* Re: [PATCH V3 1/2] mm: Add get_user_pages_cma_migrate
From: Aneesh Kumar K.V @ 2018-10-16 7:16 UTC (permalink / raw)
To: Alexey Kardashevskiy, akpm, Michal Hocko, mpe
Cc: linux-mm, linuxppc-dev, linux-kernel
In-Reply-To: <6112386d-65cd-fc1f-b012-e33da2c3b8fe@ozlabs.ru>
Alexey Kardashevskiy <aik@ozlabs.ru> writes:
> On 18/09/2018 21:58, Aneesh Kumar K.V wrote:
>> This helper does a get_user_pages_fast and if it find pages in the CMA area
>> it will try to migrate them before taking page reference. This makes sure that
>> we don't keep non-movable pages (due to page reference count) in the CMA area.
>> Not able to move pages out of CMA area result in CMA allocation failures.
>>
>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
>> ---
>> include/linux/hugetlb.h | 2 +
>> include/linux/migrate.h | 3 +
>> mm/hugetlb.c | 4 +-
>> mm/migrate.c | 132 ++++++++++++++++++++++++++++++++++++++++
>> 4 files changed, 139 insertions(+), 2 deletions(-)
>>
>> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
>> index 6b68e345f0ca..1abccb1a1ecc 100644
>> --- a/include/linux/hugetlb.h
>> +++ b/include/linux/hugetlb.h
>> @@ -357,6 +357,8 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
>> nodemask_t *nmask);
>> struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
>> unsigned long address);
>> +struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
>> + int nid, nodemask_t *nmask);
>> int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
>> pgoff_t idx);
>>
>> diff --git a/include/linux/migrate.h b/include/linux/migrate.h
>> index f2b4abbca55e..d82b35afd2eb 100644
>> --- a/include/linux/migrate.h
>> +++ b/include/linux/migrate.h
>> @@ -286,6 +286,9 @@ static inline int migrate_vma(const struct migrate_vma_ops *ops,
>> }
>> #endif /* IS_ENABLED(CONFIG_MIGRATE_VMA_HELPER) */
>>
>> +extern int get_user_pages_cma_migrate(unsigned long start, int nr_pages, int write,
>> + struct page **pages);
>> +
>> #endif /* CONFIG_MIGRATION */
>>
>> #endif /* _LINUX_MIGRATE_H */
>> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
>> index 3c21775f196b..1abbfcb84f66 100644
>> --- a/mm/hugetlb.c
>> +++ b/mm/hugetlb.c
>> @@ -1585,8 +1585,8 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
>> return page;
>> }
>>
>> -static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
>> - int nid, nodemask_t *nmask)
>> +struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
>> + int nid, nodemask_t *nmask)
>> {
>> struct page *page;
>>
>> diff --git a/mm/migrate.c b/mm/migrate.c
>> index d6a2e89b086a..2f92534ea7a1 100644
>> --- a/mm/migrate.c
>> +++ b/mm/migrate.c
>> @@ -3006,3 +3006,135 @@ int migrate_vma(const struct migrate_vma_ops *ops,
>> }
>> EXPORT_SYMBOL(migrate_vma);
>> #endif /* defined(MIGRATE_VMA_HELPER) */
>> +
>> +static struct page *new_non_cma_page(struct page *page, unsigned long private)
>> +{
>> + /*
>> + * We want to make sure we allocate the new page from the same node
>> + * as the source page.
>> + */
>> + int nid = page_to_nid(page);
>> + gfp_t gfp_mask = GFP_USER | __GFP_THISNODE;
>> +
>> + if (PageHighMem(page))
>> + gfp_mask |= __GFP_HIGHMEM;
>> +
>> + if (PageTransHuge(page)) {
>> + struct page *thp;
>> + gfp_t thp_gfpmask = GFP_TRANSHUGE | __GFP_THISNODE;
>> +
>> + /*
>> + * Remove the movable mask so that we don't allocate from
>> + * CMA area again.
>> + */
>> + thp_gfpmask &= ~__GFP_MOVABLE;
>> + thp = __alloc_pages_node(nid, thp_gfpmask, HPAGE_PMD_ORDER);
>
>
> HPAGE_PMD_ORDER is 2MB or 1GB? THP are always that PMD order?
2M or 16M. THP is at PMD level.
>
>
>> + if (!thp)
>> + return NULL;
>> + prep_transhuge_page(thp);
>> + return thp;
>> +
>> +#ifdef CONFIG_HUGETLB_PAGE
>> + } else if (PageHuge(page)) {
>> +
>> + struct hstate *h = page_hstate(page);
>> + /*
>> + * We don't want to dequeue from the pool because pool pages will
>> + * mostly be from the CMA region.
>> + */
>> + return alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
>> +#endif
>> + }
>> +
>> + return __alloc_pages_node(nid, gfp_mask, 0);
>> +}
>> +
>> +/**
>> + * get_user_pages_cma_migrate() - pin user pages in memory by migrating pages in CMA region
>> + * @start: starting user address
>> + * @nr_pages: number of pages from start to pin
>> + * @write: whether pages will be written to
>> + * @pages: array that receives pointers to the pages pinned.
>> + * Should be at least nr_pages long.
>> + *
>> + * Attempt to pin user pages in memory without taking mm->mmap_sem.
>> + * If not successful, it will fall back to taking the lock and
>> + * calling get_user_pages().
>
>
> I do not see any locking or get_user_pages(), hidden somewhere?
>
The rules are same as get_user_pages_fast, which does that pin attempt
without taking mm->mmap_sem. If it fail get_user_pages_fast will take
the mmap_sem and try to pin the pages. The details are in
get_user_pages_fast. You can look at get_user_pages_unlocked
>> + *
>> + * If the pinned pages are backed by CMA region, we migrate those pages out,
>> + * allocating new pages from non-CMA region. This helps in avoiding keeping
>> + * pages pinned in the CMA region for a long time thereby resulting in
>> + * CMA allocation failures.
>> + *
>> + * Returns number of pages pinned. This may be fewer than the number
>> + * requested. If nr_pages is 0 or negative, returns 0. If no pages
>> + * were pinned, returns -errno.
>> + */
>> +
>> +int get_user_pages_cma_migrate(unsigned long start, int nr_pages, int write,
>> + struct page **pages)
>> +{
>> + int i, ret;
>> + bool drain_allow = true;
>> + bool migrate_allow = true;
>> + LIST_HEAD(cma_page_list);
>> +
>> +get_user_again:
>> + ret = get_user_pages_fast(start, nr_pages, write, pages);
>> + if (ret <= 0)
>> + return ret;
>> +
>> + for (i = 0; i < ret; ++i) {
>> + /*
>> + * If we get a page from the CMA zone, since we are going to
>> + * be pinning these entries, we might as well move them out
>> + * of the CMA zone if possible.
>> + */
>> + if (is_migrate_cma_page(pages[i]) && migrate_allow) {
>> + if (PageHuge(pages[i]))
>> + isolate_huge_page(pages[i], &cma_page_list);
>> + else {
>> + struct page *head = compound_head(pages[i]);
>> +
>> + if (!PageLRU(head) && drain_allow) {
>> + lru_add_drain_all();
>> + drain_allow = false;
>> + }
>> +
>> + if (!isolate_lru_page(head)) {
>> + list_add_tail(&head->lru, &cma_page_list);
>> + mod_node_page_state(page_pgdat(head),
>> + NR_ISOLATED_ANON +
>> + page_is_file_cache(head),
>> + hpage_nr_pages(head));
>
>
> Above 10 lines I cannot really comment due to my massive ignorance in
> this area, especially about what lru_add_drain_all() and
> mod_node_page_state() :(
That makes sure we move the pages from per cpu lru vec and add them to
the right lru list so that we can isolate the pages correctly.
>
>
>> + }
>> + }
>> + }
>> + }
>> + if (!list_empty(&cma_page_list)) {
>> + /*
>> + * drop the above get_user_pages reference.
>> + */
>> + for (i = 0; i < ret; ++i)
>> + put_page(pages[i]);
>> +
>> + if (migrate_pages(&cma_page_list, new_non_cma_page,
>> + NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
>> + /*
>> + * some of the pages failed migration. Do get_user_pages
>> + * without migration.
>> + */
>> + migrate_allow = false;
>
>
> migrate_allow seems useless, simply calling get_user_pages_fast() should
> make the code easier to read imho. And the comment says
> get_user_pages(), where does this guy hide?
I didn't get that suggestion. What we want to do here is try to migrate pages as
long as we find CMA pages in the result of get_user_pages_fast. If we
failed any migration attempt, don't try to migrate again.
>
>> +
>> + if (!list_empty(&cma_page_list))
>> + putback_movable_pages(&cma_page_list);
>> + }
>> + /*
>> + * We did migrate all the pages, Try to get the page references again
>> + * migrating any new CMA pages which we failed to isolate earlier.
>> + */
>> + drain_allow = true;
>
> Move this "drain_allow = true" right after "get_user_again:"? 1
>
>
>> + goto get_user_again;
>> + }
>> + return ret;
>> +}
>>
>
> --
> Alexey
-aneesh
^ permalink raw reply
* [PATCH kernel] powerpc/powernv/tce: Implement pnv_phb::tce_invalidate
From: Alexey Kardashevskiy @ 2018-10-16 5:49 UTC (permalink / raw)
To: linuxppc-dev
Cc: Alexey Kardashevskiy, Alistair Popple, Andrew Donnellan,
David Gibson
At the moment there are 5 types of TCE invalidation:
- IODA1/POWER7 - uses raw PHB registers;
- IODA2 "direct" - uses raw PHB3 registers;
- IODA2 "opal" - calls OPAL for invalidation;
- NPU - always invalidates the entire cache;
- NPU2 - calls OPAL for invalidation but uses wrong OPAL_PCI_TCE_KILL
(which is an OPAL token and @kill_type should be one of
OPAL_PCI_TCE_KILL_xxx).
We also have separate helpers for invalidating entire PE or some pages,
with ambiguous names such as pnv_pci_phb3_tce_invalidate_pe() and
pnv_pci_ioda2_tce_invalidate_pe() which difference is not clear at all.
This defines a new powernv-phb hook: tce_invalidate(). This adds a new
helper - pnv_pci_tce_invalidate() - which walks through all attached
PEs and calls tce_invalidate(). Depending on parameters, new hook
invalidates TCE for specific pages or for the entire PE.
This defines a pnv_pci_ioda_tce_invalidate_pe() helper to invalidate a PE,
and uses it instead of pnv_pci_ioda2_tce_invalidate_entire() (NPU) and
pnv_pci_ioda2_tce_invalidate_pe() (IODA2). This does not cause a change
as for NPU2 skiboot falls through to OPAL_PCI_TCE_KILL_ALL since the NPU2
introduction anyway.
While we at it, this changes IODA1's iommu_table_ops to use the same
get/clear/exchange handlers which now get more generic name (i.e.
s/ioda2/ioda/).
As a result, the redesigned code uses now the correct kill_type
for NPU2 PHBs.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
arch/powerpc/platforms/powernv/pci.h | 10 +-
arch/powerpc/platforms/powernv/npu-dma.c | 8 +-
arch/powerpc/platforms/powernv/pci-ioda-tce.c | 16 ++
arch/powerpc/platforms/powernv/pci-ioda.c | 310 ++++++++++----------------
4 files changed, 147 insertions(+), 197 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 2131373..a4b4863 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -119,6 +119,9 @@ struct pnv_phb {
int (*get_pe_state)(struct pnv_phb *phb, int pe_no);
void (*freeze_pe)(struct pnv_phb *phb, int pe_no);
int (*unfreeze_pe)(struct pnv_phb *phb, int pe_no, int opt);
+ void (*tce_invalidate)(struct pnv_phb *phb, struct pnv_ioda_pe *pe,
+ struct iommu_table *tbl, unsigned long index,
+ unsigned long npages, bool realmode);
struct {
/* Global bridge info */
@@ -229,7 +232,6 @@ extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
/* Nvlink functions */
extern void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass);
-extern void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm);
extern struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe);
extern long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num,
struct iommu_table *tbl);
@@ -266,5 +268,11 @@ extern void pnv_pci_unlink_table_and_group(struct iommu_table *tbl,
extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
void *tce_mem, u64 tce_size,
u64 dma_offset, unsigned int page_shift);
+extern void pnv_pci_tce_invalidate(struct iommu_table *tbl,
+ unsigned long index, unsigned long npages, bool realmode);
+static inline void pnv_pci_ioda_tce_invalidate_pe(struct pnv_ioda_pe *pe)
+{
+ pe->phb->tce_invalidate(pe->phb, pe, NULL, 0, 0, false);
+}
#endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 8006c54..7931d42 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -223,7 +223,7 @@ long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num,
pe_err(npe, "Failed to configure TCE table, err %lld\n", rc);
return rc;
}
- pnv_pci_ioda2_tce_invalidate_entire(phb, false);
+ pnv_pci_ioda_tce_invalidate_pe(npe);
/* Add the table to the list so its TCE cache will get invalidated */
pnv_pci_link_table_and_group(phb->hose->node, num,
@@ -247,7 +247,7 @@ long pnv_npu_unset_window(struct pnv_ioda_pe *npe, int num)
pe_err(npe, "Unmapping failed, ret = %lld\n", rc);
return rc;
}
- pnv_pci_ioda2_tce_invalidate_entire(phb, false);
+ pnv_pci_ioda_tce_invalidate_pe(npe);
pnv_pci_unlink_table_and_group(npe->table_group.tables[num],
&npe->table_group);
@@ -313,7 +313,7 @@ static int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe)
0 /* bypass base */, top);
if (rc == OPAL_SUCCESS)
- pnv_pci_ioda2_tce_invalidate_entire(phb, false);
+ pnv_pci_ioda_tce_invalidate_pe(npe);
return rc;
}
@@ -377,7 +377,7 @@ void pnv_npu_take_ownership(struct pnv_ioda_pe *npe)
pe_err(npe, "Failed to disable bypass, err %lld\n", rc);
return;
}
- pnv_pci_ioda2_tce_invalidate_entire(npe->phb, false);
+ pnv_pci_ioda_tce_invalidate_pe(npe);
}
struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe)
diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
index fe96910..1942c40 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
@@ -84,6 +84,22 @@ static __be64 *pnv_tce(struct iommu_table *tbl, bool user, long idx, bool alloc)
return tmp + idx;
}
+void pnv_pci_tce_invalidate(struct iommu_table *tbl,
+ unsigned long index, unsigned long npages, bool rm)
+{
+ struct iommu_table_group_link *tgl;
+
+ list_for_each_entry_lockless(tgl, &tbl->it_group_list, next) {
+ struct pnv_ioda_pe *pe = container_of(tgl->table_group,
+ struct pnv_ioda_pe, table_group);
+
+ if (!pe->phb->tce_invalidate)
+ continue;
+
+ pe->phb->tce_invalidate(pe->phb, pe, tbl, index, npages, rm);
+ }
+}
+
int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
unsigned long uaddr, enum dma_data_direction direction,
unsigned long attrs)
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 15a4556..c76c395 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1947,15 +1947,11 @@ static inline __be64 __iomem *pnv_ioda_get_inval_reg(struct pnv_phb *phb,
(phb->regs + 0x210);
}
-static void pnv_pci_p7ioc_tce_invalidate(struct iommu_table *tbl,
+static void pnv_ioda1_tce_invalidate(struct pnv_phb *phb,
+ struct pnv_ioda_pe *pe, struct iommu_table *tbl,
unsigned long index, unsigned long npages, bool rm)
{
- struct iommu_table_group_link *tgl = list_first_entry_or_null(
- &tbl->it_group_list, struct iommu_table_group_link,
- next);
- struct pnv_ioda_pe *pe = container_of(tgl->table_group,
- struct pnv_ioda_pe, table_group);
- __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm);
+ __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(phb, rm);
unsigned long start, end, inc;
start = __pa(((__be64 *)tbl->it_base) + index - tbl->it_offset);
@@ -1984,7 +1980,7 @@ static void pnv_pci_p7ioc_tce_invalidate(struct iommu_table *tbl,
*/
}
-static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index,
+static int pnv_ioda_tce_build(struct iommu_table *tbl, long index,
long npages, unsigned long uaddr,
enum dma_data_direction direction,
unsigned long attrs)
@@ -1993,220 +1989,66 @@ static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index,
attrs);
if (!ret)
- pnv_pci_p7ioc_tce_invalidate(tbl, index, npages, false);
+ pnv_pci_tce_invalidate(tbl, index, npages, false);
return ret;
}
#ifdef CONFIG_IOMMU_API
-static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
+static int pnv_ioda_tce_xchg(struct iommu_table *tbl, long index,
unsigned long *hpa, enum dma_data_direction *direction)
{
long ret = pnv_tce_xchg(tbl, index, hpa, direction, true);
if (!ret)
- pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, false);
+ pnv_pci_tce_invalidate(tbl, index, 1, false);
return ret;
}
-static int pnv_ioda1_tce_xchg_rm(struct iommu_table *tbl, long index,
+static int pnv_ioda_tce_xchg_rm(struct iommu_table *tbl, long index,
unsigned long *hpa, enum dma_data_direction *direction)
{
long ret = pnv_tce_xchg(tbl, index, hpa, direction, false);
if (!ret)
- pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, true);
+ pnv_pci_tce_invalidate(tbl, index, 1, true);
return ret;
}
#endif
-static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
+static void pnv_ioda_tce_free(struct iommu_table *tbl, long index,
long npages)
{
pnv_tce_free(tbl, index, npages);
- pnv_pci_p7ioc_tce_invalidate(tbl, index, npages, false);
-}
-
-static struct iommu_table_ops pnv_ioda1_iommu_ops = {
- .set = pnv_ioda1_tce_build,
-#ifdef CONFIG_IOMMU_API
- .exchange = pnv_ioda1_tce_xchg,
- .exchange_rm = pnv_ioda1_tce_xchg_rm,
- .useraddrptr = pnv_tce_useraddrptr,
-#endif
- .clear = pnv_ioda1_tce_free,
- .get = pnv_tce_get,
-};
-
-#define PHB3_TCE_KILL_INVAL_ALL PPC_BIT(0)
-#define PHB3_TCE_KILL_INVAL_PE PPC_BIT(1)
-#define PHB3_TCE_KILL_INVAL_ONE PPC_BIT(2)
-
-static void pnv_pci_phb3_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
-{
- __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(phb, rm);
- const unsigned long val = PHB3_TCE_KILL_INVAL_ALL;
-
- mb(); /* Ensure previous TCE table stores are visible */
- if (rm)
- __raw_rm_writeq_be(val, invalidate);
- else
- __raw_writeq_be(val, invalidate);
-}
-
-static inline void pnv_pci_phb3_tce_invalidate_pe(struct pnv_ioda_pe *pe)
-{
- /* 01xb - invalidate TCEs that match the specified PE# */
- __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, false);
- unsigned long val = PHB3_TCE_KILL_INVAL_PE | (pe->pe_number & 0xFF);
-
- mb(); /* Ensure above stores are visible */
- __raw_writeq_be(val, invalidate);
-}
-
-static void pnv_pci_phb3_tce_invalidate(struct pnv_ioda_pe *pe, bool rm,
- unsigned shift, unsigned long index,
- unsigned long npages)
-{
- __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm);
- unsigned long start, end, inc;
-
- /* We'll invalidate DMA address in PE scope */
- start = PHB3_TCE_KILL_INVAL_ONE;
- start |= (pe->pe_number & 0xFF);
- end = start;
-
- /* Figure out the start, end and step */
- start |= (index << shift);
- end |= ((index + npages - 1) << shift);
- inc = (0x1ull << shift);
- mb();
-
- while (start <= end) {
- if (rm)
- __raw_rm_writeq_be(start, invalidate);
- else
- __raw_writeq_be(start, invalidate);
- start += inc;
- }
-}
-
-static inline void pnv_pci_ioda2_tce_invalidate_pe(struct pnv_ioda_pe *pe)
-{
- struct pnv_phb *phb = pe->phb;
-
- if (phb->model == PNV_PHB_MODEL_PHB3 && phb->regs)
- pnv_pci_phb3_tce_invalidate_pe(pe);
- else
- opal_pci_tce_kill(phb->opal_id, OPAL_PCI_TCE_KILL_PE,
- pe->pe_number, 0, 0, 0);
-}
-
-static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
- unsigned long index, unsigned long npages, bool rm)
-{
- struct iommu_table_group_link *tgl;
-
- list_for_each_entry_lockless(tgl, &tbl->it_group_list, next) {
- struct pnv_ioda_pe *pe = container_of(tgl->table_group,
- struct pnv_ioda_pe, table_group);
- struct pnv_phb *phb = pe->phb;
- unsigned int shift = tbl->it_page_shift;
-
- /*
- * NVLink1 can use the TCE kill register directly as
- * it's the same as PHB3. NVLink2 is different and
- * should go via the OPAL call.
- */
- if (phb->model == PNV_PHB_MODEL_NPU) {
- /*
- * The NVLink hardware does not support TCE kill
- * per TCE entry so we have to invalidate
- * the entire cache for it.
- */
- pnv_pci_phb3_tce_invalidate_entire(phb, rm);
- continue;
- }
- if (phb->model == PNV_PHB_MODEL_PHB3 && phb->regs)
- pnv_pci_phb3_tce_invalidate(pe, rm, shift,
- index, npages);
- else
- opal_pci_tce_kill(phb->opal_id,
- OPAL_PCI_TCE_KILL_PAGES,
- pe->pe_number, 1u << shift,
- index << shift, npages);
- }
-}
-
-void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
-{
- if (phb->model == PNV_PHB_MODEL_NPU || phb->model == PNV_PHB_MODEL_PHB3)
- pnv_pci_phb3_tce_invalidate_entire(phb, rm);
- else
- opal_pci_tce_kill(phb->opal_id, OPAL_PCI_TCE_KILL, 0, 0, 0, 0);
-}
-
-static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index,
- long npages, unsigned long uaddr,
- enum dma_data_direction direction,
- unsigned long attrs)
-{
- int ret = pnv_tce_build(tbl, index, npages, uaddr, direction,
- attrs);
-
- if (!ret)
- pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
-
- return ret;
-}
-
-#ifdef CONFIG_IOMMU_API
-static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
- unsigned long *hpa, enum dma_data_direction *direction)
-{
- long ret = pnv_tce_xchg(tbl, index, hpa, direction, true);
-
- if (!ret)
- pnv_pci_ioda2_tce_invalidate(tbl, index, 1, false);
-
- return ret;
-}
-
-static int pnv_ioda2_tce_xchg_rm(struct iommu_table *tbl, long index,
- unsigned long *hpa, enum dma_data_direction *direction)
-{
- long ret = pnv_tce_xchg(tbl, index, hpa, direction, false);
-
- if (!ret)
- pnv_pci_ioda2_tce_invalidate(tbl, index, 1, true);
-
- return ret;
-}
-#endif
-
-static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
- long npages)
-{
- pnv_tce_free(tbl, index, npages);
-
- pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
+ pnv_pci_tce_invalidate(tbl, index, npages, false);
}
static struct iommu_table_ops pnv_ioda2_iommu_ops = {
- .set = pnv_ioda2_tce_build,
+ .set = pnv_ioda_tce_build,
#ifdef CONFIG_IOMMU_API
- .exchange = pnv_ioda2_tce_xchg,
- .exchange_rm = pnv_ioda2_tce_xchg_rm,
+ .exchange = pnv_ioda_tce_xchg,
+ .exchange_rm = pnv_ioda_tce_xchg_rm,
.useraddrptr = pnv_tce_useraddrptr,
#endif
- .clear = pnv_ioda2_tce_free,
+ .clear = pnv_ioda_tce_free,
.get = pnv_tce_get,
.free = pnv_pci_ioda2_table_free_pages,
};
+static struct iommu_table_ops pnv_ioda1_iommu_ops = {
+ .set = pnv_ioda_tce_build,
+#ifdef CONFIG_IOMMU_API
+ .exchange = pnv_ioda_tce_xchg,
+ .exchange_rm = pnv_ioda_tce_xchg_rm,
+ .useraddrptr = pnv_tce_useraddrptr,
+#endif
+ .clear = pnv_ioda_tce_free,
+ .get = pnv_tce_get,
+};
+
static int pnv_pci_ioda_dev_dma_weight(struct pci_dev *dev, void *data)
{
unsigned int *weight = (unsigned int *)data;
@@ -2413,7 +2255,7 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group,
pnv_pci_link_table_and_group(phb->hose->node, num,
tbl, &pe->table_group);
- pnv_pci_ioda2_tce_invalidate_pe(pe);
+ pnv_pci_ioda_tce_invalidate_pe(pe);
return 0;
}
@@ -2547,7 +2389,7 @@ static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
if (ret)
pe_warn(pe, "Unmapping failed, ret = %ld\n", ret);
else
- pnv_pci_ioda2_tce_invalidate_pe(pe);
+ pnv_pci_ioda_tce_invalidate_pe(pe);
pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);
@@ -3525,7 +3367,7 @@ static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe)
if (rc != OPAL_SUCCESS)
return;
- pnv_pci_p7ioc_tce_invalidate(tbl, tbl->it_offset, tbl->it_size, false);
+ pnv_pci_tce_invalidate(tbl, tbl->it_offset, tbl->it_size, false);
if (pe->table_group.group) {
iommu_group_put(pe->table_group.group);
WARN_ON(pe->table_group.group);
@@ -3730,6 +3572,82 @@ static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = {
.shutdown = pnv_pci_ioda_shutdown,
};
+#define PHB3_TCE_KILL_INVAL_ALL PPC_BIT(0)
+#define PHB3_TCE_KILL_INVAL_PE PPC_BIT(1)
+#define PHB3_TCE_KILL_INVAL_ONE PPC_BIT(2)
+
+static void pnv_ioda2_direct_tce_invalidate(struct pnv_phb *phb,
+ struct pnv_ioda_pe *pe, struct iommu_table *tbl,
+ unsigned long index, unsigned long npages, bool rm)
+{
+ __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(phb, rm);
+ unsigned int shift = tbl->it_page_shift;
+ unsigned long start, end, inc;
+
+ if (!tbl || tbl->it_size == npages) {
+ /* 01xb - invalidate TCEs that match the specified PE# */
+ unsigned long val = PHB3_TCE_KILL_INVAL_PE |
+ (pe->pe_number & 0xFF);
+
+ mb(); /* Ensure above stores are visible */
+ __raw_writeq_be(val, invalidate);
+ return;
+ }
+
+ /* We'll invalidate DMA address in PE scope */
+ start = PHB3_TCE_KILL_INVAL_ONE;
+ start |= (pe->pe_number & 0xFF);
+ end = start;
+
+ /* Figure out the start, end and step */
+ start |= (index << shift);
+ end |= ((index + npages - 1) << shift);
+ inc = (0x1ull << shift);
+ mb(); /* Ensure above stores are visible */
+
+ while (start <= end) {
+ if (rm)
+ __raw_rm_writeq_be(start, invalidate);
+ else
+ __raw_writeq_be(start, invalidate);
+ start += inc;
+ }
+}
+
+static void pnv_ioda2_opal_tce_invalidate(struct pnv_phb *phb,
+ struct pnv_ioda_pe *pe, struct iommu_table *tbl,
+ unsigned long index, unsigned long npages, bool realmode)
+{
+ if (!tbl || tbl->it_size == npages) {
+ opal_pci_tce_kill(phb->opal_id, OPAL_PCI_TCE_KILL_PE,
+ pe->pe_number, 0, 0, 0);
+ return;
+ }
+
+ opal_pci_tce_kill(phb->opal_id, OPAL_PCI_TCE_KILL_PAGES, pe->pe_number,
+ 1u << tbl->it_page_shift, index << tbl->it_page_shift,
+ npages);
+}
+
+static void pnv_ioda2_npu_tce_invalidate(struct pnv_phb *phb,
+ struct pnv_ioda_pe *npe, struct iommu_table *tbl,
+ unsigned long index, unsigned long npages, bool rm)
+{
+ /*
+ * The NVLink hardware does not support TCE kill
+ * per TCE entry so we have to invalidate
+ * the entire cache for it.
+ */
+ __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(phb, rm);
+ const unsigned long val = PHB3_TCE_KILL_INVAL_ALL;
+
+ mb(); /* Ensure previous TCE table stores are visible */
+ if (rm)
+ __raw_rm_writeq_be(val, invalidate);
+ else
+ __raw_writeq_be(val, invalidate);
+}
+
static void __init pnv_pci_init_ioda_phb(struct device_node *np,
u64 hub_id, int ioda_type)
{
@@ -3787,16 +3705,22 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
mutex_init(&phb->ioda.pe_alloc_mutex);
/* Detect specific models for error handling */
- if (of_device_is_compatible(np, "ibm,p7ioc-pciex"))
+ if (of_device_is_compatible(np, "ibm,p7ioc-pciex")) {
phb->model = PNV_PHB_MODEL_P7IOC;
- else if (of_device_is_compatible(np, "ibm,power8-pciex"))
+ phb->tce_invalidate = pnv_ioda1_tce_invalidate;
+ } else if (of_device_is_compatible(np, "ibm,power8-pciex")) {
phb->model = PNV_PHB_MODEL_PHB3;
- else if (of_device_is_compatible(np, "ibm,power8-npu-pciex"))
+ phb->tce_invalidate = pnv_ioda2_opal_tce_invalidate;
+ } else if (of_device_is_compatible(np, "ibm,power8-npu-pciex")) {
phb->model = PNV_PHB_MODEL_NPU;
- else if (of_device_is_compatible(np, "ibm,power9-npu-pciex"))
+ phb->tce_invalidate = pnv_ioda2_npu_tce_invalidate;
+ } else if (of_device_is_compatible(np, "ibm,power9-npu-pciex")) {
phb->model = PNV_PHB_MODEL_NPU2;
- else
+ phb->tce_invalidate = pnv_ioda2_opal_tce_invalidate;
+ } else {
phb->model = PNV_PHB_MODEL_UNKNOWN;
+ phb->tce_invalidate = pnv_ioda2_opal_tce_invalidate;
+ }
/* Initialize diagnostic data buffer */
prop32 = of_get_property(np, "ibm,phb-diag-data-size", NULL);
@@ -3816,6 +3740,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
phb->regs = ioremap(r.start, resource_size(&r));
if (phb->regs == NULL)
pr_err(" Failed to map registers !\n");
+ else if (phb->model == PNV_PHB_MODEL_PHB3)
+ phb->tce_invalidate = pnv_ioda2_direct_tce_invalidate;
}
/* Initialize more IODA stuff */
--
2.11.0
^ permalink raw reply related
* Re: [PATCH 8/8] kconfig: remove CONFIG_MCA leftovers
From: Masahiro Yamada @ 2018-10-16 5:20 UTC (permalink / raw)
To: Christoph Hellwig
Cc: linux-arch, linux-scsi, Linux Kbuild mailing list, linux-pci,
Linux Kernel Mailing List, Dominik Brodowski, Alex Bounine,
linuxppc-dev
In-Reply-To: <20181013151016.31674-9-hch@lst.de>
On Sun, Oct 14, 2018 at 12:11 AM Christoph Hellwig <hch@lst.de> wrote:
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
Can you use "powerpc:" or something
for the subject line?
I'd like to see "kconfig:" only for patches
that touch the scripts/kconfig/ directory.
> arch/powerpc/Kconfig | 4 ----
> drivers/scsi/Kconfig | 6 +++---
> 2 files changed, 3 insertions(+), 7 deletions(-)
>
> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> index f0ea460653cd..8b9edf7caf96 100644
> --- a/arch/powerpc/Kconfig
> +++ b/arch/powerpc/Kconfig
> @@ -944,10 +944,6 @@ config FSL_GTM
> help
> Freescale General-purpose Timers support
>
> -# Yes MCA RS/6000s exist but Linux-PPC does not currently support any
> -config MCA
> - bool
> -
> config PCI_DOMAINS
> def_bool PCI
>
> diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
> index 7c097006c54d..d3734c54aec9 100644
> --- a/drivers/scsi/Kconfig
> +++ b/drivers/scsi/Kconfig
> @@ -535,7 +535,7 @@ config SCSI_HPTIOP
>
> config SCSI_BUSLOGIC
> tristate "BusLogic SCSI support"
> - depends on (PCI || ISA || MCA) && SCSI && ISA_DMA_API && VIRT_TO_BUS
> + depends on (PCI || ISA) && SCSI && ISA_DMA_API && VIRT_TO_BUS
> ---help---
> This is support for BusLogic MultiMaster and FlashPoint SCSI Host
> Adapters. Consult the SCSI-HOWTO, available from
> @@ -1142,12 +1142,12 @@ config SCSI_LPFC_DEBUG_FS
>
> config SCSI_SIM710
> tristate "Simple 53c710 SCSI support (Compaq, NCR machines)"
> - depends on (EISA || MCA) && SCSI
> + depends on EISA && SCSI
> select SCSI_SPI_ATTRS
> ---help---
> This driver is for NCR53c710 based SCSI host adapters.
>
> - It currently supports Compaq EISA cards and NCR MCA cards
> + It currently supports Compaq EISA cards.
>
> config SCSI_DC395x
> tristate "Tekram DC395(U/UW/F) and DC315(U) SCSI support"
> --
> 2.19.1
>
--
Best Regards
Masahiro Yamada
^ permalink raw reply
* [PATCH v8 9/9] powerpc: clean stack pointers naming
From: Christophe Leroy @ 2018-10-16 5:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1539623258.git.christophe.leroy@c-s.fr>
Some stack pointers used to also be thread_info pointers
and were called tp. Now that they are only stack pointers,
rename them sp.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/kernel/irq.c | 17 +++++++----------
arch/powerpc/kernel/setup_64.c | 20 ++++++++++----------
2 files changed, 17 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 62cfccf4af89..754f0efc507b 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -659,21 +659,21 @@ void __do_irq(struct pt_regs *regs)
void do_IRQ(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
- void *curtp, *irqtp, *sirqtp;
+ void *cursp, *irqsp, *sirqsp;
/* Switch to the irq stack to handle this */
- curtp = (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
- irqtp = hardirq_ctx[raw_smp_processor_id()];
- sirqtp = softirq_ctx[raw_smp_processor_id()];
+ cursp = (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
+ irqsp = hardirq_ctx[raw_smp_processor_id()];
+ sirqsp = softirq_ctx[raw_smp_processor_id()];
/* Already there ? */
- if (unlikely(curtp == irqtp || curtp == sirqtp)) {
+ if (unlikely(cursp == irqsp || cursp == sirqsp)) {
__do_irq(regs);
set_irq_regs(old_regs);
return;
}
/* Switch stack and call */
- call_do_irq(regs, irqtp);
+ call_do_irq(regs, irqsp);
set_irq_regs(old_regs);
}
@@ -732,10 +732,7 @@ void irq_ctx_init(void)
void do_softirq_own_stack(void)
{
- void *irqtp;
-
- irqtp = softirq_ctx[smp_processor_id()];
- call_do_softirq(irqtp);
+ call_do_softirq(softirq_ctx[smp_processor_id()]);
}
irq_hw_number_t virq_to_hw(unsigned int virq)
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 6792e9c90689..4912ec0320b8 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -717,22 +717,22 @@ void __init emergency_stack_init(void)
limit = min(ppc64_bolted_size(), ppc64_rma_size);
for_each_possible_cpu(i) {
- void *ti;
+ void *sp;
- ti = alloc_stack(limit, i);
- memset(ti, 0, THREAD_SIZE);
- paca_ptrs[i]->emergency_sp = ti + THREAD_SIZE;
+ sp = alloc_stack(limit, i);
+ memset(sp, 0, THREAD_SIZE);
+ paca_ptrs[i]->emergency_sp = sp + THREAD_SIZE;
#ifdef CONFIG_PPC_BOOK3S_64
/* emergency stack for NMI exception handling. */
- ti = alloc_stack(limit, i);
- memset(ti, 0, THREAD_SIZE);
- paca_ptrs[i]->nmi_emergency_sp = ti + THREAD_SIZE;
+ sp = alloc_stack(limit, i);
+ memset(sp, 0, THREAD_SIZE);
+ paca_ptrs[i]->nmi_emergency_sp = sp + THREAD_SIZE;
/* emergency stack for machine check exception handling. */
- ti = alloc_stack(limit, i);
- memset(ti, 0, THREAD_SIZE);
- paca_ptrs[i]->mc_emergency_sp = ti + THREAD_SIZE;
+ sp = alloc_stack(limit, i);
+ memset(sp, 0, THREAD_SIZE);
+ paca_ptrs[i]->mc_emergency_sp = sp + THREAD_SIZE;
#endif
}
}
--
2.13.3
^ permalink raw reply related
* [PATCH v8 8/9] powerpc/64: Remove CURRENT_THREAD_INFO
From: Christophe Leroy @ 2018-10-16 5:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1539623258.git.christophe.leroy@c-s.fr>
Now that current_thread_info is located at the beginning of 'current'
task struct, CURRENT_THREAD_INFO macro is not really needed any more.
This patch replaces it by loads of the value at PACACURRENT(r13).
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/exception-64s.h | 4 ++--
arch/powerpc/include/asm/thread_info.h | 4 ----
arch/powerpc/kernel/entry_64.S | 10 +++++-----
arch/powerpc/kernel/exceptions-64e.S | 2 +-
arch/powerpc/kernel/exceptions-64s.S | 2 +-
arch/powerpc/kernel/idle_book3e.S | 2 +-
arch/powerpc/kernel/idle_power4.S | 2 +-
arch/powerpc/kernel/trace/ftrace_64_mprofile.S | 6 +++---
8 files changed, 14 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 3b4767ed3ec5..dd6a5ae7a769 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -671,7 +671,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
#define RUNLATCH_ON \
BEGIN_FTR_SECTION \
- CURRENT_THREAD_INFO(r3, r1); \
+ ld r3, PACACURRENT(r13); \
ld r4,TI_LOCAL_FLAGS(r3); \
andi. r0,r4,_TLF_RUNLATCH; \
beql ppc64_runlatch_on_trampoline; \
@@ -721,7 +721,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
#ifdef CONFIG_PPC_970_NAP
#define FINISH_NAP \
BEGIN_FTR_SECTION \
- CURRENT_THREAD_INFO(r11, r1); \
+ ld r11, PACACURRENT(r13); \
ld r9,TI_LOCAL_FLAGS(r11); \
andi. r10,r9,_TLF_NAPPING; \
bnel power4_fixup_nap; \
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index c959b8d66cac..8e1d0195ac36 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -17,10 +17,6 @@
#define THREAD_SIZE (1 << THREAD_SHIFT)
-#ifdef CONFIG_PPC64
-#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(ld dest, PACACURRENT(r13))
-#endif
-
#ifndef __ASSEMBLY__
#include <linux/cache.h>
#include <asm/processor.h>
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 03cbf409c3f8..b017bd3da1ed 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -158,7 +158,7 @@ system_call: /* label this so stack traces look sane */
li r10,IRQS_ENABLED
std r10,SOFTE(r1)
- CURRENT_THREAD_INFO(r11, r1)
+ ld r11, PACACURRENT(r13)
ld r10,TI_FLAGS(r11)
andi. r11,r10,_TIF_SYSCALL_DOTRACE
bne .Lsyscall_dotrace /* does not return */
@@ -205,7 +205,7 @@ system_call: /* label this so stack traces look sane */
ld r3,RESULT(r1)
#endif
- CURRENT_THREAD_INFO(r12, r1)
+ ld r12, PACACURRENT(r13)
ld r8,_MSR(r1)
#ifdef CONFIG_PPC_BOOK3S
@@ -336,7 +336,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
/* Repopulate r9 and r10 for the syscall path */
addi r9,r1,STACK_FRAME_OVERHEAD
- CURRENT_THREAD_INFO(r10, r1)
+ ld r10, PACACURRENT(r13)
ld r10,TI_FLAGS(r10)
cmpldi r0,NR_syscalls
@@ -734,7 +734,7 @@ _GLOBAL(ret_from_except_lite)
mtmsrd r10,1 /* Update machine state */
#endif /* CONFIG_PPC_BOOK3E */
- CURRENT_THREAD_INFO(r9, r1)
+ ld r9, PACACURRENT(r13)
ld r3,_MSR(r1)
#ifdef CONFIG_PPC_BOOK3E
ld r10,PACACURRENT(r13)
@@ -848,7 +848,7 @@ resume_kernel:
1: bl preempt_schedule_irq
/* Re-test flags and eventually loop */
- CURRENT_THREAD_INFO(r9, r1)
+ ld r9, PACACURRENT(r13)
ld r4,TI_FLAGS(r9)
andi. r0,r4,_TIF_NEED_RESCHED
bne 1b
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 231d066b4a3d..dfafcd0af009 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -469,7 +469,7 @@ exc_##n##_bad_stack: \
* interrupts happen before the wait instruction.
*/
#define CHECK_NAPPING() \
- CURRENT_THREAD_INFO(r11, r1); \
+ ld r11, PACACURRENT(r13); \
ld r10,TI_LOCAL_FLAGS(r11); \
andi. r9,r10,_TLF_NAPPING; \
beq+ 1f; \
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 89d32bb79d5e..1cbe1a78df57 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1620,7 +1620,7 @@ do_hash_page:
ori r0,r0,DSISR_BAD_FAULT_64S@l
and. r0,r4,r0 /* weird error? */
bne- handle_page_fault /* if not, try to insert a HPTE */
- CURRENT_THREAD_INFO(r11, r1)
+ ld r11, PACACURRENT(r13)
lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */
andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */
bne 77f /* then don't call hash_page now */
diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S
index 4e0d94d02030..31e732c378ad 100644
--- a/arch/powerpc/kernel/idle_book3e.S
+++ b/arch/powerpc/kernel/idle_book3e.S
@@ -63,7 +63,7 @@ _GLOBAL(\name)
1: /* Let's set the _TLF_NAPPING flag so interrupts make us return
* to the right spot
*/
- CURRENT_THREAD_INFO(r11, r1)
+ ld r11, PACACURRENT(r13)
ld r10,TI_LOCAL_FLAGS(r11)
ori r10,r10,_TLF_NAPPING
std r10,TI_LOCAL_FLAGS(r11)
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index a09b3c7ca176..61ac89fd0a05 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -68,7 +68,7 @@ BEGIN_FTR_SECTION
DSSALL
sync
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
- CURRENT_THREAD_INFO(r9, r1)
+ ld r9, PACACURRENT(r13)
ld r8,TI_LOCAL_FLAGS(r9) /* set napping bit */
ori r8,r8,_TLF_NAPPING /* so when we take an exception */
std r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 32476a6e4e9c..202bec086e3b 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -229,7 +229,7 @@ ftrace_call:
* - r0, r11 & r12 are free
*/
livepatch_handler:
- CURRENT_THREAD_INFO(r12, r1)
+ ld r12, PACACURRENT(r13)
/* Allocate 3 x 8 bytes */
ld r11, TI_livepatch_sp(r12)
@@ -256,7 +256,7 @@ livepatch_handler:
* restore it.
*/
- CURRENT_THREAD_INFO(r12, r1)
+ ld r12, PACACURRENT(r13)
ld r11, TI_livepatch_sp(r12)
@@ -273,7 +273,7 @@ livepatch_handler:
ld r2, -24(r11)
/* Pop livepatch stack frame */
- CURRENT_THREAD_INFO(r12, r1)
+ ld r12, PACACURRENT(r13)
subi r11, r11, 24
std r11, TI_livepatch_sp(r12)
--
2.13.3
^ permalink raw reply related
* [PATCH v8 7/9] powerpc/32: Remove CURRENT_THREAD_INFO and rename TI_CPU
From: Christophe Leroy @ 2018-10-16 5:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1539623258.git.christophe.leroy@c-s.fr>
Now that thread_info is similar to task_struct, it's address is in r2
so CURRENT_THREAD_INFO() macro is useless. This patch removes it.
At the same time, as the 'cpu' field is not anymore in thread_info,
this patch renames it to TASK_CPU.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Makefile | 2 +-
arch/powerpc/include/asm/thread_info.h | 2 --
arch/powerpc/kernel/asm-offsets.c | 2 +-
arch/powerpc/kernel/entry_32.S | 43 ++++++++++++----------------------
arch/powerpc/kernel/epapr_hcalls.S | 5 ++--
arch/powerpc/kernel/head_fsl_booke.S | 5 ++--
arch/powerpc/kernel/idle_6xx.S | 8 +++----
arch/powerpc/kernel/idle_e500.S | 8 +++----
arch/powerpc/kernel/misc_32.S | 3 +--
arch/powerpc/mm/hash_low_32.S | 14 ++++-------
arch/powerpc/sysdev/6xx-suspend.S | 5 ++--
11 files changed, 35 insertions(+), 62 deletions(-)
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index c363e765ee38..a81e5b5aa37a 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -430,7 +430,7 @@ ifdef CONFIG_SMP
prepare: task_cpu_prepare
task_cpu_prepare: prepare0
- $(eval KBUILD_CFLAGS += -D_TASK_CPU=$(shell awk '{if ($$2 == "TI_CPU") print $$3;}' include/generated/asm-offsets.h))
+ $(eval KBUILD_CFLAGS += -D_TASK_CPU=$(shell awk '{if ($$2 == "TASK_CPU") print $$3;}' include/generated/asm-offsets.h))
endif
# Check toolchain versions:
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index d91523c2c7d8..c959b8d66cac 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -19,8 +19,6 @@
#ifdef CONFIG_PPC64
#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(ld dest, PACACURRENT(r13))
-#else
-#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(mr dest, r2)
#endif
#ifndef __ASSEMBLY__
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 93040c19942e..1191791edc7e 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -96,7 +96,7 @@ int main(void)
#endif /* CONFIG_PPC64 */
OFFSET(TASK_STACK, task_struct, stack);
#ifdef CONFIG_SMP
- OFFSET(TI_CPU, task_struct, cpu);
+ OFFSET(TASK_CPU, task_struct, cpu);
#endif
#ifdef CONFIG_LIVEPATCH
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index bd3b146e18a3..d0c546ce387e 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -168,8 +168,7 @@ transfer_to_handler:
tophys(r11,r11)
addi r11,r11,global_dbcr0@l
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r9, r1)
- lwz r9,TI_CPU(r9)
+ lwz r9,TASK_CPU(r2)
slwi r9,r9,3
add r11,r11,r9
#endif
@@ -180,8 +179,7 @@ transfer_to_handler:
stw r12,4(r11)
#endif
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
- CURRENT_THREAD_INFO(r9, r1)
- tophys(r9, r9)
+ tophys(r9, r2)
ACCOUNT_CPU_USER_ENTRY(r9, r11, r12)
#endif
@@ -195,8 +193,7 @@ transfer_to_handler:
ble- stack_ovf /* then the kernel stack overflowed */
5:
#if defined(CONFIG_6xx) || defined(CONFIG_E500)
- CURRENT_THREAD_INFO(r9, r1)
- tophys(r9,r9) /* check local flags */
+ tophys(r9,r2) /* check local flags */
lwz r12,TI_LOCAL_FLAGS(r9)
mtcrf 0x01,r12
bt- 31-TLF_NAPPING,4f
@@ -345,8 +342,7 @@ _GLOBAL(DoSyscall)
mtmsr r11
1:
#endif /* CONFIG_TRACE_IRQFLAGS */
- CURRENT_THREAD_INFO(r10, r1)
- lwz r11,TI_FLAGS(r10)
+ lwz r11,TI_FLAGS(r2)
andi. r11,r11,_TIF_SYSCALL_DOTRACE
bne- syscall_dotrace
syscall_dotrace_cont:
@@ -379,13 +375,12 @@ ret_from_syscall:
lwz r3,GPR3(r1)
#endif
mr r6,r3
- CURRENT_THREAD_INFO(r12, r1)
/* disable interrupts so current_thread_info()->flags can't change */
LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */
/* Note: We don't bother telling lockdep about it */
SYNC
MTMSRD(r10)
- lwz r9,TI_FLAGS(r12)
+ lwz r9,TI_FLAGS(r2)
li r8,-MAX_ERRNO
andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
bne- syscall_exit_work
@@ -432,8 +427,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
andi. r4,r8,MSR_PR
beq 3f
- CURRENT_THREAD_INFO(r4, r1)
- ACCOUNT_CPU_USER_EXIT(r4, r5, r7)
+ ACCOUNT_CPU_USER_EXIT(r2, r5, r7)
3:
#endif
lwz r4,_LINK(r1)
@@ -526,7 +520,7 @@ syscall_exit_work:
/* Clear per-syscall TIF flags if any are set. */
li r11,_TIF_PERSYSCALL_MASK
- addi r12,r12,TI_FLAGS
+ addi r12,r2,TI_FLAGS
3: lwarx r8,0,r12
andc r8,r8,r11
#ifdef CONFIG_IBM405_ERR77
@@ -534,7 +528,6 @@ syscall_exit_work:
#endif
stwcx. r8,0,r12
bne- 3b
- subi r12,r12,TI_FLAGS
4: /* Anything which requires enabling interrupts? */
andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
@@ -813,8 +806,7 @@ ret_from_except:
user_exc_return: /* r10 contains MSR_KERNEL here */
/* Check current_thread_info()->flags */
- CURRENT_THREAD_INFO(r9, r1)
- lwz r9,TI_FLAGS(r9)
+ lwz r9,TI_FLAGS(r2)
andi. r0,r9,_TIF_USER_WORK_MASK
bne do_work
@@ -827,8 +819,7 @@ restore_user:
bnel- load_dbcr0
#endif
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
- CURRENT_THREAD_INFO(r9, r1)
- ACCOUNT_CPU_USER_EXIT(r9, r10, r11)
+ ACCOUNT_CPU_USER_EXIT(r2, r10, r11)
#endif
b restore
@@ -836,8 +827,7 @@ restore_user:
/* N.B. the only way to get here is from the beq following ret_from_except. */
resume_kernel:
/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
- CURRENT_THREAD_INFO(r9, r1)
- lwz r8,TI_FLAGS(r9)
+ lwz r8,TI_FLAGS(r2)
andis. r0,r8,_TIF_EMULATE_STACK_STORE@h
beq+ 1f
@@ -863,7 +853,7 @@ resume_kernel:
/* Clear _TIF_EMULATE_STACK_STORE flag */
lis r11,_TIF_EMULATE_STACK_STORE@h
- addi r5,r9,TI_FLAGS
+ addi r5,r2,TI_FLAGS
0: lwarx r8,0,r5
andc r8,r8,r11
#ifdef CONFIG_IBM405_ERR77
@@ -875,7 +865,7 @@ resume_kernel:
#ifdef CONFIG_PREEMPT
/* check current_thread_info->preempt_count */
- lwz r0,TI_PREEMPT(r9)
+ lwz r0,TI_PREEMPT(r2)
cmpwi 0,r0,0 /* if non-zero, just restore regs and return */
bne restore
andi. r8,r8,_TIF_NEED_RESCHED
@@ -891,8 +881,7 @@ resume_kernel:
bl trace_hardirqs_off
#endif
1: bl preempt_schedule_irq
- CURRENT_THREAD_INFO(r9, r1)
- lwz r3,TI_FLAGS(r9)
+ lwz r3,TI_FLAGS(r2)
andi. r0,r3,_TIF_NEED_RESCHED
bne- 1b
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -1191,8 +1180,7 @@ load_dbcr0:
lis r11,global_dbcr0@ha
addi r11,r11,global_dbcr0@l
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r9, r1)
- lwz r9,TI_CPU(r9)
+ lwz r9,TASK_CPU(r2)
slwi r9,r9,3
add r11,r11,r9
#endif
@@ -1232,8 +1220,7 @@ recheck:
LOAD_MSR_KERNEL(r10,MSR_KERNEL)
SYNC
MTMSRD(r10) /* disable interrupts */
- CURRENT_THREAD_INFO(r9, r1)
- lwz r9,TI_FLAGS(r9)
+ lwz r9,TI_FLAGS(r2)
andi. r0,r9,_TIF_NEED_RESCHED
bne- do_resched
andi. r0,r9,_TIF_USER_WORK_MASK
diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S
index 52ca2471ee1a..d252f4663a23 100644
--- a/arch/powerpc/kernel/epapr_hcalls.S
+++ b/arch/powerpc/kernel/epapr_hcalls.S
@@ -21,10 +21,9 @@
#ifndef CONFIG_PPC64
/* epapr_ev_idle() was derived from e500_idle() */
_GLOBAL(epapr_ev_idle)
- CURRENT_THREAD_INFO(r3, r1)
- PPC_LL r4, TI_LOCAL_FLAGS(r3) /* set napping bit */
+ PPC_LL r4, TI_LOCAL_FLAGS(r2) /* set napping bit */
ori r4, r4,_TLF_NAPPING /* so when we take an exception */
- PPC_STL r4, TI_LOCAL_FLAGS(r3) /* it will return to our caller */
+ PPC_STL r4, TI_LOCAL_FLAGS(r2) /* it will return to our caller */
wrteei 1
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 0d27bfff52dd..38918f82bc5b 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -244,8 +244,7 @@ set_ivor:
stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r22, r1)
- stw r24, TI_CPU(r22)
+ stw r24, TASK_CPU(r2)
#endif
bl early_init
@@ -704,7 +703,7 @@ finish_tlb_load:
/* Get the next_tlbcam_idx percpu var */
#ifdef CONFIG_SMP
- lwz r15, TI_CPU-THREAD(r12)
+ lwz r15, TASK_CPU-THREAD(r12)
lis r14, __per_cpu_offset@h
ori r14, r14, __per_cpu_offset@l
rlwinm r15, r15, 2, 0, 29
diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S
index ff026c9d3cab..5afd2e236990 100644
--- a/arch/powerpc/kernel/idle_6xx.S
+++ b/arch/powerpc/kernel/idle_6xx.S
@@ -136,10 +136,9 @@ BEGIN_FTR_SECTION
DSSALL
sync
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
- CURRENT_THREAD_INFO(r9, r1)
- lwz r8,TI_LOCAL_FLAGS(r9) /* set napping bit */
+ lwz r8,TI_LOCAL_FLAGS(r2) /* set napping bit */
ori r8,r8,_TLF_NAPPING /* so when we take an exception */
- stw r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */
+ stw r8,TI_LOCAL_FLAGS(r2) /* it will return to our caller */
mfmsr r7
ori r7,r7,MSR_EE
oris r7,r7,MSR_POW@h
@@ -159,8 +158,7 @@ _GLOBAL(power_save_ppc32_restore)
stw r9,_NIP(r11) /* make it do a blr */
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r12, r11)
- lwz r11,TI_CPU(r12) /* get cpu number * 4 */
+ lwz r11,TASK_CPU(r2) /* get cpu number * 4 */
slwi r11,r11,2
#else
li r11,0
diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S
index 583e55ac7d26..69dfcd2ca011 100644
--- a/arch/powerpc/kernel/idle_e500.S
+++ b/arch/powerpc/kernel/idle_e500.S
@@ -22,10 +22,9 @@
.text
_GLOBAL(e500_idle)
- CURRENT_THREAD_INFO(r3, r1)
- lwz r4,TI_LOCAL_FLAGS(r3) /* set napping bit */
+ lwz r4,TI_LOCAL_FLAGS(r2) /* set napping bit */
ori r4,r4,_TLF_NAPPING /* so when we take an exception */
- stw r4,TI_LOCAL_FLAGS(r3) /* it will return to our caller */
+ stw r4,TI_LOCAL_FLAGS(r2) /* it will return to our caller */
#ifdef CONFIG_PPC_E500MC
wrteei 1
@@ -88,8 +87,7 @@ _GLOBAL(power_save_ppc32_restore)
stw r9,_NIP(r11) /* make it do a blr */
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r12, r1)
- lwz r11,TI_CPU(r12) /* get cpu number * 4 */
+ lwz r11,TASK_CPU(r2) /* get cpu number * 4 */
slwi r11,r11,2
#else
li r11,0
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index a3663ad62f16..0e4da0fe5cbf 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -183,8 +183,7 @@ _GLOBAL(low_choose_750fx_pll)
#ifdef CONFIG_SMP
/* Store new HID1 image */
- CURRENT_THREAD_INFO(r6, r1)
- lwz r6,TI_CPU(r6)
+ lwz r6,TASK_CPU(r2)
slwi r6,r6,2
#else
li r6, 0
diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index 26acf6c8c20c..27edbfddebaa 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -185,8 +185,7 @@ _GLOBAL(add_hash_page)
add r3,r3,r0 /* note create_hpte trims to 24 bits */
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r8, r1) /* use cpu number to make tag */
- lwz r8,TI_CPU(r8) /* to go in mmu_hash_lock */
+ lwz r8,TASK_CPU(r2) /* to go in mmu_hash_lock */
oris r8,r8,12
#endif /* CONFIG_SMP */
@@ -546,9 +545,8 @@ _GLOBAL(flush_hash_pages)
#ifdef CONFIG_SMP
addis r9,r7,mmu_hash_lock@ha
addi r9,r9,mmu_hash_lock@l
- CURRENT_THREAD_INFO(r8, r1)
- add r8,r8,r7
- lwz r8,TI_CPU(r8)
+ add r8,r2,r7
+ lwz r8,TASK_CPU(r8)
oris r8,r8,9
10: lwarx r0,0,r9
cmpi 0,r0,0
@@ -641,8 +639,7 @@ EXPORT_SYMBOL(flush_hash_pages)
*/
_GLOBAL(_tlbie)
#ifdef CONFIG_SMP
- CURRENT_THREAD_INFO(r8, r1)
- lwz r8,TI_CPU(r8)
+ lwz r8,TASK_CPU(r2)
oris r8,r8,11
mfmsr r10
SYNC
@@ -679,8 +676,7 @@ _GLOBAL(_tlbie)
*/
_GLOBAL(_tlbia)
#if defined(CONFIG_SMP)
- CURRENT_THREAD_INFO(r8, r1)
- lwz r8,TI_CPU(r8)
+ lwz r8,TASK_CPU(r2)
oris r8,r8,10
mfmsr r10
SYNC
diff --git a/arch/powerpc/sysdev/6xx-suspend.S b/arch/powerpc/sysdev/6xx-suspend.S
index cf48e9cb2575..6c4aec25c4ba 100644
--- a/arch/powerpc/sysdev/6xx-suspend.S
+++ b/arch/powerpc/sysdev/6xx-suspend.S
@@ -29,10 +29,9 @@ _GLOBAL(mpc6xx_enter_standby)
ori r5, r5, ret_from_standby@l
mtlr r5
- CURRENT_THREAD_INFO(r5, r1)
- lwz r6, TI_LOCAL_FLAGS(r5)
+ lwz r6, TI_LOCAL_FLAGS(r2)
ori r6, r6, _TLF_SLEEPING
- stw r6, TI_LOCAL_FLAGS(r5)
+ stw r6, TI_LOCAL_FLAGS(r2)
mfmsr r5
ori r5, r5, MSR_EE
--
2.13.3
^ permalink raw reply related
* [PATCH v8 6/9] powerpc: 'current_set' is now a table of task_struct pointers
From: Christophe Leroy @ 2018-10-16 5:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1539623258.git.christophe.leroy@c-s.fr>
The table of pointers 'current_set' has been used for retrieving
the stack and current. They used to be thread_info pointers as
they were pointing to the stack and current was taken from the
'task' field of the thread_info.
Now, the pointers of 'current_set' table are now both pointers
to task_struct and pointers to thread_info.
As they are used to get current, and the stack pointer is
retrieved from current's stack field, this patch changes
their type to task_struct, and renames secondary_ti to
secondary_current.
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/asm-prototypes.h | 4 ++--
arch/powerpc/kernel/head_32.S | 6 +++---
arch/powerpc/kernel/head_44x.S | 4 ++--
arch/powerpc/kernel/head_fsl_booke.S | 4 ++--
arch/powerpc/kernel/smp.c | 10 ++++------
5 files changed, 13 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 2741831482f4..d6fdc7e79d09 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -23,8 +23,8 @@
#include <uapi/asm/ucontext.h>
/* SMP */
-extern struct thread_info *current_set[NR_CPUS];
-extern struct thread_info *secondary_ti;
+extern struct task_struct *current_set[NR_CPUS];
+extern struct task_struct *secondary_current;
void start_secondary(void *unused);
/* kexec */
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 44dfd73b2a62..ba0341bd5a00 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -842,9 +842,9 @@ __secondary_start:
#endif /* CONFIG_6xx */
/* get current's stack and current */
- lis r1,secondary_ti@ha
- tophys(r1,r1)
- lwz r2,secondary_ti@l(r1)
+ lis r2,secondary_current@ha
+ tophys(r2,r2)
+ lwz r2,secondary_current@l(r2)
tophys(r1,r2)
lwz r1,TASK_STACK(r1)
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 2c7e90f36358..48e4de4dfd0c 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -1021,8 +1021,8 @@ _GLOBAL(start_secondary_47x)
/* Now we can get our task struct and real stack pointer */
/* Get current's stack and current */
- lis r1,secondary_ti@ha
- lwz r2,secondary_ti@l(r1)
+ lis r2,secondary_current@ha
+ lwz r2,secondary_current@l(r2)
lwz r1,TASK_STACK(r2)
/* Current stack pointer */
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index b8a2b789677e..0d27bfff52dd 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -1076,8 +1076,8 @@ __secondary_start:
bl call_setup_cpu
/* get current's stack and current */
- lis r1,secondary_ti@ha
- lwz r2,secondary_ti@l(r1)
+ lis r2,secondary_current@ha
+ lwz r2,secondary_current@l(r2)
lwz r1,TASK_STACK(r2)
/* stack */
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 0f9f7f1f4e2f..2df2bc3ea17d 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -75,7 +75,7 @@
static DEFINE_PER_CPU(int, cpu_state) = { 0 };
#endif
-struct thread_info *secondary_ti;
+struct task_struct *secondary_current;
bool has_big_cores;
DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
@@ -663,7 +663,7 @@ void smp_send_stop(void)
}
#endif /* CONFIG_NMI_IPI */
-struct thread_info *current_set[NR_CPUS];
+struct task_struct *current_set[NR_CPUS];
static void smp_store_cpu_info(int id)
{
@@ -928,7 +928,7 @@ void smp_prepare_boot_cpu(void)
paca_ptrs[boot_cpuid]->__current = current;
#endif
set_numa_node(numa_cpu_lookup_table[boot_cpuid]);
- current_set[boot_cpuid] = task_thread_info(current);
+ current_set[boot_cpuid] = current;
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -1013,8 +1013,6 @@ static bool secondaries_inhibited(void)
static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
{
- struct thread_info *ti = task_thread_info(idle);
-
#ifdef CONFIG_STACKPROTECTOR
idle->stack_canary = get_random_canary();
#endif
@@ -1028,7 +1026,7 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
#endif
#endif
idle->cpu = cpu;
- secondary_ti = current_set[cpu] = ti;
+ secondary_current = current_set[cpu] = idle;
}
int __cpu_up(unsigned int cpu, struct task_struct *tidle)
--
2.13.3
^ permalink raw reply related
* [PATCH v8 5/9] powerpc: regain entire stack space
From: Christophe Leroy @ 2018-10-16 5:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1539623258.git.christophe.leroy@c-s.fr>
thread_info is not anymore in the stack, so the entire stack
can now be used.
There is also no risk anymore of corrupting task_cpu(p) with a
stack overflow so the patch removes the test.
When doing this, an explicit test for NULL stack pointer is
needed in validate_sp() as it is not anymore implicitely covered
by the sizeof(thread_info) gap.
In the meantime, with the previous patch all pointers to the stacks
are not anymore pointers to thread_info so this patch changes them
to void*
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/irq.h | 10 +++++-----
arch/powerpc/include/asm/processor.h | 3 +--
arch/powerpc/kernel/asm-offsets.c | 1 -
arch/powerpc/kernel/entry_32.S | 14 ++++----------
arch/powerpc/kernel/irq.c | 19 +++++++++----------
arch/powerpc/kernel/misc_32.S | 6 ++----
arch/powerpc/kernel/process.c | 32 +++++++++++++-------------------
arch/powerpc/kernel/setup_64.c | 8 ++++----
8 files changed, 38 insertions(+), 55 deletions(-)
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 2efbae8d93be..966ddd4d2414 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -48,9 +48,9 @@ struct pt_regs;
* Per-cpu stacks for handling critical, debug and machine check
* level interrupts.
*/
-extern struct thread_info *critirq_ctx[NR_CPUS];
-extern struct thread_info *dbgirq_ctx[NR_CPUS];
-extern struct thread_info *mcheckirq_ctx[NR_CPUS];
+extern void *critirq_ctx[NR_CPUS];
+extern void *dbgirq_ctx[NR_CPUS];
+extern void *mcheckirq_ctx[NR_CPUS];
extern void exc_lvl_ctx_init(void);
#else
#define exc_lvl_ctx_init()
@@ -59,8 +59,8 @@ extern void exc_lvl_ctx_init(void);
/*
* Per-cpu stacks for handling hard and soft interrupts.
*/
-extern struct thread_info *hardirq_ctx[NR_CPUS];
-extern struct thread_info *softirq_ctx[NR_CPUS];
+extern void *hardirq_ctx[NR_CPUS];
+extern void *softirq_ctx[NR_CPUS];
extern void irq_ctx_init(void);
void call_do_softirq(void *sp);
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 53649b9b7dc4..238f0938c859 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -331,8 +331,7 @@ struct thread_struct {
#define ARCH_MIN_TASKALIGN 16
#define INIT_SP (sizeof(init_stack) + (unsigned long) &init_stack)
-#define INIT_SP_LIMIT \
- (_ALIGN_UP(sizeof(struct thread_info), 16) + (unsigned long)&init_stack)
+#define INIT_SP_LIMIT ((unsigned long)&init_stack)
#ifdef CONFIG_SPE
#define SPEFSCR_INIT \
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 5ef6db2d8a9e..93040c19942e 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -92,7 +92,6 @@ int main(void)
DEFINE(SIGSEGV, SIGSEGV);
DEFINE(NMI_MASK, NMI_MASK);
#else
- DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
OFFSET(KSP_LIMIT, thread_struct, ksp_limit);
#endif /* CONFIG_PPC64 */
OFFSET(TASK_STACK, task_struct, stack);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index fa7a69ffb37a..bd3b146e18a3 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -97,14 +97,11 @@ crit_transfer_to_handler:
mfspr r0,SPRN_SRR1
stw r0,_SRR1(r11)
- /* set the stack limit to the current stack
- * and set the limit to protect the thread_info
- * struct
- */
+ /* set the stack limit to the current stack */
mfspr r8,SPRN_SPRG_THREAD
lwz r0,KSP_LIMIT(r8)
stw r0,SAVED_KSP_LIMIT(r11)
- rlwimi r0,r1,0,0,(31-THREAD_SHIFT)
+ rlwinm r0,r1,0,0,(31 - THREAD_SHIFT)
stw r0,KSP_LIMIT(r8)
/* fall through */
#endif
@@ -121,14 +118,11 @@ crit_transfer_to_handler:
mfspr r0,SPRN_SRR1
stw r0,crit_srr1@l(0)
- /* set the stack limit to the current stack
- * and set the limit to protect the thread_info
- * struct
- */
+ /* set the stack limit to the current stack */
mfspr r8,SPRN_SPRG_THREAD
lwz r0,KSP_LIMIT(r8)
stw r0,saved_ksp_limit@l(0)
- rlwimi r0,r1,0,0,(31-THREAD_SHIFT)
+ rlwinm r0,r1,0,0,(31 - THREAD_SHIFT)
stw r0,KSP_LIMIT(r8)
/* fall through */
#endif
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 3fdb6b6973cf..62cfccf4af89 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -618,9 +618,8 @@ static inline void check_stack_overflow(void)
sp = current_stack_pointer() & (THREAD_SIZE-1);
/* check for stack overflow: is there less than 2KB free? */
- if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
- pr_err("do_IRQ: stack overflow: %ld\n",
- sp - sizeof(struct thread_info));
+ if (unlikely(sp < 2048)) {
+ pr_err("do_IRQ: stack overflow: %ld\n", sp);
dump_stack();
}
#endif
@@ -660,7 +659,7 @@ void __do_irq(struct pt_regs *regs)
void do_IRQ(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
- struct thread_info *curtp, *irqtp, *sirqtp;
+ void *curtp, *irqtp, *sirqtp;
/* Switch to the irq stack to handle this */
curtp = (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
@@ -690,9 +689,9 @@ void __init init_IRQ(void)
}
#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
-struct thread_info *critirq_ctx[NR_CPUS] __read_mostly;
-struct thread_info *dbgirq_ctx[NR_CPUS] __read_mostly;
-struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly;
+void *critirq_ctx[NR_CPUS] __read_mostly;
+void *dbgirq_ctx[NR_CPUS] __read_mostly;
+void *mcheckirq_ctx[NR_CPUS] __read_mostly;
void exc_lvl_ctx_init(void)
{
@@ -718,8 +717,8 @@ void exc_lvl_ctx_init(void)
}
#endif
-struct thread_info *softirq_ctx[NR_CPUS] __read_mostly;
-struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly;
+void *softirq_ctx[NR_CPUS] __read_mostly;
+void *hardirq_ctx[NR_CPUS] __read_mostly;
void irq_ctx_init(void)
{
@@ -733,7 +732,7 @@ void irq_ctx_init(void)
void do_softirq_own_stack(void)
{
- struct thread_info *irqtp;
+ void *irqtp;
irqtp = softirq_ctx[smp_processor_id()];
call_do_softirq(irqtp);
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 32762f4c3458..a3663ad62f16 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -46,11 +46,10 @@ _GLOBAL(call_do_softirq)
mflr r0
stw r0,4(r1)
lwz r10,THREAD+KSP_LIMIT(r2)
- addi r11,r3,THREAD_INFO_GAP
+ stw r3, THREAD+KSP_LIMIT(r2)
stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
mr r1,r3
stw r10,8(r1)
- stw r11,THREAD+KSP_LIMIT(r2)
bl __do_softirq
lwz r10,8(r1)
lwz r1,0(r1)
@@ -66,11 +65,10 @@ _GLOBAL(call_do_irq)
mflr r0
stw r0,4(r1)
lwz r10,THREAD+KSP_LIMIT(r2)
- addi r11,r4,THREAD_INFO_GAP
+ stw r4, THREAD+KSP_LIMIT(r2)
stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
mr r1,r4
stw r10,8(r1)
- stw r11,THREAD+KSP_LIMIT(r2)
bl __do_irq
lwz r10,8(r1)
lwz r1,0(r1)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 84e39cedf03b..16d937a8c378 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1699,8 +1699,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
sp -= STACK_FRAME_OVERHEAD;
p->thread.ksp = sp;
#ifdef CONFIG_PPC32
- p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
- _ALIGN_UP(sizeof(struct thread_info), 16);
+ p->thread.ksp_limit = (unsigned long)end_of_stack(p);
#endif
#ifdef CONFIG_HAVE_HW_BREAKPOINT
p->thread.ptrace_bps[0] = NULL;
@@ -2003,21 +2002,14 @@ static inline int valid_irq_stack(unsigned long sp, struct task_struct *p,
unsigned long stack_page;
unsigned long cpu = task_cpu(p);
- /*
- * Avoid crashing if the stack has overflowed and corrupted
- * task_cpu(p), which is in the thread_info struct.
- */
- if (cpu < NR_CPUS && cpu_possible(cpu)) {
- stack_page = (unsigned long) hardirq_ctx[cpu];
- if (sp >= stack_page + sizeof(struct thread_struct)
- && sp <= stack_page + THREAD_SIZE - nbytes)
- return 1;
-
- stack_page = (unsigned long) softirq_ctx[cpu];
- if (sp >= stack_page + sizeof(struct thread_struct)
- && sp <= stack_page + THREAD_SIZE - nbytes)
- return 1;
- }
+ stack_page = (unsigned long)hardirq_ctx[cpu];
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
+ stack_page = (unsigned long)softirq_ctx[cpu];
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
return 0;
}
@@ -2026,8 +2018,10 @@ int validate_sp(unsigned long sp, struct task_struct *p,
{
unsigned long stack_page = (unsigned long)task_stack_page(p);
- if (sp >= stack_page + sizeof(struct thread_struct)
- && sp <= stack_page + THREAD_SIZE - nbytes)
+ if (sp < THREAD_SIZE)
+ return 0;
+
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
return 1;
return valid_irq_stack(sp, p, nbytes);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 2d682f3e31c6..6792e9c90689 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -717,22 +717,22 @@ void __init emergency_stack_init(void)
limit = min(ppc64_bolted_size(), ppc64_rma_size);
for_each_possible_cpu(i) {
- struct thread_info *ti;
+ void *ti;
ti = alloc_stack(limit, i);
memset(ti, 0, THREAD_SIZE);
- paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE;
+ paca_ptrs[i]->emergency_sp = ti + THREAD_SIZE;
#ifdef CONFIG_PPC_BOOK3S_64
/* emergency stack for NMI exception handling. */
ti = alloc_stack(limit, i);
memset(ti, 0, THREAD_SIZE);
- paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE;
+ paca_ptrs[i]->nmi_emergency_sp = ti + THREAD_SIZE;
/* emergency stack for machine check exception handling. */
ti = alloc_stack(limit, i);
memset(ti, 0, THREAD_SIZE);
- paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;
+ paca_ptrs[i]->mc_emergency_sp = ti + THREAD_SIZE;
#endif
}
}
--
2.13.3
^ permalink raw reply related
* [PATCH v8 4/9] powerpc: Activate CONFIG_THREAD_INFO_IN_TASK
From: Christophe Leroy @ 2018-10-16 5:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1539623258.git.christophe.leroy@c-s.fr>
This patch activates CONFIG_THREAD_INFO_IN_TASK which
moves the thread_info into task_struct.
Moving thread_info into task_struct has the following advantages:
- It protects thread_info from corruption in the case of stack
overflows.
- Its address is harder to determine if stack addresses are
leaked, making a number of attacks more difficult.
This has the following consequences:
- thread_info is now located at the beginning of task_struct.
- The 'cpu' field is now in task_struct, and only exists when
CONFIG_SMP is active.
- thread_info doesn't have anymore the 'task' field.
This patch:
- Removes all recopy of thread_info struct when the stack changes.
- Changes the CURRENT_THREAD_INFO() macro to point to current.
- Selects CONFIG_THREAD_INFO_IN_TASK.
- Modifies raw_smp_processor_id() to get ->cpu from current without
including linux/sched.h to avoid circular inclusion and without
including asm/asm-offsets.h to avoid symbol names duplication
between ASM constants and C constants.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/Makefile | 7 +++++
arch/powerpc/include/asm/ptrace.h | 2 +-
arch/powerpc/include/asm/smp.h | 17 +++++++++++-
arch/powerpc/include/asm/thread_info.h | 17 ++----------
arch/powerpc/kernel/asm-offsets.c | 7 +++--
arch/powerpc/kernel/entry_32.S | 9 +++----
arch/powerpc/kernel/exceptions-64e.S | 11 --------
arch/powerpc/kernel/head_32.S | 6 ++---
arch/powerpc/kernel/head_44x.S | 4 +--
arch/powerpc/kernel/head_64.S | 1 +
arch/powerpc/kernel/head_booke.h | 8 +-----
arch/powerpc/kernel/head_fsl_booke.S | 7 +++--
arch/powerpc/kernel/irq.c | 47 +---------------------------------
arch/powerpc/kernel/kgdb.c | 28 --------------------
arch/powerpc/kernel/machine_kexec_64.c | 6 ++---
arch/powerpc/kernel/setup_64.c | 21 ---------------
arch/powerpc/kernel/smp.c | 2 +-
arch/powerpc/net/bpf_jit32.h | 5 ++--
19 files changed, 52 insertions(+), 154 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 3d008115fe18..96cb2cee4a5e 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -239,6 +239,7 @@ config PPC
select RTC_LIB
select SPARSE_IRQ
select SYSCTL_EXCEPTION_TRACE
+ select THREAD_INFO_IN_TASK
select VIRT_TO_BUS if !PPC64
#
# Please keep this list sorted alphabetically.
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 6c4f8a099bbb..c363e765ee38 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -426,6 +426,13 @@ else
endif
endif
+ifdef CONFIG_SMP
+prepare: task_cpu_prepare
+
+task_cpu_prepare: prepare0
+ $(eval KBUILD_CFLAGS += -D_TASK_CPU=$(shell awk '{if ($$2 == "TI_CPU") print $$3;}' include/generated/asm-offsets.h))
+endif
+
# Check toolchain versions:
# - gcc-4.6 is the minimum kernel-wide version so nothing required.
checkbin:
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 2ba2a1e52291..69fd72834a41 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -151,7 +151,7 @@ extern int ptrace_put_reg(struct task_struct *task, int regno,
unsigned long data);
#define current_pt_regs() \
- ((struct pt_regs *)((unsigned long)current_thread_info() + THREAD_SIZE) - 1)
+ ((struct pt_regs *)((unsigned long)task_stack_page(current) + THREAD_SIZE) - 1)
/*
* We use the least-significant bit of the trap field to indicate
* whether we have saved the full set of registers, or only a
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 41695745032c..0de717e16dd6 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -83,7 +83,22 @@ int is_cpu_dead(unsigned int cpu);
/* 32-bit */
extern int smp_hw_index[];
-#define raw_smp_processor_id() (current_thread_info()->cpu)
+/*
+ * This is particularly ugly: it appears we can't actually get the definition
+ * of task_struct here, but we need access to the CPU this task is running on.
+ * Instead of using task_struct we're using _TASK_CPU which is extracted from
+ * asm-offsets.h by kbuild to get the current processor ID.
+ *
+ * This also needs to be safeguarded when building asm-offsets.s because at
+ * that time _TASK_CPU is not defined yet. It could have been guarded by
+ * _TASK_CPU itself, but we want the build to fail if _TASK_CPU is missing
+ * when building something else than asm-offsets.s
+ */
+#ifdef GENERATING_ASM_OFFSETS
+#define raw_smp_processor_id() (0)
+#else
+#define raw_smp_processor_id() (*(unsigned int *)((void *)current + _TASK_CPU))
+#endif
#define hard_smp_processor_id() (smp_hw_index[smp_processor_id()])
static inline int get_hard_smp_processor_id(int cpu)
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 544cac0474cb..d91523c2c7d8 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -18,9 +18,9 @@
#define THREAD_SIZE (1 << THREAD_SHIFT)
#ifdef CONFIG_PPC64
-#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(clrrdi dest, sp, THREAD_SHIFT)
+#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(ld dest, PACACURRENT(r13))
#else
-#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(rlwinm dest, sp, 0, 0, 31-THREAD_SHIFT)
+#define CURRENT_THREAD_INFO(dest, sp) stringify_in_c(mr dest, r2)
#endif
#ifndef __ASSEMBLY__
@@ -34,8 +34,6 @@
* low level task data.
*/
struct thread_info {
- struct task_struct *task; /* main task structure */
- int cpu; /* cpu we're on */
int preempt_count; /* 0 => preemptable,
<0 => BUG */
unsigned long local_flags; /* private flags for thread */
@@ -58,8 +56,6 @@ struct thread_info {
*/
#define INIT_THREAD_INFO(tsk) \
{ \
- .task = &tsk, \
- .cpu = 0, \
.preempt_count = INIT_PREEMPT_COUNT, \
.flags = 0, \
}
@@ -67,15 +63,6 @@ struct thread_info {
#define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT)
/* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
- unsigned long val;
-
- asm (CURRENT_THREAD_INFO(%0,1) : "=r" (val));
-
- return (struct thread_info *)val;
-}
-
extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
#ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 47adbb8673f1..5ef6db2d8a9e 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -13,6 +13,8 @@
* 2 of the License, or (at your option) any later version.
*/
+#define GENERATING_ASM_OFFSETS /* asm/smp.h */
+
#include <linux/compat.h>
#include <linux/signal.h>
#include <linux/sched.h>
@@ -94,6 +96,9 @@ int main(void)
OFFSET(KSP_LIMIT, thread_struct, ksp_limit);
#endif /* CONFIG_PPC64 */
OFFSET(TASK_STACK, task_struct, stack);
+#ifdef CONFIG_SMP
+ OFFSET(TI_CPU, task_struct, cpu);
+#endif
#ifdef CONFIG_LIVEPATCH
OFFSET(TI_livepatch_sp, thread_info, livepatch_sp);
@@ -161,8 +166,6 @@ int main(void)
OFFSET(TI_FLAGS, thread_info, flags);
OFFSET(TI_LOCAL_FLAGS, thread_info, local_flags);
OFFSET(TI_PREEMPT, thread_info, preempt_count);
- OFFSET(TI_TASK, thread_info, task);
- OFFSET(TI_CPU, thread_info, cpu);
#ifdef CONFIG_PPC64
OFFSET(DCACHEL1BLOCKSIZE, ppc64_caches, l1d.block_size);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 7ea1d71f4546..fa7a69ffb37a 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -1166,10 +1166,6 @@ ret_from_debug_exc:
mfspr r9,SPRN_SPRG_THREAD
lwz r10,SAVED_KSP_LIMIT(r1)
stw r10,KSP_LIMIT(r9)
- lwz r9,TASK_STACK-THREAD(r9)
- CURRENT_THREAD_INFO(r10, r1)
- lwz r10,TI_PREEMPT(r10)
- stw r10,TI_PREEMPT(r9)
RESTORE_xSRR(SRR0,SRR1);
RESTORE_xSRR(CSRR0,CSRR1);
RESTORE_MMU_REGS;
@@ -1292,10 +1288,13 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFSET(CPU_FTR_601)
lwz r3,_TRAP(r1)
andi. r0,r3,1
- beq 4f
+ beq 5f
SAVE_NVGPRS(r1)
rlwinm r3,r3,0,0,30
stw r3,_TRAP(r1)
+5: mfspr r2,SPRN_SPRG_THREAD
+ addi r2,r2,-THREAD
+ tovirt(r2,r2) /* set back r2 to current */
4: addi r3,r1,STACK_FRAME_OVERHEAD
bl unrecoverable_exception
/* shouldn't return */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 6d6e144a28ce..231d066b4a3d 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -77,17 +77,6 @@ special_reg_save:
andi. r3,r3,MSR_PR
bnelr
- /* Copy info into temporary exception thread info */
- ld r11,PACAKSAVE(r13)
- CURRENT_THREAD_INFO(r11, r11)
- CURRENT_THREAD_INFO(r12, r1)
- ld r10,TI_FLAGS(r11)
- std r10,TI_FLAGS(r12)
- ld r10,TI_PREEMPT(r11)
- std r10,TI_PREEMPT(r12)
- ld r10,TI_TASK(r11)
- std r10,TI_TASK(r12)
-
/*
* Advance to the next TLB exception frame for handler
* types that don't do it automatically.
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index dce6f2ff07e5..44dfd73b2a62 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -844,9 +844,9 @@ __secondary_start:
/* get current's stack and current */
lis r1,secondary_ti@ha
tophys(r1,r1)
- lwz r1,secondary_ti@l(r1)
- tophys(r2,r1)
- lwz r2,TI_TASK(r2)
+ lwz r2,secondary_ti@l(r1)
+ tophys(r1,r2)
+ lwz r1,TASK_STACK(r1)
/* stack */
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 15d39b2499de..2c7e90f36358 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -1022,8 +1022,8 @@ _GLOBAL(start_secondary_47x)
/* Get current's stack and current */
lis r1,secondary_ti@ha
- lwz r1,secondary_ti@l(r1)
- lwz r2,TI_TASK(r1)
+ lwz r2,secondary_ti@l(r1)
+ lwz r1,TASK_STACK(r2)
/* Current stack pointer */
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 4898e9491a1c..c6a9bf7b34bf 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -805,6 +805,7 @@ __secondary_start:
LOAD_REG_ADDR(r3, current_set)
sldi r28,r24,3 /* get current_set[cpu#] */
ldx r14,r3,r28
+ ld r14,TASK_STACK(r14)
addi r14,r14,THREAD_SIZE-STACK_FRAME_OVERHEAD
std r14,PACAKSAVE(r13)
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 175f812066dc..f0c254ab9703 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -143,13 +143,7 @@
stw r10,GPR11(r11); \
b 2f; \
/* COMING FROM PRIV MODE */ \
-1: lwz r9,TI_FLAGS-EXC_LVL_FRAME_OVERHEAD(r11); \
- lwz r10,TI_PREEMPT-EXC_LVL_FRAME_OVERHEAD(r11); \
- stw r9,TI_FLAGS-EXC_LVL_FRAME_OVERHEAD(r8); \
- stw r10,TI_PREEMPT-EXC_LVL_FRAME_OVERHEAD(r8); \
- lwz r9,TI_TASK-EXC_LVL_FRAME_OVERHEAD(r11); \
- stw r9,TI_TASK-EXC_LVL_FRAME_OVERHEAD(r8); \
- mr r11,r8; \
+1: mr r11, r8; \
2: mfspr r8,SPRN_SPRG_RSCRATCH_##exc_level; \
stw r12,GPR12(r11); /* save various registers */\
mflr r10; \
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 239ad8a4754e..b8a2b789677e 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -704,8 +704,7 @@ finish_tlb_load:
/* Get the next_tlbcam_idx percpu var */
#ifdef CONFIG_SMP
- lwz r12, TASK_STACK-THREAD(r12)
- lwz r15, TI_CPU(r12)
+ lwz r15, TI_CPU-THREAD(r12)
lis r14, __per_cpu_offset@h
ori r14, r14, __per_cpu_offset@l
rlwinm r15, r15, 2, 0, 29
@@ -1078,8 +1077,8 @@ __secondary_start:
/* get current's stack and current */
lis r1,secondary_ti@ha
- lwz r1,secondary_ti@l(r1)
- lwz r2,TI_TASK(r1)
+ lwz r2,secondary_ti@l(r1)
+ lwz r1,TASK_STACK(r2)
/* stack */
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 9e7dc4468c8c..3fdb6b6973cf 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -673,24 +673,9 @@ void do_IRQ(struct pt_regs *regs)
set_irq_regs(old_regs);
return;
}
-
- /* Prepare the thread_info in the irq stack */
- irqtp->task = curtp->task;
- irqtp->flags = 0;
-
- /* Copy the preempt_count so that the [soft]irq checks work. */
- irqtp->preempt_count = curtp->preempt_count;
-
/* Switch stack and call */
call_do_irq(regs, irqtp);
- /* Restore stack limit */
- irqtp->task = NULL;
-
- /* Copy back updates to the thread_info */
- if (irqtp->flags)
- set_bits(irqtp->flags, &curtp->flags);
-
set_irq_regs(old_regs);
}
@@ -711,7 +696,6 @@ struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly;
void exc_lvl_ctx_init(void)
{
- struct thread_info *tp;
int i, cpu_nr;
for_each_possible_cpu(i) {
@@ -726,20 +710,9 @@ void exc_lvl_ctx_init(void)
#endif
memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE);
- tp = critirq_ctx[cpu_nr];
- tp->cpu = cpu_nr;
- tp->preempt_count = 0;
-
#ifdef CONFIG_BOOKE
memset((void *)dbgirq_ctx[cpu_nr], 0, THREAD_SIZE);
- tp = dbgirq_ctx[cpu_nr];
- tp->cpu = cpu_nr;
- tp->preempt_count = 0;
-
memset((void *)mcheckirq_ctx[cpu_nr], 0, THREAD_SIZE);
- tp = mcheckirq_ctx[cpu_nr];
- tp->cpu = cpu_nr;
- tp->preempt_count = HARDIRQ_OFFSET;
#endif
}
}
@@ -750,38 +723,20 @@ struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly;
void irq_ctx_init(void)
{
- struct thread_info *tp;
int i;
for_each_possible_cpu(i) {
memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
- tp = softirq_ctx[i];
- tp->cpu = i;
- klp_init_thread_info(tp);
-
memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
- tp = hardirq_ctx[i];
- tp->cpu = i;
- klp_init_thread_info(tp);
}
}
void do_softirq_own_stack(void)
{
- struct thread_info *curtp, *irqtp;
+ struct thread_info *irqtp;
- curtp = current_thread_info();
irqtp = softirq_ctx[smp_processor_id()];
- irqtp->task = curtp->task;
- irqtp->flags = 0;
call_do_softirq(irqtp);
- irqtp->task = NULL;
-
- /* Set any flag that may have been set on the
- * alternate stack
- */
- if (irqtp->flags)
- set_bits(irqtp->flags, &curtp->flags);
}
irq_hw_number_t virq_to_hw(unsigned int virq)
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 35e240a0a408..f4a34e46ee34 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -150,41 +150,13 @@ static int kgdb_handle_breakpoint(struct pt_regs *regs)
return 1;
}
-static DEFINE_PER_CPU(struct thread_info, kgdb_thread_info);
static int kgdb_singlestep(struct pt_regs *regs)
{
- struct thread_info *thread_info, *exception_thread_info;
- struct thread_info *backup_current_thread_info =
- this_cpu_ptr(&kgdb_thread_info);
-
if (user_mode(regs))
return 0;
- /*
- * On Book E and perhaps other processors, singlestep is handled on
- * the critical exception stack. This causes current_thread_info()
- * to fail, since it it locates the thread_info by masking off
- * the low bits of the current stack pointer. We work around
- * this issue by copying the thread_info from the kernel stack
- * before calling kgdb_handle_exception, and copying it back
- * afterwards. On most processors the copy is avoided since
- * exception_thread_info == thread_info.
- */
- thread_info = (struct thread_info *)(regs->gpr[1] & ~(THREAD_SIZE-1));
- exception_thread_info = current_thread_info();
-
- if (thread_info != exception_thread_info) {
- /* Save the original current_thread_info. */
- memcpy(backup_current_thread_info, exception_thread_info, sizeof *thread_info);
- memcpy(exception_thread_info, thread_info, sizeof *thread_info);
- }
-
kgdb_handle_exception(0, SIGTRAP, 0, regs);
- if (thread_info != exception_thread_info)
- /* Restore current_thread_info lastly. */
- memcpy(exception_thread_info, backup_current_thread_info, sizeof *thread_info);
-
return 1;
}
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index a0f6f45005bd..75692c327ba0 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -317,10 +317,8 @@ void default_machine_kexec(struct kimage *image)
* We setup preempt_count to avoid using VMX in memcpy.
* XXX: the task struct will likely be invalid once we do the copy!
*/
- kexec_stack.thread_info.task = current_thread_info()->task;
- kexec_stack.thread_info.flags = 0;
- kexec_stack.thread_info.preempt_count = HARDIRQ_OFFSET;
- kexec_stack.thread_info.cpu = current_thread_info()->cpu;
+ current_thread_info()->flags = 0;
+ current_thread_info()->preempt_count = HARDIRQ_OFFSET;
/* We need a static PACA, too; copy this CPU's PACA over and switch to
* it. Also poison per_cpu_offset and NULL lppaca to catch anyone using
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index faf00222b324..2d682f3e31c6 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -691,24 +691,6 @@ void __init exc_lvl_early_init(void)
#endif
/*
- * Emergency stacks are used for a range of things, from asynchronous
- * NMIs (system reset, machine check) to synchronous, process context.
- * We set preempt_count to zero, even though that isn't necessarily correct. To
- * get the right value we'd need to copy it from the previous thread_info, but
- * doing that might fault causing more problems.
- * TODO: what to do with accounting?
- */
-static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu)
-{
- ti->task = NULL;
- ti->cpu = cpu;
- ti->preempt_count = 0;
- ti->local_flags = 0;
- ti->flags = 0;
- klp_init_thread_info(ti);
-}
-
-/*
* Stack space used when we detect a bad kernel stack pointer, and
* early in SMP boots before relocation is enabled. Exclusive emergency
* stack for machine checks.
@@ -739,20 +721,17 @@ void __init emergency_stack_init(void)
ti = alloc_stack(limit, i);
memset(ti, 0, THREAD_SIZE);
- emerg_stack_init_thread_info(ti, i);
paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE;
#ifdef CONFIG_PPC_BOOK3S_64
/* emergency stack for NMI exception handling. */
ti = alloc_stack(limit, i);
memset(ti, 0, THREAD_SIZE);
- emerg_stack_init_thread_info(ti, i);
paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE;
/* emergency stack for machine check exception handling. */
ti = alloc_stack(limit, i);
memset(ti, 0, THREAD_SIZE);
- emerg_stack_init_thread_info(ti, i);
paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;
#endif
}
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 5613c9617840..0f9f7f1f4e2f 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1027,7 +1027,7 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
paca_ptrs[cpu]->canary = idle->stack_canary;
#endif
#endif
- ti->cpu = cpu;
+ idle->cpu = cpu;
secondary_ti = current_set[cpu] = ti;
}
diff --git a/arch/powerpc/net/bpf_jit32.h b/arch/powerpc/net/bpf_jit32.h
index 6f4daacad296..dc50a8d4b3b9 100644
--- a/arch/powerpc/net/bpf_jit32.h
+++ b/arch/powerpc/net/bpf_jit32.h
@@ -106,9 +106,8 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
} while (0)
#else
#define PPC_BPF_LOAD_CPU(r) \
- do { BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4); \
- PPC_LHZ_OFFS(r, (1 & ~(THREAD_SIZE - 1)), \
- offsetof(struct thread_info, cpu)); \
+ do { BUILD_BUG_ON(FIELD_SIZEOF(struct task_struct, cpu) != 4); \
+ PPC_LHZ_OFFS(r, 2, offsetof(struct task_struct, cpu)); \
} while(0)
#endif
#else
--
2.13.3
^ permalink raw reply related
* [PATCH v8 3/9] powerpc: Prepare for moving thread_info into task_struct
From: Christophe Leroy @ 2018-10-16 5:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1539623258.git.christophe.leroy@c-s.fr>
This patch cleans the powerpc kernel before activating
CONFIG_THREAD_INFO_IN_TASK:
- The purpose of the pointer given to call_do_softirq() and
call_do_irq() is to point the new stack ==> change it to void* and
rename it 'sp'
- Don't use CURRENT_THREAD_INFO() to locate the stack.
- Fix a few comments.
- Replace current_thread_info()->task by current
- Remove unnecessary casts to thread_info, as they'll become invalid
once thread_info is not in stack anymore.
- Rename THREAD_INFO to TASK_STASK: as it is in fact the offset of the
pointer to the stack in task_struct, this pointer will not be impacted
by the move of THREAD_INFO.
- Makes TASK_STACK available to PPC64. PPC64 will need it to get the
stack pointer from current once the thread_info have been moved.
- Modifies klp_init_thread_info() to take task_struct pointer argument.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/irq.h | 4 ++--
arch/powerpc/include/asm/livepatch.h | 7 ++++---
arch/powerpc/include/asm/processor.h | 4 ++--
arch/powerpc/include/asm/reg.h | 2 +-
arch/powerpc/kernel/asm-offsets.c | 2 +-
arch/powerpc/kernel/entry_32.S | 2 +-
arch/powerpc/kernel/entry_64.S | 2 +-
arch/powerpc/kernel/head_32.S | 4 ++--
arch/powerpc/kernel/head_40x.S | 4 ++--
arch/powerpc/kernel/head_44x.S | 2 +-
arch/powerpc/kernel/head_8xx.S | 2 +-
arch/powerpc/kernel/head_booke.h | 4 ++--
arch/powerpc/kernel/head_fsl_booke.S | 4 ++--
arch/powerpc/kernel/irq.c | 2 +-
arch/powerpc/kernel/misc_32.S | 4 ++--
arch/powerpc/kernel/process.c | 8 ++++----
arch/powerpc/kernel/setup-common.c | 2 +-
arch/powerpc/kernel/setup_32.c | 15 +++++----------
arch/powerpc/kernel/smp.c | 4 +++-
19 files changed, 38 insertions(+), 40 deletions(-)
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index ee39ce56b2a2..2efbae8d93be 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -63,8 +63,8 @@ extern struct thread_info *hardirq_ctx[NR_CPUS];
extern struct thread_info *softirq_ctx[NR_CPUS];
extern void irq_ctx_init(void);
-extern void call_do_softirq(struct thread_info *tp);
-extern void call_do_irq(struct pt_regs *regs, struct thread_info *tp);
+void call_do_softirq(void *sp);
+void call_do_irq(struct pt_regs *regs, void *sp);
extern void do_IRQ(struct pt_regs *regs);
extern void __init init_IRQ(void);
extern void __do_irq(struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/livepatch.h b/arch/powerpc/include/asm/livepatch.h
index 47a03b9b528b..8a81d10ccc82 100644
--- a/arch/powerpc/include/asm/livepatch.h
+++ b/arch/powerpc/include/asm/livepatch.h
@@ -43,13 +43,14 @@ static inline unsigned long klp_get_ftrace_location(unsigned long faddr)
return ftrace_location_range(faddr, faddr + 16);
}
-static inline void klp_init_thread_info(struct thread_info *ti)
+static inline void klp_init_thread_info(struct task_struct *p)
{
+ struct thread_info *ti = task_thread_info(p);
/* + 1 to account for STACK_END_MAGIC */
- ti->livepatch_sp = (unsigned long *)(ti + 1) + 1;
+ ti->livepatch_sp = end_of_stack(p) + 1;
}
#else
-static void klp_init_thread_info(struct thread_info *ti) { }
+static inline void klp_init_thread_info(struct task_struct *p) { }
#endif /* CONFIG_LIVEPATCH */
#endif /* _ASM_POWERPC_LIVEPATCH_H */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 2caa44db709a..53649b9b7dc4 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -40,7 +40,7 @@
#ifndef __ASSEMBLY__
#include <linux/types.h>
-#include <asm/thread_info.h>
+#include <linux/thread_info.h>
#include <asm/ptrace.h>
#include <asm/hw_breakpoint.h>
@@ -332,7 +332,7 @@ struct thread_struct {
#define INIT_SP (sizeof(init_stack) + (unsigned long) &init_stack)
#define INIT_SP_LIMIT \
- (_ALIGN_UP(sizeof(init_thread_info), 16) + (unsigned long) &init_stack)
+ (_ALIGN_UP(sizeof(struct thread_info), 16) + (unsigned long)&init_stack)
#ifdef CONFIG_SPE
#define SPEFSCR_INIT \
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 640a4d818772..d2528a0b2f5b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1058,7 +1058,7 @@
* - SPRG9 debug exception scratch
*
* All 32-bit:
- * - SPRG3 current thread_info pointer
+ * - SPRG3 current thread_struct physical addr pointer
* (virtual on BookE, physical on others)
*
* 32-bit classic:
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 10ef2e4db2fd..47adbb8673f1 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -90,10 +90,10 @@ int main(void)
DEFINE(SIGSEGV, SIGSEGV);
DEFINE(NMI_MASK, NMI_MASK);
#else
- OFFSET(THREAD_INFO, task_struct, stack);
DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
OFFSET(KSP_LIMIT, thread_struct, ksp_limit);
#endif /* CONFIG_PPC64 */
+ OFFSET(TASK_STACK, task_struct, stack);
#ifdef CONFIG_LIVEPATCH
OFFSET(TI_livepatch_sp, thread_info, livepatch_sp);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 77decded1175..7ea1d71f4546 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -1166,7 +1166,7 @@ ret_from_debug_exc:
mfspr r9,SPRN_SPRG_THREAD
lwz r10,SAVED_KSP_LIMIT(r1)
stw r10,KSP_LIMIT(r9)
- lwz r9,THREAD_INFO-THREAD(r9)
+ lwz r9,TASK_STACK-THREAD(r9)
CURRENT_THREAD_INFO(r10, r1)
lwz r10,TI_PREEMPT(r10)
stw r10,TI_PREEMPT(r9)
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 7b1693adff2a..03cbf409c3f8 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -683,7 +683,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
2:
#endif /* CONFIG_PPC_BOOK3S_64 */
- CURRENT_THREAD_INFO(r7, r8) /* base of new stack */
+ clrrdi r7, r8, THREAD_SHIFT /* base of new stack */
/* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE
because we don't need to leave the 288-byte ABI gap at the
top of the kernel stack. */
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 61ca27929355..dce6f2ff07e5 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -261,7 +261,7 @@ __secondary_hold_acknowledge:
tophys(r11,r1); /* use tophys(r1) if kernel */ \
beq 1f; \
mfspr r11,SPRN_SPRG_THREAD; \
- lwz r11,THREAD_INFO-THREAD(r11); \
+ lwz r11,TASK_STACK-THREAD(r11); \
addi r11,r11,THREAD_SIZE; \
tophys(r11,r11); \
1: subi r11,r11,INT_FRAME_SIZE /* alloc exc. frame */
@@ -841,7 +841,7 @@ __secondary_start:
bl init_idle_6xx
#endif /* CONFIG_6xx */
- /* get current_thread_info and current */
+ /* get current's stack and current */
lis r1,secondary_ti@ha
tophys(r1,r1)
lwz r1,secondary_ti@l(r1)
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index b19d78410511..3088c9f29f5e 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -115,7 +115,7 @@ _ENTRY(saved_ksp_limit)
andi. r11,r11,MSR_PR; \
beq 1f; \
mfspr r1,SPRN_SPRG_THREAD; /* if from user, start at top of */\
- lwz r1,THREAD_INFO-THREAD(r1); /* this thread's kernel stack */\
+ lwz r1,TASK_STACK-THREAD(r1); /* this thread's kernel stack */\
addi r1,r1,THREAD_SIZE; \
1: subi r1,r1,INT_FRAME_SIZE; /* Allocate an exception frame */\
tophys(r11,r1); \
@@ -158,7 +158,7 @@ _ENTRY(saved_ksp_limit)
beq 1f; \
/* COMING FROM USER MODE */ \
mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\
- lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
+ lwz r11,TASK_STACK-THREAD(r11); /* this thread's kernel stack */\
1: addi r11,r11,THREAD_SIZE-INT_FRAME_SIZE; /* Alloc an excpt frm */\
tophys(r11,r11); \
stw r10,_CCR(r11); /* save various registers */\
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 37e4a7cf0065..15d39b2499de 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -1020,7 +1020,7 @@ _GLOBAL(start_secondary_47x)
/* Now we can get our task struct and real stack pointer */
- /* Get current_thread_info and current */
+ /* Get current's stack and current */
lis r1,secondary_ti@ha
lwz r1,secondary_ti@l(r1)
lwz r2,TI_TASK(r1)
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 134a573a9f2d..5eeca20e195e 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -124,7 +124,7 @@ turn_on_mmu:
tophys(r11,r1); /* use tophys(r1) if kernel */ \
beq 1f; \
mfspr r11,SPRN_SPRG_THREAD; \
- lwz r11,THREAD_INFO-THREAD(r11); \
+ lwz r11,TASK_STACK-THREAD(r11); \
addi r11,r11,THREAD_SIZE; \
tophys(r11,r11); \
1: subi r11,r11,INT_FRAME_SIZE /* alloc exc. frame */
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index d0862a100d29..175f812066dc 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -44,7 +44,7 @@
mr r11, r1; \
beq 1f; \
/* if from user, start at top of this thread's kernel stack */ \
- lwz r11, THREAD_INFO-THREAD(r10); \
+ lwz r11, TASK_STACK - THREAD(r10); \
ALLOC_STACK_FRAME(r11, THREAD_SIZE); \
1 : subi r11, r11, INT_FRAME_SIZE; /* Allocate exception frame */ \
stw r13, _CCR(r11); /* save various registers */ \
@@ -130,7 +130,7 @@
DO_KVM BOOKE_INTERRUPT_##intno exc_level_srr1; \
andi. r11,r11,MSR_PR; \
mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\
- lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
+ lwz r11, TASK_STACK - THREAD(r11); /* this thread's kernel stack */\
addi r11,r11,EXC_LVL_FRAME_OVERHEAD; /* allocate stack frame */\
beq 1f; \
/* COMING FROM USER MODE */ \
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 05b574f416b3..239ad8a4754e 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -704,7 +704,7 @@ finish_tlb_load:
/* Get the next_tlbcam_idx percpu var */
#ifdef CONFIG_SMP
- lwz r12, THREAD_INFO-THREAD(r12)
+ lwz r12, TASK_STACK-THREAD(r12)
lwz r15, TI_CPU(r12)
lis r14, __per_cpu_offset@h
ori r14, r14, __per_cpu_offset@l
@@ -1076,7 +1076,7 @@ __secondary_start:
mr r4,r24 /* Why? */
bl call_setup_cpu
- /* get current_thread_info and current */
+ /* get current's stack and current */
lis r1,secondary_ti@ha
lwz r1,secondary_ti@l(r1)
lwz r2,TI_TASK(r1)
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 916ddc4aac44..9e7dc4468c8c 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -663,7 +663,7 @@ void do_IRQ(struct pt_regs *regs)
struct thread_info *curtp, *irqtp, *sirqtp;
/* Switch to the irq stack to handle this */
- curtp = current_thread_info();
+ curtp = (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
irqtp = hardirq_ctx[raw_smp_processor_id()];
sirqtp = softirq_ctx[raw_smp_processor_id()];
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 2f0fe8bfc078..32762f4c3458 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -60,7 +60,7 @@ _GLOBAL(call_do_softirq)
blr
/*
- * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
+ * void call_do_irq(struct pt_regs *regs, void *sp);
*/
_GLOBAL(call_do_irq)
mflr r0
@@ -603,7 +603,7 @@ EXPORT_SYMBOL(__bswapdi2)
#ifdef CONFIG_SMP
_GLOBAL(start_secondary_resume)
/* Reset stack */
- CURRENT_THREAD_INFO(r1, r1)
+ rlwinm r1, r1, 0, 0, 31 - THREAD_SHIFT
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
li r3,0
stw r3,0(r1) /* Zero the stack frame pointer */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 7ad304a3cc7d..84e39cedf03b 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1239,8 +1239,8 @@ struct task_struct *__switch_to(struct task_struct *prev,
batch->active = 1;
}
- if (current_thread_info()->task->thread.regs) {
- restore_math(current_thread_info()->task->thread.regs);
+ if (current->thread.regs) {
+ restore_math(current->thread.regs);
/*
* The copy-paste buffer can only store into foreign real
@@ -1250,7 +1250,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
* mappings, we must issue a cp_abort to clear any state and
* prevent snooping, corruption or a covert channel.
*/
- if (current_thread_info()->task->thread.used_vas)
+ if (current->thread.used_vas)
asm volatile(PPC_CP_ABORT);
}
#endif /* CONFIG_PPC_BOOK3S_64 */
@@ -1642,7 +1642,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
struct thread_info *ti = task_thread_info(p);
- klp_init_thread_info(ti);
+ klp_init_thread_info(p);
/* Copy registers */
sp -= sizeof(struct pt_regs);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 9ca9db707bcb..8054a7b9e026 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -940,7 +940,7 @@ void __init setup_arch(char **cmdline_p)
/* Reserve large chunks of memory for use by CMA for KVM. */
kvm_cma_reserve();
- klp_init_thread_info(&init_thread_info);
+ klp_init_thread_info(&init_task);
init_mm.start_code = (unsigned long)_stext;
init_mm.end_code = (unsigned long) _etext;
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 8c507be12c3c..81ebf7d6f526 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -205,10 +205,8 @@ void __init irqstack_early_init(void)
/* interrupt stacks must be in lowmem, we get that for free on ppc32
* as the memblock is limited to lowmem by default */
for_each_possible_cpu(i) {
- softirq_ctx[i] = (struct thread_info *)
- __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
- hardirq_ctx[i] = (struct thread_info *)
- __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
+ softirq_ctx[i] = __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
+ hardirq_ctx[i] = __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
}
}
@@ -226,13 +224,10 @@ void __init exc_lvl_early_init(void)
hw_cpu = 0;
#endif
- critirq_ctx[hw_cpu] = (struct thread_info *)
- __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
+ critirq_ctx[hw_cpu] = __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
#ifdef CONFIG_BOOKE
- dbgirq_ctx[hw_cpu] = (struct thread_info *)
- __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
- mcheckirq_ctx[hw_cpu] = (struct thread_info *)
- __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
+ dbgirq_ctx[hw_cpu] = __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
+ mcheckirq_ctx[hw_cpu] = __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
#endif
}
}
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 8e3a5da24d59..5613c9617840 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -20,6 +20,7 @@
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/sched/mm.h>
+#include <linux/sched/task_stack.h>
#include <linux/sched/topology.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
@@ -1020,7 +1021,8 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
#ifdef CONFIG_PPC64
paca_ptrs[cpu]->__current = idle;
- paca_ptrs[cpu]->kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
+ paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) +
+ THREAD_SIZE - STACK_FRAME_OVERHEAD;
#ifdef CONFIG_STACKPROTECTOR
paca_ptrs[cpu]->canary = idle->stack_canary;
#endif
--
2.13.3
^ permalink raw reply related
* [PATCH v8 2/9] powerpc: Only use task_struct 'cpu' field on SMP
From: Christophe Leroy @ 2018-10-16 5:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1539623258.git.christophe.leroy@c-s.fr>
When moving to CONFIG_THREAD_INFO_IN_TASK, the thread_info 'cpu' field
gets moved into task_struct and only defined when CONFIG_SMP is set.
This patch ensures that TI_CPU is only used when CONFIG_SMP is set and
that task_struct 'cpu' field is not used directly out of SMP code.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/head_fsl_booke.S | 2 ++
arch/powerpc/kernel/misc_32.S | 4 ++++
arch/powerpc/xmon/xmon.c | 2 +-
3 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index e2750b856c8f..05b574f416b3 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -243,8 +243,10 @@ set_ivor:
li r0,0
stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
+#ifdef CONFIG_SMP
CURRENT_THREAD_INFO(r22, r1)
stw r24, TI_CPU(r22)
+#endif
bl early_init
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 695b24a2d954..2f0fe8bfc078 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -183,10 +183,14 @@ _GLOBAL(low_choose_750fx_pll)
or r4,r4,r5
mtspr SPRN_HID1,r4
+#ifdef CONFIG_SMP
/* Store new HID1 image */
CURRENT_THREAD_INFO(r6, r1)
lwz r6,TI_CPU(r6)
slwi r6,r6,2
+#else
+ li r6, 0
+#endif
addis r6,r6,nap_save_hid1@ha
stw r4,nap_save_hid1@l(r6)
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 58e67b67a97c..7fb265cca4fb 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2991,7 +2991,7 @@ static void show_task(struct task_struct *tsk)
printf("%px %016lx %6d %6d %c %2d %s\n", tsk,
tsk->thread.ksp,
tsk->pid, tsk->parent->pid,
- state, task_thread_info(tsk)->cpu,
+ state, task_cpu(tsk),
tsk->comm);
}
--
2.13.3
^ permalink raw reply related
* [PATCH v8 1/9] book3s/64: avoid circular header inclusion in mmu-hash.h
From: Christophe Leroy @ 2018-10-16 5:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1539623258.git.christophe.leroy@c-s.fr>
When activating CONFIG_THREAD_INFO_IN_TASK, linux/sched.h
includes asm/current.h. This generates a circular dependency.
To avoid that, asm/processor.h shall not be included in mmu-hash.h
In order to do that, this patch moves into a new header called
asm/task_size_user64.h the information from asm/processor.h required
by mmu-hash.h
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 2 +-
arch/powerpc/include/asm/processor.h | 34 +---------------------
arch/powerpc/include/asm/task_size_user64.h | 42 +++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv_hmi.c | 1 +
4 files changed, 45 insertions(+), 34 deletions(-)
create mode 100644 arch/powerpc/include/asm/task_size_user64.h
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index fc7f056e9d97..026450f8304e 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -23,7 +23,7 @@
*/
#include <asm/book3s/64/pgtable.h>
#include <asm/bug.h>
-#include <asm/processor.h>
+#include <asm/task_size_user64.h>
#include <asm/cpu_has_feature.h>
/*
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 7d04d60a39c9..2caa44db709a 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -101,40 +101,8 @@ void release_thread(struct task_struct *);
#endif
#ifdef CONFIG_PPC64
-/*
- * 64-bit user address space can have multiple limits
- * For now supported values are:
- */
-#define TASK_SIZE_64TB (0x0000400000000000UL)
-#define TASK_SIZE_128TB (0x0000800000000000UL)
-#define TASK_SIZE_512TB (0x0002000000000000UL)
-#define TASK_SIZE_1PB (0x0004000000000000UL)
-#define TASK_SIZE_2PB (0x0008000000000000UL)
-/*
- * With 52 bits in the address we can support
- * upto 4PB of range.
- */
-#define TASK_SIZE_4PB (0x0010000000000000UL)
-/*
- * For now 512TB is only supported with book3s and 64K linux page size.
- */
-#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_64K_PAGES)
-/*
- * Max value currently used:
- */
-#define TASK_SIZE_USER64 TASK_SIZE_4PB
-#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_128TB
-#define TASK_CONTEXT_SIZE TASK_SIZE_512TB
-#else
-#define TASK_SIZE_USER64 TASK_SIZE_64TB
-#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_64TB
-/*
- * We don't need to allocate extended context ids for 4K page size, because
- * we limit the max effective address on this config to 64TB.
- */
-#define TASK_CONTEXT_SIZE TASK_SIZE_64TB
-#endif
+#include <asm/task_size_user64.h>
/*
* 32-bit user address space is 4GB - 1 page
diff --git a/arch/powerpc/include/asm/task_size_user64.h b/arch/powerpc/include/asm/task_size_user64.h
new file mode 100644
index 000000000000..a4043075864b
--- /dev/null
+++ b/arch/powerpc/include/asm/task_size_user64.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_TASK_SIZE_USER64_H
+#define _ASM_POWERPC_TASK_SIZE_USER64_H
+
+#ifdef CONFIG_PPC64
+/*
+ * 64-bit user address space can have multiple limits
+ * For now supported values are:
+ */
+#define TASK_SIZE_64TB (0x0000400000000000UL)
+#define TASK_SIZE_128TB (0x0000800000000000UL)
+#define TASK_SIZE_512TB (0x0002000000000000UL)
+#define TASK_SIZE_1PB (0x0004000000000000UL)
+#define TASK_SIZE_2PB (0x0008000000000000UL)
+/*
+ * With 52 bits in the address we can support
+ * upto 4PB of range.
+ */
+#define TASK_SIZE_4PB (0x0010000000000000UL)
+
+/*
+ * For now 512TB is only supported with book3s and 64K linux page size.
+ */
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_64K_PAGES)
+/*
+ * Max value currently used:
+ */
+#define TASK_SIZE_USER64 TASK_SIZE_4PB
+#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_128TB
+#define TASK_CONTEXT_SIZE TASK_SIZE_512TB
+#else
+#define TASK_SIZE_USER64 TASK_SIZE_64TB
+#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_64TB
+/*
+ * We don't need to allocate extended context ids for 4K page size, because
+ * we limit the max effective address on this config to 64TB.
+ */
+#define TASK_CONTEXT_SIZE TASK_SIZE_64TB
+#endif
+
+#endif /* CONFIG_PPC64 */
+#endif /* _ASM_POWERPC_TASK_SIZE_USER64_H */
diff --git a/arch/powerpc/kvm/book3s_hv_hmi.c b/arch/powerpc/kvm/book3s_hv_hmi.c
index e3f738eb1cac..64b5011475c7 100644
--- a/arch/powerpc/kvm/book3s_hv_hmi.c
+++ b/arch/powerpc/kvm/book3s_hv_hmi.c
@@ -24,6 +24,7 @@
#include <linux/compiler.h>
#include <asm/paca.h>
#include <asm/hmi.h>
+#include <asm/processor.h>
void wait_for_subcore_guest_exit(void)
{
--
2.13.3
^ permalink raw reply related
* [PATCH v8 0/9] powerpc: Switch to CONFIG_THREAD_INFO_IN_TASK
From: Christophe Leroy @ 2018-10-16 5:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
The purpose of this serie is to activate CONFIG_THREAD_INFO_IN_TASK which
moves the thread_info into task_struct.
Moving thread_info into task_struct has the following advantages:
- It protects thread_info from corruption in the case of stack
overflows.
- Its address is harder to determine if stack addresses are
leaked, making a number of attacks more difficult.
Changes since v7:
- Rebased on fb6c6ce7907d ("Automatic merge of branches 'master', 'next' and 'fixes' into merge")
Changes since v6:
- Fixed validate_sp() to exclude NULL sp in 'regain entire stack space' patch (early crash with CONFIG_KMEMLEAK)
Changes since v5:
- Fixed livepatch_sp setup by using end_of_stack() instead of hardcoding
- Fixed PPC_BPF_LOAD_CPU() macro
Changes since v4:
- Fixed a build failure on 32bits SMP when include/generated/asm-offsets.h is not
already existing, was due to spaces instead of a tab in the Makefile
Changes since RFC v3: (based on Nick's review)
- Renamed task_size.h to task_size_user64.h to better relate to what it contains.
- Handling of the isolation of thread_info cpu field inside CONFIG_SMP #ifdefs moved to a separate patch.
- Removed CURRENT_THREAD_INFO macro completely.
- Added a guard in asm/smp.h to avoid build failure before _TASK_CPU is defined.
- Added a patch at the end to rename 'tp' pointers to 'sp' pointers
- Renamed 'tp' into 'sp' pointers in preparation patch when relevant
- Fixed a few commit logs
- Fixed checkpatch report.
Changes since RFC v2:
- Removed the modification of names in asm-offsets
- Created a rule in arch/powerpc/Makefile to append the offset of current->cpu in CFLAGS
- Modified asm/smp.h to use the offset set in CFLAGS
- Squashed the renaming of THREAD_INFO to TASK_STACK in the preparation patch
- Moved the modification of current_pt_regs in the patch activating CONFIG_THREAD_INFO_IN_TASK
Changes since RFC v1:
- Removed the first patch which was modifying header inclusion order in timer
- Modified some names in asm-offsets to avoid conflicts when including asm-offsets in C files
- Modified asm/smp.h to avoid having to include linux/sched.h (using asm-offsets instead)
- Moved some changes from the activation patch to the preparation patch.
Christophe Leroy (9):
book3s/64: avoid circular header inclusion in mmu-hash.h
powerpc: Only use task_struct 'cpu' field on SMP
powerpc: Prepare for moving thread_info into task_struct
powerpc: Activate CONFIG_THREAD_INFO_IN_TASK
powerpc: regain entire stack space
powerpc: 'current_set' is now a table of task_struct pointers
powerpc/32: Remove CURRENT_THREAD_INFO and rename TI_CPU
powerpc/64: Remove CURRENT_THREAD_INFO
powerpc: clean stack pointers naming
arch/powerpc/Kconfig | 1 +
arch/powerpc/Makefile | 7 +++
arch/powerpc/include/asm/asm-prototypes.h | 4 +-
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 2 +-
arch/powerpc/include/asm/exception-64s.h | 4 +-
arch/powerpc/include/asm/irq.h | 14 ++---
arch/powerpc/include/asm/livepatch.h | 7 ++-
arch/powerpc/include/asm/processor.h | 39 +------------
arch/powerpc/include/asm/ptrace.h | 2 +-
arch/powerpc/include/asm/reg.h | 2 +-
arch/powerpc/include/asm/smp.h | 17 +++++-
arch/powerpc/include/asm/task_size_user64.h | 42 ++++++++++++++
arch/powerpc/include/asm/thread_info.h | 19 -------
arch/powerpc/kernel/asm-offsets.c | 10 ++--
arch/powerpc/kernel/entry_32.S | 66 ++++++++--------------
arch/powerpc/kernel/entry_64.S | 12 ++--
arch/powerpc/kernel/epapr_hcalls.S | 5 +-
arch/powerpc/kernel/exceptions-64e.S | 13 +----
arch/powerpc/kernel/exceptions-64s.S | 2 +-
arch/powerpc/kernel/head_32.S | 14 ++---
arch/powerpc/kernel/head_40x.S | 4 +-
arch/powerpc/kernel/head_44x.S | 8 +--
arch/powerpc/kernel/head_64.S | 1 +
arch/powerpc/kernel/head_8xx.S | 2 +-
arch/powerpc/kernel/head_booke.h | 12 +---
arch/powerpc/kernel/head_fsl_booke.S | 16 +++---
arch/powerpc/kernel/idle_6xx.S | 8 +--
arch/powerpc/kernel/idle_book3e.S | 2 +-
arch/powerpc/kernel/idle_e500.S | 8 +--
arch/powerpc/kernel/idle_power4.S | 2 +-
arch/powerpc/kernel/irq.c | 77 +++++---------------------
arch/powerpc/kernel/kgdb.c | 28 ----------
arch/powerpc/kernel/machine_kexec_64.c | 6 +-
arch/powerpc/kernel/misc_32.S | 17 +++---
arch/powerpc/kernel/process.c | 40 ++++++-------
arch/powerpc/kernel/setup-common.c | 2 +-
arch/powerpc/kernel/setup_32.c | 15 ++---
arch/powerpc/kernel/setup_64.c | 41 ++++----------
arch/powerpc/kernel/smp.c | 16 +++---
arch/powerpc/kernel/trace/ftrace_64_mprofile.S | 6 +-
arch/powerpc/kvm/book3s_hv_hmi.c | 1 +
arch/powerpc/mm/hash_low_32.S | 14 ++---
arch/powerpc/net/bpf_jit32.h | 5 +-
arch/powerpc/sysdev/6xx-suspend.S | 5 +-
arch/powerpc/xmon/xmon.c | 2 +-
45 files changed, 240 insertions(+), 380 deletions(-)
create mode 100644 arch/powerpc/include/asm/task_size_user64.h
--
2.13.3
^ permalink raw reply
* Re: [PATCH V3 2/2] powerpc/mm/iommu: Allow migration of cma allocated pages during mm_iommu_get
From: Alexey Kardashevskiy @ 2018-10-16 4:57 UTC (permalink / raw)
To: Aneesh Kumar K.V, akpm, Michal Hocko, mpe
Cc: linux-mm, linuxppc-dev, linux-kernel
In-Reply-To: <20180918115839.22154-3-aneesh.kumar@linux.ibm.com>
On 18/09/2018 21:58, Aneesh Kumar K.V wrote:
> Current code doesn't do page migration if the page allocated is a compound page.
> With HugeTLB migration support, we can end up allocating hugetlb pages from
> CMA region. Also THP pages can be allocated from CMA region. This patch updates
> the code to handle compound pages correctly.
>
> This use the new helper get_user_pages_cma_migrate. It does one get_user_pages
> with right count, instead of doing one get_user_pages per page. That avoids
> reading page table multiple times.
>
> The patch also convert the hpas member of mm_iommu_table_group_mem_t to a union.
> We use the same storage location to store pointers to struct page. We cannot
> update alll the code path use struct page *, because we access hpas in real mode
> and we can't do that struct page * to pfn conversion in real mode.
>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
> ---
> arch/powerpc/mm/mmu_context_iommu.c | 120 ++++++++--------------------
> 1 file changed, 35 insertions(+), 85 deletions(-)
>
> diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
> index c9ee9e23845f..f0d8645872cb 100644
> --- a/arch/powerpc/mm/mmu_context_iommu.c
> +++ b/arch/powerpc/mm/mmu_context_iommu.c
> @@ -20,6 +20,7 @@
> #include <linux/swap.h>
> #include <asm/mmu_context.h>
> #include <asm/pte-walk.h>
> +#include <linux/mm_inline.h>
>
> static DEFINE_MUTEX(mem_list_mutex);
>
> @@ -30,8 +31,18 @@ struct mm_iommu_table_group_mem_t {
> atomic64_t mapped;
> unsigned int pageshift;
> u64 ua; /* userspace address */
> - u64 entries; /* number of entries in hpas[] */
> - u64 *hpas; /* vmalloc'ed */
> + u64 entries; /* number of entries in hpages[] */
> + /*
> + * in mm_iommu_get we temporarily use this to store
> + * struct page address.
> + *
> + * We need to convert ua to hpa in real mode. Make it
> + * simpler by storing physicall address.
> + */
> + union {
> + struct page **hpages; /* vmalloc'ed */
> + phys_addr_t *hpas;
It could always be hpages. Now it is slightly complicated though because
of MM_IOMMU_TABLE_GROUP_PAGE_DIRTY...
> + };
> };
>
> static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
> @@ -74,63 +85,14 @@ bool mm_iommu_preregistered(struct mm_struct *mm)
> }
> EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
>
> -/*
> - * Taken from alloc_migrate_target with changes to remove CMA allocations
> - */
> -struct page *new_iommu_non_cma_page(struct page *page, unsigned long private)
> -{
> - gfp_t gfp_mask = GFP_USER;
> - struct page *new_page;
> -
> - if (PageCompound(page))
> - return NULL;
> -
> - if (PageHighMem(page))
> - gfp_mask |= __GFP_HIGHMEM;
> -
> - /*
> - * We don't want the allocation to force an OOM if possibe
> - */
> - new_page = alloc_page(gfp_mask | __GFP_NORETRY | __GFP_NOWARN);
> - return new_page;
> -}
> -
> -static int mm_iommu_move_page_from_cma(struct page *page)
> -{
> - int ret = 0;
> - LIST_HEAD(cma_migrate_pages);
> -
> - /* Ignore huge pages for now */
> - if (PageCompound(page))
> - return -EBUSY;
> -
> - lru_add_drain();
> - ret = isolate_lru_page(page);
> - if (ret)
> - return ret;
> -
> - list_add(&page->lru, &cma_migrate_pages);
> - put_page(page); /* Drop the gup reference */
> -
> - ret = migrate_pages(&cma_migrate_pages, new_iommu_non_cma_page,
> - NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE);
> - if (ret) {
> - if (!list_empty(&cma_migrate_pages))
> - putback_movable_pages(&cma_migrate_pages);
> - }
> -
> - return 0;
> -}
> -
> long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
> struct mm_iommu_table_group_mem_t **pmem)
> {
> struct mm_iommu_table_group_mem_t *mem;
> - long i, j, ret = 0, locked_entries = 0;
> + long i, ret = 0, locked_entries = 0;
> unsigned int pageshift;
> unsigned long flags;
> unsigned long cur_ua;
> - struct page *page = NULL;
>
> mutex_lock(&mem_list_mutex);
>
> @@ -177,41 +139,24 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
> goto unlock_exit;
> }
>
> + ret = get_user_pages_cma_migrate(ua, entries, 1, mem->hpages);
> + if (ret != entries) {
> + /* free the reference taken */
> + for (i = 0; i < ret; i++)
> + put_page(mem->hpages[i]);
> +
> + vfree(mem->hpas);
> + kfree(mem);
> + ret = -EFAULT;
> + goto unlock_exit;
> + } else
Do not need "else".
> + ret = 0;
> +
> + pageshift = PAGE_SHIFT;
> for (i = 0; i < entries; ++i) {
> + struct page *page = mem->hpages[i];
> cur_ua = ua + (i << PAGE_SHIFT);
> - if (1 != get_user_pages_fast(cur_ua,
> - 1/* pages */, 1/* iswrite */, &page)) {
> - ret = -EFAULT;
> - for (j = 0; j < i; ++j)
> - put_page(pfn_to_page(mem->hpas[j] >>
> - PAGE_SHIFT));
> - vfree(mem->hpas);
> - kfree(mem);
> - goto unlock_exit;
> - }
> - /*
> - * If we get a page from the CMA zone, since we are going to
> - * be pinning these entries, we might as well move them out
> - * of the CMA zone if possible. NOTE: faulting in + migration
> - * can be expensive. Batching can be considered later
> - */
> - if (is_migrate_cma_page(page)) {
> - if (mm_iommu_move_page_from_cma(page))
> - goto populate;
> - if (1 != get_user_pages_fast(cur_ua,
> - 1/* pages */, 1/* iswrite */,
> - &page)) {
> - ret = -EFAULT;
> - for (j = 0; j < i; ++j)
> - put_page(pfn_to_page(mem->hpas[j] >>
> - PAGE_SHIFT));
> - vfree(mem->hpas);
> - kfree(mem);
> - goto unlock_exit;
> - }
> - }
> -populate:
> - pageshift = PAGE_SHIFT;
> +
> if (mem->pageshift > PAGE_SHIFT && PageCompound(page)) {
> pte_t *pte;
> struct page *head = compound_head(page);
> @@ -229,7 +174,12 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
> local_irq_restore(flags);
> }
> mem->pageshift = min(mem->pageshift, pageshift);
> + /*
> + * We don't need struct page reference any more, switch
> + * physicall address.
> + */
> mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
> +
nit: do not need an empty line here.
> }
>
> atomic64_set(&mem->mapped, 1);
>
--
Alexey
^ permalink raw reply
* Re: [PATCH V3 1/2] mm: Add get_user_pages_cma_migrate
From: Alexey Kardashevskiy @ 2018-10-16 4:57 UTC (permalink / raw)
To: Aneesh Kumar K.V, akpm, Michal Hocko, mpe
Cc: linux-mm, linuxppc-dev, linux-kernel
In-Reply-To: <20180918115839.22154-2-aneesh.kumar@linux.ibm.com>
On 18/09/2018 21:58, Aneesh Kumar K.V wrote:
> This helper does a get_user_pages_fast and if it find pages in the CMA area
> it will try to migrate them before taking page reference. This makes sure that
> we don't keep non-movable pages (due to page reference count) in the CMA area.
> Not able to move pages out of CMA area result in CMA allocation failures.
>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
> ---
> include/linux/hugetlb.h | 2 +
> include/linux/migrate.h | 3 +
> mm/hugetlb.c | 4 +-
> mm/migrate.c | 132 ++++++++++++++++++++++++++++++++++++++++
> 4 files changed, 139 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
> index 6b68e345f0ca..1abccb1a1ecc 100644
> --- a/include/linux/hugetlb.h
> +++ b/include/linux/hugetlb.h
> @@ -357,6 +357,8 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
> nodemask_t *nmask);
> struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
> unsigned long address);
> +struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
> + int nid, nodemask_t *nmask);
> int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
> pgoff_t idx);
>
> diff --git a/include/linux/migrate.h b/include/linux/migrate.h
> index f2b4abbca55e..d82b35afd2eb 100644
> --- a/include/linux/migrate.h
> +++ b/include/linux/migrate.h
> @@ -286,6 +286,9 @@ static inline int migrate_vma(const struct migrate_vma_ops *ops,
> }
> #endif /* IS_ENABLED(CONFIG_MIGRATE_VMA_HELPER) */
>
> +extern int get_user_pages_cma_migrate(unsigned long start, int nr_pages, int write,
> + struct page **pages);
> +
> #endif /* CONFIG_MIGRATION */
>
> #endif /* _LINUX_MIGRATE_H */
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 3c21775f196b..1abbfcb84f66 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -1585,8 +1585,8 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
> return page;
> }
>
> -static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
> - int nid, nodemask_t *nmask)
> +struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
> + int nid, nodemask_t *nmask)
> {
> struct page *page;
>
> diff --git a/mm/migrate.c b/mm/migrate.c
> index d6a2e89b086a..2f92534ea7a1 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -3006,3 +3006,135 @@ int migrate_vma(const struct migrate_vma_ops *ops,
> }
> EXPORT_SYMBOL(migrate_vma);
> #endif /* defined(MIGRATE_VMA_HELPER) */
> +
> +static struct page *new_non_cma_page(struct page *page, unsigned long private)
> +{
> + /*
> + * We want to make sure we allocate the new page from the same node
> + * as the source page.
> + */
> + int nid = page_to_nid(page);
> + gfp_t gfp_mask = GFP_USER | __GFP_THISNODE;
> +
> + if (PageHighMem(page))
> + gfp_mask |= __GFP_HIGHMEM;
> +
> + if (PageTransHuge(page)) {
> + struct page *thp;
> + gfp_t thp_gfpmask = GFP_TRANSHUGE | __GFP_THISNODE;
> +
> + /*
> + * Remove the movable mask so that we don't allocate from
> + * CMA area again.
> + */
> + thp_gfpmask &= ~__GFP_MOVABLE;
> + thp = __alloc_pages_node(nid, thp_gfpmask, HPAGE_PMD_ORDER);
HPAGE_PMD_ORDER is 2MB or 1GB? THP are always that PMD order?
> + if (!thp)
> + return NULL;
> + prep_transhuge_page(thp);
> + return thp;
> +
> +#ifdef CONFIG_HUGETLB_PAGE
> + } else if (PageHuge(page)) {
> +
> + struct hstate *h = page_hstate(page);
> + /*
> + * We don't want to dequeue from the pool because pool pages will
> + * mostly be from the CMA region.
> + */
> + return alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
> +#endif
> + }
> +
> + return __alloc_pages_node(nid, gfp_mask, 0);
> +}
> +
> +/**
> + * get_user_pages_cma_migrate() - pin user pages in memory by migrating pages in CMA region
> + * @start: starting user address
> + * @nr_pages: number of pages from start to pin
> + * @write: whether pages will be written to
> + * @pages: array that receives pointers to the pages pinned.
> + * Should be at least nr_pages long.
> + *
> + * Attempt to pin user pages in memory without taking mm->mmap_sem.
> + * If not successful, it will fall back to taking the lock and
> + * calling get_user_pages().
I do not see any locking or get_user_pages(), hidden somewhere?
> + *
> + * If the pinned pages are backed by CMA region, we migrate those pages out,
> + * allocating new pages from non-CMA region. This helps in avoiding keeping
> + * pages pinned in the CMA region for a long time thereby resulting in
> + * CMA allocation failures.
> + *
> + * Returns number of pages pinned. This may be fewer than the number
> + * requested. If nr_pages is 0 or negative, returns 0. If no pages
> + * were pinned, returns -errno.
> + */
> +
> +int get_user_pages_cma_migrate(unsigned long start, int nr_pages, int write,
> + struct page **pages)
> +{
> + int i, ret;
> + bool drain_allow = true;
> + bool migrate_allow = true;
> + LIST_HEAD(cma_page_list);
> +
> +get_user_again:
> + ret = get_user_pages_fast(start, nr_pages, write, pages);
> + if (ret <= 0)
> + return ret;
> +
> + for (i = 0; i < ret; ++i) {
> + /*
> + * If we get a page from the CMA zone, since we are going to
> + * be pinning these entries, we might as well move them out
> + * of the CMA zone if possible.
> + */
> + if (is_migrate_cma_page(pages[i]) && migrate_allow) {
> + if (PageHuge(pages[i]))
> + isolate_huge_page(pages[i], &cma_page_list);
> + else {
> + struct page *head = compound_head(pages[i]);
> +
> + if (!PageLRU(head) && drain_allow) {
> + lru_add_drain_all();
> + drain_allow = false;
> + }
> +
> + if (!isolate_lru_page(head)) {
> + list_add_tail(&head->lru, &cma_page_list);
> + mod_node_page_state(page_pgdat(head),
> + NR_ISOLATED_ANON +
> + page_is_file_cache(head),
> + hpage_nr_pages(head));
Above 10 lines I cannot really comment due to my massive ignorance in
this area, especially about what lru_add_drain_all() and
mod_node_page_state() :(
> + }
> + }
> + }
> + }
> + if (!list_empty(&cma_page_list)) {
> + /*
> + * drop the above get_user_pages reference.
> + */
> + for (i = 0; i < ret; ++i)
> + put_page(pages[i]);
> +
> + if (migrate_pages(&cma_page_list, new_non_cma_page,
> + NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
> + /*
> + * some of the pages failed migration. Do get_user_pages
> + * without migration.
> + */
> + migrate_allow = false;
migrate_allow seems useless, simply calling get_user_pages_fast() should
make the code easier to read imho. And the comment says
get_user_pages(), where does this guy hide?
> +
> + if (!list_empty(&cma_page_list))
> + putback_movable_pages(&cma_page_list);
> + }
> + /*
> + * We did migrate all the pages, Try to get the page references again
> + * migrating any new CMA pages which we failed to isolate earlier.
> + */
> + drain_allow = true;
Move this "drain_allow = true" right after "get_user_again:"?
> + goto get_user_again;
> + }
> + return ret;
> +}
>
--
Alexey
^ permalink raw reply
* Re: linux-next: Tree for Oct 15
From: Benjamin Herrenschmidt @ 2018-10-16 3:12 UTC (permalink / raw)
To: Stephen Rothwell, Guenter Roeck
Cc: Linux Kernel Mailing List, Mike Rapoport, Linux-Next Mailing List,
Andrew Morton, PowerPC
In-Reply-To: <20181016131927.6ceba6ab@canb.auug.org.au>
On Tue, 2018-10-16 at 13:19 +1100, Stephen Rothwell wrote:
> Hi all,
>
> On Tue, 16 Oct 2018 13:02:16 +1100 Stephen Rothwell <sfr@canb.auug.org.au> wrote:
> >
> > Reverting fe3d2a45e8079fdd7d4da1ff07f4b40bc3cb499f (and the following 2
> > commits) produces a kernel that boots.
>
> Instead of that, I applied this patch on top of linux-next and it boots
> and produces a stack trace ...
>
> From: Stephen Rothwell <sfr@canb.auug.org.au>
> Date: Tue, 16 Oct 2018 13:07:01 +1100
> Subject: [PATCH] mm/memblock.c: use dump_stack() instead of WARN_ON_ONCE for
> the alignment checks
>
> Using WARN_ON_ONCE too early causes the PowerPC kernel to fail.
Interesting ... I thought I had fixed that. Might need to be re-fixed.
> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
> ---
> mm/memblock.c | 8 ++++++--
> 1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/mm/memblock.c b/mm/memblock.c
> index 5fefc70253ee..f2ef3915a356 100644
> --- a/mm/memblock.c
> +++ b/mm/memblock.c
> @@ -1298,8 +1298,10 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
> {
> phys_addr_t found;
>
> - if (WARN_ON_ONCE(!align))
> + if (!align) {
> + dump_stack();
> align = SMP_CACHE_BYTES;
> + }
>
> found = memblock_find_in_range_node(size, align, start, end, nid,
> flags);
> @@ -1423,8 +1425,10 @@ static void * __init memblock_alloc_internal(
> if (WARN_ON_ONCE(slab_is_available()))
> return kzalloc_node(size, GFP_NOWAIT, nid);
>
> - if (WARN_ON_ONCE(!align))
> + if (!align) {
> + dump_stack();
> align = SMP_CACHE_BYTES;
> + }
>
> if (max_addr > memblock.current_limit)
> max_addr = memblock.current_limit;
> --
> 2.18.0
>
> So, patch "memblock: stop using implicit alignment to SMP_CACHE_BYTES"
> should *not* remove the 0 -> SMP_CACHE_BYTES update from mm/memblock.c
> and just add the dump_stack().
^ permalink raw reply
* Re: [PATCH v2 2/2] mm: speed up mremap by 500x on large regions
From: Joel Fernandes @ 2018-10-16 2:08 UTC (permalink / raw)
To: Martin Schwidefsky
Cc: linux-mips, Rich Felker, linux-ia64, linux-sh, Peter Zijlstra,
Catalin Marinas, Dave Hansen, Will Deacon, mhocko, linux-mm,
lokeshgidra, sparclinux, linux-riscv, elfring, Jonas Bonn,
linux-s390, dancol, Yoshinori Sato, linux-xtensa, linux-hexagon,
Helge Deller, maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT),
hughd, James E.J. Bottomley, kasan-dev, kvmarm,
Christian Borntraeger, Ingo Molnar, Geert Uytterhoeven,
Andrey Ryabinin, linux-snps-arc, kernel-team, Sam Creasey,
Fenghua Yu, Jeff Dike, linux-um, Stefan Kristiansson,
Julia Lawall, linux-m68k, openrisc, Borislav Petkov,
Andy Lutomirski, nios2-dev, kirill, Stafford Horne, Guan Xuetao,
linux-arm-kernel, Chris Zankel, Tony Luck, Richard Weinberger,
linux-parisc, pantin, Max Filippov, linux-kernel, minchan,
Thomas Gleixner, linux-alpha, Ley Foon Tan, akpm, linuxppc-dev,
David S. Miller
In-Reply-To: <20181015101814.306d257c@mschwideX1>
On Mon, Oct 15, 2018 at 10:18:14AM +0200, Martin Schwidefsky wrote:
> On Mon, 15 Oct 2018 09:10:53 +0200
> Christian Borntraeger <borntraeger@de.ibm.com> wrote:
>
> > On 10/12/2018 03:37 AM, Joel Fernandes (Google) wrote:
> > > Android needs to mremap large regions of memory during memory management
> > > related operations. The mremap system call can be really slow if THP is
> > > not enabled. The bottleneck is move_page_tables, which is copying each
> > > pte at a time, and can be really slow across a large map. Turning on THP
> > > may not be a viable option, and is not for us. This patch speeds up the
> > > performance for non-THP system by copying at the PMD level when possible.
> > >
> > > The speed up is three orders of magnitude. On a 1GB mremap, the mremap
> > > completion times drops from 160-250 millesconds to 380-400 microseconds.
> > >
> > > Before:
> > > Total mremap time for 1GB data: 242321014 nanoseconds.
> > > Total mremap time for 1GB data: 196842467 nanoseconds.
> > > Total mremap time for 1GB data: 167051162 nanoseconds.
> > >
> > > After:
> > > Total mremap time for 1GB data: 385781 nanoseconds.
> > > Total mremap time for 1GB data: 388959 nanoseconds.
> > > Total mremap time for 1GB data: 402813 nanoseconds.
> > >
> > > Incase THP is enabled, the optimization is skipped. I also flush the
> > > tlb every time we do this optimization since I couldn't find a way to
> > > determine if the low-level PTEs are dirty. It is seen that the cost of
> > > doing so is not much compared the improvement, on both x86-64 and arm64.
> > >
> > > Cc: minchan@kernel.org
> > > Cc: pantin@google.com
> > > Cc: hughd@google.com
> > > Cc: lokeshgidra@google.com
> > > Cc: dancol@google.com
> > > Cc: mhocko@kernel.org
> > > Cc: kirill@shutemov.name
> > > Cc: akpm@linux-foundation.org
> > > Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
> > > ---
> > > mm/mremap.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++++
> > > 1 file changed, 62 insertions(+)
> > >
> > > diff --git a/mm/mremap.c b/mm/mremap.c
> > > index 9e68a02a52b1..d82c485822ef 100644
> > > --- a/mm/mremap.c
> > > +++ b/mm/mremap.c
> > > @@ -191,6 +191,54 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
> > > drop_rmap_locks(vma);
> > > }
> > >
> > > +static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
> > > + unsigned long new_addr, unsigned long old_end,
> > > + pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush)
> > > +{
> > > + spinlock_t *old_ptl, *new_ptl;
> > > + struct mm_struct *mm = vma->vm_mm;
> > > +
> > > + if ((old_addr & ~PMD_MASK) || (new_addr & ~PMD_MASK)
> > > + || old_end - old_addr < PMD_SIZE)
> > > + return false;
> > > +
> > > + /*
> > > + * The destination pmd shouldn't be established, free_pgtables()
> > > + * should have release it.
> > > + */
> > > + if (WARN_ON(!pmd_none(*new_pmd)))
> > > + return false;
> > > +
> > > + /*
> > > + * We don't have to worry about the ordering of src and dst
> > > + * ptlocks because exclusive mmap_sem prevents deadlock.
> > > + */
> > > + old_ptl = pmd_lock(vma->vm_mm, old_pmd);
> > > + if (old_ptl) {
> > > + pmd_t pmd;
> > > +
> > > + new_ptl = pmd_lockptr(mm, new_pmd);
> > > + if (new_ptl != old_ptl)
> > > + spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
> > > +
> > > + /* Clear the pmd */
> > > + pmd = *old_pmd;
> > > + pmd_clear(old_pmd);
> >
> > Adding Martin Schwidefsky.
> > Is this mapping maybe still in use on other CPUs? If yes, I think for
> > s390 we need to flush here as well (in other word we might need to introduce
> > pmd_clear_flush). On s390 you have to use instructions like CRDTE,IPTE or IDTE
> > to modify page table entries that are still in use. Otherwise you can get a
> > delayed access exception which is - in contrast to page faults - not recoverable.
>
> Just clearing an active pmd would be broken for s390. We need the equivalent
> of the ptep_get_and_clear() function for pmds. For s390 this function would
> look like this:
>
> static inline pte_t pmdp_get_and_clear(struct mm_struct *mm,
> unsigned long addr, pmd_t *pmdp)
> {
> return pmdp_xchg_lazy(mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_INVALID));
> }
>
> Just like pmdp_huge_get_and_clear() in fact.
I agree architecture like s390 may need additional explicit instructions to
avoid any unrecoverable failure. So the good news is in my last patch I sent, I
have put this behind an architecture flag (HAVE_MOVE_PMD), so we don't have
to enable it with architectures that cannot handle it:
https://www.spinics.net/lists/linux-mm/msg163621.html
Also we are triggering this optimization only if the page is not a transparent
huge page by calling pmd_trans_huge(). For regular pages, it should be safe to
not do the atomic get_and_clear AIUI because Linux doesn't use any bits from
the PMD like the dirty bit if THP is not in use (and the processors that I
saw (not s390) should not storing anything in the bits anyway when the page
is not a huge page. I have gone through various scenarios and read both arm
32-bit and 64-bit and x86 64-bit manuals, and I believe it to be safe.
For s390, lets not set the HAVE_MOVE_PMD flag. Does that work for you?
> > > +
> > > + VM_BUG_ON(!pmd_none(*new_pmd));
> > > +
> > > + /* Set the new pmd */
> > > + set_pmd_at(mm, new_addr, new_pmd, pmd);
> > > + if (new_ptl != old_ptl)
> > > + spin_unlock(new_ptl);
> > > + spin_unlock(old_ptl);
> > > +
> > > + *need_flush = true;
> > > + return true;
> > > + }
> > > + return false;
> > > +}
> > > +
>
> So the idea is to move the pmd entry to the new location, dragging
> the whole pte table to a new location with a different address.
> I wonder if that is safe in regard to get_user_pages_fast().
Could you elaborate why you feel it may not be?
Are you concerned that the PMD moving interferes with the page walk? Incase
the tree changes during page-walking, the number of pages pinned by
get_user_pages_fast may be less than the number requested. In this case,
get_user_pages_fast would fall back to the slow path which should be
synchronized with the mremap by courtesy of the mm->mmap_sem. But please let
me know the scenario you have in mind and if I missed something.
thanks,
- Joel
^ permalink raw reply
* [PATCH v4 18/18] of: unittest: initialize args before calling of_*parse_*()
From: frowand.list @ 2018-10-16 2:37 UTC (permalink / raw)
To: Rob Herring, Pantelis Antoniou, Michael Ellerman,
Benjamin Herrenschmidt, Paul Mackerras, Alan Tull, Moritz Fischer
Cc: devicetree, linux-fpga, linuxppc-dev, linux-kernel
In-Reply-To: <1539657458-24401-1-git-send-email-frowand.list@gmail.com>
From: Frank Rowand <frank.rowand@sony.com>
Callers of of_irq_parse_one() blindly use the pointer args.np
without checking whether of_irq_parse_one() had an error and
thus did not set the value of args.np. Initialize args to
zero so that using the format "%pOF" to show the value of
args.np will show "(null)" when of_irq_parse_one() has an
error. This prevents the dereference of a random value.
Make the same fix for callers of of_parse_phandle_with_args()
and of_parse_phandle_with_args_map().
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Frank Rowand <frank.rowand@sony.com>
---
drivers/of/unittest.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 785985bdbfa6..5f4db23e4752 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -375,6 +375,7 @@ static void __init of_unittest_parse_phandle_with_args(void)
for (i = 0; i < 8; i++) {
bool passed = true;
+ memset(&args, 0, sizeof(args));
rc = of_parse_phandle_with_args(np, "phandle-list",
"#phandle-cells", i, &args);
@@ -428,6 +429,7 @@ static void __init of_unittest_parse_phandle_with_args(void)
}
/* Check for missing list property */
+ memset(&args, 0, sizeof(args));
rc = of_parse_phandle_with_args(np, "phandle-list-missing",
"#phandle-cells", 0, &args);
unittest(rc == -ENOENT, "expected:%i got:%i\n", -ENOENT, rc);
@@ -436,6 +438,7 @@ static void __init of_unittest_parse_phandle_with_args(void)
unittest(rc == -ENOENT, "expected:%i got:%i\n", -ENOENT, rc);
/* Check for missing cells property */
+ memset(&args, 0, sizeof(args));
rc = of_parse_phandle_with_args(np, "phandle-list",
"#phandle-cells-missing", 0, &args);
unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
@@ -444,6 +447,7 @@ static void __init of_unittest_parse_phandle_with_args(void)
unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
/* Check for bad phandle in list */
+ memset(&args, 0, sizeof(args));
rc = of_parse_phandle_with_args(np, "phandle-list-bad-phandle",
"#phandle-cells", 0, &args);
unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
@@ -452,6 +456,7 @@ static void __init of_unittest_parse_phandle_with_args(void)
unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
/* Check for incorrectly formed argument list */
+ memset(&args, 0, sizeof(args));
rc = of_parse_phandle_with_args(np, "phandle-list-bad-args",
"#phandle-cells", 1, &args);
unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
@@ -502,6 +507,7 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
for (i = 0; i < 8; i++) {
bool passed = true;
+ memset(&args, 0, sizeof(args));
rc = of_parse_phandle_with_args_map(np, "phandle-list",
"phandle", i, &args);
@@ -559,21 +565,25 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
}
/* Check for missing list property */
+ memset(&args, 0, sizeof(args));
rc = of_parse_phandle_with_args_map(np, "phandle-list-missing",
"phandle", 0, &args);
unittest(rc == -ENOENT, "expected:%i got:%i\n", -ENOENT, rc);
/* Check for missing cells,map,mask property */
+ memset(&args, 0, sizeof(args));
rc = of_parse_phandle_with_args_map(np, "phandle-list",
"phandle-missing", 0, &args);
unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
/* Check for bad phandle in list */
+ memset(&args, 0, sizeof(args));
rc = of_parse_phandle_with_args_map(np, "phandle-list-bad-phandle",
"phandle", 0, &args);
unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
/* Check for incorrectly formed argument list */
+ memset(&args, 0, sizeof(args));
rc = of_parse_phandle_with_args_map(np, "phandle-list-bad-args",
"phandle", 1, &args);
unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
@@ -780,7 +790,7 @@ static void __init of_unittest_parse_interrupts(void)
for (i = 0; i < 4; i++) {
bool passed = true;
- args.args_count = 0;
+ memset(&args, 0, sizeof(args));
rc = of_irq_parse_one(np, i, &args);
passed &= !rc;
@@ -801,7 +811,7 @@ static void __init of_unittest_parse_interrupts(void)
for (i = 0; i < 4; i++) {
bool passed = true;
- args.args_count = 0;
+ memset(&args, 0, sizeof(args));
rc = of_irq_parse_one(np, i, &args);
/* Test the values from tests-phandle.dtsi */
@@ -854,6 +864,7 @@ static void __init of_unittest_parse_interrupts_extended(void)
for (i = 0; i < 7; i++) {
bool passed = true;
+ memset(&args, 0, sizeof(args));
rc = of_irq_parse_one(np, i, &args);
/* Test the values from tests-phandle.dtsi */
--
Frank Rowand <frank.rowand@sony.com>
^ permalink raw reply related
* [PATCH v4 17/18] of: unittest: find overlays[] entry by name instead of index
From: frowand.list @ 2018-10-16 2:37 UTC (permalink / raw)
To: Rob Herring, Pantelis Antoniou, Michael Ellerman,
Benjamin Herrenschmidt, Paul Mackerras, Alan Tull, Moritz Fischer
Cc: devicetree, linux-fpga, linuxppc-dev, linux-kernel
In-Reply-To: <1539657458-24401-1-git-send-email-frowand.list@gmail.com>
From: Frank Rowand <frank.rowand@sony.com>
One accessor of overlays[] was using a hard coded index value to
find the correct array entry instead of searching for the entry
containing the correct name.
Signed-off-by: Frank Rowand <frank.rowand@sony.com>
---
drivers/of/unittest.c | 21 +++++++++++++++++----
1 file changed, 17 insertions(+), 4 deletions(-)
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 1c2bd8503095..785985bdbfa6 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -2178,7 +2178,7 @@ struct overlay_info {
OVERLAY_INFO_EXTERN(overlay_bad_phandle);
OVERLAY_INFO_EXTERN(overlay_bad_symbol);
-/* order of entries is hard-coded into users of overlays[] */
+/* entries found by name */
static struct overlay_info overlays[] = {
OVERLAY_INFO(overlay_base, -9999),
OVERLAY_INFO(overlay, 0),
@@ -2201,7 +2201,8 @@ struct overlay_info {
OVERLAY_INFO(overlay_bad_add_dup_prop, -EINVAL),
OVERLAY_INFO(overlay_bad_phandle, -EINVAL),
OVERLAY_INFO(overlay_bad_symbol, -EINVAL),
- {}
+ /* end marker */
+ {.dtb_begin = NULL, .dtb_end = NULL, .expected_result = 0, .name = NULL}
};
static struct device_node *overlay_base_root;
@@ -2231,6 +2232,19 @@ void __init unittest_unflatten_overlay_base(void)
u32 data_size;
void *new_fdt;
u32 size;
+ int found = 0;
+ const char *overlay_name = "overlay_base";
+
+ for (info = overlays; info && info->name; info++) {
+ if (!strcmp(overlay_name, info->name)) {
+ found = 1;
+ break;
+ }
+ }
+ if (!found) {
+ pr_err("no overlay data for %s\n", overlay_name);
+ return;
+ }
info = &overlays[0];
@@ -2278,11 +2292,10 @@ static int __init overlay_data_apply(const char *overlay_name, int *overlay_id)
{
struct overlay_info *info;
int found = 0;
- int k;
int ret;
u32 size;
- for (k = 0, info = overlays; info && info->name; info++, k++) {
+ for (info = overlays; info && info->name; info++) {
if (!strcmp(overlay_name, info->name)) {
found = 1;
break;
--
Frank Rowand <frank.rowand@sony.com>
^ permalink raw reply related
* [PATCH v4 16/18] of: unittest: allow base devicetree to have symbol metadata
From: frowand.list @ 2018-10-16 2:37 UTC (permalink / raw)
To: Rob Herring, Pantelis Antoniou, Michael Ellerman,
Benjamin Herrenschmidt, Paul Mackerras, Alan Tull, Moritz Fischer
Cc: devicetree, linux-fpga, linuxppc-dev, linux-kernel
In-Reply-To: <1539657458-24401-1-git-send-email-frowand.list@gmail.com>
From: Frank Rowand <frank.rowand@sony.com>
The overlay metadata nodes in the FDT created from testcases.dts
are not handled properly.
The __fixups__ and __local_fixups__ node were added to the live
devicetree, but should not be.
Only the first property in the /__symbols__ node was added to the
live devicetree if the live devicetree already contained a
/__symbols node. All of the node's properties must be added.
Signed-off-by: Frank Rowand <frank.rowand@sony.com>
---
drivers/of/unittest.c | 43 +++++++++++++++++++++++++++++++++++--------
1 file changed, 35 insertions(+), 8 deletions(-)
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 6d80f474c8f2..1c2bd8503095 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -1057,20 +1057,44 @@ static void __init of_unittest_platform_populate(void)
* of np into dup node (present in live tree) and
* updates parent of children of np to dup.
*
- * @np: node already present in live tree
+ * @np: node whose properties are being added to the live tree
* @dup: node present in live tree to be updated
*/
static void update_node_properties(struct device_node *np,
struct device_node *dup)
{
struct property *prop;
+ struct property *save_next;
struct device_node *child;
-
- for_each_property_of_node(np, prop)
- of_add_property(dup, prop);
+ int ret;
for_each_child_of_node(np, child)
child->parent = dup;
+
+ /*
+ * "unittest internal error: unable to add testdata property"
+ *
+ * If this message reports a property in node '/__symbols__' then
+ * the respective unittest overlay contains a label that has the
+ * same name as a label in the live devicetree. The label will
+ * be in the live devicetree only if the devicetree source was
+ * compiled with the '-@' option. If you encounter this error,
+ * please consider renaming __all__ of the labels in the unittest
+ * overlay dts files with an odd prefix that is unlikely to be
+ * used in a real devicetree.
+ */
+
+ /*
+ * open code for_each_property_of_node() because of_add_property()
+ * sets prop->next to NULL
+ */
+ for (prop = np->properties; prop != NULL; prop = save_next) {
+ save_next = prop->next;
+ ret = of_add_property(dup, prop);
+ if (ret)
+ pr_err("unittest internal error: unable to add testdata property %pOF/%s",
+ np, prop->name);
+ }
}
/**
@@ -1079,18 +1103,23 @@ static void update_node_properties(struct device_node *np,
*
* @np: Node to attach to live tree
*/
-static int attach_node_and_children(struct device_node *np)
+static void attach_node_and_children(struct device_node *np)
{
struct device_node *next, *dup, *child;
unsigned long flags;
const char *full_name;
full_name = kasprintf(GFP_KERNEL, "%pOF", np);
+
+ if (!strcmp(full_name, "/__local_fixups__") ||
+ !strcmp(full_name, "/__fixups__"))
+ return;
+
dup = of_find_node_by_path(full_name);
kfree(full_name);
if (dup) {
update_node_properties(np, dup);
- return 0;
+ return;
}
child = np->child;
@@ -1111,8 +1140,6 @@ static int attach_node_and_children(struct device_node *np)
attach_node_and_children(child);
child = next;
}
-
- return 0;
}
/**
--
Frank Rowand <frank.rowand@sony.com>
^ permalink raw reply related
* [PATCH v4 15/18] of: overlay: set node fields from properties when add new overlay node
From: frowand.list @ 2018-10-16 2:37 UTC (permalink / raw)
To: Rob Herring, Pantelis Antoniou, Michael Ellerman,
Benjamin Herrenschmidt, Paul Mackerras, Alan Tull, Moritz Fischer
Cc: devicetree, linux-fpga, linuxppc-dev, linux-kernel
In-Reply-To: <1539657458-24401-1-git-send-email-frowand.list@gmail.com>
From: Frank Rowand <frank.rowand@sony.com>
Overlay nodes added by add_changeset_node() do not have the node
fields name, phandle, and type set.
The node passed to __of_attach_node() when the add node changeset
entry is processed does not contain any properties. The node's
properties are located in add property changeset entries that will
be processed after the add node changeset is applied.
Set the node's fields in the node contained in the add node
changeset entry and do not set them to incorrect values in
add_changeset_node().
A visible symptom that is fixed by this patch is the names of nodes
added by overlays that have an entry in /sys/bus/platform/drivers/*/
will contain the unit-address but the node-name will be <NULL>, for
example, "fc4ab000.<NULL>". After applying the patch the name, in
this example, for node restart@fc4ab000 is "fc4ab000.restart".
Signed-off-by: Frank Rowand <frank.rowand@sony.com>
---
drivers/of/dynamic.c | 27 ++++++++++++++++++---------
drivers/of/overlay.c | 29 ++++++++++++++++++++++++-----
2 files changed, 42 insertions(+), 14 deletions(-)
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index a94f727ec3da..a9f5d5fb3f25 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -205,15 +205,24 @@ static void __of_attach_node(struct device_node *np)
const __be32 *phandle;
int sz;
- np->name = __of_get_property(np, "name", NULL) ? : "<NULL>";
- np->type = __of_get_property(np, "device_type", NULL) ? : "<NULL>";
-
- phandle = __of_get_property(np, "phandle", &sz);
- if (!phandle)
- phandle = __of_get_property(np, "linux,phandle", &sz);
- if (IS_ENABLED(CONFIG_PPC_PSERIES) && !phandle)
- phandle = __of_get_property(np, "ibm,phandle", &sz);
- np->phandle = (phandle && (sz >= 4)) ? be32_to_cpup(phandle) : 0;
+ if (!of_node_check_flag(np, OF_OVERLAY)) {
+ np->name = __of_get_property(np, "name", NULL);
+ np->type = __of_get_property(np, "device_type", NULL);
+ if (!np->name)
+ np->name = "<NULL>";
+ if (!np->type)
+ np->type = "<NULL>";
+
+ phandle = __of_get_property(np, "phandle", &sz);
+ if (!phandle)
+ phandle = __of_get_property(np, "linux,phandle", &sz);
+ if (IS_ENABLED(CONFIG_PPC_PSERIES) && !phandle)
+ phandle = __of_get_property(np, "ibm,phandle", &sz);
+ if (phandle && (sz >= 4))
+ np->phandle = be32_to_cpup(phandle);
+ else
+ np->phandle = 0;
+ }
np->child = NULL;
np->sibling = np->parent->child;
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index 01afd22566ed..d011177e5aaa 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -307,10 +307,11 @@ static int add_changeset_property(struct overlay_changeset *ovcs,
int ret = 0;
bool check_for_non_overlay_node = false;
- if (!of_prop_cmp(overlay_prop->name, "name") ||
- !of_prop_cmp(overlay_prop->name, "phandle") ||
- !of_prop_cmp(overlay_prop->name, "linux,phandle"))
- return 0;
+ if (target->in_livetree)
+ if (!of_prop_cmp(overlay_prop->name, "name") ||
+ !of_prop_cmp(overlay_prop->name, "phandle") ||
+ !of_prop_cmp(overlay_prop->name, "linux,phandle"))
+ return 0;
if (target->in_livetree)
prop = of_find_property(target->np, overlay_prop->name, NULL);
@@ -331,6 +332,10 @@ static int add_changeset_property(struct overlay_changeset *ovcs,
if (!prop) {
check_for_non_overlay_node = true;
+ if (!target->in_livetree) {
+ new_prop->next = target->np->deadprops;
+ target->np->deadprops = new_prop;
+ }
ret = of_changeset_add_property(&ovcs->cset, target->np,
new_prop);
@@ -410,9 +415,10 @@ static int add_changeset_node(struct overlay_changeset *ovcs,
struct target *target, struct device_node *node)
{
const char *node_kbasename;
+ const __be32 *phandle;
struct device_node *tchild;
struct target target_child;
- int ret = 0;
+ int ret = 0, size;
node_kbasename = kbasename(node->full_name);
@@ -426,6 +432,19 @@ static int add_changeset_node(struct overlay_changeset *ovcs,
return -ENOMEM;
tchild->parent = target->np;
+ tchild->name = __of_get_property(node, "name", NULL);
+ tchild->type = __of_get_property(node, "device_type", NULL);
+
+ if (!tchild->name)
+ tchild->name = "<NULL>";
+ if (!tchild->type)
+ tchild->type = "<NULL>";
+
+ /* ignore obsolete "linux,phandle" */
+ phandle = __of_get_property(node, "phandle", &size);
+ if (phandle && (size == 4))
+ tchild->phandle = be32_to_cpup(phandle);
+
of_node_set_flag(tchild, OF_OVERLAY);
ret = of_changeset_attach_node(&ovcs->cset, tchild);
--
Frank Rowand <frank.rowand@sony.com>
^ permalink raw reply related
* [PATCH v4 14/18] of: unittest: remove unused of_unittest_apply_overlay() argument
From: frowand.list @ 2018-10-16 2:37 UTC (permalink / raw)
To: Rob Herring, Pantelis Antoniou, Michael Ellerman,
Benjamin Herrenschmidt, Paul Mackerras, Alan Tull, Moritz Fischer
Cc: devicetree, linux-fpga, linuxppc-dev, linux-kernel
In-Reply-To: <1539657458-24401-1-git-send-email-frowand.list@gmail.com>
From: Frank Rowand <frank.rowand@sony.com>
Argument unittest_nr is not used in of_unittest_apply_overlay(),
remove it.
Signed-off-by: Frank Rowand <frank.rowand@sony.com>
---
drivers/of/unittest.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index efd9c947f192..6d80f474c8f2 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -1419,8 +1419,7 @@ static void of_unittest_destroy_tracked_overlays(void)
} while (defers > 0);
}
-static int __init of_unittest_apply_overlay(int overlay_nr, int unittest_nr,
- int *overlay_id)
+static int __init of_unittest_apply_overlay(int overlay_nr, int *overlay_id)
{
const char *overlay_name;
@@ -1453,7 +1452,7 @@ static int __init of_unittest_apply_overlay_check(int overlay_nr,
}
ovcs_id = 0;
- ret = of_unittest_apply_overlay(overlay_nr, unittest_nr, &ovcs_id);
+ ret = of_unittest_apply_overlay(overlay_nr, &ovcs_id);
if (ret != 0) {
/* of_unittest_apply_overlay already called unittest() */
return ret;
@@ -1489,7 +1488,7 @@ static int __init of_unittest_apply_revert_overlay_check(int overlay_nr,
/* apply the overlay */
ovcs_id = 0;
- ret = of_unittest_apply_overlay(overlay_nr, unittest_nr, &ovcs_id);
+ ret = of_unittest_apply_overlay(overlay_nr, &ovcs_id);
if (ret != 0) {
/* of_unittest_apply_overlay already called unittest() */
return ret;
--
Frank Rowand <frank.rowand@sony.com>
^ permalink raw reply related
* [PATCH v4 13/18] of: overlay: check prevents multiple fragments touching same property
From: frowand.list @ 2018-10-16 2:37 UTC (permalink / raw)
To: Rob Herring, Pantelis Antoniou, Michael Ellerman,
Benjamin Herrenschmidt, Paul Mackerras, Alan Tull, Moritz Fischer
Cc: devicetree, linux-fpga, linuxppc-dev, linux-kernel
In-Reply-To: <1539657458-24401-1-git-send-email-frowand.list@gmail.com>
From: Frank Rowand <frank.rowand@sony.com>
Add test case of two fragments updating the same property. After
adding the test case, the system hangs at end of boot, after
after slub stack dumps from kfree() in crypto modprobe code.
Multiple overlay fragments adding, modifying, or deleting the same
property is not supported. Add check to detect the attempt and fail
the overlay apply.
Before this patch, the first fragment error would terminate
processing. Allow fragment checking to proceed and report all
of the fragment errors before terminating the overlay apply. This
is not a hot path, thus not a performance issue (the error is not
transient and requires fixing the overlay before attempting to
apply it again).
After applying this patch, the devicetree unittest messages will
include:
OF: overlay: ERROR: multiple fragments add, update, and/or delete property /testcase-data-2/substation@100/motor-1/rpm_avail
...
### dt-test ### end of unittest - 212 passed, 0 failed
The check to detect two fragments updating the same property is
folded into the patch that created the test case to maintain
bisectability.
Signed-off-by: Frank Rowand <frank.rowand@sony.com>
---
Changes since v3:
- Update patch comment header to state that this patch modifies the
previous patch to not return immediately on fragment error and
explain this is not a performance issue.
- remove redundant "overlay" from two error messages. "OF: overlay:"
is already present in pr_fmt()
drivers/of/overlay.c | 118 ++++++++++++++-------
drivers/of/unittest-data/Makefile | 1 +
.../of/unittest-data/overlay_bad_add_dup_prop.dts | 24 +++++
drivers/of/unittest-data/overlay_base.dts | 1 +
drivers/of/unittest.c | 5 +
5 files changed, 112 insertions(+), 37 deletions(-)
create mode 100644 drivers/of/unittest-data/overlay_bad_add_dup_prop.dts
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index 0dc7452e2ed5..01afd22566ed 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -518,52 +518,96 @@ static int build_changeset_symbols_node(struct overlay_changeset *ovcs,
return 0;
}
+static int find_dup_cset_node_entry(struct overlay_changeset *ovcs,
+ struct of_changeset_entry *ce_1)
+{
+ struct of_changeset_entry *ce_2;
+ char *fn_1, *fn_2;
+ int node_path_match;
+
+ if (ce_1->action != OF_RECONFIG_ATTACH_NODE &&
+ ce_1->action != OF_RECONFIG_DETACH_NODE)
+ return 0;
+
+ ce_2 = ce_1;
+ list_for_each_entry_continue(ce_2, &ovcs->cset.entries, node) {
+ if ((ce_2->action != OF_RECONFIG_ATTACH_NODE &&
+ ce_2->action != OF_RECONFIG_DETACH_NODE) ||
+ of_node_cmp(ce_1->np->full_name, ce_2->np->full_name))
+ continue;
+
+ fn_1 = kasprintf(GFP_KERNEL, "%pOF", ce_1->np);
+ fn_2 = kasprintf(GFP_KERNEL, "%pOF", ce_2->np);
+ node_path_match = !strcmp(fn_1, fn_2);
+ kfree(fn_1);
+ kfree(fn_2);
+ if (node_path_match) {
+ pr_err("ERROR: multiple fragments add and/or delete node %pOF\n",
+ ce_1->np);
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+static int find_dup_cset_prop(struct overlay_changeset *ovcs,
+ struct of_changeset_entry *ce_1)
+{
+ struct of_changeset_entry *ce_2;
+ char *fn_1, *fn_2;
+ int node_path_match;
+
+ if (ce_1->action != OF_RECONFIG_ADD_PROPERTY &&
+ ce_1->action != OF_RECONFIG_REMOVE_PROPERTY &&
+ ce_1->action != OF_RECONFIG_UPDATE_PROPERTY)
+ return 0;
+
+ ce_2 = ce_1;
+ list_for_each_entry_continue(ce_2, &ovcs->cset.entries, node) {
+ if ((ce_2->action != OF_RECONFIG_ADD_PROPERTY &&
+ ce_2->action != OF_RECONFIG_REMOVE_PROPERTY &&
+ ce_2->action != OF_RECONFIG_UPDATE_PROPERTY) ||
+ of_node_cmp(ce_1->np->full_name, ce_2->np->full_name))
+ continue;
+
+ fn_1 = kasprintf(GFP_KERNEL, "%pOF", ce_1->np);
+ fn_2 = kasprintf(GFP_KERNEL, "%pOF", ce_2->np);
+ node_path_match = !strcmp(fn_1, fn_2);
+ kfree(fn_1);
+ kfree(fn_2);
+ if (node_path_match &&
+ !of_prop_cmp(ce_1->prop->name, ce_2->prop->name)) {
+ pr_err("ERROR: multiple fragments add, update, and/or delete property %pOF/%s\n",
+ ce_1->np, ce_1->prop->name);
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
/**
- * check_changeset_dup_add_node() - changeset validation: duplicate add node
+ * changeset_dup_entry_check() - check for duplicate entries
* @ovcs: Overlay changeset
*
- * Check changeset @ovcs->cset for multiple add node entries for the same
- * node.
+ * Check changeset @ovcs->cset for multiple {add or delete} node entries for
+ * the same node or duplicate {add, delete, or update} properties entries
+ * for the same property.
*
- * Returns 0 on success, -ENOMEM if memory allocation failure, or -EINVAL if
- * invalid overlay in @ovcs->fragments[].
+ * Returns 0 on success, or -EINVAL if duplicate changeset entry found.
*/
-static int check_changeset_dup_add_node(struct overlay_changeset *ovcs)
+static int changeset_dup_entry_check(struct overlay_changeset *ovcs)
{
- struct of_changeset_entry *ce_1, *ce_2;
- char *fn_1, *fn_2;
- int name_match;
+ struct of_changeset_entry *ce_1;
+ int dup_entry = 0;
list_for_each_entry(ce_1, &ovcs->cset.entries, node) {
-
- if (ce_1->action == OF_RECONFIG_ATTACH_NODE ||
- ce_1->action == OF_RECONFIG_DETACH_NODE) {
-
- ce_2 = ce_1;
- list_for_each_entry_continue(ce_2, &ovcs->cset.entries, node) {
- if (ce_2->action == OF_RECONFIG_ATTACH_NODE ||
- ce_2->action == OF_RECONFIG_DETACH_NODE) {
- /* inexpensive name compare */
- if (!of_node_cmp(ce_1->np->full_name,
- ce_2->np->full_name)) {
- /* expensive full path name compare */
- fn_1 = kasprintf(GFP_KERNEL, "%pOF", ce_1->np);
- fn_2 = kasprintf(GFP_KERNEL, "%pOF", ce_2->np);
- name_match = !strcmp(fn_1, fn_2);
- kfree(fn_1);
- kfree(fn_2);
- if (name_match) {
- pr_err("ERROR: multiple overlay fragments add and/or delete node %pOF\n",
- ce_1->np);
- return -EINVAL;
- }
- }
- }
- }
- }
+ dup_entry |= find_dup_cset_node_entry(ovcs, ce_1);
+ dup_entry |= find_dup_cset_prop(ovcs, ce_1);
}
- return 0;
+ return dup_entry ? -EINVAL : 0;
}
/**
@@ -621,7 +665,7 @@ static int build_changeset(struct overlay_changeset *ovcs)
}
}
- return check_changeset_dup_add_node(ovcs);
+ return changeset_dup_entry_check(ovcs);
}
/*
diff --git a/drivers/of/unittest-data/Makefile b/drivers/of/unittest-data/Makefile
index 166dbdbfd1c5..9b6807065827 100644
--- a/drivers/of/unittest-data/Makefile
+++ b/drivers/of/unittest-data/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_OF_OVERLAY) += overlay.dtb.o \
overlay_13.dtb.o \
overlay_15.dtb.o \
overlay_bad_add_dup_node.dtb.o \
+ overlay_bad_add_dup_prop.dtb.o \
overlay_bad_phandle.dtb.o \
overlay_bad_symbol.dtb.o \
overlay_base.dtb.o
diff --git a/drivers/of/unittest-data/overlay_bad_add_dup_prop.dts b/drivers/of/unittest-data/overlay_bad_add_dup_prop.dts
new file mode 100644
index 000000000000..c190da54f175
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_bad_add_dup_prop.dts
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/*
+ * &electric_1/motor-1 and &spin_ctrl_1 are the same node:
+ * /testcase-data-2/substation@100/motor-1
+ *
+ * Thus the property "rpm_avail" in each fragment will
+ * result in an attempt to update the same property twice.
+ * This will result in an error and the overlay apply
+ * will fail.
+ */
+
+&electric_1 {
+
+ motor-1 {
+ rpm_avail = < 100 >;
+ };
+};
+
+&spin_ctrl_1 {
+ rpm_avail = < 100 200 >;
+};
diff --git a/drivers/of/unittest-data/overlay_base.dts b/drivers/of/unittest-data/overlay_base.dts
index 820b79ca378a..99ab9d12d00b 100644
--- a/drivers/of/unittest-data/overlay_base.dts
+++ b/drivers/of/unittest-data/overlay_base.dts
@@ -30,6 +30,7 @@
spin_ctrl_1: motor-1 {
compatible = "ot,ferris-wheel-motor";
spin = "clockwise";
+ rpm_avail = < 50 >;
};
spin_ctrl_2: motor-8 {
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 471b8eb6e842..efd9c947f192 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -2148,6 +2148,7 @@ struct overlay_info {
OVERLAY_INFO_EXTERN(overlay_13);
OVERLAY_INFO_EXTERN(overlay_15);
OVERLAY_INFO_EXTERN(overlay_bad_add_dup_node);
+OVERLAY_INFO_EXTERN(overlay_bad_add_dup_prop);
OVERLAY_INFO_EXTERN(overlay_bad_phandle);
OVERLAY_INFO_EXTERN(overlay_bad_symbol);
@@ -2171,6 +2172,7 @@ struct overlay_info {
OVERLAY_INFO(overlay_13, 0),
OVERLAY_INFO(overlay_15, 0),
OVERLAY_INFO(overlay_bad_add_dup_node, -EINVAL),
+ OVERLAY_INFO(overlay_bad_add_dup_prop, -EINVAL),
OVERLAY_INFO(overlay_bad_phandle, -EINVAL),
OVERLAY_INFO(overlay_bad_symbol, -EINVAL),
{}
@@ -2418,6 +2420,9 @@ static __init void of_unittest_overlay_high_level(void)
unittest(overlay_data_apply("overlay_bad_add_dup_node", NULL),
"Adding overlay 'overlay_bad_add_dup_node' failed\n");
+ unittest(overlay_data_apply("overlay_bad_add_dup_prop", NULL),
+ "Adding overlay 'overlay_bad_add_dup_prop' failed\n");
+
unittest(overlay_data_apply("overlay_bad_phandle", NULL),
"Adding overlay 'overlay_bad_phandle' failed\n");
--
Frank Rowand <frank.rowand@sony.com>
^ permalink raw reply related
* [PATCH v4 12/18] of: overlay: check prevents multiple fragments add or delete same node
From: frowand.list @ 2018-10-16 2:37 UTC (permalink / raw)
To: Rob Herring, Pantelis Antoniou, Michael Ellerman,
Benjamin Herrenschmidt, Paul Mackerras, Alan Tull, Moritz Fischer
Cc: devicetree, linux-fpga, linuxppc-dev, linux-kernel
In-Reply-To: <1539657458-24401-1-git-send-email-frowand.list@gmail.com>
From: Frank Rowand <frank.rowand@sony.com>
Multiple overlay fragments adding or deleting the same node is not
supported. Replace code comment of such, with check to detect the
attempt and fail the overlay apply.
Devicetree unittest where multiple fragments added the same node was
added in the previous patch in the series. After applying this patch
the unittest messages will no longer include:
Duplicate name in motor-1, renamed to "controller#1"
OF: overlay: of_overlay_apply() err=0
### dt-test ### of_overlay_fdt_apply() expected -22, ret=0, overlay_bad_add_dup_node
### dt-test ### FAIL of_unittest_overlay_high_level():2419 Adding overlay 'overlay_bad_add_dup_node' failed
...
### dt-test ### end of unittest - 210 passed, 1 failed
but will instead include:
OF: overlay: ERROR: multiple overlay fragments add and/or delete node /testcase-data-2/substation@100/motor-1/controller
...
### dt-test ### end of unittest - 211 passed, 0 failed
Signed-off-by: Frank Rowand <frank.rowand@sony.com>
---
checkpatch errors "line over 80 characters" are ok, they will be
fixed later in this series
drivers/of/overlay.c | 58 ++++++++++++++++++++++++++++++++++++++++++++--------
1 file changed, 49 insertions(+), 9 deletions(-)
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index 34396d6db1b3..0dc7452e2ed5 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -402,14 +402,6 @@ static int add_changeset_property(struct overlay_changeset *ovcs,
* a live devicetree created from Open Firmware.
*
* NOTE_2: Multiple mods of created nodes not supported.
- * If more than one fragment contains a node that does not already exist
- * in the live tree, then for each fragment of_changeset_attach_node()
- * will add a changeset entry to add the node. When the changeset is
- * applied, __of_attach_node() will attach the node twice (once for
- * each fragment). At this point the device tree will be corrupted.
- *
- * TODO: add integrity check to ensure that multiple fragments do not
- * create the same node.
*
* Returns 0 on success, -ENOMEM if memory allocation failure, or -EINVAL if
* invalid @overlay.
@@ -527,6 +519,54 @@ static int build_changeset_symbols_node(struct overlay_changeset *ovcs,
}
/**
+ * check_changeset_dup_add_node() - changeset validation: duplicate add node
+ * @ovcs: Overlay changeset
+ *
+ * Check changeset @ovcs->cset for multiple add node entries for the same
+ * node.
+ *
+ * Returns 0 on success, -ENOMEM if memory allocation failure, or -EINVAL if
+ * invalid overlay in @ovcs->fragments[].
+ */
+static int check_changeset_dup_add_node(struct overlay_changeset *ovcs)
+{
+ struct of_changeset_entry *ce_1, *ce_2;
+ char *fn_1, *fn_2;
+ int name_match;
+
+ list_for_each_entry(ce_1, &ovcs->cset.entries, node) {
+
+ if (ce_1->action == OF_RECONFIG_ATTACH_NODE ||
+ ce_1->action == OF_RECONFIG_DETACH_NODE) {
+
+ ce_2 = ce_1;
+ list_for_each_entry_continue(ce_2, &ovcs->cset.entries, node) {
+ if (ce_2->action == OF_RECONFIG_ATTACH_NODE ||
+ ce_2->action == OF_RECONFIG_DETACH_NODE) {
+ /* inexpensive name compare */
+ if (!of_node_cmp(ce_1->np->full_name,
+ ce_2->np->full_name)) {
+ /* expensive full path name compare */
+ fn_1 = kasprintf(GFP_KERNEL, "%pOF", ce_1->np);
+ fn_2 = kasprintf(GFP_KERNEL, "%pOF", ce_2->np);
+ name_match = !strcmp(fn_1, fn_2);
+ kfree(fn_1);
+ kfree(fn_2);
+ if (name_match) {
+ pr_err("ERROR: multiple overlay fragments add and/or delete node %pOF\n",
+ ce_1->np);
+ return -EINVAL;
+ }
+ }
+ }
+ }
+ }
+ }
+
+ return 0;
+}
+
+/**
* build_changeset() - populate overlay changeset in @ovcs from @ovcs->fragments
* @ovcs: Overlay changeset
*
@@ -581,7 +621,7 @@ static int build_changeset(struct overlay_changeset *ovcs)
}
}
- return 0;
+ return check_changeset_dup_add_node(ovcs);
}
/*
--
Frank Rowand <frank.rowand@sony.com>
^ permalink raw reply related
* [PATCH v4 11/18] of: overlay: test case of two fragments adding same node
From: frowand.list @ 2018-10-16 2:37 UTC (permalink / raw)
To: Rob Herring, Pantelis Antoniou, Michael Ellerman,
Benjamin Herrenschmidt, Paul Mackerras, Alan Tull, Moritz Fischer
Cc: devicetree, linux-fpga, linuxppc-dev, linux-kernel
In-Reply-To: <1539657458-24401-1-git-send-email-frowand.list@gmail.com>
From: Frank Rowand <frank.rowand@sony.com>
Multiple overlay fragments adding or deleting the same node is not
supported. An attempt to do so results in an incorrect devicetree.
The node name will be munged for the second add.
After adding this patch, the unittest messages will show:
Duplicate name in motor-1, renamed to "controller#1"
OF: overlay: of_overlay_apply() err=0
### dt-test ### of_overlay_fdt_apply() expected -22, ret=0, overlay_bad_add_dup_node
### dt-test ### FAIL of_unittest_overlay_high_level():2419 Adding overlay 'overlay_bad_add_dup_node' failed
...
### dt-test ### end of unittest - 210 passed, 1 failed
The incorrect (munged) node name "controller#1" can be seen in the
/proc filesystem:
$ pwd
/proc/device-tree/testcase-data-2/substation@100/motor-1
$ ls
compatible controller controller#1 name phandle spin
$ ls controller
power_bus
$ ls controller#1
power_bus_emergency
Signed-off-by: Frank Rowand <frank.rowand@sony.com>
---
drivers/of/unittest-data/Makefile | 1 +
.../of/unittest-data/overlay_bad_add_dup_node.dts | 28 ++++++++++++++++++++++
drivers/of/unittest.c | 5 ++++
3 files changed, 34 insertions(+)
create mode 100644 drivers/of/unittest-data/overlay_bad_add_dup_node.dts
diff --git a/drivers/of/unittest-data/Makefile b/drivers/of/unittest-data/Makefile
index 013d85e694c6..166dbdbfd1c5 100644
--- a/drivers/of/unittest-data/Makefile
+++ b/drivers/of/unittest-data/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_OF_OVERLAY) += overlay.dtb.o \
overlay_12.dtb.o \
overlay_13.dtb.o \
overlay_15.dtb.o \
+ overlay_bad_add_dup_node.dtb.o \
overlay_bad_phandle.dtb.o \
overlay_bad_symbol.dtb.o \
overlay_base.dtb.o
diff --git a/drivers/of/unittest-data/overlay_bad_add_dup_node.dts b/drivers/of/unittest-data/overlay_bad_add_dup_node.dts
new file mode 100644
index 000000000000..145dfc3b1024
--- /dev/null
+++ b/drivers/of/unittest-data/overlay_bad_add_dup_node.dts
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+/plugin/;
+
+/*
+ * &electric_1/motor-1 and &spin_ctrl_1 are the same node:
+ * /testcase-data-2/substation@100/motor-1
+ *
+ * Thus the new node "controller" in each fragment will
+ * result in an attempt to add the same node twice.
+ * This will result in an error and the overlay apply
+ * will fail.
+ */
+
+&electric_1 {
+
+ motor-1 {
+ controller {
+ power_bus = < 0x1 0x2 >;
+ };
+ };
+};
+
+&spin_ctrl_1 {
+ controller {
+ power_bus_emergency = < 0x101 0x102 >;
+ };
+};
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 722537e14848..471b8eb6e842 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -2147,6 +2147,7 @@ struct overlay_info {
OVERLAY_INFO_EXTERN(overlay_12);
OVERLAY_INFO_EXTERN(overlay_13);
OVERLAY_INFO_EXTERN(overlay_15);
+OVERLAY_INFO_EXTERN(overlay_bad_add_dup_node);
OVERLAY_INFO_EXTERN(overlay_bad_phandle);
OVERLAY_INFO_EXTERN(overlay_bad_symbol);
@@ -2169,6 +2170,7 @@ struct overlay_info {
OVERLAY_INFO(overlay_12, 0),
OVERLAY_INFO(overlay_13, 0),
OVERLAY_INFO(overlay_15, 0),
+ OVERLAY_INFO(overlay_bad_add_dup_node, -EINVAL),
OVERLAY_INFO(overlay_bad_phandle, -EINVAL),
OVERLAY_INFO(overlay_bad_symbol, -EINVAL),
{}
@@ -2413,6 +2415,9 @@ static __init void of_unittest_overlay_high_level(void)
unittest(overlay_data_apply("overlay", NULL),
"Adding overlay 'overlay' failed\n");
+ unittest(overlay_data_apply("overlay_bad_add_dup_node", NULL),
+ "Adding overlay 'overlay_bad_add_dup_node' failed\n");
+
unittest(overlay_data_apply("overlay_bad_phandle", NULL),
"Adding overlay 'overlay_bad_phandle' failed\n");
--
Frank Rowand <frank.rowand@sony.com>
^ 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