @@ void dma_direct_sync_sg_for_device(struct device *dev,
for_each_sg(sgl, sg, nents, i) {
phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg));
- if (unlikely(is_swiotlb_buffer(paddr)))
+ if (unlikely(is_swiotlb_buffer(dev, paddr)))
swiotlb_sync_single_for_device(dev, paddr, sg->length,
dir);
@@ -369,7 +369,7 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
if (!dev_is_dma_coherent(dev))
arch_sync_dma_for_cpu(paddr, sg->length, dir);
- if (unlikely(is_swiotlb_buffer(paddr)))
+ if (unlikely(is_swiotlb_buffer(dev, paddr)))
swiotlb_sync_single_for_cpu(dev, paddr, sg->length,
dir);
@@ -504,7 +504,7 @@ size_t dma_direct_max_mapping_size(struct device *dev)
bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
{
return !dev_is_dma_coherent(dev) ||
- is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
+ is_swiotlb_buffer(dev, dma_to_phys(dev, dma_addr));
}
/**
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index 50afc05b6f1d..13e9e7158d94 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -56,7 +56,7 @@ static inline void dma_direct_sync_single_for_device(struct device *dev,
{
phys_addr_t paddr = dma_to_phys(dev, addr);
- if (unlikely(is_swiotlb_buffer(paddr)))
+ if (unlikely(is_swiotlb_buffer(dev, paddr)))
swiotlb_sync_single_for_device(dev, paddr, size, dir);
if (!dev_is_dma_coherent(dev))
@@ -73,7 +73,7 @@ static inline void dma_direct_sync_single_for_cpu(struct device *dev,
arch_sync_dma_for_cpu_all();
}
- if (unlikely(is_swiotlb_buffer(paddr)))
+ if (unlikely(is_swiotlb_buffer(dev, paddr)))
swiotlb_sync_single_for_cpu(dev, paddr, size, dir);
if (dir == DMA_FROM_DEVICE)
@@ -113,7 +113,7 @@ static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
dma_direct_sync_single_for_cpu(dev, addr, size, dir);
- if (unlikely(is_swiotlb_buffer(phys)))
+ if (unlikely(is_swiotlb_buffer(dev, phys)))
swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
}
#endif /* _KERNEL_DMA_DIRECT_H */
--
2.31.1.368.gbe11c130af-goog
^ permalink raw reply related
* [PATCH v5 08/16] swiotlb: Update is_swiotlb_active to add a struct device argument
From: Claire Chang @ 2021-04-22 8:15 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Frank Rowand, Konrad Rzeszutek Wilk,
boris.ostrovsky, jgross, Christoph Hellwig, Marek Szyprowski
Cc: heikki.krogerus, thomas.hellstrom, peterz, joonas.lahtinen,
dri-devel, chris, grant.likely, paulus, mingo, jxgao, sstabellini,
Saravana Kannan, xypron.glpk, Rafael J . Wysocki,
Bartosz Golaszewski, bskeggs, linux-pci, xen-devel,
Thierry Reding, intel-gfx, matthew.auld, linux-devicetree, daniel,
airlied, maarten.lankhorst, linuxppc-dev, jani.nikula,
Nicolas Boichat, rodrigo.vivi, bhelgaas, tientzu, Dan Williams,
Andy Shevchenko, nouveau, Greg KH, Randy Dunlap, lkml, tfiga,
list@263.net:IOMMU DRIVERS, Jim Quinlan, Robin Murphy, bauerman
In-Reply-To: <20210422081508.3942748-1-tientzu@chromium.org>
Update is_swiotlb_active to add a struct device argument. This will be
useful later to allow for restricted DMA pool.
Signed-off-by: Claire Chang <tientzu@chromium.org>
---
drivers/gpu/drm/i915/gem/i915_gem_internal.c | 2 +-
drivers/gpu/drm/nouveau/nouveau_ttm.c | 2 +-
drivers/pci/xen-pcifront.c | 2 +-
include/linux/swiotlb.h | 4 ++--
kernel/dma/direct.c | 2 +-
kernel/dma/swiotlb.c | 4 ++--
6 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
index ce6b664b10aa..7d48c433446b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
@@ -42,7 +42,7 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj)
max_order = MAX_ORDER;
#ifdef CONFIG_SWIOTLB
- if (is_swiotlb_active()) {
+ if (is_swiotlb_active(NULL)) {
unsigned int max_segment;
max_segment = swiotlb_max_segment();
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index e8b506a6685b..2a2ae6d6cf6d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -321,7 +321,7 @@ nouveau_ttm_init(struct nouveau_drm *drm)
}
#if IS_ENABLED(CONFIG_SWIOTLB) && IS_ENABLED(CONFIG_X86)
- need_swiotlb = is_swiotlb_active();
+ need_swiotlb = is_swiotlb_active(NULL);
#endif
ret = ttm_device_init(&drm->ttm.bdev, &nouveau_bo_driver, drm->dev->dev,
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index b7a8f3a1921f..6d548ce53ce7 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -693,7 +693,7 @@ static int pcifront_connect_and_init_dma(struct pcifront_device *pdev)
spin_unlock(&pcifront_dev_lock);
- if (!err && !is_swiotlb_active()) {
+ if (!err && !is_swiotlb_active(NULL)) {
err = pci_xen_swiotlb_init_late();
if (err)
dev_err(&pdev->xdev->dev, "Could not setup SWIOTLB!\n");
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 2a6cca07540b..c530c976d18b 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -123,7 +123,7 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr)
void __init swiotlb_exit(void);
unsigned int swiotlb_max_segment(void);
size_t swiotlb_max_mapping_size(struct device *dev);
-bool is_swiotlb_active(void);
+bool is_swiotlb_active(struct device *dev);
void __init swiotlb_adjust_size(unsigned long size);
#else
#define swiotlb_force SWIOTLB_NO_FORCE
@@ -143,7 +143,7 @@ static inline size_t swiotlb_max_mapping_size(struct device *dev)
return SIZE_MAX;
}
-static inline bool is_swiotlb_active(void)
+static inline bool is_swiotlb_active(struct device *dev)
{
return false;
}
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 84c9feb5474a..7a88c34d0867 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -495,7 +495,7 @@ int dma_direct_supported(struct device *dev, u64 mask)
size_t dma_direct_max_mapping_size(struct device *dev)
{
/* If SWIOTLB is active, use its maximum mapping size */
- if (is_swiotlb_active() &&
+ if (is_swiotlb_active(dev) &&
(dma_addressing_limited(dev) || swiotlb_force == SWIOTLB_FORCE))
return swiotlb_max_mapping_size(dev);
return SIZE_MAX;
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index ffbb8724e06c..1d221343f1c8 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -659,9 +659,9 @@ size_t swiotlb_max_mapping_size(struct device *dev)
return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE;
}
-bool is_swiotlb_active(void)
+bool is_swiotlb_active(struct device *dev)
{
- return io_tlb_default_mem != NULL;
+ return get_io_tlb_mem(dev) != NULL;
}
EXPORT_SYMBOL_GPL(is_swiotlb_active);
--
2.31.1.368.gbe11c130af-goog
^ permalink raw reply related
* [PATCH v5 09/16] swiotlb: Bounce data from/to restricted DMA pool if available
From: Claire Chang @ 2021-04-22 8:15 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Frank Rowand, Konrad Rzeszutek Wilk,
boris.ostrovsky, jgross, Christoph Hellwig, Marek Szyprowski
Cc: heikki.krogerus, thomas.hellstrom, peterz, joonas.lahtinen,
dri-devel, chris, grant.likely, paulus, mingo, jxgao, sstabellini,
Saravana Kannan, xypron.glpk, Rafael J . Wysocki,
Bartosz Golaszewski, bskeggs, linux-pci, xen-devel,
Thierry Reding, intel-gfx, matthew.auld, linux-devicetree, daniel,
airlied, maarten.lankhorst, linuxppc-dev, jani.nikula,
Nicolas Boichat, rodrigo.vivi, bhelgaas, tientzu, Dan Williams,
Andy Shevchenko, nouveau, Greg KH, Randy Dunlap, lkml, tfiga,
list@263.net:IOMMU DRIVERS, Jim Quinlan, Robin Murphy, bauerman
In-Reply-To: <20210422081508.3942748-1-tientzu@chromium.org>
Regardless of swiotlb setting, the restricted DMA pool is preferred if
available.
The restricted DMA pools provide a basic level of protection against the
DMA overwriting buffer contents at unexpected times. However, to protect
against general data leakage and system memory corruption, the system
needs to provide a way to lock down the memory access, e.g., MPU.
Note that is_dev_swiotlb_force doesn't check if
swiotlb_force == SWIOTLB_FORCE. Otherwise the memory allocation behavior
with default swiotlb will be changed by the following patche
("dma-direct: Allocate memory from restricted DMA pool if available").
Signed-off-by: Claire Chang <tientzu@chromium.org>
---
include/linux/swiotlb.h | 13 +++++++++++++
kernel/dma/direct.h | 3 ++-
kernel/dma/swiotlb.c | 8 ++++----
3 files changed, 19 insertions(+), 5 deletions(-)
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index c530c976d18b..0c5a18d9cf89 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -120,6 +120,15 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr)
return mem && paddr >= mem->start && paddr < mem->end;
}
+static inline bool is_dev_swiotlb_force(struct device *dev)
+{
+#ifdef CONFIG_DMA_RESTRICTED_POOL
+ if (dev->dma_io_tlb_mem)
+ return true;
+#endif /* CONFIG_DMA_RESTRICTED_POOL */
+ return false;
+}
+
void __init swiotlb_exit(void);
unsigned int swiotlb_max_segment(void);
size_t swiotlb_max_mapping_size(struct device *dev);
@@ -131,6 +140,10 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr)
{
return false;
}
+static inline bool is_dev_swiotlb_force(struct device *dev)
+{
+ return false;
+}
static inline void swiotlb_exit(void)
{
}
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index 13e9e7158d94..f94813674e23 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -87,7 +87,8 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
phys_addr_t phys = page_to_phys(page) + offset;
dma_addr_t dma_addr = phys_to_dma(dev, phys);
- if (unlikely(swiotlb_force == SWIOTLB_FORCE))
+ if (unlikely(swiotlb_force == SWIOTLB_FORCE) ||
+ is_dev_swiotlb_force(dev))
return swiotlb_map(dev, phys, size, dir, attrs);
if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 1d221343f1c8..96ff36d8ec53 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -344,7 +344,7 @@ void __init swiotlb_exit(void)
static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size,
enum dma_data_direction dir)
{
- struct io_tlb_mem *mem = io_tlb_default_mem;
+ struct io_tlb_mem *mem = get_io_tlb_mem(dev);
int index = (tlb_addr - mem->start) >> IO_TLB_SHIFT;
phys_addr_t orig_addr = mem->slots[index].orig_addr;
size_t alloc_size = mem->slots[index].alloc_size;
@@ -426,7 +426,7 @@ static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index)
static int find_slots(struct device *dev, phys_addr_t orig_addr,
size_t alloc_size)
{
- struct io_tlb_mem *mem = io_tlb_default_mem;
+ struct io_tlb_mem *mem = get_io_tlb_mem(dev);
unsigned long boundary_mask = dma_get_seg_boundary(dev);
dma_addr_t tbl_dma_addr =
phys_to_dma_unencrypted(dev, mem->start) & boundary_mask;
@@ -503,7 +503,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
size_t mapping_size, size_t alloc_size,
enum dma_data_direction dir, unsigned long attrs)
{
- struct io_tlb_mem *mem = io_tlb_default_mem;
+ struct io_tlb_mem *mem = get_io_tlb_mem(dev);
unsigned int offset = swiotlb_align_offset(dev, orig_addr);
unsigned int i;
int index;
@@ -554,7 +554,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
size_t mapping_size, enum dma_data_direction dir,
unsigned long attrs)
{
- struct io_tlb_mem *mem = io_tlb_default_mem;
+ struct io_tlb_mem *mem = get_io_tlb_mem(hwdev);
unsigned long flags;
unsigned int offset = swiotlb_align_offset(hwdev, tlb_addr);
int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
--
2.31.1.368.gbe11c130af-goog
^ permalink raw reply related
* [PATCH v5 10/16] swiotlb: Move alloc_size to find_slots
From: Claire Chang @ 2021-04-22 8:15 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Frank Rowand, Konrad Rzeszutek Wilk,
boris.ostrovsky, jgross, Christoph Hellwig, Marek Szyprowski
Cc: heikki.krogerus, thomas.hellstrom, peterz, joonas.lahtinen,
dri-devel, chris, grant.likely, paulus, mingo, jxgao, sstabellini,
Saravana Kannan, xypron.glpk, Rafael J . Wysocki,
Bartosz Golaszewski, bskeggs, linux-pci, xen-devel,
Thierry Reding, intel-gfx, matthew.auld, linux-devicetree, daniel,
airlied, maarten.lankhorst, linuxppc-dev, jani.nikula,
Nicolas Boichat, rodrigo.vivi, bhelgaas, tientzu, Dan Williams,
Andy Shevchenko, nouveau, Greg KH, Randy Dunlap, lkml, tfiga,
list@263.net:IOMMU DRIVERS, Jim Quinlan, Robin Murphy, bauerman
In-Reply-To: <20210422081508.3942748-1-tientzu@chromium.org>
Move the maintenance of alloc_size to find_slots for better code
reusability later.
Signed-off-by: Claire Chang <tientzu@chromium.org>
---
kernel/dma/swiotlb.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 96ff36d8ec53..b7d634d7a7eb 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -479,8 +479,11 @@ static int find_slots(struct device *dev, phys_addr_t orig_addr,
return -1;
found:
- for (i = index; i < index + nslots; i++)
+ for (i = index; i < index + nslots; i++) {
mem->slots[i].list = 0;
+ mem->slots[i].alloc_size =
+ alloc_size - ((i - index) << IO_TLB_SHIFT);
+ }
for (i = index - 1;
io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 &&
mem->slots[i].list; i--)
@@ -535,11 +538,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
* This is needed when we sync the memory. Then we sync the buffer if
* needed.
*/
- for (i = 0; i < nr_slots(alloc_size + offset); i++) {
+ for (i = 0; i < nr_slots(alloc_size + offset); i++)
mem->slots[index + i].orig_addr = slot_addr(orig_addr, i);
- mem->slots[index + i].alloc_size =
- alloc_size - (i << IO_TLB_SHIFT);
- }
tlb_addr = slot_addr(mem->start, index) + offset;
if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
--
2.31.1.368.gbe11c130af-goog
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox