* [PATCH 15/18] iommu: remove iommu_set_cmd_line_dma_api and iommu_cmd_line_dma_api
From: Christoph Hellwig @ 2021-03-16 15:38 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Li Yang
Cc: freedreno, kvm, linuxppc-dev, dri-devel, virtualization, iommu,
netdev, linux-arm-msm, David Woodhouse, linux-arm-kernel,
Lu Baolu
In-Reply-To: <20210316153825.135976-1-hch@lst.de>
Don't obsfucate the trivial bit flag check.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/iommu/iommu.c | 23 +++++------------------
1 file changed, 5 insertions(+), 18 deletions(-)
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 58d1d11a8d5c10..052cef11ae30df 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -70,16 +70,6 @@ static const char * const iommu_group_resv_type_string[] = {
#define IOMMU_CMD_LINE_DMA_API BIT(0)
-static void iommu_set_cmd_line_dma_api(void)
-{
- iommu_cmd_line |= IOMMU_CMD_LINE_DMA_API;
-}
-
-static bool iommu_cmd_line_dma_api(void)
-{
- return !!(iommu_cmd_line & IOMMU_CMD_LINE_DMA_API);
-}
-
static int iommu_alloc_default_domain(struct iommu_group *group,
struct device *dev);
static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
@@ -130,9 +120,7 @@ static const char *iommu_domain_type_str(unsigned int t)
static int __init iommu_subsys_init(void)
{
- bool cmd_line = iommu_cmd_line_dma_api();
-
- if (!cmd_line) {
+ if (!(iommu_cmd_line & IOMMU_CMD_LINE_DMA_API)) {
if (IS_ENABLED(CONFIG_IOMMU_DEFAULT_PASSTHROUGH))
iommu_set_default_passthrough(false);
else
@@ -146,7 +134,8 @@ static int __init iommu_subsys_init(void)
pr_info("Default domain type: %s %s\n",
iommu_domain_type_str(iommu_def_domain_type),
- cmd_line ? "(set via kernel command line)" : "");
+ (iommu_cmd_line & IOMMU_CMD_LINE_DMA_API) ?
+ "(set via kernel command line)" : "");
return 0;
}
@@ -2757,16 +2746,14 @@ EXPORT_SYMBOL_GPL(iommu_alloc_resv_region);
void iommu_set_default_passthrough(bool cmd_line)
{
if (cmd_line)
- iommu_set_cmd_line_dma_api();
-
+ iommu_cmd_line |= IOMMU_CMD_LINE_DMA_API;
iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY;
}
void iommu_set_default_translated(bool cmd_line)
{
if (cmd_line)
- iommu_set_cmd_line_dma_api();
-
+ iommu_cmd_line |= IOMMU_CMD_LINE_DMA_API;
iommu_def_domain_type = IOMMU_DOMAIN_DMA;
}
--
2.30.1
^ permalink raw reply related
* [PATCH 16/18] iommu: remove DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE
From: Christoph Hellwig @ 2021-03-16 15:38 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Li Yang
Cc: freedreno, kvm, linuxppc-dev, dri-devel, virtualization, iommu,
netdev, linux-arm-msm, Robin Murphy, David Woodhouse,
linux-arm-kernel, Lu Baolu
In-Reply-To: <20210316153825.135976-1-hch@lst.de>
From: Robin Murphy <robin.murphy@arm.com>
Instead make the global iommu_dma_strict paramete in iommu.c canonical by
exporting helpers to get and set it and use those directly in the drivers.
This make sure that the iommu.strict parameter also works for the AMD and
Intel IOMMU drivers on x86. As those default to lazy flushing a new
IOMMU_CMD_LINE_STRICT is used to turn the value into a tristate to
represent the default if not overriden by an explicit parameter.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>.
[ported on top of the other iommu_attr changes and added a few small
missing bits]
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/iommu/amd/iommu.c | 23 +-------
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 50 +---------------
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 1 -
drivers/iommu/arm/arm-smmu/arm-smmu.c | 27 +--------
drivers/iommu/dma-iommu.c | 9 +--
drivers/iommu/intel/iommu.c | 64 ++++-----------------
drivers/iommu/iommu.c | 27 ++++++---
include/linux/iommu.h | 4 +-
8 files changed, 40 insertions(+), 165 deletions(-)
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index a69a8b573e40d0..ce6393d2224d86 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1771,26 +1771,6 @@ static struct iommu_group *amd_iommu_device_group(struct device *dev)
return acpihid_device_group(dev);
}
-static int amd_iommu_domain_get_attr(struct iommu_domain *domain,
- enum iommu_attr attr, void *data)
-{
- switch (domain->type) {
- case IOMMU_DOMAIN_UNMANAGED:
- return -ENODEV;
- case IOMMU_DOMAIN_DMA:
- switch (attr) {
- case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
- *(int *)data = !amd_iommu_unmap_flush;
- return 0;
- default:
- return -ENODEV;
- }
- break;
- default:
- return -EINVAL;
- }
-}
-
/*****************************************************************************
*
* The next functions belong to the dma_ops mapping/unmapping code.
@@ -1855,7 +1835,7 @@ int __init amd_iommu_init_dma_ops(void)
pr_info("IO/TLB flush on unmap enabled\n");
else
pr_info("Lazy IO/TLB flushing enabled\n");
-
+ iommu_set_dma_strict(amd_iommu_unmap_flush);
return 0;
}
@@ -2257,7 +2237,6 @@ const struct iommu_ops amd_iommu_ops = {
.release_device = amd_iommu_release_device,
.probe_finalize = amd_iommu_probe_finalize,
.device_group = amd_iommu_device_group,
- .domain_get_attr = amd_iommu_domain_get_attr,
.get_resv_regions = amd_iommu_get_resv_regions,
.put_resv_regions = generic_iommu_put_resv_regions,
.is_attach_deferred = amd_iommu_is_attach_deferred,
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index f1e38526d5bd40..996dfdf9d375dd 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -2017,7 +2017,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain,
.iommu_dev = smmu->dev,
};
- if (smmu_domain->non_strict)
+ if (!iommu_get_dma_strict())
pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
@@ -2449,52 +2449,6 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
return group;
}
-static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
- enum iommu_attr attr, void *data)
-{
- struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
-
- switch (domain->type) {
- case IOMMU_DOMAIN_DMA:
- switch (attr) {
- case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
- *(int *)data = smmu_domain->non_strict;
- return 0;
- default:
- return -ENODEV;
- }
- break;
- default:
- return -EINVAL;
- }
-}
-
-static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
- enum iommu_attr attr, void *data)
-{
- int ret = 0;
- struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
-
- mutex_lock(&smmu_domain->init_mutex);
-
- switch (domain->type) {
- case IOMMU_DOMAIN_DMA:
- switch(attr) {
- case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
- smmu_domain->non_strict = *(int *)data;
- break;
- default:
- ret = -ENODEV;
- }
- break;
- default:
- ret = -EINVAL;
- }
-
- mutex_unlock(&smmu_domain->init_mutex);
- return ret;
-}
-
static int arm_smmu_enable_nesting(struct iommu_domain *domain)
{
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
@@ -2607,8 +2561,6 @@ static struct iommu_ops arm_smmu_ops = {
.probe_device = arm_smmu_probe_device,
.release_device = arm_smmu_release_device,
.device_group = arm_smmu_device_group,
- .domain_get_attr = arm_smmu_domain_get_attr,
- .domain_set_attr = arm_smmu_domain_set_attr,
.enable_nesting = arm_smmu_enable_nesting,
.of_xlate = arm_smmu_of_xlate,
.get_resv_regions = arm_smmu_get_resv_regions,
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index f985817c967a25..edb1de479dd1a7 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -668,7 +668,6 @@ struct arm_smmu_domain {
struct mutex init_mutex; /* Protects smmu pointer */
struct io_pgtable_ops *pgtbl_ops;
- bool non_strict;
atomic_t nr_ats_masters;
enum arm_smmu_domain_stage stage;
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 0aa6d667274970..3dde22b1f8ffb0 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -761,6 +761,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
.iommu_dev = smmu->dev,
};
+ if (!iommu_get_dma_strict())
+ pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
+
if (smmu->impl && smmu->impl->init_context) {
ret = smmu->impl->init_context(smmu_domain, &pgtbl_cfg, dev);
if (ret)
@@ -1499,18 +1502,6 @@ static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
return -ENODEV;
}
break;
- case IOMMU_DOMAIN_DMA:
- switch (attr) {
- case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE: {
- bool non_strict = smmu_domain->pgtbl_cfg.quirks &
- IO_PGTABLE_QUIRK_NON_STRICT;
- *(int *)data = non_strict;
- return 0;
- }
- default:
- return -ENODEV;
- }
- break;
default:
return -EINVAL;
}
@@ -1557,18 +1548,6 @@ static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
ret = -ENODEV;
}
break;
- case IOMMU_DOMAIN_DMA:
- switch (attr) {
- case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
- if (*(int *)data)
- smmu_domain->pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
- else
- smmu_domain->pgtbl_cfg.quirks &= ~IO_PGTABLE_QUIRK_NON_STRICT;
- break;
- default:
- ret = -ENODEV;
- }
- break;
default:
ret = -EINVAL;
}
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index af765c813cc84c..49cec03dec3dd2 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -304,10 +304,7 @@ static void iommu_dma_flush_iotlb_all(struct iova_domain *iovad)
cookie = container_of(iovad, struct iommu_dma_cookie, iovad);
domain = cookie->fq_domain;
- /*
- * The IOMMU driver supporting DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE
- * implies that ops->flush_iotlb_all must be non-NULL.
- */
+
domain->ops->flush_iotlb_all(domain);
}
@@ -334,7 +331,6 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
struct iommu_dma_cookie *cookie = domain->iova_cookie;
unsigned long order, base_pfn;
struct iova_domain *iovad;
- int attr;
if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
return -EINVAL;
@@ -371,8 +367,7 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
init_iova_domain(iovad, 1UL << order, base_pfn);
if (!cookie->fq_domain && (!dev || !dev_is_untrusted(dev)) &&
- !iommu_domain_get_attr(domain, DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, &attr) &&
- attr) {
+ domain->ops->flush_iotlb_all && !iommu_get_dma_strict()) {
if (init_iova_flush_queue(iovad, iommu_dma_flush_iotlb_all,
iommu_dma_entry_dtor))
pr_warn("iova flush queue initialization failed\n");
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 070ba76242e819..5b00adfb7212a7 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4377,6 +4377,17 @@ int __init intel_iommu_init(void)
down_read(&dmar_global_lock);
for_each_active_iommu(iommu, drhd) {
+ /*
+ * The flush queue implementation does not perform
+ * page-selective invalidations that are required for efficient
+ * TLB flushes in virtual environments. The benefit of batching
+ * is likely to be much lower than the overhead of synchronizing
+ * the virtual and physical IOMMU page-tables.
+ */
+ if (!intel_iommu_strict && cap_caching_mode(iommu->cap)) {
+ pr_warn("IOMMU batching is disabled due to virtualization");
+ intel_iommu_strict = 1;
+ }
iommu_device_sysfs_add(&iommu->iommu, NULL,
intel_iommu_groups,
"%s", iommu->name);
@@ -4385,6 +4396,7 @@ int __init intel_iommu_init(void)
}
up_read(&dmar_global_lock);
+ iommu_set_dma_strict(intel_iommu_strict);
bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
if (si_domain && !hw_pass_through)
register_memory_notifier(&intel_iommu_memory_nb);
@@ -5440,57 +5452,6 @@ intel_iommu_enable_nesting(struct iommu_domain *domain)
return ret;
}
-static bool domain_use_flush_queue(void)
-{
- struct dmar_drhd_unit *drhd;
- struct intel_iommu *iommu;
- bool r = true;
-
- if (intel_iommu_strict)
- return false;
-
- /*
- * The flush queue implementation does not perform page-selective
- * invalidations that are required for efficient TLB flushes in virtual
- * environments. The benefit of batching is likely to be much lower than
- * the overhead of synchronizing the virtual and physical IOMMU
- * page-tables.
- */
- rcu_read_lock();
- for_each_active_iommu(iommu, drhd) {
- if (!cap_caching_mode(iommu->cap))
- continue;
-
- pr_warn_once("IOMMU batching is disabled due to virtualization");
- r = false;
- break;
- }
- rcu_read_unlock();
-
- return r;
-}
-
-static int
-intel_iommu_domain_get_attr(struct iommu_domain *domain,
- enum iommu_attr attr, void *data)
-{
- switch (domain->type) {
- case IOMMU_DOMAIN_UNMANAGED:
- return -ENODEV;
- case IOMMU_DOMAIN_DMA:
- switch (attr) {
- case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
- *(int *)data = domain_use_flush_queue();
- return 0;
- default:
- return -ENODEV;
- }
- break;
- default:
- return -EINVAL;
- }
-}
-
/*
* Check that the device does not live on an external facing PCI port that is
* marked as untrusted. Such devices should not be able to apply quirks and
@@ -5563,7 +5524,6 @@ const struct iommu_ops intel_iommu_ops = {
.capable = intel_iommu_capable,
.domain_alloc = intel_iommu_domain_alloc,
.domain_free = intel_iommu_domain_free,
- .domain_get_attr = intel_iommu_domain_get_attr,
.enable_nesting = intel_iommu_enable_nesting,
.attach_dev = intel_iommu_attach_device,
.detach_dev = intel_iommu_detach_device,
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 052cef11ae30df..e193ea88f3f842 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -69,6 +69,7 @@ static const char * const iommu_group_resv_type_string[] = {
};
#define IOMMU_CMD_LINE_DMA_API BIT(0)
+#define IOMMU_CMD_LINE_STRICT BIT(1)
static int iommu_alloc_default_domain(struct iommu_group *group,
struct device *dev);
@@ -318,10 +319,26 @@ early_param("iommu.passthrough", iommu_set_def_domain_type);
static int __init iommu_dma_setup(char *str)
{
- return kstrtobool(str, &iommu_dma_strict);
+ int ret = kstrtobool(str, &iommu_dma_strict);
+
+ if (!ret)
+ iommu_cmd_line |= IOMMU_CMD_LINE_STRICT;
+ return ret;
}
early_param("iommu.strict", iommu_dma_setup);
+void iommu_set_dma_strict(bool strict)
+{
+ if (strict || !(iommu_cmd_line & IOMMU_CMD_LINE_STRICT))
+ iommu_dma_strict = strict;
+}
+
+bool iommu_get_dma_strict(void)
+{
+ return iommu_dma_strict;
+}
+EXPORT_SYMBOL_GPL(iommu_get_dma_strict);
+
static ssize_t iommu_group_attr_show(struct kobject *kobj,
struct attribute *__attr, char *buf)
{
@@ -1500,14 +1517,6 @@ static int iommu_group_alloc_default_domain(struct bus_type *bus,
group->default_domain = dom;
if (!group->domain)
group->domain = dom;
-
- if (!iommu_dma_strict) {
- int attr = 1;
- iommu_domain_set_attr(dom,
- DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE,
- &attr);
- }
-
return 0;
}
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 670e7a3523f286..3d50ecf3a49c24 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -107,7 +107,6 @@ enum iommu_cap {
*/
enum iommu_attr {
- DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE,
DOMAIN_ATTR_IO_PGTABLE_CFG,
DOMAIN_ATTR_MAX,
};
@@ -498,6 +497,9 @@ extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr,
void *data);
int iommu_enable_nesting(struct iommu_domain *domain);
+void iommu_set_dma_strict(bool val);
+bool iommu_get_dma_strict(void);
+
extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
unsigned long iova, int flags);
--
2.30.1
^ permalink raw reply related
* [PATCH 17/18] iommu: remove DOMAIN_ATTR_IO_PGTABLE_CFG
From: Christoph Hellwig @ 2021-03-16 15:38 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Li Yang
Cc: freedreno, kvm, linuxppc-dev, dri-devel, virtualization, iommu,
netdev, linux-arm-msm, David Woodhouse, linux-arm-kernel,
Lu Baolu
In-Reply-To: <20210316153825.135976-1-hch@lst.de>
Use an explicit set_pgtable_quirks method instead that just passes
the actual quirk bitmask instead.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Li Yang <leoyang.li@nxp.com>
---
drivers/gpu/drm/msm/adreno/adreno_gpu.c | 5 +-
drivers/iommu/arm/arm-smmu/arm-smmu.c | 64 +++++--------------------
drivers/iommu/arm/arm-smmu/arm-smmu.h | 2 +-
drivers/iommu/iommu.c | 11 +++++
include/linux/io-pgtable.h | 4 --
include/linux/iommu.h | 12 ++++-
6 files changed, 35 insertions(+), 63 deletions(-)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 0f184c3dd9d9ec..4a0b14dad93e2e 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -188,10 +188,7 @@ int adreno_zap_shader_load(struct msm_gpu *gpu, u32 pasid)
void adreno_set_llc_attributes(struct iommu_domain *iommu)
{
- struct io_pgtable_domain_attr pgtbl_cfg;
-
- pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_ARM_OUTER_WBWA;
- iommu_domain_set_attr(iommu, DOMAIN_ATTR_IO_PGTABLE_CFG, &pgtbl_cfg);
+ iommu_set_pgtable_quirks(iommu, IO_PGTABLE_QUIRK_ARM_OUTER_WBWA);
}
struct msm_gem_address_space *
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 3dde22b1f8ffb0..b5e747eeed1362 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -770,8 +770,8 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
goto out_clear_smmu;
}
- if (smmu_domain->pgtbl_cfg.quirks)
- pgtbl_cfg.quirks |= smmu_domain->pgtbl_cfg.quirks;
+ if (smmu_domain->pgtbl_quirks)
+ pgtbl_cfg.quirks |= smmu_domain->pgtbl_quirks;
pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
if (!pgtbl_ops) {
@@ -1484,29 +1484,6 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
return group;
}
-static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
- enum iommu_attr attr, void *data)
-{
- struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
-
- switch(domain->type) {
- case IOMMU_DOMAIN_UNMANAGED:
- switch (attr) {
- case DOMAIN_ATTR_IO_PGTABLE_CFG: {
- struct io_pgtable_domain_attr *pgtbl_cfg = data;
- *pgtbl_cfg = smmu_domain->pgtbl_cfg;
-
- return 0;
- }
- default:
- return -ENODEV;
- }
- break;
- default:
- return -EINVAL;
- }
-}
-
static int arm_smmu_enable_nesting(struct iommu_domain *domain)
{
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
@@ -1522,37 +1499,19 @@ static int arm_smmu_enable_nesting(struct iommu_domain *domain)
return ret;
}
-static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
- enum iommu_attr attr, void *data)
+static int arm_smmu_set_pgtable_quirks(struct iommu_domain *domain,
+ unsigned long quirks)
{
- int ret = 0;
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ int ret = 0;
mutex_lock(&smmu_domain->init_mutex);
-
- switch(domain->type) {
- case IOMMU_DOMAIN_UNMANAGED:
- switch (attr) {
- case DOMAIN_ATTR_IO_PGTABLE_CFG: {
- struct io_pgtable_domain_attr *pgtbl_cfg = data;
-
- if (smmu_domain->smmu) {
- ret = -EPERM;
- goto out_unlock;
- }
-
- smmu_domain->pgtbl_cfg = *pgtbl_cfg;
- break;
- }
- default:
- ret = -ENODEV;
- }
- break;
- default:
- ret = -EINVAL;
- }
-out_unlock:
+ if (smmu_domain->smmu)
+ ret = -EPERM;
+ else
+ smmu_domain->pgtbl_quirks = quirks;
mutex_unlock(&smmu_domain->init_mutex);
+
return ret;
}
@@ -1611,9 +1570,8 @@ static struct iommu_ops arm_smmu_ops = {
.probe_device = arm_smmu_probe_device,
.release_device = arm_smmu_release_device,
.device_group = arm_smmu_device_group,
- .domain_get_attr = arm_smmu_domain_get_attr,
- .domain_set_attr = arm_smmu_domain_set_attr,
.enable_nesting = arm_smmu_enable_nesting,
+ .set_pgtable_quirks = arm_smmu_set_pgtable_quirks,
.of_xlate = arm_smmu_of_xlate,
.get_resv_regions = arm_smmu_get_resv_regions,
.put_resv_regions = generic_iommu_put_resv_regions,
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
index d2a2d1bc58bad8..c31a59d35c64da 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -364,7 +364,7 @@ enum arm_smmu_domain_stage {
struct arm_smmu_domain {
struct arm_smmu_device *smmu;
struct io_pgtable_ops *pgtbl_ops;
- struct io_pgtable_domain_attr pgtbl_cfg;
+ unsigned long pgtbl_quirks;
const struct iommu_flush_ops *flush_ops;
struct arm_smmu_cfg cfg;
enum arm_smmu_domain_stage stage;
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index e193ea88f3f842..afd21b37e319ee 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2698,6 +2698,17 @@ int iommu_enable_nesting(struct iommu_domain *domain)
}
EXPORT_SYMBOL_GPL(iommu_enable_nesting);
+int iommu_set_pgtable_quirks(struct iommu_domain *domain,
+ unsigned long quirk)
+{
+ if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+ return -EINVAL;
+ if (!domain->ops->set_pgtable_quirks)
+ return -EINVAL;
+ return domain->ops->set_pgtable_quirks(domain, quirk);
+}
+EXPORT_SYMBOL_GPL(iommu_set_pgtable_quirks);
+
void iommu_get_resv_regions(struct device *dev, struct list_head *list)
{
const struct iommu_ops *ops = dev->bus->iommu_ops;
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index a4c9ca2c31f10a..4d40dfa75b55fe 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -204,10 +204,6 @@ struct io_pgtable {
#define io_pgtable_ops_to_pgtable(x) container_of((x), struct io_pgtable, ops)
-struct io_pgtable_domain_attr {
- unsigned long quirks;
-};
-
static inline void io_pgtable_tlb_flush_all(struct io_pgtable *iop)
{
if (iop->cfg.tlb && iop->cfg.tlb->tlb_flush_all)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 3d50ecf3a49c24..a53d74f2007b14 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -107,7 +107,6 @@ enum iommu_cap {
*/
enum iommu_attr {
- DOMAIN_ATTR_IO_PGTABLE_CFG,
DOMAIN_ATTR_MAX,
};
@@ -195,6 +194,7 @@ struct iommu_iotlb_gather {
* @domain_get_attr: Query domain attributes
* @domain_set_attr: Change domain attributes
* @enable_nesting: Enable nesting
+ * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*)
* @get_resv_regions: Request list of reserved regions for a device
* @put_resv_regions: Free list of reserved regions for a device
* @apply_resv_region: Temporary helper call-back for iova reserved ranges
@@ -248,6 +248,8 @@ struct iommu_ops {
int (*domain_set_attr)(struct iommu_domain *domain,
enum iommu_attr attr, void *data);
int (*enable_nesting)(struct iommu_domain *domain);
+ int (*set_pgtable_quirks)(struct iommu_domain *domain,
+ unsigned long quirks);
/* Request/Free a list of reserved regions for a device */
void (*get_resv_regions)(struct device *dev, struct list_head *list);
@@ -496,6 +498,8 @@ extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr,
extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr,
void *data);
int iommu_enable_nesting(struct iommu_domain *domain);
+int iommu_set_pgtable_quirks(struct iommu_domain *domain,
+ unsigned long quirks);
void iommu_set_dma_strict(bool val);
bool iommu_get_dma_strict(void);
@@ -877,6 +881,12 @@ static inline int iommu_domain_set_attr(struct iommu_domain *domain,
return -EINVAL;
}
+static inline int iommu_set_pgtable_quirks(struct iommu_domain *domain,
+ unsigned long quirks)
+{
+ return 0;
+}
+
static inline int iommu_device_register(struct iommu_device *iommu)
{
return -ENODEV;
--
2.30.1
^ permalink raw reply related
* [PATCH 18/18] iommu: remove iommu_domain_{get,set}_attr
From: Christoph Hellwig @ 2021-03-16 15:38 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Li Yang
Cc: freedreno, kvm, linuxppc-dev, dri-devel, virtualization, iommu,
netdev, linux-arm-msm, David Woodhouse, linux-arm-kernel,
Lu Baolu
In-Reply-To: <20210316153825.135976-1-hch@lst.de>
Remove the now unused iommu attr infrastructure.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/iommu/iommu.c | 26 --------------------------
include/linux/iommu.h | 36 ------------------------------------
2 files changed, 62 deletions(-)
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index afd21b37e319ee..d8df26d13c7371 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2662,32 +2662,6 @@ static int __init iommu_init(void)
}
core_initcall(iommu_init);
-int iommu_domain_get_attr(struct iommu_domain *domain,
- enum iommu_attr attr, void *data)
-{
- if (!domain->ops->domain_get_attr)
- return -EINVAL;
- return domain->ops->domain_get_attr(domain, attr, data);
-}
-EXPORT_SYMBOL_GPL(iommu_domain_get_attr);
-
-int iommu_domain_set_attr(struct iommu_domain *domain,
- enum iommu_attr attr, void *data)
-{
- int ret = 0;
-
- switch (attr) {
- default:
- if (domain->ops->domain_set_attr == NULL)
- return -EINVAL;
-
- ret = domain->ops->domain_set_attr(domain, attr, data);
- }
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(iommu_domain_set_attr);
-
int iommu_enable_nesting(struct iommu_domain *domain)
{
if (domain->type != IOMMU_DOMAIN_UNMANAGED)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index a53d74f2007b14..9319333ca0b827 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -96,20 +96,6 @@ enum iommu_cap {
IOMMU_CAP_NOEXEC, /* IOMMU_NOEXEC flag */
};
-/*
- * Following constraints are specifc to FSL_PAMUV1:
- * -aperture must be power of 2, and naturally aligned
- * -number of windows must be power of 2, and address space size
- * of each window is determined by aperture size / # of windows
- * -the actual size of the mapped region of a window must be power
- * of 2 starting with 4KB and physical address must be naturally
- * aligned.
- */
-
-enum iommu_attr {
- DOMAIN_ATTR_MAX,
-};
-
/* These are the possible reserved region types */
enum iommu_resv_type {
/* Memory regions which must be mapped 1:1 at all times */
@@ -191,8 +177,6 @@ struct iommu_iotlb_gather {
* @probe_finalize: Do final setup work after the device is added to an IOMMU
* group and attached to the groups domain
* @device_group: find iommu group for a particular device
- * @domain_get_attr: Query domain attributes
- * @domain_set_attr: Change domain attributes
* @enable_nesting: Enable nesting
* @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*)
* @get_resv_regions: Request list of reserved regions for a device
@@ -243,10 +227,6 @@ struct iommu_ops {
void (*release_device)(struct device *dev);
void (*probe_finalize)(struct device *dev);
struct iommu_group *(*device_group)(struct device *dev);
- int (*domain_get_attr)(struct iommu_domain *domain,
- enum iommu_attr attr, void *data);
- int (*domain_set_attr)(struct iommu_domain *domain,
- enum iommu_attr attr, void *data);
int (*enable_nesting)(struct iommu_domain *domain);
int (*set_pgtable_quirks)(struct iommu_domain *domain,
unsigned long quirks);
@@ -493,10 +473,6 @@ extern int iommu_page_response(struct device *dev,
extern int iommu_group_id(struct iommu_group *group);
extern struct iommu_domain *iommu_group_default_domain(struct iommu_group *);
-extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr,
- void *data);
-extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr,
- void *data);
int iommu_enable_nesting(struct iommu_domain *domain);
int iommu_set_pgtable_quirks(struct iommu_domain *domain,
unsigned long quirks);
@@ -869,18 +845,6 @@ static inline int iommu_group_id(struct iommu_group *group)
return -ENODEV;
}
-static inline int iommu_domain_get_attr(struct iommu_domain *domain,
- enum iommu_attr attr, void *data)
-{
- return -EINVAL;
-}
-
-static inline int iommu_domain_set_attr(struct iommu_domain *domain,
- enum iommu_attr attr, void *data)
-{
- return -EINVAL;
-}
-
static inline int iommu_set_pgtable_quirks(struct iommu_domain *domain,
unsigned long quirks)
{
--
2.30.1
^ permalink raw reply related
* [PATCH] MAINTAINERS: Update Spidernet network driver
From: Geoff Levand @ 2021-03-16 17:13 UTC (permalink / raw)
To: David S. Miller, Jakub Kicinski; +Cc: netdev, linuxppc-dev
Change the Spidernet network driver from supported to
maintained, add the linuxppc-dev ML, and add myself as
a 'maintainer'.
Cc: Ishizaki Kou <kou.ishizaki@toshiba.co.jp>
Signed-off-by: Geoff Levand <geoff@infradead.org>
---
MAINTAINERS | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index aa84121c5611..7451cd55af18 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16887,8 +16887,10 @@ F: tools/spi/
SPIDERNET NETWORK DRIVER for CELL
M: Ishizaki Kou <kou.ishizaki@toshiba.co.jp>
+M: Geoff Levand <geoff@infradead.org>
L: netdev@vger.kernel.org
-S: Supported
+L: linuxppc-dev@lists.ozlabs.org
+S: Maintained
F: Documentation/networking/device_drivers/ethernet/toshiba/spider_net.rst
F: drivers/net/ethernet/toshiba/spider_net*
--
2.25.1
^ permalink raw reply related
* [PATCH v1 2/2] powerpc/ps3: Re-align DTB in image
From: Geoff Levand @ 2021-03-16 17:51 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
In-Reply-To: <cover.1615916650.git.geoff@infradead.org>
Change the PS3 linker script to align the DTB at 8 bytes,
the same alignment as that of the of the 'generic' powerpc
linker script.
Signed-off-by: Geoff Levand <geoff@infradead.org>
---
arch/powerpc/boot/zImage.ps3.lds.S | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/boot/zImage.ps3.lds.S b/arch/powerpc/boot/zImage.ps3.lds.S
index 7b2ff2eaa73a..d0ffb493614d 100644
--- a/arch/powerpc/boot/zImage.ps3.lds.S
+++ b/arch/powerpc/boot/zImage.ps3.lds.S
@@ -8,7 +8,7 @@ SECTIONS
.kernel:vmlinux.bin : { *(.kernel:vmlinux.bin) }
_vmlinux_end = .;
- . = ALIGN(4096);
+ . = ALIGN(8);
_dtb_start = .;
.kernel:dtb : { *(.kernel:dtb) }
_dtb_end = .;
--
2.25.1
^ permalink raw reply related
* [PATCH v1 1/2] powerpc/ps3: Add firmware version to proc
From: Geoff Levand @ 2021-03-16 17:51 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
In-Reply-To: <cover.1615916650.git.geoff@infradead.org>
Add a new proc FS entry /proc/ps3/firmware-version that exports the
PS3's firmware version.
The firmware version is available through an LV1 hypercall, and we've
been printing it to the boot log, but haven't provided an easy way for
user utilities to get it.
Signed-off-by: Geoff Levand <geoff@infradead.org>
---
arch/powerpc/platforms/ps3/setup.c | 62 ++++++++++++++++++++++++++++--
1 file changed, 59 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index e9ae5dd03593..c3c4cbf16632 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -13,6 +13,7 @@
#include <linux/console.h>
#include <linux/export.h>
#include <linux/memblock.h>
+#include <linux/proc_fs.h>
#include <asm/machdep.h>
#include <asm/firmware.h>
@@ -36,6 +37,7 @@ DEFINE_MUTEX(ps3_gpu_mutex);
EXPORT_SYMBOL_GPL(ps3_gpu_mutex);
static union ps3_firmware_version ps3_firmware_version;
+static char ps3_firmware_version_str[16];
void ps3_get_firmware_version(union ps3_firmware_version *v)
{
@@ -182,6 +184,58 @@ static int ps3_set_dabr(unsigned long dabr, unsigned long dabrx)
return lv1_set_dabr(dabr, dabrx) ? -1 : 0;
}
+static ssize_t ps3_fw_ver_read(struct file *file, char __user *buf, size_t size,
+ loff_t *ppos)
+{
+ ssize_t bytes = simple_read_from_buffer(buf, size, ppos,
+ ps3_firmware_version_str, strlen(ps3_firmware_version_str));
+
+ pr_debug("%s:%d: %zd bytes '%s'\n", __func__, __LINE__, bytes,
+ ps3_firmware_version_str);
+
+ if (bytes < 0) {
+ pr_err("%s:%d: failed: %zd\n", __func__, __LINE__, bytes);
+ return bytes;
+ }
+
+ buf += bytes;
+ size -= bytes;
+
+ return bytes;
+}
+
+static int __init ps3_setup_proc(void)
+{
+ static const struct proc_ops proc_ops = {
+ .proc_read = ps3_fw_ver_read,
+ .proc_lseek = default_llseek,
+ };
+ struct proc_dir_entry *entry;
+
+ entry = proc_mkdir("ps3", NULL);
+
+ if (!entry) {
+ pr_err("%s:%d: failed.\n", __func__, __LINE__);
+ return 1;
+ }
+
+ entry = proc_create_data("ps3/firmware-version", S_IFREG | 0444, NULL,
+ &proc_ops, NULL);
+
+ if (!entry) {
+ pr_err("%s:%d: failed.\n", __func__, __LINE__);
+ return 1;
+ }
+
+ proc_set_size(entry, strlen(ps3_firmware_version_str));
+
+ pr_debug("%s:%d: '%s' = %zd bytes\n", __func__, __LINE__,
+ ps3_firmware_version_str, strlen(ps3_firmware_version_str));
+
+ return 0;
+}
+core_initcall(ps3_setup_proc);
+
static void __init ps3_setup_arch(void)
{
u64 tmp;
@@ -190,9 +244,11 @@ static void __init ps3_setup_arch(void)
lv1_get_version_info(&ps3_firmware_version.raw, &tmp);
- printk(KERN_INFO "PS3 firmware version %u.%u.%u\n",
- ps3_firmware_version.major, ps3_firmware_version.minor,
- ps3_firmware_version.rev);
+ snprintf(ps3_firmware_version_str, sizeof(ps3_firmware_version_str),
+ "%u.%u.%u", ps3_firmware_version.major,
+ ps3_firmware_version.minor, ps3_firmware_version.rev);
+
+ printk(KERN_INFO "PS3 firmware version %s\n", ps3_firmware_version_str);
ps3_spu_set_platform();
--
2.25.1
^ permalink raw reply related
* [PATCH v1 0/2] PS3 Updates
From: Geoff Levand @ 2021-03-16 17:51 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
Hi Michael,
Here are two minor updates for PS3. The first exports the firmware version to
the proc FS, and the second re-aligns the DTB to save a little space in the
PS3's limited flash memory.
-Geoff
The following changes since commit f40ddce88593482919761f74910f42f4b84c004b:
Linux 5.11 (2021-02-14 14:32:24 -0800)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/geoff/ps3-linux.git for-merge-powerpc
for you to fetch changes up to 7bee1153671a3ec71775246887894eefbfcb4b25:
powerpc/ps3: Re-align DTB in image (2021-03-13 18:43:16 -0800)
----------------------------------------------------------------
Geoff Levand (2):
powerpc/ps3: Add firmware version to proc
powerpc/ps3: Re-align DTB in image
arch/powerpc/boot/zImage.ps3.lds.S | 2 +-
arch/powerpc/platforms/ps3/setup.c | 62 ++++++++++++++++++++++++++++++++++++--
2 files changed, 60 insertions(+), 4 deletions(-)
--
2.25.1
^ permalink raw reply
* Re: [PATCH] ASoC: fsl_spdif: use snd_ctl_boolean_mono_info
From: Mark Brown @ 2021-03-16 17:59 UTC (permalink / raw)
To: Xiubo.Lee, linux-kernel, perex, timur, linuxppc-dev, tiwai,
Shengjiu Wang, festevam, lgirdwood, nicoleotsuka, alsa-devel
Cc: Mark Brown
In-Reply-To: <1615887736-31217-1-git-send-email-shengjiu.wang@nxp.com>
On Tue, 16 Mar 2021 17:42:16 +0800, Shengjiu Wang wrote:
> Remove redundant code and use snd_ctl_boolean_mono_info
> instead.
Applied to
https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git for-next
Thanks!
[1/1] ASoC: fsl_spdif: use snd_ctl_boolean_mono_info
commit: 6ad864ed6ac50f11a6d8575fda79991cca8f245c
All being well this means that it will be integrated into the linux-next
tree (usually sometime in the next 24 hours) and sent to Linus during
the next merge window (or sooner if it is a bug fix), however if
problems are discovered then the patch may be dropped or reverted.
You may get further e-mails resulting from automated or manual testing
and review of the tree, please engage with people reporting problems and
send followup patches addressing any issues that are reported if needed.
If any updates are required or you are submitting further changes they
should be sent as incremental updates against current git, existing
patches will not be replaced.
Please add any relevant lists and maintainers to the CCs when replying
to this mail.
Thanks,
Mark
^ permalink raw reply
* Re: [PATCH] ASoC: hdmi-codec: fix platform_no_drv_owner.cocci warnings
From: Mark Brown @ 2021-03-16 17:59 UTC (permalink / raw)
To: timur, Yang Li
Cc: alsa-devel, lgirdwood, shengjiu.wang, Xiubo.Lee, festevam,
s.hauer, linux-kernel, tiwai, nicoleotsuka, Mark Brown, linux-imx,
kernel, shawnguo, linuxppc-dev, linux-arm-kernel
In-Reply-To: <1614761651-86898-1-git-send-email-yang.lee@linux.alibaba.com>
On Wed, 3 Mar 2021 16:54:11 +0800, Yang Li wrote:
> ./sound/soc/fsl/imx-hdmi.c:226:3-8: No need to set .owner here. The core
> will do it.
>
> Remove .owner field if calls are used which set it automatically
Applied to
https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git for-next
Thanks!
[1/1] ASoC: hdmi-codec: fix platform_no_drv_owner.cocci warnings
commit: 2e2bf6d479616a15c54c4e668558f61caffa4db4
All being well this means that it will be integrated into the linux-next
tree (usually sometime in the next 24 hours) and sent to Linus during
the next merge window (or sooner if it is a bug fix), however if
problems are discovered then the patch may be dropped or reverted.
You may get further e-mails resulting from automated or manual testing
and review of the tree, please engage with people reporting problems and
send followup patches addressing any issues that are reported if needed.
If any updates are required or you are submitting further changes they
should be sent as incremental updates against current git, existing
patches will not be replaced.
Please add any relevant lists and maintainers to the CCs when replying
to this mail.
Thanks,
Mark
^ permalink raw reply
* Re: [PATCH v2] ASoC: imx-hdmi: fix platform_no_drv_owner.cocci warnings
From: Mark Brown @ 2021-03-16 17:59 UTC (permalink / raw)
To: timur, Yang Li
Cc: alsa-devel, lgirdwood, shengjiu.wang, Xiubo.Lee, festevam,
s.hauer, linux-kernel, tiwai, nicoleotsuka, Mark Brown, linux-imx,
kernel, shawnguo, linuxppc-dev, linux-arm-kernel
In-Reply-To: <1614848881-29637-1-git-send-email-yang.lee@linux.alibaba.com>
On Thu, 4 Mar 2021 17:08:01 +0800, Yang Li wrote:
> ./sound/soc/fsl/imx-hdmi.c:226:3-8: No need to set .owner here. The core
> will do it.
>
> Remove .owner field if calls are used which set it automatically
Applied to
https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git for-next
Thanks!
[1/1] ASoC: imx-hdmi: fix platform_no_drv_owner.cocci warnings
commit: 2e2bf6d479616a15c54c4e668558f61caffa4db4
All being well this means that it will be integrated into the linux-next
tree (usually sometime in the next 24 hours) and sent to Linus during
the next merge window (or sooner if it is a bug fix), however if
problems are discovered then the patch may be dropped or reverted.
You may get further e-mails resulting from automated or manual testing
and review of the tree, please engage with people reporting problems and
send followup patches addressing any issues that are reported if needed.
If any updates are required or you are submitting further changes they
should be sent as incremental updates against current git, existing
patches will not be replaced.
Please add any relevant lists and maintainers to the CCs when replying
to this mail.
Thanks,
Mark
^ permalink raw reply
* Re: [PATCH] net: ethernet: fs-enet: remove casting dma_alloc_coherent
From: Christophe Leroy @ 2021-03-16 18:10 UTC (permalink / raw)
To: David Laight, Xu Wang, pantelis.antoniou@gmail.com,
davem@davemloft.net, kuba@kernel.org,
linuxppc-dev@lists.ozlabs.org
Cc: linux-kernel@vger.kernel.org
In-Reply-To: <3f31140339c94652b1e7116e91cfd9c8@AcuMS.aculab.com>
Le 11/12/2020 à 17:55, David Laight a écrit :
> From: Christophe Leroy
>> Sent: 11 December 2020 16:43
>>
>> Le 11/12/2020 à 17:07, David Laight a écrit :
>>> From: Christophe Leroy
>>>> Sent: 11 December 2020 15:22
>>>>
>>>> Le 11/12/2020 à 09:52, Xu Wang a écrit :
>>>>> Remove casting the values returned by dma_alloc_coherent.
>>>>
>>>> Can you explain more in the commit log ?
>>>>
>>>> As far as I can see, dma_alloc_coherent() doesn't return __iomem, and ring_base member is __iomem
>>>
>>> Which is probably wrong - that is the kernel address of kernel memory.
>>> So it shouldn't have the __iomem marker.
>>
>> That's where the buffer descriptors are, the driver accesses to the content of the buffer
>> descriptors using the IO accessors in_be16()/out_be16(). Is it not correct ?
>
> I've just been looking at the crap in there.
> My understanding is that IO accessors are for IO devices (eg addresses
> from io_remap() etc).
>
> Buffers allocated by dma_alloc_coherent() are normal kernel memory
> and don't need any accessors.
> Now you might need some barriers - mostly because an ethernet chip
> can typically read a ring entry without being prodded.
> IIRC there is a barrier in writel() to ensure the dma master will
> 'see' all memory writes done before the IO write that kicks it into
> doing some processing.
As far as I can see, writel() is using __iomem memory, see
https://elixir.bootlin.com/linux/v5.12-rc2/source/include/asm-generic/io.h#L221
>
> The fact that the driver contains so many __iomem casts (eg in
> tx_restart) is an indication that something is badly awry.
> __iomem exists to check you are using the correct type of pointer.
> Any __iomem casts are dubious.
I agree, but what else can we do to guarantee proper access to that memory ?
Christophe
^ permalink raw reply
* Re: [PATCH 10/14] powerpc/64: use interrupt restart table to speed up return from interrupt
From: Christophe Leroy @ 2021-03-16 19:34 UTC (permalink / raw)
To: Nicholas Piggin, linuxppc-dev
In-Reply-To: <20210315220402.260594-11-npiggin@gmail.com>
Le 15/03/2021 à 23:03, Nicholas Piggin a écrit :
> The restart table facility is used to return from interrupt without
> disabling MSR EE or RI.
What happens when an interrupt happens between the point you restore the user r1 and the rfi which
returns to user ?
If an interrupt happens there, the interrupt prolog sees it as an interrupt coming from kernel, so
it uses r1 as is, but r1 points to user stack.
Don't we end up in kernel_bad_stack() ?
Or we take a KUAP fault and end-up in an infinite loop ?
>
> Interrupt return code is put into the low soft-masked region.
>
> Critical code that has no exit work, SRRs set, soft-masked state set to
> return state, saves r1 in the PACA and then begins to run instructions
> that have an alternate return handler.
>
> In this region, pending interrupts are checked, and if any exist then
> it branches directly to the restart handler.
>
> If it does not branch, then no masked interrupts are pending, and if any
> interrupts do hit, we will go out the restart handler.
>
> The restart handler re-loads the saved r1, and from there we can find
> regs, and reload critical state before setting things up to replay
> interrupts and go around the exit prepare sequence again.
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
^ permalink raw reply
* Re: [PATCH] mm: Move mem_init_print_info() into mm_init()
From: Dave Hansen @ 2021-03-16 21:16 UTC (permalink / raw)
To: Kefeng Wang, linux-kernel, Andrew Morton
Cc: linux-ia64, linux-sh, Peter Zijlstra, Catalin Marinas,
Dave Hansen, linux-mm, Guo Ren, sparclinux, linux-riscv,
Jonas Bonn, linux-s390, Yoshinori Sato, linux-hexagon,
Huacai Chen, Russell King, linux-csky, Ingo Molnar,
linux-snps-arc, linux-xtensa, Heiko Carstens, linux-um,
linux-m68k, openrisc, linux-arm-kernel, Richard Henderson,
linux-parisc, linux-mips, Palmer Dabbelt, linux-alpha,
linuxppc-dev, David S. Miller
In-Reply-To: <20210316142637.92193-1-wangkefeng.wang@huawei.com>
On 3/16/21 7:26 AM, Kefeng Wang wrote:
> diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
> index 5430c81eefc9..aa8387aab9c1 100644
> --- a/arch/x86/mm/init_64.c
> +++ b/arch/x86/mm/init_64.c
> @@ -1350,8 +1350,6 @@ void __init mem_init(void)
> kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER);
>
> preallocate_vmalloc_pages();
> -
> - mem_init_print_info(NULL);
> }
Ignoring any issues with the printk...
Looks harmless enough on x86. The 32-bit code has some cruft in
mem_init() after mem_init_print_info(), so this patch will change the
location of the mem_init_print_info(), but I think it's actually for the
better, since it will be pushed later in boot. As long as the x86
pieces stay the same:
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
^ permalink raw reply
* Re: [PATCH] MAINTAINERS: Update Spidernet network driver
From: patchwork-bot+netdevbpf @ 2021-03-16 22:50 UTC (permalink / raw)
To: Geoff Levand; +Cc: kuba, netdev, linuxppc-dev, davem
In-Reply-To: <6399e3a4-c8b0-e015-c766-07cbb87780ab@infradead.org>
Hello:
This patch was applied to netdev/net.git (refs/heads/master):
On Tue, 16 Mar 2021 10:13:52 -0700 you wrote:
> Change the Spidernet network driver from supported to
> maintained, add the linuxppc-dev ML, and add myself as
> a 'maintainer'.
>
> Cc: Ishizaki Kou <kou.ishizaki@toshiba.co.jp>
> Signed-off-by: Geoff Levand <geoff@infradead.org>
>
> [...]
Here is the summary with links:
- MAINTAINERS: Update Spidernet network driver
https://git.kernel.org/netdev/net/c/fc649670ba50
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply
* [PATCH next v1 2/3] printk: remove safe buffers
From: John Ogness @ 2021-03-16 23:33 UTC (permalink / raw)
To: Petr Mladek
Cc: Sergey Senozhatsky, Peter Zijlstra, Paul Mackerras, Tiezhu Yang,
Rafael Aquini, Alexey Kardashevskiy, Yue Hu, Jordan Niethe,
Kees Cook, Paul E. McKenney, Alistair Popple,
Guilherme G. Piccoli, Nicholas Piggin, Steven Rostedt,
Thomas Gleixner, kexec, linux-kernel, Sergey Senozhatsky,
Eric Biederman, Andrew Morton, linuxppc-dev,
Cédric Le Goater
In-Reply-To: <20210316233326.10778-1-john.ogness@linutronix.de>
With @logbuf_lock removed, the high level printk functions for
storing messages are lockless. Messages can be stored from any
context, so there is no need for the NMI and safe buffers anymore.
Remove the NMI and safe buffers.
Although the safe buffers are removed, the NMI and safe context
tracking is still in place. In these contexts, store the message
immediately but still use irq_work to defer the console printing.
Since printk recursion tracking is in place, safe context tracking
for most of printk is not needed. Remove it. Only safe context
tracking relating to the console lock is left in place. This is
because the console lock is needed for the actual printing.
Signed-off-by: John Ogness <john.ogness@linutronix.de>
---
arch/powerpc/kernel/traps.c | 1 -
arch/powerpc/kernel/watchdog.c | 5 -
include/linux/printk.h | 10 -
kernel/kexec_core.c | 1 -
kernel/panic.c | 3 -
kernel/printk/internal.h | 2 -
kernel/printk/printk.c | 81 ++------
kernel/printk/printk_safe.c | 332 +--------------------------------
lib/nmi_backtrace.c | 6 -
9 files changed, 18 insertions(+), 423 deletions(-)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index a44a30b0688c..5828c83eaca6 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -171,7 +171,6 @@ extern void panic_flush_kmsg_start(void)
extern void panic_flush_kmsg_end(void)
{
- printk_safe_flush_on_panic();
kmsg_dump(KMSG_DUMP_PANIC);
bust_spinlocks(0);
debug_locks_off();
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index c9a8f4781a10..dc17d8903d4f 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -183,11 +183,6 @@ static void watchdog_smp_panic(int cpu, u64 tb)
wd_smp_unlock(&flags);
- printk_safe_flush();
- /*
- * printk_safe_flush() seems to require another print
- * before anything actually goes out to console.
- */
if (sysctl_hardlockup_all_cpu_backtrace)
trigger_allbutself_cpu_backtrace();
diff --git a/include/linux/printk.h b/include/linux/printk.h
index fe7eb2351610..2476796c1150 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -207,8 +207,6 @@ __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...);
void dump_stack_print_info(const char *log_lvl);
void show_regs_print_info(const char *log_lvl);
extern asmlinkage void dump_stack(void) __cold;
-extern void printk_safe_flush(void);
-extern void printk_safe_flush_on_panic(void);
#else
static inline __printf(1, 0)
int vprintk(const char *s, va_list args)
@@ -272,14 +270,6 @@ static inline void show_regs_print_info(const char *log_lvl)
static inline void dump_stack(void)
{
}
-
-static inline void printk_safe_flush(void)
-{
-}
-
-static inline void printk_safe_flush_on_panic(void)
-{
-}
#endif
extern int kptr_restrict;
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index f04d04d1b855..64bf5d5cdd06 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -977,7 +977,6 @@ void crash_kexec(struct pt_regs *regs)
old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
if (old_cpu == PANIC_CPU_INVALID) {
/* This is the 1st CPU which comes here, so go ahead. */
- printk_safe_flush_on_panic();
__crash_kexec(regs);
/*
diff --git a/kernel/panic.c b/kernel/panic.c
index 332736a72a58..1f0df42f8d0c 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -247,7 +247,6 @@ void panic(const char *fmt, ...)
* Bypass the panic_cpu check and call __crash_kexec directly.
*/
if (!_crash_kexec_post_notifiers) {
- printk_safe_flush_on_panic();
__crash_kexec(NULL);
/*
@@ -271,8 +270,6 @@ void panic(const char *fmt, ...)
*/
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
- /* Call flush even twice. It tries harder with a single online CPU */
- printk_safe_flush_on_panic();
kmsg_dump(KMSG_DUMP_PANIC);
/*
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index e7acc2888c8e..e108b2ece8c7 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -23,7 +23,6 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args);
void __printk_safe_enter(void);
void __printk_safe_exit(void);
-void printk_safe_init(void);
bool printk_percpu_data_ready(void);
#define printk_safe_enter_irqsave(flags) \
@@ -67,6 +66,5 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args) { return 0; }
#define printk_safe_enter_irq() local_irq_disable()
#define printk_safe_exit_irq() local_irq_enable()
-static inline void printk_safe_init(void) { }
static inline bool printk_percpu_data_ready(void) { return false; }
#endif /* CONFIG_PRINTK */
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index c666e3e43f0c..fa52a5daa232 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -732,27 +732,22 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
if (ret)
return ret;
- printk_safe_enter_irq();
if (!prb_read_valid(prb, atomic64_read(&user->seq), r)) {
if (file->f_flags & O_NONBLOCK) {
ret = -EAGAIN;
- printk_safe_exit_irq();
goto out;
}
- printk_safe_exit_irq();
ret = wait_event_interruptible(log_wait,
prb_read_valid(prb, atomic64_read(&user->seq), r));
if (ret)
goto out;
- printk_safe_enter_irq();
}
if (r->info->seq != atomic64_read(&user->seq)) {
/* our last seen message is gone, return error and reset */
atomic64_set(&user->seq, r->info->seq);
ret = -EPIPE;
- printk_safe_exit_irq();
goto out;
}
@@ -762,7 +757,6 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
&r->info->dev_info);
atomic64_set(&user->seq, r->info->seq + 1);
- printk_safe_exit_irq();
if (len > count) {
ret = -EINVAL;
@@ -797,7 +791,6 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
if (offset)
return -ESPIPE;
- printk_safe_enter_irq();
switch (whence) {
case SEEK_SET:
/* the first record */
@@ -818,7 +811,6 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
default:
ret = -EINVAL;
}
- printk_safe_exit_irq();
return ret;
}
@@ -833,7 +825,6 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait)
poll_wait(file, &log_wait, wait);
- printk_safe_enter_irq();
if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) {
/* return error when data has vanished underneath us */
if (info.seq != atomic64_read(&user->seq))
@@ -841,7 +832,6 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait)
else
ret = EPOLLIN|EPOLLRDNORM;
}
- printk_safe_exit_irq();
return ret;
}
@@ -874,9 +864,7 @@ static int devkmsg_open(struct inode *inode, struct file *file)
prb_rec_init_rd(&user->record, &user->info,
&user->text_buf[0], sizeof(user->text_buf));
- printk_safe_enter_irq();
atomic64_set(&user->seq, prb_first_valid_seq(prb));
- printk_safe_exit_irq();
file->private_data = user;
return 0;
@@ -1042,9 +1030,6 @@ static inline void log_buf_add_cpu(void) {}
static void __init set_percpu_data_ready(void)
{
- printk_safe_init();
- /* Make sure we set this flag only after printk_safe() init is done */
- barrier();
__printk_percpu_data_ready = true;
}
@@ -1084,7 +1069,6 @@ void __init setup_log_buf(int early)
struct printk_record r;
size_t new_descs_size;
size_t new_infos_size;
- unsigned long flags;
char *new_log_buf;
unsigned int free;
u64 seq;
@@ -1142,8 +1126,6 @@ void __init setup_log_buf(int early)
new_descs, ilog2(new_descs_count),
new_infos);
- printk_safe_enter_irqsave(flags);
-
log_buf_len = new_log_buf_len;
log_buf = new_log_buf;
new_log_buf_len = 0;
@@ -1159,8 +1141,6 @@ void __init setup_log_buf(int early)
*/
prb = &printk_rb_dynamic;
- printk_safe_exit_irqrestore(flags);
-
if (seq != prb_next_seq(&printk_rb_static)) {
pr_err("dropped %llu messages\n",
prb_next_seq(&printk_rb_static) - seq);
@@ -1498,11 +1478,9 @@ static int syslog_print(char __user *buf, int size)
size_t n;
size_t skip;
- printk_safe_enter_irq();
- raw_spin_lock(&syslog_lock);
+ raw_spin_lock_irq(&syslog_lock);
if (!prb_read_valid(prb, syslog_seq, &r)) {
- raw_spin_unlock(&syslog_lock);
- printk_safe_exit_irq();
+ raw_spin_unlock_irq(&syslog_lock);
break;
}
if (r.info->seq != syslog_seq) {
@@ -1531,8 +1509,7 @@ static int syslog_print(char __user *buf, int size)
syslog_partial += n;
} else
n = 0;
- raw_spin_unlock(&syslog_lock);
- printk_safe_exit_irq();
+ raw_spin_unlock_irq(&syslog_lock);
if (!n)
break;
@@ -1566,7 +1543,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
return -ENOMEM;
time = printk_time;
- printk_safe_enter_irq();
/*
* Find first record that fits, including all following records,
* into the user-provided buffer for this dump.
@@ -1587,23 +1563,20 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
break;
}
- printk_safe_exit_irq();
if (copy_to_user(buf + len, text, textlen))
len = -EFAULT;
else
len += textlen;
- printk_safe_enter_irq();
if (len < 0)
break;
}
if (clear) {
- raw_spin_lock(&syslog_lock);
+ raw_spin_lock_irq(&syslog_lock);
latched_seq_write(&clear_seq, seq);
- raw_spin_unlock(&syslog_lock);
+ raw_spin_unlock_irq(&syslog_lock);
}
- printk_safe_exit_irq();
kfree(text);
return len;
@@ -1611,11 +1584,9 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
static void syslog_clear(void)
{
- printk_safe_enter_irq();
- raw_spin_lock(&syslog_lock);
+ raw_spin_lock_irq(&syslog_lock);
latched_seq_write(&clear_seq, prb_next_seq(prb));
- raw_spin_unlock(&syslog_lock);
- printk_safe_exit_irq();
+ raw_spin_unlock_irq(&syslog_lock);
}
/* Return a consistent copy of @syslog_seq. */
@@ -1703,12 +1674,10 @@ int do_syslog(int type, char __user *buf, int len, int source)
break;
/* Number of chars in the log buffer */
case SYSLOG_ACTION_SIZE_UNREAD:
- printk_safe_enter_irq();
- raw_spin_lock(&syslog_lock);
+ raw_spin_lock_irq(&syslog_lock);
if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) {
/* No unread messages. */
- raw_spin_unlock(&syslog_lock);
- printk_safe_exit_irq();
+ raw_spin_unlock_irq(&syslog_lock);
return 0;
}
if (info.seq != syslog_seq) {
@@ -1736,8 +1705,7 @@ int do_syslog(int type, char __user *buf, int len, int source)
}
error -= syslog_partial;
}
- raw_spin_unlock(&syslog_lock);
- printk_safe_exit_irq();
+ raw_spin_unlock_irq(&syslog_lock);
break;
/* Size of the log buffer */
case SYSLOG_ACTION_SIZE_BUFFER:
@@ -2213,7 +2181,6 @@ asmlinkage int vprintk_emit(int facility, int level,
{
int printed_len;
bool in_sched = false;
- unsigned long flags;
/* Suppress unimportant messages after panic happens */
if (unlikely(suppress_printk))
@@ -2227,9 +2194,7 @@ asmlinkage int vprintk_emit(int facility, int level,
boot_delay_msec(level);
printk_delay();
- printk_safe_enter_irqsave(flags);
printed_len = vprintk_store(facility, level, dev_info, fmt, args);
- printk_safe_exit_irqrestore(flags);
/* If called from the scheduler, we can not call up(). */
if (!in_sched) {
@@ -2666,7 +2631,6 @@ void console_unlock(void)
size_t ext_len = 0;
size_t len;
- printk_safe_enter_irqsave(flags);
skip:
if (!prb_read_valid(prb, console_seq, &r))
break;
@@ -2711,6 +2675,8 @@ void console_unlock(void)
printk_time);
console_seq++;
+ printk_safe_enter_irqsave(flags);
+
/*
* While actively printing out messages, if another printk()
* were to occur on another CPU, it may wait for this one to
@@ -2745,8 +2711,6 @@ void console_unlock(void)
* flush, no worries.
*/
retry = prb_read_valid(prb, console_seq, NULL);
- printk_safe_exit_irqrestore(flags);
-
if (retry && console_trylock())
goto again;
}
@@ -2808,13 +2772,8 @@ void console_flush_on_panic(enum con_flush_mode mode)
console_trylock();
console_may_schedule = 0;
- if (mode == CONSOLE_REPLAY_ALL) {
- unsigned long flags;
-
- printk_safe_enter_irqsave(flags);
+ if (mode == CONSOLE_REPLAY_ALL)
console_seq = prb_first_valid_seq(prb);
- printk_safe_exit_irqrestore(flags);
- }
console_unlock();
}
@@ -3466,14 +3425,12 @@ bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog,
struct printk_info info;
unsigned int line_count;
struct printk_record r;
- unsigned long flags;
size_t l = 0;
bool ret = false;
if (iter->cur_seq < min_seq)
iter->cur_seq = min_seq;
- printk_safe_enter_irqsave(flags);
prb_rec_init_rd(&r, &info, line, size);
/* Read text or count text lines? */
@@ -3494,7 +3451,6 @@ bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog,
iter->cur_seq = r.info->seq + 1;
ret = true;
out:
- printk_safe_exit_irqrestore(flags);
if (len)
*len = l;
return ret;
@@ -3526,7 +3482,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog,
u64 min_seq = latched_seq_read_nolock(&clear_seq);
struct printk_info info;
struct printk_record r;
- unsigned long flags;
u64 seq;
u64 next_seq;
size_t len = 0;
@@ -3539,7 +3494,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog,
if (iter->cur_seq < min_seq)
iter->cur_seq = min_seq;
- printk_safe_enter_irqsave(flags);
if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) {
if (info.seq != iter->cur_seq) {
/* messages are gone, move to first available one */
@@ -3548,10 +3502,8 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog,
}
/* last entry */
- if (iter->cur_seq >= iter->next_seq) {
- printk_safe_exit_irqrestore(flags);
+ if (iter->cur_seq >= iter->next_seq)
goto out;
- }
/*
* Find first record that fits, including all following records,
@@ -3583,7 +3535,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog,
iter->next_seq = next_seq;
ret = true;
- printk_safe_exit_irqrestore(flags);
out:
if (len_out)
*len_out = len;
@@ -3601,12 +3552,8 @@ EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer);
*/
void kmsg_dump_rewind(struct kmsg_dump_iter *iter)
{
- unsigned long flags;
-
- printk_safe_enter_irqsave(flags);
iter->cur_seq = latched_seq_read_nolock(&clear_seq);
iter->next_seq = prb_next_seq(prb);
- printk_safe_exit_irqrestore(flags);
}
EXPORT_SYMBOL_GPL(kmsg_dump_rewind);
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index bbf5c1993636..ccebce4d5207 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -15,286 +15,9 @@
#include "internal.h"
-/*
- * In NMI and safe mode, printk() avoids taking locks. Instead,
- * it uses an alternative implementation that temporary stores
- * the strings into a per-CPU buffer. The content of the buffer
- * is later flushed into the main ring buffer via IRQ work.
- *
- * The alternative implementation is chosen transparently
- * by examining current printk() context mask stored in @printk_context
- * per-CPU variable.
- *
- * The implementation allows to flush the strings also from another CPU.
- * There are situations when we want to make sure that all buffers
- * were handled or when IRQs are blocked.
- */
-
-#define SAFE_LOG_BUF_LEN ((1 << CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT) - \
- sizeof(atomic_t) - \
- sizeof(atomic_t) - \
- sizeof(struct irq_work))
-
-struct printk_safe_seq_buf {
- atomic_t len; /* length of written data */
- atomic_t message_lost;
- struct irq_work work; /* IRQ work that flushes the buffer */
- unsigned char buffer[SAFE_LOG_BUF_LEN];
-};
-
-static DEFINE_PER_CPU(struct printk_safe_seq_buf, safe_print_seq);
static DEFINE_PER_CPU(int, printk_context);
-static DEFINE_RAW_SPINLOCK(safe_read_lock);
-
-#ifdef CONFIG_PRINTK_NMI
-static DEFINE_PER_CPU(struct printk_safe_seq_buf, nmi_print_seq);
-#endif
-
-/* Get flushed in a more safe context. */
-static void queue_flush_work(struct printk_safe_seq_buf *s)
-{
- if (printk_percpu_data_ready())
- irq_work_queue(&s->work);
-}
-
-/*
- * Add a message to per-CPU context-dependent buffer. NMI and printk-safe
- * have dedicated buffers, because otherwise printk-safe preempted by
- * NMI-printk would have overwritten the NMI messages.
- *
- * The messages are flushed from irq work (or from panic()), possibly,
- * from other CPU, concurrently with printk_safe_log_store(). Should this
- * happen, printk_safe_log_store() will notice the buffer->len mismatch
- * and repeat the write.
- */
-static __printf(2, 0) int printk_safe_log_store(struct printk_safe_seq_buf *s,
- const char *fmt, va_list args)
-{
- int add;
- size_t len;
- va_list ap;
-
-again:
- len = atomic_read(&s->len);
-
- /* The trailing '\0' is not counted into len. */
- if (len >= sizeof(s->buffer) - 1) {
- atomic_inc(&s->message_lost);
- queue_flush_work(s);
- return 0;
- }
-
- /*
- * Make sure that all old data have been read before the buffer
- * was reset. This is not needed when we just append data.
- */
- if (!len)
- smp_rmb();
-
- va_copy(ap, args);
- add = vscnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, ap);
- va_end(ap);
- if (!add)
- return 0;
-
- /*
- * Do it once again if the buffer has been flushed in the meantime.
- * Note that atomic_cmpxchg() is an implicit memory barrier that
- * makes sure that the data were written before updating s->len.
- */
- if (atomic_cmpxchg(&s->len, len, len + add) != len)
- goto again;
-
- queue_flush_work(s);
- return add;
-}
-
-static inline void printk_safe_flush_line(const char *text, int len)
-{
- /*
- * Avoid any console drivers calls from here, because we may be
- * in NMI or printk_safe context (when in panic). The messages
- * must go only into the ring buffer at this stage. Consoles will
- * get explicitly called later when a crashdump is not generated.
- */
- printk_deferred("%.*s", len, text);
-}
-
-/* printk part of the temporary buffer line by line */
-static int printk_safe_flush_buffer(const char *start, size_t len)
-{
- const char *c, *end;
- bool header;
-
- c = start;
- end = start + len;
- header = true;
-
- /* Print line by line. */
- while (c < end) {
- if (*c == '\n') {
- printk_safe_flush_line(start, c - start + 1);
- start = ++c;
- header = true;
- continue;
- }
-
- /* Handle continuous lines or missing new line. */
- if ((c + 1 < end) && printk_get_level(c)) {
- if (header) {
- c = printk_skip_level(c);
- continue;
- }
-
- printk_safe_flush_line(start, c - start);
- start = c++;
- header = true;
- continue;
- }
-
- header = false;
- c++;
- }
-
- /* Check if there was a partial line. Ignore pure header. */
- if (start < end && !header) {
- static const char newline[] = KERN_CONT "\n";
-
- printk_safe_flush_line(start, end - start);
- printk_safe_flush_line(newline, strlen(newline));
- }
-
- return len;
-}
-
-static void report_message_lost(struct printk_safe_seq_buf *s)
-{
- int lost = atomic_xchg(&s->message_lost, 0);
-
- if (lost)
- printk_deferred("Lost %d message(s)!\n", lost);
-}
-
-/*
- * Flush data from the associated per-CPU buffer. The function
- * can be called either via IRQ work or independently.
- */
-static void __printk_safe_flush(struct irq_work *work)
-{
- struct printk_safe_seq_buf *s =
- container_of(work, struct printk_safe_seq_buf, work);
- unsigned long flags;
- size_t len;
- int i;
-
- /*
- * The lock has two functions. First, one reader has to flush all
- * available message to make the lockless synchronization with
- * writers easier. Second, we do not want to mix messages from
- * different CPUs. This is especially important when printing
- * a backtrace.
- */
- raw_spin_lock_irqsave(&safe_read_lock, flags);
-
- i = 0;
-more:
- len = atomic_read(&s->len);
-
- /*
- * This is just a paranoid check that nobody has manipulated
- * the buffer an unexpected way. If we printed something then
- * @len must only increase. Also it should never overflow the
- * buffer size.
- */
- if ((i && i >= len) || len > sizeof(s->buffer)) {
- const char *msg = "printk_safe_flush: internal error\n";
-
- printk_safe_flush_line(msg, strlen(msg));
- len = 0;
- }
-
- if (!len)
- goto out; /* Someone else has already flushed the buffer. */
-
- /* Make sure that data has been written up to the @len */
- smp_rmb();
- i += printk_safe_flush_buffer(s->buffer + i, len - i);
-
- /*
- * Check that nothing has got added in the meantime and truncate
- * the buffer. Note that atomic_cmpxchg() is an implicit memory
- * barrier that makes sure that the data were copied before
- * updating s->len.
- */
- if (atomic_cmpxchg(&s->len, len, 0) != len)
- goto more;
-
-out:
- report_message_lost(s);
- raw_spin_unlock_irqrestore(&safe_read_lock, flags);
-}
-
-/**
- * printk_safe_flush - flush all per-cpu nmi buffers.
- *
- * The buffers are flushed automatically via IRQ work. This function
- * is useful only when someone wants to be sure that all buffers have
- * been flushed at some point.
- */
-void printk_safe_flush(void)
-{
- int cpu;
-
- for_each_possible_cpu(cpu) {
-#ifdef CONFIG_PRINTK_NMI
- __printk_safe_flush(&per_cpu(nmi_print_seq, cpu).work);
-#endif
- __printk_safe_flush(&per_cpu(safe_print_seq, cpu).work);
- }
-}
-
-/**
- * printk_safe_flush_on_panic - flush all per-cpu nmi buffers when the system
- * goes down.
- *
- * Similar to printk_safe_flush() but it can be called even in NMI context when
- * the system goes down. It does the best effort to get NMI messages into
- * the main ring buffer.
- *
- * Note that it could try harder when there is only one CPU online.
- */
-void printk_safe_flush_on_panic(void)
-{
- /*
- * Make sure that we could access the safe buffers.
- * Do not risk a double release when more CPUs are up.
- */
- if (raw_spin_is_locked(&safe_read_lock)) {
- if (num_online_cpus() > 1)
- return;
-
- debug_locks_off();
- raw_spin_lock_init(&safe_read_lock);
- }
-
- printk_safe_flush();
-}
-
#ifdef CONFIG_PRINTK_NMI
-/*
- * Safe printk() for NMI context. It uses a per-CPU buffer to
- * store the message. NMIs are not nested, so there is always only
- * one writer running. But the buffer might get flushed from another
- * CPU, so we need to be careful.
- */
-static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args)
-{
- struct printk_safe_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
-
- return printk_safe_log_store(s, fmt, args);
-}
-
void noinstr printk_nmi_enter(void)
{
this_cpu_add(printk_context, PRINTK_NMI_CONTEXT_OFFSET);
@@ -309,9 +32,6 @@ void noinstr printk_nmi_exit(void)
* Marks a code that might produce many messages in NMI context
* and the risk of losing them is more critical than eventual
* reordering.
- *
- * It has effect only when called in NMI context. Then printk()
- * will store the messages into the main logbuf directly.
*/
void printk_nmi_direct_enter(void)
{
@@ -324,27 +44,8 @@ void printk_nmi_direct_exit(void)
this_cpu_and(printk_context, ~PRINTK_NMI_DIRECT_CONTEXT_MASK);
}
-#else
-
-static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args)
-{
- return 0;
-}
-
#endif /* CONFIG_PRINTK_NMI */
-/*
- * Lock-less printk(), to avoid deadlocks should the printk() recurse
- * into itself. It uses a per-CPU buffer to store the message, just like
- * NMI.
- */
-static __printf(1, 0) int vprintk_safe(const char *fmt, va_list args)
-{
- struct printk_safe_seq_buf *s = this_cpu_ptr(&safe_print_seq);
-
- return printk_safe_log_store(s, fmt, args);
-}
-
/* Can be preempted by NMI. */
void __printk_safe_enter(void)
{
@@ -369,7 +70,10 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
* Use the main logbuf even in NMI. But avoid calling console
* drivers that might have their own locks.
*/
- if ((this_cpu_read(printk_context) & PRINTK_NMI_DIRECT_CONTEXT_MASK)) {
+ if (this_cpu_read(printk_context) &
+ (PRINTK_NMI_DIRECT_CONTEXT_MASK |
+ PRINTK_NMI_CONTEXT_MASK |
+ PRINTK_SAFE_CONTEXT_MASK)) {
unsigned long flags;
int len;
@@ -380,34 +84,6 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
return len;
}
- /* Use extra buffer in NMI. */
- if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK)
- return vprintk_nmi(fmt, args);
-
- /* Use extra buffer to prevent a recursion deadlock in safe mode. */
- if (this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK)
- return vprintk_safe(fmt, args);
-
/* No obstacles. */
return vprintk_default(fmt, args);
}
-
-void __init printk_safe_init(void)
-{
- int cpu;
-
- for_each_possible_cpu(cpu) {
- struct printk_safe_seq_buf *s;
-
- s = &per_cpu(safe_print_seq, cpu);
- init_irq_work(&s->work, __printk_safe_flush);
-
-#ifdef CONFIG_PRINTK_NMI
- s = &per_cpu(nmi_print_seq, cpu);
- init_irq_work(&s->work, __printk_safe_flush);
-#endif
- }
-
- /* Flush pending messages that did not have scheduled IRQ works. */
- printk_safe_flush();
-}
diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
index 8abe1870dba4..b09a490f5f70 100644
--- a/lib/nmi_backtrace.c
+++ b/lib/nmi_backtrace.c
@@ -75,12 +75,6 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask,
touch_softlockup_watchdog();
}
- /*
- * Force flush any remote buffers that might be stuck in IRQ context
- * and therefore could not run their irq_work.
- */
- printk_safe_flush();
-
clear_bit_unlock(0, &backtrace_flag);
put_cpu();
}
--
2.20.1
^ permalink raw reply related
* [PATCH next v1 0/3] printk: remove safe buffers
From: John Ogness @ 2021-03-16 23:33 UTC (permalink / raw)
To: Petr Mladek
Cc: Sergey Senozhatsky, Peter Zijlstra, Paul Mackerras, Tiezhu Yang,
Rafael Aquini, Alexey Kardashevskiy, Yue Hu, Jordan Niethe,
Kees Cook, Paul E. McKenney, Alistair Popple,
Guilherme G. Piccoli, Nicholas Piggin, Steven Rostedt,
Thomas Gleixner, kexec, linux-kernel, Sergey Senozhatsky,
Eric Biederman, Andrew Morton, linuxppc-dev,
Cédric Le Goater
Hello,
Here is v1 of a series to remove the safe buffers. They are no
longer needed because messages can be stored directly into the
log buffer from any context.
However, the safe buffers also provided a form of recursion
protection. For that reason, explicit recursion protection is
also implemented for this series.
This series falls in line with the printk-rework plan as
presented [0] at Linux Plumbers in Lisbon 2019.
This series is based on next-20210316.
John Ogness
[0] https://linuxplumbersconf.org/event/4/contributions/290/attachments/276/463/lpc2019_jogness_printk.pdf (slide 23)
John Ogness (3):
printk: track/limit recursion
printk: remove safe buffers
printk: convert @syslog_lock to spin_lock
arch/powerpc/kernel/traps.c | 1 -
arch/powerpc/kernel/watchdog.c | 5 -
include/linux/printk.h | 10 -
kernel/kexec_core.c | 1 -
kernel/panic.c | 3 -
kernel/printk/internal.h | 2 -
kernel/printk/printk.c | 171 +++++++++--------
kernel/printk/printk_safe.c | 332 +--------------------------------
lib/nmi_backtrace.c | 6 -
9 files changed, 100 insertions(+), 431 deletions(-)
--
2.20.1
^ permalink raw reply
* Re: [PATCH 10/14] powerpc/64: use interrupt restart table to speed up return from interrupt
From: Nicholas Piggin @ 2021-03-16 23:46 UTC (permalink / raw)
To: Christophe Leroy, linuxppc-dev
In-Reply-To: <f39dab9b-2f16-4c3d-9d7e-4fd2487c5c7d@csgroup.eu>
Excerpts from Christophe Leroy's message of March 17, 2021 5:34 am:
>
>
> Le 15/03/2021 à 23:03, Nicholas Piggin a écrit :
>> The restart table facility is used to return from interrupt without
>> disabling MSR EE or RI.
>
> What happens when an interrupt happens between the point you restore the user r1 and the rfi which
> returns to user ?
> If an interrupt happens there, the interrupt prolog sees it as an interrupt coming from kernel, so
> it uses r1 as is, but r1 points to user stack.
The interrupt is "soft-masked" because it arrives from kernel with an
address below __end_soft_masked. Masked interrupts never touch the
stack. It then checks the restart table and finds an entry, so it
returns to the restart which loads the previous r1 from paca.
Thanks,
Nick
^ permalink raw reply
* Re: [PATCH 02/14] swiotlb: remove the alloc_size parameter to swiotlb_tbl_unmap_single
From: Konrad Rzeszutek Wilk @ 2021-03-17 0:24 UTC (permalink / raw)
To: Christoph Hellwig
Cc: xen-devel, iommu, Dongli Zhang, Claire Chang, linuxppc-dev
In-Reply-To: <20210301074436.919889-3-hch@lst.de>
On Mon, Mar 01, 2021 at 08:44:24AM +0100, Christoph Hellwig wrote:
> Now that swiotlb remembers the allocation size there is no need to pass
> it back to swiotlb_tbl_unmap_single.
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
^ permalink raw reply
* Re: [PATCH v9 2/8] powerpc/lib/code-patching: Set up Strict RWX patching earlier
From: Jordan Niethe @ 2021-03-17 0:38 UTC (permalink / raw)
To: Christophe Leroy
Cc: Christophe Leroy, ajd, Nicholas Piggin, naveen.n.rao,
linuxppc-dev, Daniel Axtens
In-Reply-To: <bd0e37b6-22cb-6dbc-1ef8-b6eac4b4c6e6@csgroup.eu>
On Tue, Mar 16, 2021 at 5:32 PM Christophe Leroy
<christophe.leroy@csgroup.eu> wrote:
>
>
>
> Le 16/03/2021 à 04:17, Jordan Niethe a écrit :
> > setup_text_poke_area() is a late init call so it runs before
> > mark_rodata_ro() and after the init calls. This lets all the init code
> > patching simply write to their locations. In the future, kprobes is
> > going to allocate its instruction pages RO which means they will need
> > setup_text__poke_area() to have been already called for their code
> > patching. However, init_kprobes() (which allocates and patches some
> > instruction pages) is an early init call so it happens before
> > setup_text__poke_area().
> >
> > start_kernel() calls poking_init() before any of the init calls. On
> > powerpc, poking_init() is currently a nop. setup_text_poke_area() relies
> > on kernel virtual memory, cpu hotplug and per_cpu_areas being setup.
> > setup_per_cpu_areas(), boot_cpu_hotplug_init() and mm_init() are called
> > before poking_init().
> >
> > Turn setup_text_poke_area() into poking_init().
> >
> > Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
> > ---
> > v9: New to series
> > ---
> > arch/powerpc/lib/code-patching.c | 12 ++++--------
> > 1 file changed, 4 insertions(+), 8 deletions(-)
> >
> > diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
> > index 2333625b5e31..b28afa1133db 100644
> > --- a/arch/powerpc/lib/code-patching.c
> > +++ b/arch/powerpc/lib/code-patching.c
> > @@ -65,14 +65,11 @@ static int text_area_cpu_down(unsigned int cpu)
> > }
> >
> > /*
> > - * Run as a late init call. This allows all the boot time patching to be done
> > - * simply by patching the code, and then we're called here prior to
> > - * mark_rodata_ro(), which happens after all init calls are run. Although
> > - * BUG_ON() is rude, in this case it should only happen if ENOMEM, and we judge
> > - * it as being preferable to a kernel that will crash later when someone tries
> > - * to use patch_instruction().
> > + * Although BUG_ON() is rude, in this case it should only happen if ENOMEM, and
> > + * we judge it as being preferable to a kernel that will crash later when
> > + * someone tries to use patch_instruction().
>
> Please use WARN_ON(), see why at https://www.kernel.org/doc/html/latest/process/deprecated.html
Ok I can include a change to WARN_ON() as a separate patch.
>
> > */
> > -static int __init setup_text_poke_area(void)
> > +int __init poking_init(void)
> > {
> > BUG_ON(!cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
> > "powerpc/text_poke:online", text_area_cpu_up,
> > @@ -80,7 +77,6 @@ static int __init setup_text_poke_area(void)
> >
> > return 0;
> > }
> > -late_initcall(setup_text_poke_area);
> >
> > /*
> > * This can be called for kernel text or a module.
> >
^ permalink raw reply
* Re: [PATCH v9 3/8] powerpc/kprobes: Mark newly allocated probes as RO
From: Jordan Niethe @ 2021-03-17 0:50 UTC (permalink / raw)
To: Christophe Leroy
Cc: Christophe Leroy, ajd, Nicholas Piggin, naveen.n.rao,
linuxppc-dev, Daniel Axtens
In-Reply-To: <6d04f7c6-8950-2666-13cc-d2f7bf788952@csgroup.eu>
On Tue, Mar 16, 2021 at 5:44 PM Christophe Leroy
<christophe.leroy@csgroup.eu> wrote:
>
>
>
> Le 16/03/2021 à 04:17, Jordan Niethe a écrit :
> > From: Russell Currey <ruscur@russell.cc>
> >
> > With CONFIG_STRICT_KERNEL_RWX=y and CONFIG_KPROBES=y, there will be one
> > W+X page at boot by default. This can be tested with
> > CONFIG_PPC_PTDUMP=y and CONFIG_PPC_DEBUG_WX=y set, and checking the
> > kernel log during boot.
> >
>
> This text is confusing. I don't understand what is the status before the patch, and what is the
> status after.
Before the patch kprobes is allocating W+X pages. This can be seen in
the kernel log with those debug options on.
After the patch kprobes no longer allocate W+X pages.
I will reword it to more clear.
>
> "there will be one ...", does it mean after the patch ?
No, before, after there will be none.
>
> > Add an arch specific insn page allocator which returns RO pages if
> > STRICT_KERNEL_RWX is enabled. This page is only written to with
> > patch_instruction() which is able to write RO pages.
>
> "an" or "the" arch specific insn page allocator ?
Hmm, will go with "the arch specific insn page allocator for powerpc".
>
> >
> > Reviewed-by: Daniel Axtens <dja@axtens.net>
> > Signed-off-by: Russell Currey <ruscur@russell.cc>
> > Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
> > [jpn: Reword commit message, switch from vmalloc_exec(), add
> > free_insn_page()]
> > Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
> > ---
> > v9: - vmalloc_exec() no longer exists
> > - Set the page to RW before freeing it
> > ---
> > arch/powerpc/kernel/kprobes.c | 22 ++++++++++++++++++++++
> > 1 file changed, 22 insertions(+)
> >
> > diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
> > index 01ab2163659e..bb7e4d321988 100644
> > --- a/arch/powerpc/kernel/kprobes.c
> > +++ b/arch/powerpc/kernel/kprobes.c
> > @@ -25,6 +25,8 @@
> > #include <asm/sections.h>
> > #include <asm/inst.h>
> > #include <linux/uaccess.h>
> > +#include <linux/set_memory.h>
> > +#include <linux/vmalloc.h>
> >
> > DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
> > DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
> > @@ -103,6 +105,26 @@ kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset)
> > return addr;
> > }
> >
> > +void *alloc_insn_page(void)
> > +{
> > + void *page = vmalloc(PAGE_SIZE);
>
> Can't do that on book3s/32, see https://github.com/linuxppc/linux/commit/6ca05532 and
> https://github.com/linuxppc/linux/commit/7fbc22ce
>
> Should do:
> return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, GFP_KERNEL,
> PAGE_KERNEL_ROX, VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
> __builtin_return_address(0));
>
>
> To keep it simple, you'll probably need to define MODULES_VADDR and MODULES_END as resp
> VMALLOC_START and VMALLOC_END when they are not defined, maybe in asm/pgtable.h
>
> > +
> > + if (!page)
> > + return NULL;
> > +
> > + set_memory_ro((unsigned long)page, 1);
> > + set_memory_x((unsigned long)page, 1);
> > +
> > + return page;
> > +}
> > +
> > +void free_insn_page(void *page)
> > +{
> > + set_memory_nx((unsigned long)page, 1);
> > + set_memory_rw((unsigned long)page, 1);
> > + vfree(page);
> > +}
> > +
> > int arch_prepare_kprobe(struct kprobe *p)
> > {
> > int ret = 0;
> >
^ permalink raw reply
* Re: [PATCH v9 3/8] powerpc/kprobes: Mark newly allocated probes as RO
From: Jordan Niethe @ 2021-03-17 0:52 UTC (permalink / raw)
To: Christophe Leroy
Cc: Christophe Leroy, ajd, Nicholas Piggin, naveen.n.rao,
linuxppc-dev, Daniel Axtens
In-Reply-To: <6d04f7c6-8950-2666-13cc-d2f7bf788952@csgroup.eu>
On Tue, Mar 16, 2021 at 5:44 PM Christophe Leroy
<christophe.leroy@csgroup.eu> wrote:
>
>
>
> Le 16/03/2021 à 04:17, Jordan Niethe a écrit :
> > From: Russell Currey <ruscur@russell.cc>
> >
> > With CONFIG_STRICT_KERNEL_RWX=y and CONFIG_KPROBES=y, there will be one
> > W+X page at boot by default. This can be tested with
> > CONFIG_PPC_PTDUMP=y and CONFIG_PPC_DEBUG_WX=y set, and checking the
> > kernel log during boot.
> >
>
> This text is confusing. I don't understand what is the status before the patch, and what is the
> status after.
>
> "there will be one ...", does it mean after the patch ?
>
> > Add an arch specific insn page allocator which returns RO pages if
> > STRICT_KERNEL_RWX is enabled. This page is only written to with
> > patch_instruction() which is able to write RO pages.
>
> "an" or "the" arch specific insn page allocator ?
>
> >
> > Reviewed-by: Daniel Axtens <dja@axtens.net>
> > Signed-off-by: Russell Currey <ruscur@russell.cc>
> > Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
> > [jpn: Reword commit message, switch from vmalloc_exec(), add
> > free_insn_page()]
> > Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
> > ---
> > v9: - vmalloc_exec() no longer exists
> > - Set the page to RW before freeing it
> > ---
> > arch/powerpc/kernel/kprobes.c | 22 ++++++++++++++++++++++
> > 1 file changed, 22 insertions(+)
> >
> > diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
> > index 01ab2163659e..bb7e4d321988 100644
> > --- a/arch/powerpc/kernel/kprobes.c
> > +++ b/arch/powerpc/kernel/kprobes.c
> > @@ -25,6 +25,8 @@
> > #include <asm/sections.h>
> > #include <asm/inst.h>
> > #include <linux/uaccess.h>
> > +#include <linux/set_memory.h>
> > +#include <linux/vmalloc.h>
> >
> > DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
> > DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
> > @@ -103,6 +105,26 @@ kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset)
> > return addr;
> > }
> >
> > +void *alloc_insn_page(void)
> > +{
> > + void *page = vmalloc(PAGE_SIZE);
>
> Can't do that on book3s/32, see https://github.com/linuxppc/linux/commit/6ca05532 and
> https://github.com/linuxppc/linux/commit/7fbc22ce
>
> Should do:
> return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, GFP_KERNEL,
> PAGE_KERNEL_ROX, VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
> __builtin_return_address(0));
>
>
> To keep it simple, you'll probably need to define MODULES_VADDR and MODULES_END as resp
> VMALLOC_START and VMALLOC_END when they are not defined, maybe in asm/pgtable.h
Thank you, I had overlooked that. I will do it like that in the next revision.
>
> > +
> > + if (!page)
> > + return NULL;
> > +
> > + set_memory_ro((unsigned long)page, 1);
> > + set_memory_x((unsigned long)page, 1);
> > +
> > + return page;
> > +}
> > +
> > +void free_insn_page(void *page)
> > +{
> > + set_memory_nx((unsigned long)page, 1);
> > + set_memory_rw((unsigned long)page, 1);
> > + vfree(page);
> > +}
> > +
> > int arch_prepare_kprobe(struct kprobe *p)
> > {
> > int ret = 0;
> >
^ permalink raw reply
* Re: [PATCH v9 7/8] powerpc/mm: implement set_memory_attr()
From: Jordan Niethe @ 2021-03-17 0:54 UTC (permalink / raw)
To: Christophe Leroy
Cc: Christophe Leroy, ajd, Nicholas Piggin, naveen.n.rao,
Daniel Axtens, linuxppc-dev, kbuild test robot
In-Reply-To: <5a848626-cd83-e4de-f64e-2a7ee082d7d7@csgroup.eu>
On Tue, Mar 16, 2021 at 6:25 PM Christophe Leroy
<christophe.leroy@csgroup.eu> wrote:
>
>
>
> Le 16/03/2021 à 04:17, Jordan Niethe a écrit :
> > From: Christophe Leroy <christophe.leroy@c-s.fr>
>
> Can you please update the whole series with my new email address: christophe.leroy@csgroup.eu
Of course, I shall do that.
>
>
>
> >
> > In addition to the set_memory_xx() functions which allows to change
> > the memory attributes of not (yet) used memory regions, implement a
> > set_memory_attr() function to:
> > - set the final memory protection after init on currently used
> > kernel regions.
> > - enable/disable kernel memory regions in the scope of DEBUG_PAGEALLOC.
> >
> > Unlike the set_memory_xx() which can act in three step as the regions
> > are unused, this function must modify 'on the fly' as the kernel is
> > executing from them. At the moment only PPC32 will use it and changing
> > page attributes on the fly is not an issue.
> >
> > Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
> > Reported-by: kbuild test robot <lkp@intel.com>
> > [ruscur: cast "data" to unsigned long instead of int]
> > Signed-off-by: Russell Currey <ruscur@russell.cc>
> > Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
> > ---
> > arch/powerpc/include/asm/set_memory.h | 2 ++
> > arch/powerpc/mm/pageattr.c | 33 +++++++++++++++++++++++++++
> > 2 files changed, 35 insertions(+)
> >
> > diff --git a/arch/powerpc/include/asm/set_memory.h b/arch/powerpc/include/asm/set_memory.h
> > index 64011ea444b4..b040094f7920 100644
> > --- a/arch/powerpc/include/asm/set_memory.h
> > +++ b/arch/powerpc/include/asm/set_memory.h
> > @@ -29,4 +29,6 @@ static inline int set_memory_x(unsigned long addr, int numpages)
> > return change_memory_attr(addr, numpages, SET_MEMORY_X);
> > }
> >
> > +int set_memory_attr(unsigned long addr, int numpages, pgprot_t prot);
> > +
> > #endif
> > diff --git a/arch/powerpc/mm/pageattr.c b/arch/powerpc/mm/pageattr.c
> > index 2da3fbab6ff7..2fde1b195c85 100644
> > --- a/arch/powerpc/mm/pageattr.c
> > +++ b/arch/powerpc/mm/pageattr.c
> > @@ -79,3 +79,36 @@ int change_memory_attr(unsigned long addr, int numpages, long action)
> > return apply_to_existing_page_range(&init_mm, start, sz,
> > change_page_attr, (void *)action);
> > }
> > +
> > +/*
> > + * Set the attributes of a page:
> > + *
> > + * This function is used by PPC32 at the end of init to set final kernel memory
> > + * protection. It includes changing the maping of the page it is executing from
> > + * and data pages it is using.
> > + */
> > +static int set_page_attr(pte_t *ptep, unsigned long addr, void *data)
> > +{
> > + pgprot_t prot = __pgprot((unsigned long)data);
> > +
> > + spin_lock(&init_mm.page_table_lock);
> > +
> > + set_pte_at(&init_mm, addr, ptep, pte_modify(*ptep, prot));
> > + flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
> > +
> > + spin_unlock(&init_mm.page_table_lock);
> > +
> > + return 0;
> > +}
> > +
> > +int set_memory_attr(unsigned long addr, int numpages, pgprot_t prot)
> > +{
> > + unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE);
> > + unsigned long sz = numpages * PAGE_SIZE;
> > +
> > + if (numpages <= 0)
> > + return 0;
> > +
> > + return apply_to_existing_page_range(&init_mm, start, sz, set_page_attr,
> > + (void *)pgprot_val(prot));
> > +}
> >
^ permalink raw reply
* [PATCH AUTOSEL 5.11 05/61] powerpc/4xx: Fix build errors from mfdcr()
From: Sasha Levin @ 2021-03-17 0:54 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Feng Tang, kernel test robot, linuxppc-dev
In-Reply-To: <20210317005536.724046-1-sashal@kernel.org>
From: Michael Ellerman <mpe@ellerman.id.au>
[ Upstream commit eead089311f4d935ab5d1d8fbb0c42ad44699ada ]
lkp reported a build error in fsp2.o:
CC arch/powerpc/platforms/44x/fsp2.o
{standard input}:577: Error: unsupported relocation against base
Which comes from:
pr_err("GESR0: 0x%08x\n", mfdcr(base + PLB4OPB_GESR0));
Where our mfdcr() macro is stringifying "base + PLB4OPB_GESR0", and
passing that to the assembler, which obviously doesn't work.
The mfdcr() macro already checks that the argument is constant using
__builtin_constant_p(), and if not calls the out-of-line version of
mfdcr(). But in this case GCC is smart enough to notice that "base +
PLB4OPB_GESR0" will be constant, even though it's not something we can
immediately stringify into a register number.
Segher pointed out that passing the register number to the inline asm
as a constant would be better, and in fact it fixes the build error,
presumably because it gives GCC a chance to resolve the value.
While we're at it, change mtdcr() similarly.
Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Acked-by: Feng Tang <feng.tang@intel.com>
Link: https://lore.kernel.org/r/20210218123058.748882-1-mpe@ellerman.id.au
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
arch/powerpc/include/asm/dcr-native.h | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h
index 7141ccea8c94..a92059964579 100644
--- a/arch/powerpc/include/asm/dcr-native.h
+++ b/arch/powerpc/include/asm/dcr-native.h
@@ -53,8 +53,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val)
#define mfdcr(rn) \
({unsigned int rval; \
if (__builtin_constant_p(rn) && rn < 1024) \
- asm volatile("mfdcr %0," __stringify(rn) \
- : "=r" (rval)); \
+ asm volatile("mfdcr %0, %1" : "=r" (rval) \
+ : "n" (rn)); \
else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \
rval = mfdcrx(rn); \
else \
@@ -64,8 +64,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val)
#define mtdcr(rn, v) \
do { \
if (__builtin_constant_p(rn) && rn < 1024) \
- asm volatile("mtdcr " __stringify(rn) ",%0" \
- : : "r" (v)); \
+ asm volatile("mtdcr %0, %1" \
+ : : "n" (rn), "r" (v)); \
else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \
mtdcrx(rn, v); \
else \
--
2.30.1
^ permalink raw reply related
* [PATCH AUTOSEL 5.11 24/61] net: wan: fix error return code of uhdlc_init()
From: Sasha Levin @ 2021-03-17 0:54 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, netdev, Jia-Ju Bai, TOTE Robot, linuxppc-dev,
David S . Miller
In-Reply-To: <20210317005536.724046-1-sashal@kernel.org>
From: Jia-Ju Bai <baijiaju1990@gmail.com>
[ Upstream commit 62765d39553cfd1ad340124fe1e280450e8c89e2 ]
When priv->rx_skbuff or priv->tx_skbuff is NULL, no error return code of
uhdlc_init() is assigned.
To fix this bug, ret is assigned with -ENOMEM in these cases.
Reported-by: TOTE Robot <oslab@tsinghua.edu.cn>
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/wan/fsl_ucc_hdlc.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index dca97cd7c4e7..7eac6a3e1cde 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -204,14 +204,18 @@ static int uhdlc_init(struct ucc_hdlc_private *priv)
priv->rx_skbuff = kcalloc(priv->rx_ring_size,
sizeof(*priv->rx_skbuff),
GFP_KERNEL);
- if (!priv->rx_skbuff)
+ if (!priv->rx_skbuff) {
+ ret = -ENOMEM;
goto free_ucc_pram;
+ }
priv->tx_skbuff = kcalloc(priv->tx_ring_size,
sizeof(*priv->tx_skbuff),
GFP_KERNEL);
- if (!priv->tx_skbuff)
+ if (!priv->tx_skbuff) {
+ ret = -ENOMEM;
goto free_rx_skbuff;
+ }
priv->skb_curtx = 0;
priv->skb_dirtytx = 0;
--
2.30.1
^ 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