Re: [PATCH v5 06/11] powerpc/pseries/iommu: Add ddw_property_create() and refactor enable_ddw()
Hello Fred, thanks for this feedback! On Tue, 2021-07-20 at 19:49 +0200, Frederic Barrat wrote: > > > kfree(window); > > > > -out_clear_window: > > - remove_ddw(pdn, true); > > +out_del_prop: > > + of_remove_property(pdn, win64); > > > > out_free_prop: > > kfree(win64->name); > > kfree(win64->value); > > kfree(win64); > > > > +out_remove_win: > > + remove_ddw(pdn, true); > > > I believe there's a small problem here. We jump directly to > out_remove_win if allocating the property failed. Yet, the first > thing > remove_ddw() does is look for the property. So it will never find it > and > the window is never removed by the hypervisor. > > Fred That makes sense, thanks for catching this one! What I intended here was just removing the DDW, so I think it should be ok replacing remove_ddw() by a new helper that only does the rtas-call. I will send a v6 with this change soon. > > > > + > > out_failed: > > if (default_win_removed) > > reset_dma_window(dev, pdn); > >
Re: [PATCH v5 06/11] powerpc/pseries/iommu: Add ddw_property_create() and refactor enable_ddw()
On 16/07/2021 10:27, Leonardo Bras wrote:
Code used to create a ddw property that was previously scattered in
enable_ddw() is now gathered in ddw_property_create(), which deals with
allocation and filling the property, letting it ready for
of_property_add(), which now occurs in sequence.
This created an opportunity to reorganize the second part of enable_ddw():
Without this patch enable_ddw() does, in order:
kzalloc() property & members, create_ddw(), fill ddwprop inside property,
ddw_list_new_entry(), do tce_setrange_multi_pSeriesLP_walk in all memory,
of_add_property(), and list_add().
With this patch enable_ddw() does, in order:
create_ddw(), ddw_property_create(), of_add_property(),
ddw_list_new_entry(), do tce_setrange_multi_pSeriesLP_walk in all memory,
and list_add().
This change requires of_remove_property() in case anything fails after
of_add_property(), but we get to do tce_setrange_multi_pSeriesLP_walk
in all memory, which looks the most expensive operation, only if
everything else succeeds.
Signed-off-by: Leonardo Bras
Reviewed-by: Alexey Kardashevskiy
---
arch/powerpc/platforms/pseries/iommu.c | 93 --
1 file changed, 57 insertions(+), 36 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/iommu.c
b/arch/powerpc/platforms/pseries/iommu.c
index b34b473bbdc1..7ca79a04fa52 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -1153,6 +1153,35 @@ static int iommu_get_page_shift(u32 query_page_size)
return 0;
}
+static struct property *ddw_property_create(const char *propname, u32 liobn, u64 dma_addr,
+ u32 page_shift, u32 window_shift)
+{
+ struct dynamic_dma_window_prop *ddwprop;
+ struct property *win64;
+
+ win64 = kzalloc(sizeof(*win64), GFP_KERNEL);
+ if (!win64)
+ return NULL;
+
+ win64->name = kstrdup(propname, GFP_KERNEL);
+ ddwprop = kzalloc(sizeof(*ddwprop), GFP_KERNEL);
+ win64->value = ddwprop;
+ win64->length = sizeof(*ddwprop);
+ if (!win64->name || !win64->value) {
+ kfree(win64->name);
+ kfree(win64->value);
+ kfree(win64);
+ return NULL;
+ }
+
+ ddwprop->liobn = cpu_to_be32(liobn);
+ ddwprop->dma_base = cpu_to_be64(dma_addr);
+ ddwprop->tce_shift = cpu_to_be32(page_shift);
+ ddwprop->window_shift = cpu_to_be32(window_shift);
+
+ return win64;
+}
+
/*
* If the PE supports dynamic dma windows, and there is space for a table
* that can map all pages in a linear offset, then setup such a table,
@@ -1171,12 +1200,12 @@ static bool enable_ddw(struct pci_dev *dev, struct
device_node *pdn)
struct ddw_query_response query;
struct ddw_create_response create;
int page_shift;
+ u64 win_addr;
struct device_node *dn;
u32 ddw_avail[DDW_APPLICABLE_SIZE];
struct direct_window *window;
struct property *win64;
bool ddw_enabled = false;
- struct dynamic_dma_window_prop *ddwprop;
struct failed_ddw_pdn *fpdn;
bool default_win_removed = false;
bool pmem_present;
@@ -1293,72 +1322,64 @@ static bool enable_ddw(struct pci_dev *dev, struct
device_node *pdn)
1ULL << page_shift);
goto out_failed;
}
- win64 = kzalloc(sizeof(struct property), GFP_KERNEL);
- if (!win64) {
- dev_info(>dev,
- "couldn't allocate property for 64bit dma window\n");
- goto out_failed;
- }
- win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL);
- win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL);
- win64->length = sizeof(*ddwprop);
- if (!win64->name || !win64->value) {
- dev_info(>dev,
- "couldn't allocate property name and value\n");
- goto out_free_prop;
- }
ret = create_ddw(dev, ddw_avail, , page_shift, len);
if (ret != 0)
- goto out_free_prop;
-
- ddwprop->liobn = cpu_to_be32(create.liobn);
- ddwprop->dma_base = cpu_to_be64(((u64)create.addr_hi << 32) |
- create.addr_lo);
- ddwprop->tce_shift = cpu_to_be32(page_shift);
- ddwprop->window_shift = cpu_to_be32(len);
+ goto out_failed;
dev_dbg(>dev, "created tce table LIOBN 0x%x for %pOF\n",
create.liobn, dn);
- window = ddw_list_new_entry(pdn, ddwprop);
+ win_addr = ((u64)create.addr_hi << 32) | create.addr_lo;
+ win64 = ddw_property_create(DIRECT64_PROPNAME, create.liobn, win_addr,
+ page_shift, len);
+ if (!win64) {
+ dev_info(>dev,
+"couldn't allocate property, property name, or
value\n");
+ goto out_remove_win;
+ }
+
+ ret =
[PATCH v5 06/11] powerpc/pseries/iommu: Add ddw_property_create() and refactor enable_ddw()
Code used to create a ddw property that was previously scattered in
enable_ddw() is now gathered in ddw_property_create(), which deals with
allocation and filling the property, letting it ready for
of_property_add(), which now occurs in sequence.
This created an opportunity to reorganize the second part of enable_ddw():
Without this patch enable_ddw() does, in order:
kzalloc() property & members, create_ddw(), fill ddwprop inside property,
ddw_list_new_entry(), do tce_setrange_multi_pSeriesLP_walk in all memory,
of_add_property(), and list_add().
With this patch enable_ddw() does, in order:
create_ddw(), ddw_property_create(), of_add_property(),
ddw_list_new_entry(), do tce_setrange_multi_pSeriesLP_walk in all memory,
and list_add().
This change requires of_remove_property() in case anything fails after
of_add_property(), but we get to do tce_setrange_multi_pSeriesLP_walk
in all memory, which looks the most expensive operation, only if
everything else succeeds.
Signed-off-by: Leonardo Bras
Reviewed-by: Alexey Kardashevskiy
---
arch/powerpc/platforms/pseries/iommu.c | 93 --
1 file changed, 57 insertions(+), 36 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/iommu.c
b/arch/powerpc/platforms/pseries/iommu.c
index b34b473bbdc1..7ca79a04fa52 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -1153,6 +1153,35 @@ static int iommu_get_page_shift(u32 query_page_size)
return 0;
}
+static struct property *ddw_property_create(const char *propname, u32 liobn,
u64 dma_addr,
+ u32 page_shift, u32 window_shift)
+{
+ struct dynamic_dma_window_prop *ddwprop;
+ struct property *win64;
+
+ win64 = kzalloc(sizeof(*win64), GFP_KERNEL);
+ if (!win64)
+ return NULL;
+
+ win64->name = kstrdup(propname, GFP_KERNEL);
+ ddwprop = kzalloc(sizeof(*ddwprop), GFP_KERNEL);
+ win64->value = ddwprop;
+ win64->length = sizeof(*ddwprop);
+ if (!win64->name || !win64->value) {
+ kfree(win64->name);
+ kfree(win64->value);
+ kfree(win64);
+ return NULL;
+ }
+
+ ddwprop->liobn = cpu_to_be32(liobn);
+ ddwprop->dma_base = cpu_to_be64(dma_addr);
+ ddwprop->tce_shift = cpu_to_be32(page_shift);
+ ddwprop->window_shift = cpu_to_be32(window_shift);
+
+ return win64;
+}
+
/*
* If the PE supports dynamic dma windows, and there is space for a table
* that can map all pages in a linear offset, then setup such a table,
@@ -1171,12 +1200,12 @@ static bool enable_ddw(struct pci_dev *dev, struct
device_node *pdn)
struct ddw_query_response query;
struct ddw_create_response create;
int page_shift;
+ u64 win_addr;
struct device_node *dn;
u32 ddw_avail[DDW_APPLICABLE_SIZE];
struct direct_window *window;
struct property *win64;
bool ddw_enabled = false;
- struct dynamic_dma_window_prop *ddwprop;
struct failed_ddw_pdn *fpdn;
bool default_win_removed = false;
bool pmem_present;
@@ -1293,72 +1322,64 @@ static bool enable_ddw(struct pci_dev *dev, struct
device_node *pdn)
1ULL << page_shift);
goto out_failed;
}
- win64 = kzalloc(sizeof(struct property), GFP_KERNEL);
- if (!win64) {
- dev_info(>dev,
- "couldn't allocate property for 64bit dma window\n");
- goto out_failed;
- }
- win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL);
- win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL);
- win64->length = sizeof(*ddwprop);
- if (!win64->name || !win64->value) {
- dev_info(>dev,
- "couldn't allocate property name and value\n");
- goto out_free_prop;
- }
ret = create_ddw(dev, ddw_avail, , page_shift, len);
if (ret != 0)
- goto out_free_prop;
-
- ddwprop->liobn = cpu_to_be32(create.liobn);
- ddwprop->dma_base = cpu_to_be64(((u64)create.addr_hi << 32) |
- create.addr_lo);
- ddwprop->tce_shift = cpu_to_be32(page_shift);
- ddwprop->window_shift = cpu_to_be32(len);
+ goto out_failed;
dev_dbg(>dev, "created tce table LIOBN 0x%x for %pOF\n",
create.liobn, dn);
- window = ddw_list_new_entry(pdn, ddwprop);
+ win_addr = ((u64)create.addr_hi << 32) | create.addr_lo;
+ win64 = ddw_property_create(DIRECT64_PROPNAME, create.liobn, win_addr,
+ page_shift, len);
+ if (!win64) {
+ dev_info(>dev,
+"couldn't allocate property, property name, or
value\n");
+ goto out_remove_win;
+ }
+
+ ret = of_add_property(pdn, win64);
+ if (ret) {
+
