* [RESEND 6/7] IB/qib: Use the new FOLL_LONGTERM flag to get_user_pages_fast()
From: ira.weiny @ 2019-03-17 18:34 UTC (permalink / raw)
To: Andrew Morton, John Hubbard, Michal Hocko, Kirill A. Shutemov,
Peter Zijlstra, Jason Gunthorpe, Benjamin Herrenschmidt,
Paul Mackerras, David S. Miller, Martin Schwidefsky,
Heiko Carstens, Rich Felker, Yoshinori Sato, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Ralf Baechle, James Hogan
Cc: linux-s390, linux-sh, linux-rdma, Ira Weiny, linux-kernel,
linux-mips, linux-mm, netdev, sparclinux, linuxppc-dev
In-Reply-To: <20190317183438.2057-1-ira.weiny@intel.com>
From: Ira Weiny <ira.weiny@intel.com>
Use the new FOLL_LONGTERM to get_user_pages_fast() to protect against
FS DAX pages being mapped.
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
drivers/infiniband/hw/qib/qib_user_sdma.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c
index 31c523b2a9f5..b53cc0240e02 100644
--- a/drivers/infiniband/hw/qib/qib_user_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_user_sdma.c
@@ -673,7 +673,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
else
j = npages;
- ret = get_user_pages_fast(addr, j, 0, pages);
+ ret = get_user_pages_fast(addr, j, FOLL_LONGTERM, pages);
if (ret != j) {
i = 0;
j = ret;
--
2.20.1
^ permalink raw reply related
* [RESEND 5/7] IB/hfi1: Use the new FOLL_LONGTERM flag to get_user_pages_fast()
From: ira.weiny @ 2019-03-17 18:34 UTC (permalink / raw)
To: Andrew Morton, John Hubbard, Michal Hocko, Kirill A. Shutemov,
Peter Zijlstra, Jason Gunthorpe, Benjamin Herrenschmidt,
Paul Mackerras, David S. Miller, Martin Schwidefsky,
Heiko Carstens, Rich Felker, Yoshinori Sato, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Ralf Baechle, James Hogan
Cc: linux-s390, linux-sh, linux-rdma, Ira Weiny, linux-kernel,
linux-mips, linux-mm, netdev, sparclinux, linuxppc-dev
In-Reply-To: <20190317183438.2057-1-ira.weiny@intel.com>
From: Ira Weiny <ira.weiny@intel.com>
Use the new FOLL_LONGTERM to get_user_pages_fast() to protect against
FS DAX pages being mapped.
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
drivers/infiniband/hw/hfi1/user_pages.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c
index 78ccacaf97d0..6a7f9cd5a94e 100644
--- a/drivers/infiniband/hw/hfi1/user_pages.c
+++ b/drivers/infiniband/hw/hfi1/user_pages.c
@@ -104,9 +104,11 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
bool writable, struct page **pages)
{
int ret;
+ unsigned int gup_flags = writable ? FOLL_WRITE : 0;
- ret = get_user_pages_fast(vaddr, npages, writable ? FOLL_WRITE : 0,
- pages);
+ gup_flags |= FOLL_LONGTERM;
+
+ ret = get_user_pages_fast(vaddr, npages, gup_flags, pages);
if (ret < 0)
return ret;
--
2.20.1
^ permalink raw reply related
* [RESEND 4/7] mm/gup: Add FOLL_LONGTERM capability to GUP fast
From: ira.weiny @ 2019-03-17 18:34 UTC (permalink / raw)
To: Andrew Morton, John Hubbard, Michal Hocko, Kirill A. Shutemov,
Peter Zijlstra, Jason Gunthorpe, Benjamin Herrenschmidt,
Paul Mackerras, David S. Miller, Martin Schwidefsky,
Heiko Carstens, Rich Felker, Yoshinori Sato, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Ralf Baechle, James Hogan
Cc: linux-s390, linux-sh, linux-rdma, Ira Weiny, linux-kernel,
linux-mips, linux-mm, netdev, sparclinux, linuxppc-dev
In-Reply-To: <20190317183438.2057-1-ira.weiny@intel.com>
From: Ira Weiny <ira.weiny@intel.com>
DAX pages were previously unprotected from longterm pins when users
called get_user_pages_fast().
Use the new FOLL_LONGTERM flag to check for DEVMAP pages and fall
back to regular GUP processing if a DEVMAP page is encountered.
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
mm/gup.c | 29 +++++++++++++++++++++++++----
1 file changed, 25 insertions(+), 4 deletions(-)
diff --git a/mm/gup.c b/mm/gup.c
index 0684a9536207..173db0c44678 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1600,6 +1600,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
goto pte_unmap;
if (pte_devmap(pte)) {
+ if (unlikely(flags & FOLL_LONGTERM))
+ goto pte_unmap;
+
pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
if (unlikely(!pgmap)) {
undo_dev_pagemap(nr, nr_start, pages);
@@ -1739,8 +1742,11 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
if (!pmd_access_permitted(orig, flags & FOLL_WRITE))
return 0;
- if (pmd_devmap(orig))
+ if (pmd_devmap(orig)) {
+ if (unlikely(flags & FOLL_LONGTERM))
+ return 0;
return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr);
+ }
refs = 0;
page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
@@ -1777,8 +1783,11 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
if (!pud_access_permitted(orig, flags & FOLL_WRITE))
return 0;
- if (pud_devmap(orig))
+ if (pud_devmap(orig)) {
+ if (unlikely(flags & FOLL_LONGTERM))
+ return 0;
return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr);
+ }
refs = 0;
page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
@@ -2066,8 +2075,20 @@ int get_user_pages_fast(unsigned long start, int nr_pages,
start += nr << PAGE_SHIFT;
pages += nr;
- ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
- gup_flags);
+ if (gup_flags & FOLL_LONGTERM) {
+ down_read(¤t->mm->mmap_sem);
+ ret = __gup_longterm_locked(current, current->mm,
+ start, nr_pages - nr,
+ pages, NULL, gup_flags);
+ up_read(¤t->mm->mmap_sem);
+ } else {
+ /*
+ * retain FAULT_FOLL_ALLOW_RETRY optimization if
+ * possible
+ */
+ ret = get_user_pages_unlocked(start, nr_pages - nr,
+ pages, gup_flags);
+ }
/* Have to be a bit careful with return values */
if (nr > 0) {
--
2.20.1
^ permalink raw reply related
* [RESEND 3/7] mm/gup: Change GUP fast to use flags rather than a write 'bool'
From: ira.weiny @ 2019-03-17 18:34 UTC (permalink / raw)
To: Andrew Morton, John Hubbard, Michal Hocko, Kirill A. Shutemov,
Peter Zijlstra, Jason Gunthorpe, Benjamin Herrenschmidt,
Paul Mackerras, David S. Miller, Martin Schwidefsky,
Heiko Carstens, Rich Felker, Yoshinori Sato, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Ralf Baechle, James Hogan
Cc: linux-s390, linux-sh, linux-rdma, Ira Weiny, linux-kernel,
linux-mips, linux-mm, netdev, sparclinux, linuxppc-dev
In-Reply-To: <20190317183438.2057-1-ira.weiny@intel.com>
From: Ira Weiny <ira.weiny@intel.com>
To facilitate additional options to get_user_pages_fast() change the
singular write parameter to be gup_flags.
This patch does not change any functionality. New functionality will
follow in subsequent patches.
Some of the get_user_pages_fast() call sites were unchanged because they
already passed FOLL_WRITE or 0 for the write parameter.
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
Changes from V1:
Rebase to current merge tree
arch/powerpc/mm/mmu_context_iommu.c no longer calls gup_fast
The gup_longterm was converted in patch 1
arch/mips/mm/gup.c | 11 ++++++-----
arch/powerpc/kvm/book3s_64_mmu_hv.c | 4 ++--
arch/powerpc/kvm/e500_mmu.c | 2 +-
arch/s390/kvm/interrupt.c | 2 +-
arch/s390/mm/gup.c | 12 ++++++------
arch/sh/mm/gup.c | 11 ++++++-----
arch/sparc/mm/gup.c | 9 +++++----
arch/x86/kvm/paging_tmpl.h | 2 +-
arch/x86/kvm/svm.c | 2 +-
drivers/fpga/dfl-afu-dma-region.c | 2 +-
drivers/gpu/drm/via/via_dmablit.c | 3 ++-
drivers/infiniband/hw/hfi1/user_pages.c | 3 ++-
drivers/misc/genwqe/card_utils.c | 2 +-
drivers/misc/vmw_vmci/vmci_host.c | 2 +-
drivers/misc/vmw_vmci/vmci_queue_pair.c | 6 ++++--
drivers/platform/goldfish/goldfish_pipe.c | 3 ++-
drivers/rapidio/devices/rio_mport_cdev.c | 4 +++-
drivers/sbus/char/oradax.c | 2 +-
drivers/scsi/st.c | 3 ++-
drivers/staging/gasket/gasket_page_table.c | 4 ++--
drivers/tee/tee_shm.c | 2 +-
drivers/vfio/vfio_iommu_spapr_tce.c | 3 ++-
drivers/vhost/vhost.c | 2 +-
drivers/video/fbdev/pvr2fb.c | 2 +-
drivers/virt/fsl_hypervisor.c | 2 +-
drivers/xen/gntdev.c | 2 +-
fs/orangefs/orangefs-bufmap.c | 2 +-
include/linux/mm.h | 4 ++--
kernel/futex.c | 2 +-
lib/iov_iter.c | 7 +++++--
mm/gup.c | 10 +++++-----
mm/util.c | 8 ++++----
net/ceph/pagevec.c | 2 +-
net/rds/info.c | 2 +-
net/rds/rdma.c | 3 ++-
35 files changed, 79 insertions(+), 63 deletions(-)
diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c
index 0d14e0d8eacf..4c2b4483683c 100644
--- a/arch/mips/mm/gup.c
+++ b/arch/mips/mm/gup.c
@@ -235,7 +235,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
* get_user_pages_fast() - pin user pages in memory
* @start: starting user address
* @nr_pages: number of pages from start to pin
- * @write: whether pages will be written to
+ * @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
@@ -247,8 +247,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
* requested. If nr_pages is 0 or negative, returns 0. If no pages
* were pinned, returns -errno.
*/
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages)
+int get_user_pages_fast(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages)
{
struct mm_struct *mm = current->mm;
unsigned long addr, len, end;
@@ -273,7 +273,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
next = pgd_addr_end(addr, end);
if (pgd_none(pgd))
goto slow;
- if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+ if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE,
+ pages, &nr))
goto slow;
} while (pgdp++, addr = next, addr != end);
local_irq_enable();
@@ -289,7 +290,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
pages += nr;
ret = get_user_pages_unlocked(start, (end - start) >> PAGE_SHIFT,
- pages, write ? FOLL_WRITE : 0);
+ pages, gup_flags);
/* Have to be a bit careful with return values */
if (nr > 0) {
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index be7bc070eae5..ab3d484c5e2e 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -600,7 +600,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
/* If writing != 0, then the HPTE must allow writing, if we get here */
write_ok = writing;
hva = gfn_to_hva_memslot(memslot, gfn);
- npages = get_user_pages_fast(hva, 1, writing, pages);
+ npages = get_user_pages_fast(hva, 1, writing ? FOLL_WRITE : 0, pages);
if (npages < 1) {
/* Check if it's an I/O mapping */
down_read(¤t->mm->mmap_sem);
@@ -1193,7 +1193,7 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
goto err;
hva = gfn_to_hva_memslot(memslot, gfn);
- npages = get_user_pages_fast(hva, 1, 1, pages);
+ npages = get_user_pages_fast(hva, 1, FOLL_WRITE, pages);
if (npages < 1)
goto err;
page = pages[0];
diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c
index 24296f4cadc6..e0af53fd78c5 100644
--- a/arch/powerpc/kvm/e500_mmu.c
+++ b/arch/powerpc/kvm/e500_mmu.c
@@ -783,7 +783,7 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
if (!pages)
return -ENOMEM;
- ret = get_user_pages_fast(cfg->array, num_pages, 1, pages);
+ ret = get_user_pages_fast(cfg->array, num_pages, FOLL_WRITE, pages);
if (ret < 0)
goto free_pages;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 82162867f378..95ab979541be 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -2376,7 +2376,7 @@ static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr)
ret = -EFAULT;
goto out;
}
- ret = get_user_pages_fast(map->addr, 1, 1, &map->page);
+ ret = get_user_pages_fast(map->addr, 1, FOLL_WRITE, &map->page);
if (ret < 0)
goto out;
BUG_ON(ret != 1);
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 2809d11c7a28..0a6faf3d9960 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -265,7 +265,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
* get_user_pages_fast() - pin user pages in memory
* @start: starting user address
* @nr_pages: number of pages from start to pin
- * @write: whether pages will be written to
+ * @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
@@ -277,22 +277,22 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
* requested. If nr_pages is 0 or negative, returns 0. If no pages
* were pinned, returns -errno.
*/
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages)
+int get_user_pages_fast(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages)
{
int nr, ret;
might_sleep();
start &= PAGE_MASK;
- nr = __get_user_pages_fast(start, nr_pages, write, pages);
+ nr = __get_user_pages_fast(start, nr_pages, gup_flags & FOLL_WRITE,
+ pages);
if (nr == nr_pages)
return nr;
/* Try to get the remaining pages with get_user_pages */
start += nr << PAGE_SHIFT;
pages += nr;
- ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
- write ? FOLL_WRITE : 0);
+ ret = get_user_pages_unlocked(start, nr_pages - nr, pages, gup_flags);
/* Have to be a bit careful with return values */
if (nr > 0)
ret = (ret < 0) ? nr : ret + nr;
diff --git a/arch/sh/mm/gup.c b/arch/sh/mm/gup.c
index 3e27f6d1f1ec..277c882f7489 100644
--- a/arch/sh/mm/gup.c
+++ b/arch/sh/mm/gup.c
@@ -204,7 +204,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
* get_user_pages_fast() - pin user pages in memory
* @start: starting user address
* @nr_pages: number of pages from start to pin
- * @write: whether pages will be written to
+ * @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
@@ -216,8 +216,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
* requested. If nr_pages is 0 or negative, returns 0. If no pages
* were pinned, returns -errno.
*/
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages)
+int get_user_pages_fast(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages)
{
struct mm_struct *mm = current->mm;
unsigned long addr, len, end;
@@ -241,7 +241,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
next = pgd_addr_end(addr, end);
if (pgd_none(pgd))
goto slow;
- if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+ if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE,
+ pages, &nr))
goto slow;
} while (pgdp++, addr = next, addr != end);
local_irq_enable();
@@ -261,7 +262,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
ret = get_user_pages_unlocked(start,
(end - start) >> PAGE_SHIFT, pages,
- write ? FOLL_WRITE : 0);
+ gup_flags);
/* Have to be a bit careful with return values */
if (nr > 0) {
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index aee6dba83d0e..1e770a517d4a 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -245,8 +245,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
return nr;
}
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages)
+int get_user_pages_fast(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages)
{
struct mm_struct *mm = current->mm;
unsigned long addr, len, end;
@@ -303,7 +303,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
next = pgd_addr_end(addr, end);
if (pgd_none(pgd))
goto slow;
- if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+ if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE,
+ pages, &nr))
goto slow;
} while (pgdp++, addr = next, addr != end);
@@ -324,7 +325,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
ret = get_user_pages_unlocked(start,
(end - start) >> PAGE_SHIFT, pages,
- write ? FOLL_WRITE : 0);
+ gup_flags);
/* Have to be a bit careful with return values */
if (nr > 0) {
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 6bdca39829bc..08715034e315 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -140,7 +140,7 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
pt_element_t *table;
struct page *page;
- npages = get_user_pages_fast((unsigned long)ptep_user, 1, 1, &page);
+ npages = get_user_pages_fast((unsigned long)ptep_user, 1, FOLL_WRITE, &page);
/* Check if the user is doing something meaningless. */
if (unlikely(npages != 1))
return -EFAULT;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index b5b128a0a051..9d8c8d108d55 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1804,7 +1804,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
return NULL;
/* Pin the user virtual address. */
- npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages);
+ npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages);
if (npinned != npages) {
pr_err("SEV: Failure locking %lu pages.\n", npages);
goto err;
diff --git a/drivers/fpga/dfl-afu-dma-region.c b/drivers/fpga/dfl-afu-dma-region.c
index e18a786fc943..c438722bf4e1 100644
--- a/drivers/fpga/dfl-afu-dma-region.c
+++ b/drivers/fpga/dfl-afu-dma-region.c
@@ -102,7 +102,7 @@ static int afu_dma_pin_pages(struct dfl_feature_platform_data *pdata,
goto unlock_vm;
}
- pinned = get_user_pages_fast(region->user_addr, npages, 1,
+ pinned = get_user_pages_fast(region->user_addr, npages, FOLL_WRITE,
region->pages);
if (pinned < 0) {
ret = pinned;
diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c
index 8bf3a7c23ed3..062067438f1d 100644
--- a/drivers/gpu/drm/via/via_dmablit.c
+++ b/drivers/gpu/drm/via/via_dmablit.c
@@ -243,7 +243,8 @@ via_lock_all_dma_pages(drm_via_sg_info_t *vsg, drm_via_dmablit_t *xfer)
if (NULL == vsg->pages)
return -ENOMEM;
ret = get_user_pages_fast((unsigned long)xfer->mem_addr,
- vsg->num_pages, vsg->direction == DMA_FROM_DEVICE,
+ vsg->num_pages,
+ vsg->direction == DMA_FROM_DEVICE ? FOLL_WRITE : 0,
vsg->pages);
if (ret != vsg->num_pages) {
if (ret < 0)
diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c
index 24b592c6522e..78ccacaf97d0 100644
--- a/drivers/infiniband/hw/hfi1/user_pages.c
+++ b/drivers/infiniband/hw/hfi1/user_pages.c
@@ -105,7 +105,8 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
{
int ret;
- ret = get_user_pages_fast(vaddr, npages, writable, pages);
+ ret = get_user_pages_fast(vaddr, npages, writable ? FOLL_WRITE : 0,
+ pages);
if (ret < 0)
return ret;
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index 25265fd0fd6e..89cff9d1012b 100644
--- a/drivers/misc/genwqe/card_utils.c
+++ b/drivers/misc/genwqe/card_utils.c
@@ -603,7 +603,7 @@ int genwqe_user_vmap(struct genwqe_dev *cd, struct dma_mapping *m, void *uaddr,
/* pin user pages in memory */
rc = get_user_pages_fast(data & PAGE_MASK, /* page aligned addr */
m->nr_pages,
- m->write, /* readable/writable */
+ m->write ? FOLL_WRITE : 0, /* readable/writable */
m->page_list); /* ptrs to pages */
if (rc < 0)
goto fail_get_user_pages;
diff --git a/drivers/misc/vmw_vmci/vmci_host.c b/drivers/misc/vmw_vmci/vmci_host.c
index 997f92543dd4..422d08da3244 100644
--- a/drivers/misc/vmw_vmci/vmci_host.c
+++ b/drivers/misc/vmw_vmci/vmci_host.c
@@ -242,7 +242,7 @@ static int vmci_host_setup_notify(struct vmci_ctx *context,
/*
* Lock physical page backing a given user VA.
*/
- retval = get_user_pages_fast(uva, 1, 1, &context->notify_page);
+ retval = get_user_pages_fast(uva, 1, FOLL_WRITE, &context->notify_page);
if (retval != 1) {
context->notify_page = NULL;
return VMCI_ERROR_GENERIC;
diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c
index f5f1aac9d163..1174735f003d 100644
--- a/drivers/misc/vmw_vmci/vmci_queue_pair.c
+++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c
@@ -659,7 +659,8 @@ static int qp_host_get_user_memory(u64 produce_uva,
int err = VMCI_SUCCESS;
retval = get_user_pages_fast((uintptr_t) produce_uva,
- produce_q->kernel_if->num_pages, 1,
+ produce_q->kernel_if->num_pages,
+ FOLL_WRITE,
produce_q->kernel_if->u.h.header_page);
if (retval < (int)produce_q->kernel_if->num_pages) {
pr_debug("get_user_pages_fast(produce) failed (retval=%d)",
@@ -671,7 +672,8 @@ static int qp_host_get_user_memory(u64 produce_uva,
}
retval = get_user_pages_fast((uintptr_t) consume_uva,
- consume_q->kernel_if->num_pages, 1,
+ consume_q->kernel_if->num_pages,
+ FOLL_WRITE,
consume_q->kernel_if->u.h.header_page);
if (retval < (int)consume_q->kernel_if->num_pages) {
pr_debug("get_user_pages_fast(consume) failed (retval=%d)",
diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c
index 321bc673c417..cef0133aa47a 100644
--- a/drivers/platform/goldfish/goldfish_pipe.c
+++ b/drivers/platform/goldfish/goldfish_pipe.c
@@ -274,7 +274,8 @@ static int pin_user_pages(unsigned long first_page,
*iter_last_page_size = last_page_size;
}
- ret = get_user_pages_fast(first_page, requested_pages, !is_write,
+ ret = get_user_pages_fast(first_page, requested_pages,
+ !is_write ? FOLL_WRITE : 0,
pages);
if (ret <= 0)
return -EFAULT;
diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 1e1f42e210a0..4a4a75fa26d5 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -868,7 +868,9 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode,
pinned = get_user_pages_fast(
(unsigned long)xfer->loc_addr & PAGE_MASK,
- nr_pages, dir == DMA_FROM_DEVICE, page_list);
+ nr_pages,
+ dir == DMA_FROM_DEVICE ? FOLL_WRITE : 0,
+ page_list);
if (pinned != nr_pages) {
if (pinned < 0) {
diff --git a/drivers/sbus/char/oradax.c b/drivers/sbus/char/oradax.c
index 6516bc3cb58b..790aa148670d 100644
--- a/drivers/sbus/char/oradax.c
+++ b/drivers/sbus/char/oradax.c
@@ -437,7 +437,7 @@ static int dax_lock_page(void *va, struct page **p)
dax_dbg("uva %p", va);
- ret = get_user_pages_fast((unsigned long)va, 1, 1, p);
+ ret = get_user_pages_fast((unsigned long)va, 1, FOLL_WRITE, p);
if (ret == 1) {
dax_dbg("locked page %p, for VA %p", *p, va);
return 0;
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 19c022e66d63..3c6a18ad9a87 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -4922,7 +4922,8 @@ static int sgl_map_user_pages(struct st_buffer *STbp,
/* Try to fault in all of the necessary pages */
/* rw==READ means read from drive, write into memory area */
- res = get_user_pages_fast(uaddr, nr_pages, rw == READ, pages);
+ res = get_user_pages_fast(uaddr, nr_pages, rw == READ ? FOLL_WRITE : 0,
+ pages);
/* Errors and no page mapped should return here */
if (res < nr_pages)
diff --git a/drivers/staging/gasket/gasket_page_table.c b/drivers/staging/gasket/gasket_page_table.c
index 26755d9ca41d..f67fdf1d3817 100644
--- a/drivers/staging/gasket/gasket_page_table.c
+++ b/drivers/staging/gasket/gasket_page_table.c
@@ -486,8 +486,8 @@ static int gasket_perform_mapping(struct gasket_page_table *pg_tbl,
ptes[i].dma_addr = pg_tbl->coherent_pages[0].paddr +
off + i * PAGE_SIZE;
} else {
- ret = get_user_pages_fast(page_addr - offset, 1, 1,
- &page);
+ ret = get_user_pages_fast(page_addr - offset, 1,
+ FOLL_WRITE, &page);
if (ret <= 0) {
dev_err(pg_tbl->device,
diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index 0b9ab1d0dd45..49fd7312e2aa 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -273,7 +273,7 @@ struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr,
goto err;
}
- rc = get_user_pages_fast(start, num_pages, 1, shm->pages);
+ rc = get_user_pages_fast(start, num_pages, FOLL_WRITE, shm->pages);
if (rc > 0)
shm->num_pages = rc;
if (rc != num_pages) {
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 8dbb270998f4..089c59c50d97 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -532,7 +532,8 @@ static int tce_iommu_use_page(unsigned long tce, unsigned long *hpa)
enum dma_data_direction direction = iommu_tce_direction(tce);
if (get_user_pages_fast(tce & PAGE_MASK, 1,
- direction != DMA_TO_DEVICE, &page) != 1)
+ direction != DMA_TO_DEVICE ? FOLL_WRITE : 0,
+ &page) != 1)
return -EFAULT;
*hpa = __pa((unsigned long) page_address(page));
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index a2e5dc7716e2..2da5969bccb9 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1700,7 +1700,7 @@ static int set_bit_to_user(int nr, void __user *addr)
int bit = nr + (log % PAGE_SIZE) * 8;
int r;
- r = get_user_pages_fast(log, 1, 1, &page);
+ r = get_user_pages_fast(log, 1, FOLL_WRITE, &page);
if (r < 0)
return r;
BUG_ON(r != 1);
diff --git a/drivers/video/fbdev/pvr2fb.c b/drivers/video/fbdev/pvr2fb.c
index 8a53d1de611d..41390c8e0f67 100644
--- a/drivers/video/fbdev/pvr2fb.c
+++ b/drivers/video/fbdev/pvr2fb.c
@@ -686,7 +686,7 @@ static ssize_t pvr2fb_write(struct fb_info *info, const char *buf,
if (!pages)
return -ENOMEM;
- ret = get_user_pages_fast((unsigned long)buf, nr_pages, true, pages);
+ ret = get_user_pages_fast((unsigned long)buf, nr_pages, FOLL_WRITE, pages);
if (ret < nr_pages) {
nr_pages = ret;
ret = -EINVAL;
diff --git a/drivers/virt/fsl_hypervisor.c b/drivers/virt/fsl_hypervisor.c
index 8ba726e600e9..6446bcab4185 100644
--- a/drivers/virt/fsl_hypervisor.c
+++ b/drivers/virt/fsl_hypervisor.c
@@ -244,7 +244,7 @@ static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p)
/* Get the physical addresses of the source buffer */
num_pinned = get_user_pages_fast(param.local_vaddr - lb_offset,
- num_pages, param.source != -1, pages);
+ num_pages, param.source != -1 ? FOLL_WRITE : 0, pages);
if (num_pinned != num_pages) {
/* get_user_pages() failed */
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 7cf9c51318aa..02bc815982d4 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -852,7 +852,7 @@ static int gntdev_get_page(struct gntdev_copy_batch *batch, void __user *virt,
unsigned long xen_pfn;
int ret;
- ret = get_user_pages_fast(addr, 1, writeable, &page);
+ ret = get_user_pages_fast(addr, 1, writeable ? FOLL_WRITE : 0, &page);
if (ret < 0)
return ret;
diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c
index 443bcd8c3c19..5a7c4fda682f 100644
--- a/fs/orangefs/orangefs-bufmap.c
+++ b/fs/orangefs/orangefs-bufmap.c
@@ -269,7 +269,7 @@ orangefs_bufmap_map(struct orangefs_bufmap *bufmap,
/* map the pages */
ret = get_user_pages_fast((unsigned long)user_desc->ptr,
- bufmap->page_count, 1, bufmap->page_array);
+ bufmap->page_count, FOLL_WRITE, bufmap->page_array);
if (ret < 0)
return ret;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6831077d126c..6607defbd8cc 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1531,8 +1531,8 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags);
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages);
+int get_user_pages_fast(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages);
/* Container for pinned pfns / pages */
struct frame_vector {
diff --git a/kernel/futex.c b/kernel/futex.c
index c3b73b0311bc..1b9eca04fb0a 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -543,7 +543,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_a
if (unlikely(should_fail_futex(fshared)))
return -EFAULT;
- err = get_user_pages_fast(address, 1, 1, &page);
+ err = get_user_pages_fast(address, 1, FOLL_WRITE, &page);
/*
* If write access is not required (eg. FUTEX_WAIT), try
* and get read-only access.
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index ea36dc355da1..50e77ec427d0 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1293,7 +1293,9 @@ ssize_t iov_iter_get_pages(struct iov_iter *i,
len = maxpages * PAGE_SIZE;
addr &= ~(PAGE_SIZE - 1);
n = DIV_ROUND_UP(len, PAGE_SIZE);
- res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, pages);
+ res = get_user_pages_fast(addr, n,
+ iov_iter_rw(i) != WRITE ? FOLL_WRITE : 0,
+ pages);
if (unlikely(res < 0))
return res;
return (res == n ? len : res * PAGE_SIZE) - *start;
@@ -1374,7 +1376,8 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
p = get_pages_array(n);
if (!p)
return -ENOMEM;
- res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, p);
+ res = get_user_pages_fast(addr, n,
+ iov_iter_rw(i) != WRITE ? FOLL_WRITE : 0, p);
if (unlikely(res < 0)) {
kvfree(p);
return res;
diff --git a/mm/gup.c b/mm/gup.c
index 2b21eeaf8cc8..0684a9536207 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2025,7 +2025,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
* get_user_pages_fast() - pin user pages in memory
* @start: starting user address
* @nr_pages: number of pages from start to pin
- * @write: whether pages will be written to
+ * @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
@@ -2037,8 +2037,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
* requested. If nr_pages is 0 or negative, returns 0. If no pages
* were pinned, returns -errno.
*/
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages)
+int get_user_pages_fast(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages)
{
unsigned long addr, len, end;
int nr = 0, ret = 0;
@@ -2056,7 +2056,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
if (gup_fast_permitted(start, nr_pages)) {
local_irq_disable();
- gup_pgd_range(addr, end, write ? FOLL_WRITE : 0, pages, &nr);
+ gup_pgd_range(addr, end, gup_flags, pages, &nr);
local_irq_enable();
ret = nr;
}
@@ -2067,7 +2067,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
pages += nr;
ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
- write ? FOLL_WRITE : 0);
+ gup_flags);
/* Have to be a bit careful with return values */
if (nr > 0) {
diff --git a/mm/util.c b/mm/util.c
index d559bde497a9..f94a1ac09cd8 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -318,7 +318,7 @@ EXPORT_SYMBOL_GPL(__get_user_pages_fast);
* get_user_pages_fast() - pin user pages in memory
* @start: starting user address
* @nr_pages: number of pages from start to pin
- * @write: whether pages will be written to
+ * @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
@@ -339,10 +339,10 @@ EXPORT_SYMBOL_GPL(__get_user_pages_fast);
* were pinned, returns -errno.
*/
int __weak get_user_pages_fast(unsigned long start,
- int nr_pages, int write, struct page **pages)
+ int nr_pages, unsigned int gup_flags,
+ struct page **pages)
{
- return get_user_pages_unlocked(start, nr_pages, pages,
- write ? FOLL_WRITE : 0);
+ return get_user_pages_unlocked(start, nr_pages, pages, gup_flags);
}
EXPORT_SYMBOL_GPL(get_user_pages_fast);
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index d3736f5bffec..74cafc0142ea 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -27,7 +27,7 @@ struct page **ceph_get_direct_page_vector(const void __user *data,
while (got < num_pages) {
rc = get_user_pages_fast(
(unsigned long)data + ((unsigned long)got * PAGE_SIZE),
- num_pages - got, write_page, pages + got);
+ num_pages - got, write_page ? FOLL_WRITE : 0, pages + got);
if (rc < 0)
break;
BUG_ON(rc == 0);
diff --git a/net/rds/info.c b/net/rds/info.c
index e367a97a18c8..03f6fd56d237 100644
--- a/net/rds/info.c
+++ b/net/rds/info.c
@@ -193,7 +193,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
ret = -ENOMEM;
goto out;
}
- ret = get_user_pages_fast(start, nr_pages, 1, pages);
+ ret = get_user_pages_fast(start, nr_pages, FOLL_WRITE, pages);
if (ret != nr_pages) {
if (ret > 0)
nr_pages = ret;
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 182ab8430594..b340ed4fc43a 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -158,7 +158,8 @@ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages,
{
int ret;
- ret = get_user_pages_fast(user_addr, nr_pages, write, pages);
+ ret = get_user_pages_fast(user_addr, nr_pages, write ? FOLL_WRITE : 0,
+ pages);
if (ret >= 0 && ret < nr_pages) {
while (ret--)
--
2.20.1
^ permalink raw reply related
* [RESEND 2/7] mm/gup: Change write parameter to flags in fast walk
From: ira.weiny @ 2019-03-17 18:34 UTC (permalink / raw)
To: Andrew Morton, John Hubbard, Michal Hocko, Kirill A. Shutemov,
Peter Zijlstra, Jason Gunthorpe, Benjamin Herrenschmidt,
Paul Mackerras, David S. Miller, Martin Schwidefsky,
Heiko Carstens, Rich Felker, Yoshinori Sato, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Ralf Baechle, James Hogan
Cc: linux-s390, linux-sh, linux-rdma, Ira Weiny, linux-kernel,
linux-mips, linux-mm, netdev, sparclinux, linuxppc-dev
In-Reply-To: <20190317183438.2057-1-ira.weiny@intel.com>
From: Ira Weiny <ira.weiny@intel.com>
In order to support more options in the GUP fast walk, change
the write parameter to flags throughout the call stack.
This patch does not change functionality and passes FOLL_WRITE
where write was previously used.
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
mm/gup.c | 52 ++++++++++++++++++++++++++--------------------------
1 file changed, 26 insertions(+), 26 deletions(-)
diff --git a/mm/gup.c b/mm/gup.c
index 8cb4cff067bc..2b21eeaf8cc8 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1578,7 +1578,7 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+ unsigned int flags, struct page **pages, int *nr)
{
struct dev_pagemap *pgmap = NULL;
int nr_start = *nr, ret = 0;
@@ -1596,7 +1596,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
if (pte_protnone(pte))
goto pte_unmap;
- if (!pte_access_permitted(pte, write))
+ if (!pte_access_permitted(pte, flags & FOLL_WRITE))
goto pte_unmap;
if (pte_devmap(pte)) {
@@ -1648,7 +1648,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
* useful to have gup_huge_pmd even if we can't operate on ptes.
*/
static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+ unsigned int flags, struct page **pages, int *nr)
{
return 0;
}
@@ -1731,12 +1731,12 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
#endif
static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
+ unsigned long end, unsigned int flags, struct page **pages, int *nr)
{
struct page *head, *page;
int refs;
- if (!pmd_access_permitted(orig, write))
+ if (!pmd_access_permitted(orig, flags & FOLL_WRITE))
return 0;
if (pmd_devmap(orig))
@@ -1769,12 +1769,12 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
}
static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
+ unsigned long end, unsigned int flags, struct page **pages, int *nr)
{
struct page *head, *page;
int refs;
- if (!pud_access_permitted(orig, write))
+ if (!pud_access_permitted(orig, flags & FOLL_WRITE))
return 0;
if (pud_devmap(orig))
@@ -1807,13 +1807,13 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
}
static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
- unsigned long end, int write,
+ unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
int refs;
struct page *head, *page;
- if (!pgd_access_permitted(orig, write))
+ if (!pgd_access_permitted(orig, flags & FOLL_WRITE))
return 0;
BUILD_BUG_ON(pgd_devmap(orig));
@@ -1844,7 +1844,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
}
static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+ unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pmd_t *pmdp;
@@ -1867,7 +1867,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
if (pmd_protnone(pmd))
return 0;
- if (!gup_huge_pmd(pmd, pmdp, addr, next, write,
+ if (!gup_huge_pmd(pmd, pmdp, addr, next, flags,
pages, nr))
return 0;
@@ -1877,9 +1877,9 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
* pmd format and THP pmd format
*/
if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr,
- PMD_SHIFT, next, write, pages, nr))
+ PMD_SHIFT, next, flags, pages, nr))
return 0;
- } else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
+ } else if (!gup_pte_range(pmd, addr, next, flags, pages, nr))
return 0;
} while (pmdp++, addr = next, addr != end);
@@ -1887,7 +1887,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
}
static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+ unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pud_t *pudp;
@@ -1900,14 +1900,14 @@ static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
if (pud_none(pud))
return 0;
if (unlikely(pud_huge(pud))) {
- if (!gup_huge_pud(pud, pudp, addr, next, write,
+ if (!gup_huge_pud(pud, pudp, addr, next, flags,
pages, nr))
return 0;
} else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) {
if (!gup_huge_pd(__hugepd(pud_val(pud)), addr,
- PUD_SHIFT, next, write, pages, nr))
+ PUD_SHIFT, next, flags, pages, nr))
return 0;
- } else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
+ } else if (!gup_pmd_range(pud, addr, next, flags, pages, nr))
return 0;
} while (pudp++, addr = next, addr != end);
@@ -1915,7 +1915,7 @@ static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
}
static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+ unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
p4d_t *p4dp;
@@ -1930,9 +1930,9 @@ static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
BUILD_BUG_ON(p4d_huge(p4d));
if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) {
if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr,
- P4D_SHIFT, next, write, pages, nr))
+ P4D_SHIFT, next, flags, pages, nr))
return 0;
- } else if (!gup_pud_range(p4d, addr, next, write, pages, nr))
+ } else if (!gup_pud_range(p4d, addr, next, flags, pages, nr))
return 0;
} while (p4dp++, addr = next, addr != end);
@@ -1940,7 +1940,7 @@ static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
}
static void gup_pgd_range(unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+ unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pgd_t *pgdp;
@@ -1953,14 +1953,14 @@ static void gup_pgd_range(unsigned long addr, unsigned long end,
if (pgd_none(pgd))
return;
if (unlikely(pgd_huge(pgd))) {
- if (!gup_huge_pgd(pgd, pgdp, addr, next, write,
+ if (!gup_huge_pgd(pgd, pgdp, addr, next, flags,
pages, nr))
return;
} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
- PGDIR_SHIFT, next, write, pages, nr))
+ PGDIR_SHIFT, next, flags, pages, nr))
return;
- } else if (!gup_p4d_range(pgd, addr, next, write, pages, nr))
+ } else if (!gup_p4d_range(pgd, addr, next, flags, pages, nr))
return;
} while (pgdp++, addr = next, addr != end);
}
@@ -2014,7 +2014,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
if (gup_fast_permitted(start, nr_pages)) {
local_irq_save(flags);
- gup_pgd_range(start, end, write, pages, &nr);
+ gup_pgd_range(start, end, write ? FOLL_WRITE : 0, pages, &nr);
local_irq_restore(flags);
}
@@ -2056,7 +2056,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
if (gup_fast_permitted(start, nr_pages)) {
local_irq_disable();
- gup_pgd_range(addr, end, write, pages, &nr);
+ gup_pgd_range(addr, end, write ? FOLL_WRITE : 0, pages, &nr);
local_irq_enable();
ret = nr;
}
--
2.20.1
^ permalink raw reply related
* [RESEND 1/7] mm/gup: Replace get_user_pages_longterm() with FOLL_LONGTERM
From: ira.weiny @ 2019-03-17 18:34 UTC (permalink / raw)
To: Andrew Morton, John Hubbard, Michal Hocko, Kirill A. Shutemov,
Peter Zijlstra, Jason Gunthorpe, Benjamin Herrenschmidt,
Paul Mackerras, David S. Miller, Martin Schwidefsky,
Heiko Carstens, Rich Felker, Yoshinori Sato, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Ralf Baechle, James Hogan
Cc: linux-s390, linux-sh, linux-rdma, Aneesh Kumar K . V,
linuxppc-dev, linux-mips, linux-kernel, linux-mm, netdev,
sparclinux, Michal Hocko, Ira Weiny
In-Reply-To: <20190317183438.2057-1-ira.weiny@intel.com>
From: Ira Weiny <ira.weiny@intel.com>
Rather than have a separate get_user_pages_longterm() call,
introduce FOLL_LONGTERM and change the longterm callers to use
it.
This patch does not change any functionality.
FOLL_LONGTERM can only be supported with get_user_pages() as it
requires vmas to determine if DAX is in use.
CC: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
Changes from V1:
Rebased on 5.1 merge
Adjusted for changes introduced by CONFIG_CMA
Convert new users of GUP longterm
io_uring.c
xdp_umem.c
arch/powerpc/mm/mmu_context_iommu.c | 3 +-
drivers/infiniband/core/umem.c | 5 +-
drivers/infiniband/hw/qib/qib_user_pages.c | 8 +-
drivers/infiniband/hw/usnic/usnic_uiom.c | 9 +-
drivers/media/v4l2-core/videobuf-dma-sg.c | 6 +-
drivers/vfio/vfio_iommu_type1.c | 3 +-
fs/io_uring.c | 5 +-
include/linux/mm.h | 14 +-
mm/gup.c | 171 ++++++++++++---------
mm/gup_benchmark.c | 5 +-
net/xdp/xdp_umem.c | 4 +-
11 files changed, 129 insertions(+), 104 deletions(-)
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index e7a9c4f6bfca..2bd48998765e 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -148,7 +148,8 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
}
down_read(&mm->mmap_sem);
- ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL);
+ ret = get_user_pages(ua, entries, FOLL_WRITE | FOLL_LONGTERM,
+ mem->hpages, NULL);
up_read(&mm->mmap_sem);
if (ret != entries) {
/* free the reference taken */
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index fe5551562dbc..31191f098e73 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -189,10 +189,11 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
while (npages) {
down_read(&mm->mmap_sem);
- ret = get_user_pages_longterm(cur_base,
+ ret = get_user_pages(cur_base,
min_t(unsigned long, npages,
PAGE_SIZE / sizeof (struct page *)),
- gup_flags, page_list, vma_list);
+ gup_flags | FOLL_LONGTERM,
+ page_list, vma_list);
if (ret < 0) {
up_read(&mm->mmap_sem);
goto umem_release;
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index 123ca8f64f75..f712fb7fa82f 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -114,10 +114,10 @@ int qib_get_user_pages(unsigned long start_page, size_t num_pages,
down_read(¤t->mm->mmap_sem);
for (got = 0; got < num_pages; got += ret) {
- ret = get_user_pages_longterm(start_page + got * PAGE_SIZE,
- num_pages - got,
- FOLL_WRITE | FOLL_FORCE,
- p + got, NULL);
+ ret = get_user_pages(start_page + got * PAGE_SIZE,
+ num_pages - got,
+ FOLL_LONGTERM | FOLL_WRITE | FOLL_FORCE,
+ p + got, NULL);
if (ret < 0) {
up_read(¤t->mm->mmap_sem);
goto bail_release;
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 06862a6af185..1d9a182ac163 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -143,10 +143,11 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
ret = 0;
while (npages) {
- ret = get_user_pages_longterm(cur_base,
- min_t(unsigned long, npages,
- PAGE_SIZE / sizeof(struct page *)),
- gup_flags, page_list, NULL);
+ ret = get_user_pages(cur_base,
+ min_t(unsigned long, npages,
+ PAGE_SIZE / sizeof(struct page *)),
+ gup_flags | FOLL_LONGTERM,
+ page_list, NULL);
if (ret < 0)
goto out;
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index 08929c087e27..870a2a526e0b 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -186,12 +186,12 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
dprintk(1, "init user [0x%lx+0x%lx => %d pages]\n",
data, size, dma->nr_pages);
- err = get_user_pages_longterm(data & PAGE_MASK, dma->nr_pages,
- flags, dma->pages, NULL);
+ err = get_user_pages(data & PAGE_MASK, dma->nr_pages,
+ flags | FOLL_LONGTERM, dma->pages, NULL);
if (err != dma->nr_pages) {
dma->nr_pages = (err >= 0) ? err : 0;
- dprintk(1, "get_user_pages_longterm: err=%d [%d]\n", err,
+ dprintk(1, "get_user_pages: err=%d [%d]\n", err,
dma->nr_pages);
return err < 0 ? err : -EINVAL;
}
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 73652e21efec..1500bd0bb6da 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -351,7 +351,8 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
down_read(&mm->mmap_sem);
if (mm == current->mm) {
- ret = get_user_pages_longterm(vaddr, 1, flags, page, vmas);
+ ret = get_user_pages(vaddr, 1, flags | FOLL_LONGTERM, page,
+ vmas);
} else {
ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
vmas, NULL);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index e2bd77da5e21..8d61b81373bd 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2450,8 +2450,9 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
ret = 0;
down_read(¤t->mm->mmap_sem);
- pret = get_user_pages_longterm(ubuf, nr_pages, FOLL_WRITE,
- pages, vmas);
+ pret = get_user_pages(ubuf, nr_pages,
+ FOLL_WRITE | FOLL_LONGTERM,
+ pages, vmas);
if (pret == nr_pages) {
/* don't support file backed memory */
for (j = 0; j < nr_pages; j++) {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2d483dbdffc0..6831077d126c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1531,19 +1531,6 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags);
-#if defined(CONFIG_FS_DAX) || defined(CONFIG_CMA)
-long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- struct vm_area_struct **vmas);
-#else
-static inline long get_user_pages_longterm(unsigned long start,
- unsigned long nr_pages, unsigned int gup_flags,
- struct page **pages, struct vm_area_struct **vmas)
-{
- return get_user_pages(start, nr_pages, gup_flags, pages, vmas);
-}
-#endif /* CONFIG_FS_DAX */
-
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages);
@@ -2609,6 +2596,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */
#define FOLL_COW 0x4000 /* internal GUP flag */
#define FOLL_ANON 0x8000 /* don't do file mappings */
+#define FOLL_LONGTERM 0x10000 /* mapping is intended for a long term pin */
static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
{
diff --git a/mm/gup.c b/mm/gup.c
index f84e22685aaa..8cb4cff067bc 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1112,26 +1112,7 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
}
EXPORT_SYMBOL(get_user_pages_remote);
-/*
- * This is the same as get_user_pages_remote(), just with a
- * less-flexible calling convention where we assume that the task
- * and mm being operated on are the current task's and don't allow
- * passing of a locked parameter. We also obviously don't pass
- * FOLL_REMOTE in here.
- */
-long get_user_pages(unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- struct vm_area_struct **vmas)
-{
- return __get_user_pages_locked(current, current->mm, start, nr_pages,
- pages, vmas, NULL,
- gup_flags | FOLL_TOUCH);
-}
-EXPORT_SYMBOL(get_user_pages);
-
#if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA)
-
-#ifdef CONFIG_FS_DAX
static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
{
long i;
@@ -1150,12 +1131,6 @@ static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
}
return false;
}
-#else
-static inline bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
-{
- return false;
-}
-#endif
#ifdef CONFIG_CMA
static struct page *new_non_cma_page(struct page *page, unsigned long private)
@@ -1209,10 +1184,13 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private)
return __alloc_pages_node(nid, gfp_mask, 0);
}
-static long check_and_migrate_cma_pages(unsigned long start, long nr_pages,
- unsigned int gup_flags,
+static long check_and_migrate_cma_pages(struct task_struct *tsk,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long nr_pages,
struct page **pages,
- struct vm_area_struct **vmas)
+ struct vm_area_struct **vmas,
+ unsigned int gup_flags)
{
long i;
bool drain_allow = true;
@@ -1268,10 +1246,14 @@ static long check_and_migrate_cma_pages(unsigned long start, long nr_pages,
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.
+ * We did migrate all the pages, Try to get the page references
+ * again migrating any new CMA pages which we failed to isolate
+ * earlier.
*/
- nr_pages = get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+ nr_pages = __get_user_pages_locked(tsk, mm, start, nr_pages,
+ pages, vmas, NULL,
+ gup_flags);
+
if ((nr_pages > 0) && migrate_allow) {
drain_allow = true;
goto check_again;
@@ -1281,66 +1263,115 @@ static long check_and_migrate_cma_pages(unsigned long start, long nr_pages,
return nr_pages;
}
#else
-static inline long check_and_migrate_cma_pages(unsigned long start, long nr_pages,
- unsigned int gup_flags,
- struct page **pages,
- struct vm_area_struct **vmas)
+static long check_and_migrate_cma_pages(struct task_struct *tsk,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long nr_pages,
+ struct page **pages,
+ struct vm_area_struct **vmas,
+ unsigned int gup_flags)
{
return nr_pages;
}
#endif
/*
- * This is the same as get_user_pages() in that it assumes we are
- * operating on the current task's mm, but it goes further to validate
- * that the vmas associated with the address range are suitable for
- * longterm elevated page reference counts. For example, filesystem-dax
- * mappings are subject to the lifetime enforced by the filesystem and
- * we need guarantees that longterm users like RDMA and V4L2 only
- * establish mappings that have a kernel enforced revocation mechanism.
+ * __gup_longterm_locked() is a wrapper for __get_uer_pages_locked which
+ * allows us to process the FOLL_LONGTERM flag if present.
+ *
+ * FOLL_LONGTERM Checks for either DAX VMAs or PPC CMA regions and either fails
+ * the pin or attempts to migrate the page as appropriate.
+ *
+ * In the filesystem-dax case mappings are subject to the lifetime enforced by
+ * the filesystem and we need guarantees that longterm users like RDMA and V4L2
+ * only establish mappings that have a kernel enforced revocation mechanism.
+ *
+ * In the CMA case pages can't be pinned in a CMA region as this would
+ * unnecessarily fragment that region. So CMA attempts to migrate the page
+ * before pinning.
*
* "longterm" == userspace controlled elevated page count lifetime.
* Contrast this to iov_iter_get_pages() usages which are transient.
*/
-long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- struct vm_area_struct **vmas_arg)
+static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long nr_pages,
+ struct page **pages,
+ struct vm_area_struct **vmas,
+ unsigned int gup_flags)
{
- struct vm_area_struct **vmas = vmas_arg;
- unsigned long flags;
+ struct vm_area_struct **vmas_tmp = vmas;
+ unsigned long flags = 0;
long rc, i;
- if (!pages)
- return -EINVAL;
-
- if (!vmas) {
- vmas = kcalloc(nr_pages, sizeof(struct vm_area_struct *),
- GFP_KERNEL);
- if (!vmas)
- return -ENOMEM;
+ if (gup_flags & FOLL_LONGTERM) {
+ if (!pages)
+ return -EINVAL;
+
+ if (!vmas_tmp) {
+ vmas_tmp = kcalloc(nr_pages,
+ sizeof(struct vm_area_struct *),
+ GFP_KERNEL);
+ if (!vmas_tmp)
+ return -ENOMEM;
+ }
+ flags = memalloc_nocma_save();
}
- flags = memalloc_nocma_save();
- rc = get_user_pages(start, nr_pages, gup_flags, pages, vmas);
- memalloc_nocma_restore(flags);
- if (rc < 0)
- goto out;
+ rc = __get_user_pages_locked(tsk, mm, start, nr_pages, pages,
+ vmas_tmp, NULL, gup_flags);
- if (check_dax_vmas(vmas, rc)) {
- for (i = 0; i < rc; i++)
- put_page(pages[i]);
- rc = -EOPNOTSUPP;
- goto out;
+ if (gup_flags & FOLL_LONGTERM) {
+ memalloc_nocma_restore(flags);
+ if (rc < 0)
+ goto out;
+
+ if (check_dax_vmas(vmas_tmp, rc)) {
+ for (i = 0; i < rc; i++)
+ put_page(pages[i]);
+ rc = -EOPNOTSUPP;
+ goto out;
+ }
+
+ rc = check_and_migrate_cma_pages(tsk, mm, start, rc, pages,
+ vmas_tmp, gup_flags);
}
- rc = check_and_migrate_cma_pages(start, rc, gup_flags, pages, vmas);
out:
- if (vmas != vmas_arg)
- kfree(vmas);
+ if (vmas_tmp != vmas)
+ kfree(vmas_tmp);
return rc;
}
-EXPORT_SYMBOL(get_user_pages_longterm);
-#endif /* CONFIG_FS_DAX */
+#else /* !CONFIG_FS_DAX && !CONFIG_CMA */
+static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long nr_pages,
+ struct page **pages,
+ struct vm_area_struct **vmas,
+ unsigned int flags)
+{
+ return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
+ NULL, flags);
+}
+#endif /* CONFIG_FS_DAX || CONFIG_CMA */
+
+/*
+ * This is the same as get_user_pages_remote(), just with a
+ * less-flexible calling convention where we assume that the task
+ * and mm being operated on are the current task's and don't allow
+ * passing of a locked parameter. We also obviously don't pass
+ * FOLL_REMOTE in here.
+ */
+long get_user_pages(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas)
+{
+ return __gup_longterm_locked(current, current->mm, start, nr_pages,
+ pages, vmas, gup_flags | FOLL_TOUCH);
+}
+EXPORT_SYMBOL(get_user_pages);
/**
* populate_vma_page_range() - populate a range of pages in the vma.
diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index 6c0279e70cc4..7dd602d7f8db 100644
--- a/mm/gup_benchmark.c
+++ b/mm/gup_benchmark.c
@@ -54,8 +54,9 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
pages + i);
break;
case GUP_LONGTERM_BENCHMARK:
- nr = get_user_pages_longterm(addr, nr, gup->flags & 1,
- pages + i, NULL);
+ nr = get_user_pages(addr, nr,
+ (gup->flags & 1) | FOLL_LONGTERM,
+ pages + i, NULL);
break;
case GUP_BENCHMARK:
nr = get_user_pages(addr, nr, gup->flags & 1, pages + i,
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 77520eacee8f..ab489454a63e 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -267,8 +267,8 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem)
return -ENOMEM;
down_read(¤t->mm->mmap_sem);
- npgs = get_user_pages_longterm(umem->address, umem->npgs,
- gup_flags, &umem->pgs[0], NULL);
+ npgs = get_user_pages(umem->address, umem->npgs,
+ gup_flags | FOLL_LONGTERM, &umem->pgs[0], NULL);
up_read(¤t->mm->mmap_sem);
if (npgs != umem->npgs) {
--
2.20.1
^ permalink raw reply related
* [RESEND PATCH 0/7] Add FOLL_LONGTERM to GUP fast and use it
From: ira.weiny @ 2019-03-17 18:34 UTC (permalink / raw)
To: Andrew Morton, John Hubbard, Michal Hocko, Kirill A. Shutemov,
Peter Zijlstra, Jason Gunthorpe, Benjamin Herrenschmidt,
Paul Mackerras, David S. Miller, Martin Schwidefsky,
Heiko Carstens, Rich Felker, Yoshinori Sato, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Ralf Baechle, James Hogan
Cc: linux-s390, linux-sh, linux-rdma, Ira Weiny, linux-kernel,
linux-mips, linux-mm, netdev, sparclinux, linuxppc-dev
From: Ira Weiny <ira.weiny@intel.com>
Resending after rebasing to the latest mm tree.
HFI1, qib, and mthca, use get_user_pages_fast() due to it performance
advantages. These pages can be held for a significant time. But
get_user_pages_fast() does not protect against mapping FS DAX pages.
Introduce FOLL_LONGTERM and use this flag in get_user_pages_fast() which
retains the performance while also adding the FS DAX checks. XDP has also
shown interest in using this functionality.[1]
In addition we change get_user_pages() to use the new FOLL_LONGTERM flag and
remove the specialized get_user_pages_longterm call.
[1] https://lkml.org/lkml/2019/2/11/1789
Ira Weiny (7):
mm/gup: Replace get_user_pages_longterm() with FOLL_LONGTERM
mm/gup: Change write parameter to flags in fast walk
mm/gup: Change GUP fast to use flags rather than a write 'bool'
mm/gup: Add FOLL_LONGTERM capability to GUP fast
IB/hfi1: Use the new FOLL_LONGTERM flag to get_user_pages_fast()
IB/qib: Use the new FOLL_LONGTERM flag to get_user_pages_fast()
IB/mthca: Use the new FOLL_LONGTERM flag to get_user_pages_fast()
arch/mips/mm/gup.c | 11 +-
arch/powerpc/kvm/book3s_64_mmu_hv.c | 4 +-
arch/powerpc/kvm/e500_mmu.c | 2 +-
arch/powerpc/mm/mmu_context_iommu.c | 3 +-
arch/s390/kvm/interrupt.c | 2 +-
arch/s390/mm/gup.c | 12 +-
arch/sh/mm/gup.c | 11 +-
arch/sparc/mm/gup.c | 9 +-
arch/x86/kvm/paging_tmpl.h | 2 +-
arch/x86/kvm/svm.c | 2 +-
drivers/fpga/dfl-afu-dma-region.c | 2 +-
drivers/gpu/drm/via/via_dmablit.c | 3 +-
drivers/infiniband/core/umem.c | 5 +-
drivers/infiniband/hw/hfi1/user_pages.c | 5 +-
drivers/infiniband/hw/mthca/mthca_memfree.c | 3 +-
drivers/infiniband/hw/qib/qib_user_pages.c | 8 +-
drivers/infiniband/hw/qib/qib_user_sdma.c | 2 +-
drivers/infiniband/hw/usnic/usnic_uiom.c | 9 +-
drivers/media/v4l2-core/videobuf-dma-sg.c | 6 +-
drivers/misc/genwqe/card_utils.c | 2 +-
drivers/misc/vmw_vmci/vmci_host.c | 2 +-
drivers/misc/vmw_vmci/vmci_queue_pair.c | 6 +-
drivers/platform/goldfish/goldfish_pipe.c | 3 +-
drivers/rapidio/devices/rio_mport_cdev.c | 4 +-
drivers/sbus/char/oradax.c | 2 +-
drivers/scsi/st.c | 3 +-
drivers/staging/gasket/gasket_page_table.c | 4 +-
drivers/tee/tee_shm.c | 2 +-
drivers/vfio/vfio_iommu_spapr_tce.c | 3 +-
drivers/vfio/vfio_iommu_type1.c | 3 +-
drivers/vhost/vhost.c | 2 +-
drivers/video/fbdev/pvr2fb.c | 2 +-
drivers/virt/fsl_hypervisor.c | 2 +-
drivers/xen/gntdev.c | 2 +-
fs/io_uring.c | 5 +-
fs/orangefs/orangefs-bufmap.c | 2 +-
include/linux/mm.h | 18 +-
kernel/futex.c | 2 +-
lib/iov_iter.c | 7 +-
mm/gup.c | 258 ++++++++++++--------
mm/gup_benchmark.c | 5 +-
mm/util.c | 8 +-
net/ceph/pagevec.c | 2 +-
net/rds/info.c | 2 +-
net/rds/rdma.c | 3 +-
net/xdp/xdp_umem.c | 4 +-
46 files changed, 262 insertions(+), 197 deletions(-)
--
2.20.1
^ permalink raw reply
* Re: [PATCH v3 04/17] KVM: PPC: Book3S HV: XIVE: add a control to initialize a source
From: David Gibson @ 2019-03-18 1:38 UTC (permalink / raw)
To: Cédric Le Goater; +Cc: linuxppc-dev, Paul Mackerras, kvm, kvm-ppc
In-Reply-To: <20190315120609.25910-5-clg@kaod.org>
[-- Attachment #1: Type: text/plain, Size: 10180 bytes --]
On Fri, Mar 15, 2019 at 01:05:56PM +0100, Cédric Le Goater wrote:
> The XIVE KVM device maintains a list of interrupt sources for the VM
> which are allocated in the pool of generic interrupts (IPIs) of the
> main XIVE IC controller. These are used for the CPU IPIs as well as
> for virtual device interrupts. The IRQ number space is defined by
> QEMU.
>
> The XIVE device reuses the source structures of the XICS-on-XIVE
> device for the source blocks (2-level tree) and for the source
> interrupts. Under XIVE native, the source interrupt caches mostly
> configuration information and is less used than under the XICS-on-XIVE
> device in which hcalls are still necessary at run-time.
>
> When a source is initialized in KVM, an IPI interrupt source is simply
> allocated at the OPAL level and then MASKED. KVM only needs to know
> about its type: LSI or MSI.
>
> Signed-off-by: Cédric Le Goater <clg@kaod.org>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
> ---
>
> Changes since v2:
>
> - extra documentation in commit log
> - fixed comments on XIVE IRQ number space
> - removed usage of the __x_* macros
> - fixed locking on source block
>
> arch/powerpc/include/uapi/asm/kvm.h | 5 +
> arch/powerpc/kvm/book3s_xive.h | 10 ++
> arch/powerpc/kvm/book3s_xive.c | 8 +-
> arch/powerpc/kvm/book3s_xive_native.c | 106 +++++++++++++++++++++
> Documentation/virtual/kvm/devices/xive.txt | 15 +++
> 5 files changed, 140 insertions(+), 4 deletions(-)
>
> diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
> index b002c0c67787..11985148073f 100644
> --- a/arch/powerpc/include/uapi/asm/kvm.h
> +++ b/arch/powerpc/include/uapi/asm/kvm.h
> @@ -677,5 +677,10 @@ struct kvm_ppc_cpu_char {
>
> /* POWER9 XIVE Native Interrupt Controller */
> #define KVM_DEV_XIVE_GRP_CTRL 1
> +#define KVM_DEV_XIVE_GRP_SOURCE 2 /* 64-bit source identifier */
> +
> +/* Layout of 64-bit XIVE source attribute values */
> +#define KVM_XIVE_LEVEL_SENSITIVE (1ULL << 0)
> +#define KVM_XIVE_LEVEL_ASSERTED (1ULL << 1)
>
> #endif /* __LINUX_KVM_POWERPC_H */
> diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
> index d366df69b9cb..1be921cb5dcb 100644
> --- a/arch/powerpc/kvm/book3s_xive.h
> +++ b/arch/powerpc/kvm/book3s_xive.h
> @@ -12,6 +12,13 @@
> #ifdef CONFIG_KVM_XICS
> #include "book3s_xics.h"
>
> +/*
> + * The XIVE Interrupt source numbers are within the range 0 to
> + * KVMPPC_XICS_NR_IRQS.
> + */
> +#define KVMPPC_XIVE_FIRST_IRQ 0
> +#define KVMPPC_XIVE_NR_IRQS KVMPPC_XICS_NR_IRQS
> +
> /*
> * State for one guest irq source.
> *
> @@ -258,6 +265,9 @@ extern int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
> */
> void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu);
> int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu);
> +struct kvmppc_xive_src_block *kvmppc_xive_create_src_block(
> + struct kvmppc_xive *xive, int irq);
> +void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb);
>
> #endif /* CONFIG_KVM_XICS */
> #endif /* _KVM_PPC_BOOK3S_XICS_H */
> diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
> index e7f1ada1c3de..6c9f9fd0855f 100644
> --- a/arch/powerpc/kvm/book3s_xive.c
> +++ b/arch/powerpc/kvm/book3s_xive.c
> @@ -1480,8 +1480,8 @@ static int xive_get_source(struct kvmppc_xive *xive, long irq, u64 addr)
> return 0;
> }
>
> -static struct kvmppc_xive_src_block *xive_create_src_block(struct kvmppc_xive *xive,
> - int irq)
> +struct kvmppc_xive_src_block *kvmppc_xive_create_src_block(
> + struct kvmppc_xive *xive, int irq)
> {
> struct kvm *kvm = xive->kvm;
> struct kvmppc_xive_src_block *sb;
> @@ -1560,7 +1560,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
> sb = kvmppc_xive_find_source(xive, irq, &idx);
> if (!sb) {
> pr_devel("No source, creating source block...\n");
> - sb = xive_create_src_block(xive, irq);
> + sb = kvmppc_xive_create_src_block(xive, irq);
> if (!sb) {
> pr_devel("Failed to create block...\n");
> return -ENOMEM;
> @@ -1784,7 +1784,7 @@ static void kvmppc_xive_cleanup_irq(u32 hw_num, struct xive_irq_data *xd)
> xive_cleanup_irq_data(xd);
> }
>
> -static void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb)
> +void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb)
> {
> int i;
>
> diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
> index a078f99bc156..99c04d5c5566 100644
> --- a/arch/powerpc/kvm/book3s_xive_native.c
> +++ b/arch/powerpc/kvm/book3s_xive_native.c
> @@ -31,6 +31,17 @@
>
> #include "book3s_xive.h"
>
> +static u8 xive_vm_esb_load(struct xive_irq_data *xd, u32 offset)
> +{
> + u64 val;
> +
> + if (xd->flags & XIVE_IRQ_FLAG_SHIFT_BUG)
> + offset |= offset << 4;
> +
> + val = in_be64(xd->eoi_mmio + offset);
> + return (u8)val;
> +}
> +
> static void kvmppc_xive_native_cleanup_queue(struct kvm_vcpu *vcpu, int prio)
> {
> struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
> @@ -159,12 +170,94 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
> return rc;
> }
>
> +static int kvmppc_xive_native_set_source(struct kvmppc_xive *xive, long irq,
> + u64 addr)
> +{
> + struct kvmppc_xive_src_block *sb;
> + struct kvmppc_xive_irq_state *state;
> + u64 __user *ubufp = (u64 __user *) addr;
> + u64 val;
> + u16 idx;
> + int rc;
> +
> + pr_devel("%s irq=0x%lx\n", __func__, irq);
> +
> + if (irq < KVMPPC_XIVE_FIRST_IRQ || irq >= KVMPPC_XIVE_NR_IRQS)
> + return -E2BIG;
> +
> + sb = kvmppc_xive_find_source(xive, irq, &idx);
> + if (!sb) {
> + pr_debug("No source, creating source block...\n");
> + sb = kvmppc_xive_create_src_block(xive, irq);
> + if (!sb) {
> + pr_err("Failed to create block...\n");
> + return -ENOMEM;
> + }
> + }
> + state = &sb->irq_state[idx];
> +
> + if (get_user(val, ubufp)) {
> + pr_err("fault getting user info !\n");
> + return -EFAULT;
> + }
> +
> + arch_spin_lock(&sb->lock);
> +
> + /*
> + * If the source doesn't already have an IPI, allocate
> + * one and get the corresponding data
> + */
> + if (!state->ipi_number) {
> + state->ipi_number = xive_native_alloc_irq();
> + if (state->ipi_number == 0) {
> + pr_err("Failed to allocate IRQ !\n");
> + rc = -ENXIO;
> + goto unlock;
> + }
> + xive_native_populate_irq_data(state->ipi_number,
> + &state->ipi_data);
> + pr_debug("%s allocated hw_irq=0x%x for irq=0x%lx\n", __func__,
> + state->ipi_number, irq);
> + }
> +
> + /* Restore LSI state */
> + if (val & KVM_XIVE_LEVEL_SENSITIVE) {
> + state->lsi = true;
> + if (val & KVM_XIVE_LEVEL_ASSERTED)
> + state->asserted = true;
> + pr_devel(" LSI ! Asserted=%d\n", state->asserted);
> + }
> +
> + /* Mask IRQ to start with */
> + state->act_server = 0;
> + state->act_priority = MASKED;
> + xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
> + xive_native_configure_irq(state->ipi_number, 0, MASKED, 0);
> +
> + /* Increment the number of valid sources and mark this one valid */
> + if (!state->valid)
> + xive->src_count++;
> + state->valid = true;
> +
> + rc = 0;
> +
> +unlock:
> + arch_spin_unlock(&sb->lock);
> +
> + return rc;
> +}
> +
> static int kvmppc_xive_native_set_attr(struct kvm_device *dev,
> struct kvm_device_attr *attr)
> {
> + struct kvmppc_xive *xive = dev->private;
> +
> switch (attr->group) {
> case KVM_DEV_XIVE_GRP_CTRL:
> break;
> + case KVM_DEV_XIVE_GRP_SOURCE:
> + return kvmppc_xive_native_set_source(xive, attr->attr,
> + attr->addr);
> }
> return -ENXIO;
> }
> @@ -181,6 +274,11 @@ static int kvmppc_xive_native_has_attr(struct kvm_device *dev,
> switch (attr->group) {
> case KVM_DEV_XIVE_GRP_CTRL:
> break;
> + case KVM_DEV_XIVE_GRP_SOURCE:
> + if (attr->attr >= KVMPPC_XIVE_FIRST_IRQ &&
> + attr->attr < KVMPPC_XIVE_NR_IRQS)
> + return 0;
> + break;
> }
> return -ENXIO;
> }
> @@ -189,6 +287,7 @@ static void kvmppc_xive_native_free(struct kvm_device *dev)
> {
> struct kvmppc_xive *xive = dev->private;
> struct kvm *kvm = xive->kvm;
> + int i;
>
> debugfs_remove(xive->dentry);
>
> @@ -197,6 +296,13 @@ static void kvmppc_xive_native_free(struct kvm_device *dev)
> if (kvm)
> kvm->arch.xive = NULL;
>
> + for (i = 0; i <= xive->max_sbid; i++) {
> + if (xive->src_blocks[i])
> + kvmppc_xive_free_sources(xive->src_blocks[i]);
> + kfree(xive->src_blocks[i]);
> + xive->src_blocks[i] = NULL;
> + }
> +
> if (xive->vp_base != XIVE_INVALID_VP)
> xive_native_free_vp_block(xive->vp_base);
>
> diff --git a/Documentation/virtual/kvm/devices/xive.txt b/Documentation/virtual/kvm/devices/xive.txt
> index fdbd2ff92a88..cd8bfc37b72e 100644
> --- a/Documentation/virtual/kvm/devices/xive.txt
> +++ b/Documentation/virtual/kvm/devices/xive.txt
> @@ -17,3 +17,18 @@ the legacy interrupt mode, referred as XICS (POWER7/8).
>
> 1. KVM_DEV_XIVE_GRP_CTRL
> Provides global controls on the device
> +
> + 2. KVM_DEV_XIVE_GRP_SOURCE (write only)
> + Initializes a new source in the XIVE device and mask it.
> + Attributes:
> + Interrupt source number (64-bit)
> + The kvm_device_attr.addr points to a __u64 value:
> + bits: | 63 .... 2 | 1 | 0
> + values: | unused | level | type
> + - type: 0:MSI 1:LSI
> + - level: assertion level in case of an LSI.
> + Errors:
> + -E2BIG: Interrupt source number is out of range
> + -ENOMEM: Could not create a new source block
> + -EFAULT: Invalid user pointer for attr->addr.
> + -ENXIO: Could not allocate underlying HW interrupt
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply
* Re: [PATCH v3 03/17] KVM: PPC: Book3S HV: XIVE: introduce a new capability KVM_CAP_PPC_IRQ_XIVE
From: David Gibson @ 2019-03-18 0:19 UTC (permalink / raw)
To: Cédric Le Goater; +Cc: linuxppc-dev, Paul Mackerras, kvm, kvm-ppc
In-Reply-To: <20190315120609.25910-4-clg@kaod.org>
[-- Attachment #1: Type: text/plain, Size: 18917 bytes --]
On Fri, Mar 15, 2019 at 01:05:55PM +0100, Cédric Le Goater wrote:
> The user interface exposes a new capability KVM_CAP_PPC_IRQ_XIVE to
> let QEMU connect the vCPU presenters to the XIVE KVM device if
> required. The capability is not advertised for now as the full support
> for the XIVE native exploitation mode is not yet available. When this
> is case, the capability will be advertised on PowerNV Hypervisors
> only. Nested guests (pseries KVM Hypervisor) are not supported.
>
> Internally, the interface to the new KVM device is protected with a
> new interrupt mode: KVMPPC_IRQ_XIVE.
>
> Signed-off-by: Cédric Le Goater <clg@kaod.org>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Though a couple of minor nits are noted below.
> ---
>
> Changes since v2:
>
> - made use of the xive_vp() macro to compute VP identifiers
> - reworked locking in kvmppc_xive_native_connect_vcpu() to fix races
> - stop advertising KVM_CAP_PPC_IRQ_XIVE as support is not fully
> available yet
>
> arch/powerpc/include/asm/kvm_host.h | 1 +
> arch/powerpc/include/asm/kvm_ppc.h | 13 +++
> arch/powerpc/kvm/book3s_xive.h | 11 ++
> include/uapi/linux/kvm.h | 1 +
> arch/powerpc/kvm/book3s_xive.c | 88 ++++++++-------
> arch/powerpc/kvm/book3s_xive_native.c | 150 ++++++++++++++++++++++++++
> arch/powerpc/kvm/powerpc.c | 36 +++++++
> Documentation/virtual/kvm/api.txt | 9 ++
> 8 files changed, 268 insertions(+), 41 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
> index 9f75a75a07f2..eb8581be0ee8 100644
> --- a/arch/powerpc/include/asm/kvm_host.h
> +++ b/arch/powerpc/include/asm/kvm_host.h
> @@ -448,6 +448,7 @@ struct kvmppc_passthru_irqmap {
> #define KVMPPC_IRQ_DEFAULT 0
> #define KVMPPC_IRQ_MPIC 1
> #define KVMPPC_IRQ_XICS 2 /* Includes a XIVE option */
> +#define KVMPPC_IRQ_XIVE 3 /* XIVE native exploitation mode */
>
> #define MMIO_HPTE_CACHE_SIZE 4
>
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
> index 4b72ddde7dc1..1e61877fe147 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -594,6 +594,14 @@ extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
> int level, bool line_status);
> extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu);
>
> +static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
> +{
> + return vcpu->arch.irq_type == KVMPPC_IRQ_XIVE;
> +}
> +
> +extern int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
> + struct kvm_vcpu *vcpu, u32 cpu);
> +extern void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu);
> extern void kvmppc_xive_native_init_module(void);
> extern void kvmppc_xive_native_exit_module(void);
>
> @@ -621,6 +629,11 @@ static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 ir
> int level, bool line_status) { return -ENODEV; }
> static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { }
>
> +static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
> + { return 0; }
> +static inline int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
> + struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; }
> +static inline void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) { }
> static inline void kvmppc_xive_native_init_module(void) { }
> static inline void kvmppc_xive_native_exit_module(void) { }
>
> diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
> index a08ae6fd4c51..d366df69b9cb 100644
> --- a/arch/powerpc/kvm/book3s_xive.h
> +++ b/arch/powerpc/kvm/book3s_xive.h
> @@ -198,6 +198,11 @@ static inline struct kvmppc_xive_src_block *kvmppc_xive_find_source(struct kvmpp
> return xive->src_blocks[bid];
> }
>
> +static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server)
> +{
> + return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
> +}
> +
> /*
> * Mapping between guest priorities and host priorities
> * is as follow.
> @@ -248,5 +253,11 @@ extern int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
> extern int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
> extern int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
>
> +/*
> + * Common Xive routines for XICS-over-XIVE and XIVE native
> + */
> +void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu);
> +int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu);
> +
> #endif /* CONFIG_KVM_XICS */
> #endif /* _KVM_PPC_BOOK3S_XICS_H */
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index e6368163d3a0..52bf74a1616e 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -988,6 +988,7 @@ struct kvm_ppc_resize_hpt {
> #define KVM_CAP_ARM_VM_IPA_SIZE 165
> #define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166
> #define KVM_CAP_HYPERV_CPUID 167
> +#define KVM_CAP_PPC_IRQ_XIVE 168
>
> #ifdef KVM_CAP_IRQ_ROUTING
>
> diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
> index f78d002f0fe0..e7f1ada1c3de 100644
> --- a/arch/powerpc/kvm/book3s_xive.c
> +++ b/arch/powerpc/kvm/book3s_xive.c
> @@ -380,11 +380,6 @@ static int xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
> return -EBUSY;
> }
>
> -static u32 xive_vp(struct kvmppc_xive *xive, u32 server)
> -{
> - return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
> -}
> -
> static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
> struct kvmppc_xive_src_block *sb,
> struct kvmppc_xive_irq_state *state)
> @@ -430,8 +425,8 @@ static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
> */
> if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
> xive_native_configure_irq(hw_num,
> - xive_vp(xive, state->act_server),
> - MASKED, state->number);
> + kvmppc_xive_vp(xive, state->act_server),
> + MASKED, state->number);
> /* set old_p so we can track if an H_EOI was done */
> state->old_p = true;
> state->old_q = false;
> @@ -486,8 +481,8 @@ static void xive_finish_unmask(struct kvmppc_xive *xive,
> */
> if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
> xive_native_configure_irq(hw_num,
> - xive_vp(xive, state->act_server),
> - state->act_priority, state->number);
> + kvmppc_xive_vp(xive, state->act_server),
> + state->act_priority, state->number);
> /* If an EOI is needed, do it here */
> if (!state->old_p)
> xive_vm_source_eoi(hw_num, xd);
> @@ -563,7 +558,7 @@ static int xive_target_interrupt(struct kvm *kvm,
> kvmppc_xive_select_irq(state, &hw_num, NULL);
>
> return xive_native_configure_irq(hw_num,
> - xive_vp(xive, server),
> + kvmppc_xive_vp(xive, server),
> prio, state->number);
> }
>
> @@ -951,7 +946,7 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
> * which is fine for a never started interrupt.
> */
> xive_native_configure_irq(hw_irq,
> - xive_vp(xive, state->act_server),
> + kvmppc_xive_vp(xive, state->act_server),
> state->act_priority, state->number);
>
> /*
> @@ -1027,7 +1022,7 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
>
> /* Reconfigure the IPI */
> xive_native_configure_irq(state->ipi_number,
> - xive_vp(xive, state->act_server),
> + kvmppc_xive_vp(xive, state->act_server),
> state->act_priority, state->number);
>
> /*
> @@ -1049,7 +1044,7 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
> }
> EXPORT_SYMBOL_GPL(kvmppc_xive_clr_mapped);
>
> -static void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
> +void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
> {
> struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
> struct kvm *kvm = vcpu->kvm;
> @@ -1166,7 +1161,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
> xc->xive = xive;
> xc->vcpu = vcpu;
> xc->server_num = cpu;
> - xc->vp_id = xive_vp(xive, cpu);
> + xc->vp_id = kvmppc_xive_vp(xive, cpu);
> xc->mfrr = 0xff;
> xc->valid = true;
>
> @@ -1883,6 +1878,43 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
> return 0;
> }
>
> +int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu)
> +{
> + struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
> + unsigned int i;
> +
> + for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
> + struct xive_q *q = &xc->queues[i];
> + u32 i0, i1, idx;
> +
> + if (!q->qpage && !xc->esc_virq[i])
> + continue;
> +
> + seq_printf(m, " [q%d]: ", i);
> +
> + if (q->qpage) {
> + idx = q->idx;
> + i0 = be32_to_cpup(q->qpage + idx);
> + idx = (idx + 1) & q->msk;
> + i1 = be32_to_cpup(q->qpage + idx);
> + seq_printf(m, "T=%d %08x %08x...\n", q->toggle,
> + i0, i1);
> + }
> + if (xc->esc_virq[i]) {
> + struct irq_data *d = irq_get_irq_data(xc->esc_virq[i]);
> + struct xive_irq_data *xd =
> + irq_data_get_irq_handler_data(d);
> + u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET);
> +
> + seq_printf(m, "E:%c%c I(%d:%llx:%llx)",
> + (pq & XIVE_ESB_VAL_P) ? 'P' : 'p',
> + (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q',
> + xc->esc_virq[i], pq, xd->eoi_page);
> + seq_puts(m, "\n");
> + }
> + }
> + return 0;
> +}
>
> static int xive_debug_show(struct seq_file *m, void *private)
> {
> @@ -1908,7 +1940,6 @@ static int xive_debug_show(struct seq_file *m, void *private)
>
> kvm_for_each_vcpu(i, vcpu, kvm) {
> struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
> - unsigned int i;
>
> if (!xc)
> continue;
> @@ -1918,33 +1949,8 @@ static int xive_debug_show(struct seq_file *m, void *private)
> xc->server_num, xc->cppr, xc->hw_cppr,
> xc->mfrr, xc->pending,
> xc->stat_rm_h_xirr, xc->stat_vm_h_xirr);
> - for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
> - struct xive_q *q = &xc->queues[i];
> - u32 i0, i1, idx;
>
> - if (!q->qpage && !xc->esc_virq[i])
> - continue;
> -
> - seq_printf(m, " [q%d]: ", i);
> -
> - if (q->qpage) {
> - idx = q->idx;
> - i0 = be32_to_cpup(q->qpage + idx);
> - idx = (idx + 1) & q->msk;
> - i1 = be32_to_cpup(q->qpage + idx);
> - seq_printf(m, "T=%d %08x %08x... \n", q->toggle, i0, i1);
> - }
> - if (xc->esc_virq[i]) {
> - struct irq_data *d = irq_get_irq_data(xc->esc_virq[i]);
> - struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
> - u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET);
> - seq_printf(m, "E:%c%c I(%d:%llx:%llx)",
> - (pq & XIVE_ESB_VAL_P) ? 'P' : 'p',
> - (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q',
> - xc->esc_virq[i], pq, xd->eoi_page);
> - seq_printf(m, "\n");
> - }
> - }
> + kvmppc_xive_debug_show_queues(m, vcpu);
>
> t_rm_h_xirr += xc->stat_rm_h_xirr;
> t_rm_h_ipoll += xc->stat_rm_h_ipoll;
> diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
> index 76d45bcc7060..a078f99bc156 100644
> --- a/arch/powerpc/kvm/book3s_xive_native.c
> +++ b/arch/powerpc/kvm/book3s_xive_native.c
> @@ -31,6 +31,134 @@
>
> #include "book3s_xive.h"
>
> +static void kvmppc_xive_native_cleanup_queue(struct kvm_vcpu *vcpu, int prio)
> +{
> + struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
> + struct xive_q *q = &xc->queues[prio];
> +
> + xive_native_disable_queue(xc->vp_id, q, prio);
> + if (q->qpage) {
> + put_page(virt_to_page(q->qpage));
> + q->qpage = NULL;
> + }
> +}
> +
> +void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu)
> +{
> + struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
> + int i;
> +
> + if (!kvmppc_xive_enabled(vcpu))
> + return;
> +
> + if (!xc)
> + return;
> +
> + pr_devel("native_cleanup_vcpu(cpu=%d)\n", xc->server_num);
> +
> + /* Ensure no interrupt is still routed to that VP */
> + xc->valid = false;
> + kvmppc_xive_disable_vcpu_interrupts(vcpu);
> +
> + /* Disable the VP */
> + xive_native_disable_vp(xc->vp_id);
> +
> + /* Free the queues & associated interrupts */
> + for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
> + /* Free the escalation irq */
> + if (xc->esc_virq[i]) {
> + free_irq(xc->esc_virq[i], vcpu);
> + irq_dispose_mapping(xc->esc_virq[i]);
> + kfree(xc->esc_virq_names[i]);
> + xc->esc_virq[i] = 0;
Should that actually be NO_IRQ on the right (it evaluates to the same
thing). Fine to fix that as a later followup.
> + }
> +
> + /* Free the queue */
> + kvmppc_xive_native_cleanup_queue(vcpu, i);
> + }
> +
> + /* Free the VP */
> + kfree(xc);
> +
> + /* Cleanup the vcpu */
> + vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
> + vcpu->arch.xive_vcpu = NULL;
> +}
> +
> +int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
> + struct kvm_vcpu *vcpu, u32 server_num)
> +{
> + struct kvmppc_xive *xive = dev->private;
> + struct kvmppc_xive_vcpu *xc = NULL;
> + int rc;
> +
> + pr_devel("native_connect_vcpu(server=%d)\n", server_num);
> +
> + if (dev->ops != &kvm_xive_native_ops) {
> + pr_devel("Wrong ops !\n");
> + return -EPERM;
> + }
> + if (xive->kvm != vcpu->kvm)
> + return -EPERM;
> + if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
> + return -EBUSY;
> + if (server_num >= KVM_MAX_VCPUS) {
> + pr_devel("Out of bounds !\n");
> + return -EINVAL;
> + }
> +
> + mutex_lock(&vcpu->kvm->lock);
> +
> + if (kvmppc_xive_find_server(vcpu->kvm, server_num)) {
> + pr_devel("Duplicate !\n");
> + rc = -EEXIST;
> + goto bail;
> + }
> +
> + xc = kzalloc(sizeof(*xc), GFP_KERNEL);
> + if (!xc) {
> + rc = -ENOMEM;
> + goto bail;
> + }
> +
> + vcpu->arch.xive_vcpu = xc;
> + xc->xive = xive;
> + xc->vcpu = vcpu;
> + xc->server_num = server_num;
> +
> + xc->vp_id = kvmppc_xive_vp(xive, server_num);
> + xc->valid = true;
This 'valid' field doesn't seem useful, since it's initialized to true
immediately after allocating xc and set to false moments before
free()ing it. ..and I can't see anything that tests it.
Again, ok to deal with that as a later cleanup.
> + vcpu->arch.irq_type = KVMPPC_IRQ_XIVE;
> +
> + rc = xive_native_get_vp_info(xc->vp_id, &xc->vp_cam, &xc->vp_chip_id);
> + if (rc) {
> + pr_err("Failed to get VP info from OPAL: %d\n", rc);
> + goto bail;
> + }
> +
> + /*
> + * Enable the VP first as the single escalation mode will
> + * affect escalation interrupts numbering
> + */
> + rc = xive_native_enable_vp(xc->vp_id, xive->single_escalation);
> + if (rc) {
> + pr_err("Failed to enable VP in OPAL: %d\n", rc);
> + goto bail;
> + }
> +
> + /* Configure VCPU fields for use by assembly push/pull */
> + vcpu->arch.xive_saved_state.w01 = cpu_to_be64(0xff000000);
> + vcpu->arch.xive_cam_word = cpu_to_be32(xc->vp_cam | TM_QW1W2_VO);
> +
> + /* TODO: reset all queues to a clean state ? */
> +bail:
> + mutex_unlock(&vcpu->kvm->lock);
> + if (rc)
> + kvmppc_xive_native_cleanup_vcpu(vcpu);
> +
> + return rc;
> +}
> +
> static int kvmppc_xive_native_set_attr(struct kvm_device *dev,
> struct kvm_device_attr *attr)
> {
> @@ -119,10 +247,32 @@ static int xive_native_debug_show(struct seq_file *m, void *private)
> {
> struct kvmppc_xive *xive = m->private;
> struct kvm *kvm = xive->kvm;
> + struct kvm_vcpu *vcpu;
> + unsigned int i;
>
> if (!kvm)
> return 0;
>
> + seq_puts(m, "=========\nVCPU state\n=========\n");
> +
> + kvm_for_each_vcpu(i, vcpu, kvm) {
> + struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
> +
> + if (!xc)
> + continue;
> +
> + seq_printf(m, "cpu server %#x NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n",
> + xc->server_num,
> + vcpu->arch.xive_saved_state.nsr,
> + vcpu->arch.xive_saved_state.cppr,
> + vcpu->arch.xive_saved_state.ipb,
> + vcpu->arch.xive_saved_state.pipr,
> + vcpu->arch.xive_saved_state.w01,
> + (u32) vcpu->arch.xive_cam_word);
> +
> + kvmppc_xive_debug_show_queues(m, vcpu);
> + }
> +
> return 0;
> }
>
> diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
> index 8c69af10f91d..bb51faf29162 100644
> --- a/arch/powerpc/kvm/powerpc.c
> +++ b/arch/powerpc/kvm/powerpc.c
> @@ -570,6 +570,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
> case KVM_CAP_PPC_GET_CPU_CHAR:
> r = 1;
> break;
> +#ifdef CONFIG_KVM_XIVE
> + case KVM_CAP_PPC_IRQ_XIVE:
> + /*
> + * Return false until all the XIVE infrastructure is
> + * in place including support for migration.
> + */
> + r = 0;
> + break;
> +#endif
>
> case KVM_CAP_PPC_ALLOC_HTAB:
> r = hv_enabled;
> @@ -753,6 +762,9 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
> else
> kvmppc_xics_free_icp(vcpu);
> break;
> + case KVMPPC_IRQ_XIVE:
> + kvmppc_xive_native_cleanup_vcpu(vcpu);
> + break;
> }
>
> kvmppc_core_vcpu_free(vcpu);
> @@ -1941,6 +1953,30 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
> break;
> }
> #endif /* CONFIG_KVM_XICS */
> +#ifdef CONFIG_KVM_XIVE
> + case KVM_CAP_PPC_IRQ_XIVE: {
> + struct fd f;
> + struct kvm_device *dev;
> +
> + r = -EBADF;
> + f = fdget(cap->args[0]);
> + if (!f.file)
> + break;
> +
> + r = -ENXIO;
> + if (!xive_enabled())
> + break;
> +
> + r = -EPERM;
> + dev = kvm_device_from_filp(f.file);
> + if (dev)
> + r = kvmppc_xive_native_connect_vcpu(dev, vcpu,
> + cap->args[1]);
> +
> + fdput(f);
> + break;
> + }
> +#endif /* CONFIG_KVM_XIVE */
> #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
> case KVM_CAP_PPC_FWNMI:
> r = -EINVAL;
> diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
> index 356156f5c52d..1db1435769b4 100644
> --- a/Documentation/virtual/kvm/api.txt
> +++ b/Documentation/virtual/kvm/api.txt
> @@ -4458,6 +4458,15 @@ struct kvm_sync_regs {
> struct kvm_vcpu_events events;
> };
>
> +6.75 KVM_CAP_PPC_IRQ_XIVE
> +
> +Architectures: ppc
> +Target: vcpu
> +Parameters: args[0] is the XIVE device fd
> + args[1] is the XIVE CPU number (server ID) for this vcpu
> +
> +This capability connects the vcpu to an in-kernel XIVE device.
> +
> 7. Capabilities that can be enabled on VMs
> ------------------------------------------
>
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply
* Re: [PATCH 1/5] ocxl: Rename struct link to ocxl_link
From: Andrew Donnellan @ 2019-03-15 6:58 UTC (permalink / raw)
To: Alastair D'Silva
Cc: Arnd Bergmann, Greg Kroah-Hartman, Greg Kurz, linux-kernel,
Alastair D'Silva, Frederic Barrat, linuxppc-dev
In-Reply-To: <20190313040702.14276-2-alastair@au1.ibm.com>
On 13/3/19 3:06 pm, Alastair D'Silva wrote:
> From: Alastair D'Silva <alastair@d-silva.org>
>
> The term 'link' is ambiguous (especially when the struct is used for a
> list), so rename it for clarity.
>
> Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
> Reviewed-by: Greg Kurz <groug@kaod.org>
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
(In future please include a changelog to explain what's changed from v1->v2)
> ---
> drivers/misc/ocxl/file.c | 5 ++---
> drivers/misc/ocxl/link.c | 36 ++++++++++++++++++------------------
> 2 files changed, 20 insertions(+), 21 deletions(-)
>
> diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c
> index e6a607488f8a..009e09b7ded5 100644
> --- a/drivers/misc/ocxl/file.c
> +++ b/drivers/misc/ocxl/file.c
> @@ -151,10 +151,9 @@ static long afu_ioctl_enable_p9_wait(struct ocxl_context *ctx,
> mutex_unlock(&ctx->status_mutex);
>
> if (status == ATTACHED) {
> - int rc;
> - struct link *link = ctx->afu->fn->link;
> + int rc = ocxl_link_update_pe(ctx->afu->fn->link,
> + ctx->pasid, ctx->tidr);
>
> - rc = ocxl_link_update_pe(link, ctx->pasid, ctx->tidr);
> if (rc)
> return rc;
> }
> diff --git a/drivers/misc/ocxl/link.c b/drivers/misc/ocxl/link.c
> index d50b861d7e57..8d2690a1a9de 100644
> --- a/drivers/misc/ocxl/link.c
> +++ b/drivers/misc/ocxl/link.c
> @@ -76,7 +76,7 @@ struct spa {
> * limited number of opencapi slots on a system and lookup is only
> * done when the device is probed
> */
> -struct link {
> +struct ocxl_link {
> struct list_head list;
> struct kref ref;
> int domain;
> @@ -179,7 +179,7 @@ static void xsl_fault_handler_bh(struct work_struct *fault_work)
>
> static irqreturn_t xsl_fault_handler(int irq, void *data)
> {
> - struct link *link = (struct link *) data;
> + struct ocxl_link *link = (struct ocxl_link *) data;
> struct spa *spa = link->spa;
> u64 dsisr, dar, pe_handle;
> struct pe_data *pe_data;
> @@ -256,7 +256,7 @@ static int map_irq_registers(struct pci_dev *dev, struct spa *spa)
> &spa->reg_tfc, &spa->reg_pe_handle);
> }
>
> -static int setup_xsl_irq(struct pci_dev *dev, struct link *link)
> +static int setup_xsl_irq(struct pci_dev *dev, struct ocxl_link *link)
> {
> struct spa *spa = link->spa;
> int rc;
> @@ -311,7 +311,7 @@ static int setup_xsl_irq(struct pci_dev *dev, struct link *link)
> return rc;
> }
>
> -static void release_xsl_irq(struct link *link)
> +static void release_xsl_irq(struct ocxl_link *link)
> {
> struct spa *spa = link->spa;
>
> @@ -323,7 +323,7 @@ static void release_xsl_irq(struct link *link)
> unmap_irq_registers(spa);
> }
>
> -static int alloc_spa(struct pci_dev *dev, struct link *link)
> +static int alloc_spa(struct pci_dev *dev, struct ocxl_link *link)
> {
> struct spa *spa;
>
> @@ -350,7 +350,7 @@ static int alloc_spa(struct pci_dev *dev, struct link *link)
> return 0;
> }
>
> -static void free_spa(struct link *link)
> +static void free_spa(struct ocxl_link *link)
> {
> struct spa *spa = link->spa;
>
> @@ -364,12 +364,12 @@ static void free_spa(struct link *link)
> }
> }
>
> -static int alloc_link(struct pci_dev *dev, int PE_mask, struct link **out_link)
> +static int alloc_link(struct pci_dev *dev, int PE_mask, struct ocxl_link **out_link)
> {
> - struct link *link;
> + struct ocxl_link *link;
> int rc;
>
> - link = kzalloc(sizeof(struct link), GFP_KERNEL);
> + link = kzalloc(sizeof(struct ocxl_link), GFP_KERNEL);
> if (!link)
> return -ENOMEM;
>
> @@ -405,7 +405,7 @@ static int alloc_link(struct pci_dev *dev, int PE_mask, struct link **out_link)
> return rc;
> }
>
> -static void free_link(struct link *link)
> +static void free_link(struct ocxl_link *link)
> {
> release_xsl_irq(link);
> free_spa(link);
> @@ -415,7 +415,7 @@ static void free_link(struct link *link)
> int ocxl_link_setup(struct pci_dev *dev, int PE_mask, void **link_handle)
> {
> int rc = 0;
> - struct link *link;
> + struct ocxl_link *link;
>
> mutex_lock(&links_list_lock);
> list_for_each_entry(link, &links_list, list) {
> @@ -442,7 +442,7 @@ EXPORT_SYMBOL_GPL(ocxl_link_setup);
>
> static void release_xsl(struct kref *ref)
> {
> - struct link *link = container_of(ref, struct link, ref);
> + struct ocxl_link *link = container_of(ref, struct ocxl_link, ref);
>
> list_del(&link->list);
> /* call platform code before releasing data */
> @@ -452,7 +452,7 @@ static void release_xsl(struct kref *ref)
>
> void ocxl_link_release(struct pci_dev *dev, void *link_handle)
> {
> - struct link *link = (struct link *) link_handle;
> + struct ocxl_link *link = (struct ocxl_link *) link_handle;
>
> mutex_lock(&links_list_lock);
> kref_put(&link->ref, release_xsl);
> @@ -488,7 +488,7 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,
> void (*xsl_err_cb)(void *data, u64 addr, u64 dsisr),
> void *xsl_err_data)
> {
> - struct link *link = (struct link *) link_handle;
> + struct ocxl_link *link = (struct ocxl_link *) link_handle;
> struct spa *spa = link->spa;
> struct ocxl_process_element *pe;
> int pe_handle, rc = 0;
> @@ -558,7 +558,7 @@ EXPORT_SYMBOL_GPL(ocxl_link_add_pe);
>
> int ocxl_link_update_pe(void *link_handle, int pasid, __u16 tid)
> {
> - struct link *link = (struct link *) link_handle;
> + struct ocxl_link *link = (struct ocxl_link *) link_handle;
> struct spa *spa = link->spa;
> struct ocxl_process_element *pe;
> int pe_handle, rc;
> @@ -594,7 +594,7 @@ int ocxl_link_update_pe(void *link_handle, int pasid, __u16 tid)
>
> int ocxl_link_remove_pe(void *link_handle, int pasid)
> {
> - struct link *link = (struct link *) link_handle;
> + struct ocxl_link *link = (struct ocxl_link *) link_handle;
> struct spa *spa = link->spa;
> struct ocxl_process_element *pe;
> struct pe_data *pe_data;
> @@ -666,7 +666,7 @@ EXPORT_SYMBOL_GPL(ocxl_link_remove_pe);
>
> int ocxl_link_irq_alloc(void *link_handle, int *hw_irq, u64 *trigger_addr)
> {
> - struct link *link = (struct link *) link_handle;
> + struct ocxl_link *link = (struct ocxl_link *) link_handle;
> int rc, irq;
> u64 addr;
>
> @@ -687,7 +687,7 @@ EXPORT_SYMBOL_GPL(ocxl_link_irq_alloc);
>
> void ocxl_link_free_irq(void *link_handle, int hw_irq)
> {
> - struct link *link = (struct link *) link_handle;
> + struct ocxl_link *link = (struct ocxl_link *) link_handle;
>
> pnv_ocxl_free_xive_irq(hw_irq);
> atomic_inc(&link->irq_available);
>
--
Andrew Donnellan OzLabs, ADL Canberra
andrew.donnellan@au1.ibm.com IBM Australia Limited
^ permalink raw reply
* Re: [PATCH v3 02/17] KVM: PPC: Book3S HV: add a new KVM device for the XIVE native exploitation mode
From: David Gibson @ 2019-03-17 23:48 UTC (permalink / raw)
To: Cédric Le Goater; +Cc: linuxppc-dev, Paul Mackerras, kvm, kvm-ppc
In-Reply-To: <20190315120609.25910-3-clg@kaod.org>
[-- Attachment #1: Type: text/plain, Size: 11862 bytes --]
On Fri, Mar 15, 2019 at 01:05:54PM +0100, Cédric Le Goater wrote:
> This is the basic framework for the new KVM device supporting the XIVE
> native exploitation mode. The user interface exposes a new KVM device
> to be created by QEMU, only available when running on a L0 hypervisor
> only. Support for nested guests is not available yet.
>
> The XIVE device reuses the device structure of the XICS-on-XIVE device
> as they have a lot in common. That could possibly change in the future
> if the need arise.
>
> Signed-off-by: Cédric Le Goater <clg@kaod.org>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
> ---
>
> Changes since v2:
>
> - removed ->q_order setting. Only useful in the XICS-on-XIVE KVM
> device which allocates the EQs on behalf of the guest.
> - returned -ENXIO when VP base is invalid
>
> arch/powerpc/include/asm/kvm_host.h | 1 +
> arch/powerpc/include/asm/kvm_ppc.h | 8 +
> arch/powerpc/include/uapi/asm/kvm.h | 3 +
> include/uapi/linux/kvm.h | 2 +
> arch/powerpc/kvm/book3s.c | 7 +-
> arch/powerpc/kvm/book3s_xive_native.c | 184 +++++++++++++++++++++
> Documentation/virtual/kvm/devices/xive.txt | 19 +++
> arch/powerpc/kvm/Makefile | 2 +-
> 8 files changed, 224 insertions(+), 2 deletions(-)
> create mode 100644 arch/powerpc/kvm/book3s_xive_native.c
> create mode 100644 Documentation/virtual/kvm/devices/xive.txt
>
> diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
> index 091430339db1..9f75a75a07f2 100644
> --- a/arch/powerpc/include/asm/kvm_host.h
> +++ b/arch/powerpc/include/asm/kvm_host.h
> @@ -220,6 +220,7 @@ extern struct kvm_device_ops kvm_xics_ops;
> struct kvmppc_xive;
> struct kvmppc_xive_vcpu;
> extern struct kvm_device_ops kvm_xive_ops;
> +extern struct kvm_device_ops kvm_xive_native_ops;
>
> struct kvmppc_passthru_irqmap;
>
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
> index b3bf4f61b30c..4b72ddde7dc1 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -593,6 +593,10 @@ extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
> extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
> int level, bool line_status);
> extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu);
> +
> +extern void kvmppc_xive_native_init_module(void);
> +extern void kvmppc_xive_native_exit_module(void);
> +
> #else
> static inline int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
> u32 priority) { return -1; }
> @@ -616,6 +620,10 @@ static inline int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) { retur
> static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
> int level, bool line_status) { return -ENODEV; }
> static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { }
> +
> +static inline void kvmppc_xive_native_init_module(void) { }
> +static inline void kvmppc_xive_native_exit_module(void) { }
> +
> #endif /* CONFIG_KVM_XIVE */
>
> #ifdef CONFIG_PPC_POWERNV
> diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
> index 8c876c166ef2..b002c0c67787 100644
> --- a/arch/powerpc/include/uapi/asm/kvm.h
> +++ b/arch/powerpc/include/uapi/asm/kvm.h
> @@ -675,4 +675,7 @@ struct kvm_ppc_cpu_char {
> #define KVM_XICS_PRESENTED (1ULL << 43)
> #define KVM_XICS_QUEUED (1ULL << 44)
>
> +/* POWER9 XIVE Native Interrupt Controller */
> +#define KVM_DEV_XIVE_GRP_CTRL 1
> +
> #endif /* __LINUX_KVM_POWERPC_H */
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index 6d4ea4b6c922..e6368163d3a0 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -1211,6 +1211,8 @@ enum kvm_device_type {
> #define KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_ARM_VGIC_V3
> KVM_DEV_TYPE_ARM_VGIC_ITS,
> #define KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_ARM_VGIC_ITS
> + KVM_DEV_TYPE_XIVE,
> +#define KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_XIVE
> KVM_DEV_TYPE_MAX,
> };
>
> diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
> index 601c094f15ab..96d43f091255 100644
> --- a/arch/powerpc/kvm/book3s.c
> +++ b/arch/powerpc/kvm/book3s.c
> @@ -1040,6 +1040,9 @@ static int kvmppc_book3s_init(void)
> if (xics_on_xive()) {
> kvmppc_xive_init_module();
> kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS);
> + kvmppc_xive_native_init_module();
> + kvm_register_device_ops(&kvm_xive_native_ops,
> + KVM_DEV_TYPE_XIVE);
> } else
> #endif
> kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS);
> @@ -1050,8 +1053,10 @@ static int kvmppc_book3s_init(void)
> static void kvmppc_book3s_exit(void)
> {
> #ifdef CONFIG_KVM_XICS
> - if (xics_on_xive())
> + if (xics_on_xive()) {
> kvmppc_xive_exit_module();
> + kvmppc_xive_native_exit_module();
> + }
> #endif
> #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
> kvmppc_book3s_exit_pr();
> diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
> new file mode 100644
> index 000000000000..76d45bcc7060
> --- /dev/null
> +++ b/arch/powerpc/kvm/book3s_xive_native.c
> @@ -0,0 +1,184 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Copyright (c) 2017-2019, IBM Corporation.
> + */
> +
> +#define pr_fmt(fmt) "xive-kvm: " fmt
> +
> +#include <linux/anon_inodes.h>
> +#include <linux/kernel.h>
> +#include <linux/kvm_host.h>
> +#include <linux/err.h>
> +#include <linux/gfp.h>
> +#include <linux/spinlock.h>
> +#include <linux/delay.h>
> +#include <linux/percpu.h>
> +#include <linux/cpumask.h>
> +#include <asm/uaccess.h>
> +#include <asm/kvm_book3s.h>
> +#include <asm/kvm_ppc.h>
> +#include <asm/hvcall.h>
> +#include <asm/xics.h>
> +#include <asm/xive.h>
> +#include <asm/xive-regs.h>
> +#include <asm/debug.h>
> +#include <asm/debugfs.h>
> +#include <asm/time.h>
> +#include <asm/opal.h>
> +
> +#include <linux/debugfs.h>
> +#include <linux/seq_file.h>
> +
> +#include "book3s_xive.h"
> +
> +static int kvmppc_xive_native_set_attr(struct kvm_device *dev,
> + struct kvm_device_attr *attr)
> +{
> + switch (attr->group) {
> + case KVM_DEV_XIVE_GRP_CTRL:
> + break;
> + }
> + return -ENXIO;
> +}
> +
> +static int kvmppc_xive_native_get_attr(struct kvm_device *dev,
> + struct kvm_device_attr *attr)
> +{
> + return -ENXIO;
> +}
> +
> +static int kvmppc_xive_native_has_attr(struct kvm_device *dev,
> + struct kvm_device_attr *attr)
> +{
> + switch (attr->group) {
> + case KVM_DEV_XIVE_GRP_CTRL:
> + break;
> + }
> + return -ENXIO;
> +}
> +
> +static void kvmppc_xive_native_free(struct kvm_device *dev)
> +{
> + struct kvmppc_xive *xive = dev->private;
> + struct kvm *kvm = xive->kvm;
> +
> + debugfs_remove(xive->dentry);
> +
> + pr_devel("Destroying xive native device\n");
> +
> + if (kvm)
> + kvm->arch.xive = NULL;
> +
> + if (xive->vp_base != XIVE_INVALID_VP)
> + xive_native_free_vp_block(xive->vp_base);
> +
> + kfree(xive);
> + kfree(dev);
> +}
> +
> +static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
> +{
> + struct kvmppc_xive *xive;
> + struct kvm *kvm = dev->kvm;
> + int ret = 0;
> +
> + pr_devel("Creating xive native device\n");
> +
> + if (kvm->arch.xive)
> + return -EEXIST;
> +
> + xive = kzalloc(sizeof(*xive), GFP_KERNEL);
> + if (!xive)
> + return -ENOMEM;
> +
> + dev->private = xive;
> + xive->dev = dev;
> + xive->kvm = kvm;
> + kvm->arch.xive = xive;
> +
> + /*
> + * Allocate a bunch of VPs. KVM_MAX_VCPUS is a large value for
> + * a default. Getting the max number of CPUs the VM was
> + * configured with would improve our usage of the XIVE VP space.
> + */
> + xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS);
> + pr_devel("VP_Base=%x\n", xive->vp_base);
> +
> + if (xive->vp_base == XIVE_INVALID_VP)
> + ret = -ENXIO;
> +
> + xive->single_escalation = xive_native_has_single_escalation();
> +
> + if (ret)
> + kfree(xive);
> +
> + return ret;
> +}
> +
> +static int xive_native_debug_show(struct seq_file *m, void *private)
> +{
> + struct kvmppc_xive *xive = m->private;
> + struct kvm *kvm = xive->kvm;
> +
> + if (!kvm)
> + return 0;
> +
> + return 0;
> +}
> +
> +static int xive_native_debug_open(struct inode *inode, struct file *file)
> +{
> + return single_open(file, xive_native_debug_show, inode->i_private);
> +}
> +
> +static const struct file_operations xive_native_debug_fops = {
> + .open = xive_native_debug_open,
> + .read = seq_read,
> + .llseek = seq_lseek,
> + .release = single_release,
> +};
> +
> +static void xive_native_debugfs_init(struct kvmppc_xive *xive)
> +{
> + char *name;
> +
> + name = kasprintf(GFP_KERNEL, "kvm-xive-%p", xive);
> + if (!name) {
> + pr_err("%s: no memory for name\n", __func__);
> + return;
> + }
> +
> + xive->dentry = debugfs_create_file(name, 0444, powerpc_debugfs_root,
> + xive, &xive_native_debug_fops);
> +
> + pr_debug("%s: created %s\n", __func__, name);
> + kfree(name);
> +}
> +
> +static void kvmppc_xive_native_init(struct kvm_device *dev)
> +{
> + struct kvmppc_xive *xive = (struct kvmppc_xive *)dev->private;
> +
> + /* Register some debug interfaces */
> + xive_native_debugfs_init(xive);
> +}
> +
> +struct kvm_device_ops kvm_xive_native_ops = {
> + .name = "kvm-xive-native",
> + .create = kvmppc_xive_native_create,
> + .init = kvmppc_xive_native_init,
> + .destroy = kvmppc_xive_native_free,
> + .set_attr = kvmppc_xive_native_set_attr,
> + .get_attr = kvmppc_xive_native_get_attr,
> + .has_attr = kvmppc_xive_native_has_attr,
> +};
> +
> +void kvmppc_xive_native_init_module(void)
> +{
> + ;
> +}
> +
> +void kvmppc_xive_native_exit_module(void)
> +{
> + ;
> +}
> diff --git a/Documentation/virtual/kvm/devices/xive.txt b/Documentation/virtual/kvm/devices/xive.txt
> new file mode 100644
> index 000000000000..fdbd2ff92a88
> --- /dev/null
> +++ b/Documentation/virtual/kvm/devices/xive.txt
> @@ -0,0 +1,19 @@
> +POWER9 eXternal Interrupt Virtualization Engine (XIVE Gen1)
> +==========================================================
> +
> +Device types supported:
> + KVM_DEV_TYPE_XIVE POWER9 XIVE Interrupt Controller generation 1
> +
> +This device acts as a VM interrupt controller. It provides the KVM
> +interface to configure the interrupt sources of a VM in the underlying
> +POWER9 XIVE interrupt controller.
> +
> +Only one XIVE instance may be instantiated. A guest XIVE device
> +requires a POWER9 host and the guest OS should have support for the
> +XIVE native exploitation interrupt mode. If not, it should run using
> +the legacy interrupt mode, referred as XICS (POWER7/8).
> +
> +* Groups:
> +
> + 1. KVM_DEV_XIVE_GRP_CTRL
> + Provides global controls on the device
> diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
> index 64f1135e7732..806cbe488410 100644
> --- a/arch/powerpc/kvm/Makefile
> +++ b/arch/powerpc/kvm/Makefile
> @@ -99,7 +99,7 @@ endif
> kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
> book3s_xics.o
>
> -kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o
> +kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o book3s_xive_native.o
> kvm-book3s_64-objs-$(CONFIG_SPAPR_TCE_IOMMU) += book3s_64_vio.o
>
> kvm-book3s_64-module-objs := \
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply
* [PATCH v2 13/13] syscall_get_arch: add "struct task_struct *" argument
From: Dmitry V. Levin @ 2019-03-17 23:30 UTC (permalink / raw)
To: Paul Moore
Cc: linux-ia64, linux-sh, Palmer Dabbelt, linux-mips, sparclinux,
linux-hexagon, linux-riscv, linux-arch, linux-s390, linux-c6x-dev,
x86, Eugene Syromyatnikov, Elvira Khabirova, Mark Salter,
linux-snps-arc, uclinux-h8-devel, linux-xtensa, Kees Cook,
linux-um, linux-m68k, openrisc, Andy Lutomirski, linux-arm-kernel,
linux-parisc, Oleg Nesterov, linux-kernel, Paul Burton,
linux-audit, linux-alpha, nios2-dev, linuxppc-dev
This argument is required to extend the generic ptrace API with
PTRACE_GET_SYSCALL_INFO request: syscall_get_arch() is going
to be called from ptrace_request() along with syscall_get_nr(),
syscall_get_arguments(), syscall_get_error(), and
syscall_get_return_value() functions with a tracee as their argument.
The primary intent is that the triple (audit_arch, syscall_nr, arg1..arg6)
should describe what system call is being called and what its arguments
are.
Reverts: 5e937a9ae913 ("syscall_get_arch: remove useless function arguments")
Reverts: 1002d94d3076 ("syscall.h: fix doc text for syscall_get_arch()")
Reviewed-by: Andy Lutomirski <luto@kernel.org> # for x86
Reviewed-by: Palmer Dabbelt <palmer@sifive.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Acked-by: Paul Burton <paul.burton@mips.com> # MIPS parts
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Acked-by: Kees Cook <keescook@chromium.org> # seccomp parts
Acked-by: Mark Salter <msalter@redhat.com> # for the c6x bit
Cc: Elvira Khabirova <lineprinter@altlinux.org>
Cc: Eugene Syromyatnikov <esyr@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: x86@kernel.org
Cc: linux-alpha@vger.kernel.org
Cc: linux-snps-arc@lists.infradead.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-c6x-dev@linux-c6x.org
Cc: uclinux-h8-devel@lists.sourceforge.jp
Cc: linux-hexagon@vger.kernel.org
Cc: linux-ia64@vger.kernel.org
Cc: linux-m68k@lists.linux-m68k.org
Cc: linux-mips@vger.kernel.org
Cc: nios2-dev@lists.rocketboards.org
Cc: openrisc@lists.librecores.org
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-riscv@lists.infradead.org
Cc: linux-s390@vger.kernel.org
Cc: linux-sh@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Cc: linux-um@lists.infradead.org
Cc: linux-xtensa@linux-xtensa.org
Cc: linux-arch@vger.kernel.org
Cc: linux-audit@redhat.com
Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
---
Notes:
v2: unchanged
arch/alpha/include/asm/syscall.h | 2 +-
arch/arc/include/asm/syscall.h | 2 +-
arch/arm/include/asm/syscall.h | 2 +-
arch/arm64/include/asm/syscall.h | 4 ++--
arch/c6x/include/asm/syscall.h | 2 +-
arch/csky/include/asm/syscall.h | 2 +-
arch/h8300/include/asm/syscall.h | 2 +-
arch/hexagon/include/asm/syscall.h | 2 +-
arch/ia64/include/asm/syscall.h | 2 +-
arch/m68k/include/asm/syscall.h | 2 +-
arch/microblaze/include/asm/syscall.h | 2 +-
arch/mips/include/asm/syscall.h | 6 +++---
arch/mips/kernel/ptrace.c | 2 +-
arch/nds32/include/asm/syscall.h | 2 +-
arch/nios2/include/asm/syscall.h | 2 +-
arch/openrisc/include/asm/syscall.h | 2 +-
arch/parisc/include/asm/syscall.h | 4 ++--
arch/powerpc/include/asm/syscall.h | 10 ++++++++--
arch/riscv/include/asm/syscall.h | 2 +-
arch/s390/include/asm/syscall.h | 4 ++--
arch/sh/include/asm/syscall_32.h | 2 +-
arch/sh/include/asm/syscall_64.h | 2 +-
arch/sparc/include/asm/syscall.h | 5 +++--
arch/unicore32/include/asm/syscall.h | 2 +-
arch/x86/include/asm/syscall.h | 8 +++++---
arch/x86/um/asm/syscall.h | 2 +-
arch/xtensa/include/asm/syscall.h | 2 +-
include/asm-generic/syscall.h | 5 +++--
kernel/auditsc.c | 4 ++--
kernel/seccomp.c | 4 ++--
30 files changed, 52 insertions(+), 42 deletions(-)
diff --git a/arch/alpha/include/asm/syscall.h b/arch/alpha/include/asm/syscall.h
index d73a6fcb519c..11c688c1d7ec 100644
--- a/arch/alpha/include/asm/syscall.h
+++ b/arch/alpha/include/asm/syscall.h
@@ -4,7 +4,7 @@
#include <uapi/linux/audit.h>
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_ALPHA;
}
diff --git a/arch/arc/include/asm/syscall.h b/arch/arc/include/asm/syscall.h
index c7fc4c0c3bcb..caf2697ef5b7 100644
--- a/arch/arc/include/asm/syscall.h
+++ b/arch/arc/include/asm/syscall.h
@@ -70,7 +70,7 @@ syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
}
static inline int
-syscall_get_arch(void)
+syscall_get_arch(struct task_struct *task)
{
return IS_ENABLED(CONFIG_ISA_ARCOMPACT)
? (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
index 06dea6bce293..3940ceac0bdc 100644
--- a/arch/arm/include/asm/syscall.h
+++ b/arch/arm/include/asm/syscall.h
@@ -104,7 +104,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
memcpy(®s->ARM_r0 + i, args, n * sizeof(args[0]));
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
/* ARM tasks don't change audit architectures on the fly. */
return AUDIT_ARCH_ARM;
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index ad8be16a39c9..1870df03f774 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -117,9 +117,9 @@ static inline void syscall_set_arguments(struct task_struct *task,
* We don't care about endianness (__AUDIT_ARCH_LE bit) here because
* AArch64 has the same system calls both on little- and big- endian.
*/
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
- if (is_compat_task())
+ if (is_compat_thread(task_thread_info(task)))
return AUDIT_ARCH_ARM;
return AUDIT_ARCH_AARCH64;
diff --git a/arch/c6x/include/asm/syscall.h b/arch/c6x/include/asm/syscall.h
index 39dbd1ef994c..595057191c9c 100644
--- a/arch/c6x/include/asm/syscall.h
+++ b/arch/c6x/include/asm/syscall.h
@@ -121,7 +121,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
}
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
return IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)
? AUDIT_ARCH_C6XBE : AUDIT_ARCH_C6X;
diff --git a/arch/csky/include/asm/syscall.h b/arch/csky/include/asm/syscall.h
index d637445737b7..150ffb894fa2 100644
--- a/arch/csky/include/asm/syscall.h
+++ b/arch/csky/include/asm/syscall.h
@@ -70,7 +70,7 @@ syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
}
static inline int
-syscall_get_arch(void)
+syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_CSKY;
}
diff --git a/arch/h8300/include/asm/syscall.h b/arch/h8300/include/asm/syscall.h
index 5135910616e2..d316c3d40d4e 100644
--- a/arch/h8300/include/asm/syscall.h
+++ b/arch/h8300/include/asm/syscall.h
@@ -49,7 +49,7 @@ syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
}
static inline int
-syscall_get_arch(void)
+syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_H8300;
}
diff --git a/arch/hexagon/include/asm/syscall.h b/arch/hexagon/include/asm/syscall.h
index de3917aad3fd..47b0bc3f16be 100644
--- a/arch/hexagon/include/asm/syscall.h
+++ b/arch/hexagon/include/asm/syscall.h
@@ -46,7 +46,7 @@ static inline void syscall_get_arguments(struct task_struct *task,
memcpy(args, &(®s->r00)[i], n * sizeof(args[0]));
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_HEXAGON;
}
diff --git a/arch/ia64/include/asm/syscall.h b/arch/ia64/include/asm/syscall.h
index 1d0b875fec44..47ab33f5448a 100644
--- a/arch/ia64/include/asm/syscall.h
+++ b/arch/ia64/include/asm/syscall.h
@@ -81,7 +81,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
ia64_syscall_get_set_arguments(task, regs, i, n, args, 1);
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_IA64;
}
diff --git a/arch/m68k/include/asm/syscall.h b/arch/m68k/include/asm/syscall.h
index d4d7deda8d50..465ac039be09 100644
--- a/arch/m68k/include/asm/syscall.h
+++ b/arch/m68k/include/asm/syscall.h
@@ -4,7 +4,7 @@
#include <uapi/linux/audit.h>
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_M68K;
}
diff --git a/arch/microblaze/include/asm/syscall.h b/arch/microblaze/include/asm/syscall.h
index 220decd605a4..77a86fafa974 100644
--- a/arch/microblaze/include/asm/syscall.h
+++ b/arch/microblaze/include/asm/syscall.h
@@ -101,7 +101,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
asmlinkage unsigned long do_syscall_trace_enter(struct pt_regs *regs);
asmlinkage void do_syscall_trace_leave(struct pt_regs *regs);
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_MICROBLAZE;
}
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 6cf8ffb5367e..6a22c9352ef6 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -140,14 +140,14 @@ extern const unsigned long sys_call_table[];
extern const unsigned long sys32_call_table[];
extern const unsigned long sysn32_call_table[];
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
int arch = AUDIT_ARCH_MIPS;
#ifdef CONFIG_64BIT
- if (!test_thread_flag(TIF_32BIT_REGS)) {
+ if (!test_tsk_thread_flag(task, TIF_32BIT_REGS)) {
arch |= __AUDIT_ARCH_64BIT;
/* N32 sets only TIF_32BIT_ADDR */
- if (test_thread_flag(TIF_32BIT_ADDR))
+ if (test_tsk_thread_flag(task, TIF_32BIT_ADDR))
arch |= __AUDIT_ARCH_CONVENTION_MIPS64_N32;
}
#endif
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 0057c910bc2f..2ead6ff919b7 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -1418,7 +1418,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
unsigned long args[6];
sd.nr = syscall;
- sd.arch = syscall_get_arch();
+ sd.arch = syscall_get_arch(current);
syscall_get_arguments(current, regs, 0, 6, args);
for (i = 0; i < 6; i++)
sd.args[i] = args[i];
diff --git a/arch/nds32/include/asm/syscall.h b/arch/nds32/include/asm/syscall.h
index cc56a3962f8b..7501e376a6b1 100644
--- a/arch/nds32/include/asm/syscall.h
+++ b/arch/nds32/include/asm/syscall.h
@@ -188,7 +188,7 @@ void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
}
static inline int
-syscall_get_arch(void)
+syscall_get_arch(struct task_struct *task)
{
return IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)
? AUDIT_ARCH_NDS32BE : AUDIT_ARCH_NDS32;
diff --git a/arch/nios2/include/asm/syscall.h b/arch/nios2/include/asm/syscall.h
index cf35e210fc4d..f0f6ae208e78 100644
--- a/arch/nios2/include/asm/syscall.h
+++ b/arch/nios2/include/asm/syscall.h
@@ -136,7 +136,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
}
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_NIOS2;
}
diff --git a/arch/openrisc/include/asm/syscall.h b/arch/openrisc/include/asm/syscall.h
index 2db9f1cf0694..46b10c674bd2 100644
--- a/arch/openrisc/include/asm/syscall.h
+++ b/arch/openrisc/include/asm/syscall.h
@@ -72,7 +72,7 @@ syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
memcpy(®s->gpr[3 + i], args, n * sizeof(args[0]));
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_OPENRISC;
}
diff --git a/arch/parisc/include/asm/syscall.h b/arch/parisc/include/asm/syscall.h
index 8bff1a58c97f..c04ffc6ac928 100644
--- a/arch/parisc/include/asm/syscall.h
+++ b/arch/parisc/include/asm/syscall.h
@@ -62,11 +62,11 @@ static inline void syscall_rollback(struct task_struct *task,
/* do nothing */
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
int arch = AUDIT_ARCH_PARISC;
#ifdef CONFIG_64BIT
- if (!is_compat_task())
+ if (!__is_compat_task(task))
arch = AUDIT_ARCH_PARISC64;
#endif
return arch;
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index 1a0e7a8b1c81..efb50429c9f4 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -99,9 +99,15 @@ static inline void syscall_set_arguments(struct task_struct *task,
regs->orig_gpr3 = args[0];
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
- int arch = is_32bit_task() ? AUDIT_ARCH_PPC : AUDIT_ARCH_PPC64;
+ int arch;
+
+ if (IS_ENABLED(CONFIG_PPC64) && !test_tsk_thread_flag(task, TIF_32BIT))
+ arch = AUDIT_ARCH_PPC64;
+ else
+ arch = AUDIT_ARCH_PPC;
+
#ifdef __LITTLE_ENDIAN__
arch |= __AUDIT_ARCH_LE;
#endif
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index bba3da6ef157..ca120a36a037 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -100,7 +100,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
memcpy(®s->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0));
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
#ifdef CONFIG_64BIT
return AUDIT_ARCH_RISCV64;
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 96f9a9151fde..5a40ea8b90ea 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -92,10 +92,10 @@ static inline void syscall_set_arguments(struct task_struct *task,
regs->orig_gpr2 = args[0];
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
#ifdef CONFIG_COMPAT
- if (test_tsk_thread_flag(current, TIF_31BIT))
+ if (test_tsk_thread_flag(task, TIF_31BIT))
return AUDIT_ARCH_S390;
#endif
return AUDIT_ARCH_S390X;
diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h
index 6e118799831c..08de429eccd4 100644
--- a/arch/sh/include/asm/syscall_32.h
+++ b/arch/sh/include/asm/syscall_32.h
@@ -95,7 +95,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
}
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
int arch = AUDIT_ARCH_SH;
diff --git a/arch/sh/include/asm/syscall_64.h b/arch/sh/include/asm/syscall_64.h
index 43882580c7f9..9b62a2404531 100644
--- a/arch/sh/include/asm/syscall_64.h
+++ b/arch/sh/include/asm/syscall_64.h
@@ -63,7 +63,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
memcpy(®s->regs[2 + i], args, n * sizeof(args[0]));
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
int arch = AUDIT_ARCH_SH;
diff --git a/arch/sparc/include/asm/syscall.h b/arch/sparc/include/asm/syscall.h
index 053989e3f6a6..9ffb367c17fd 100644
--- a/arch/sparc/include/asm/syscall.h
+++ b/arch/sparc/include/asm/syscall.h
@@ -128,10 +128,11 @@ static inline void syscall_set_arguments(struct task_struct *task,
regs->u_regs[UREG_I0 + i + j] = args[j];
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
#if defined(CONFIG_SPARC64) && defined(CONFIG_COMPAT)
- return in_compat_syscall() ? AUDIT_ARCH_SPARC : AUDIT_ARCH_SPARC64;
+ return test_tsk_thread_flag(task, TIF_32BIT)
+ ? AUDIT_ARCH_SPARC : AUDIT_ARCH_SPARC64;
#elif defined(CONFIG_SPARC64)
return AUDIT_ARCH_SPARC64;
#else
diff --git a/arch/unicore32/include/asm/syscall.h b/arch/unicore32/include/asm/syscall.h
index 3a6b885476b4..607961797fff 100644
--- a/arch/unicore32/include/asm/syscall.h
+++ b/arch/unicore32/include/asm/syscall.h
@@ -4,7 +4,7 @@
#include <uapi/linux/audit.h>
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_UNICORE;
}
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index d653139857af..435f3f09279c 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -107,7 +107,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
memcpy(®s->bx + i, args, n * sizeof(args[0]));
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_I386;
}
@@ -236,10 +236,12 @@ static inline void syscall_set_arguments(struct task_struct *task,
}
}
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
/* x32 tasks should be considered AUDIT_ARCH_X86_64. */
- return in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
+ return (IS_ENABLED(CONFIG_IA32_EMULATION) &&
+ task->thread_info.status & TS_COMPAT)
+ ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
}
#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/um/asm/syscall.h b/arch/x86/um/asm/syscall.h
index ef898af102d1..56a2f0913e3c 100644
--- a/arch/x86/um/asm/syscall.h
+++ b/arch/x86/um/asm/syscall.h
@@ -9,7 +9,7 @@ typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
#ifdef CONFIG_X86_32
return AUDIT_ARCH_I386;
diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h
index a168bf81c7f4..0681ca656809 100644
--- a/arch/xtensa/include/asm/syscall.h
+++ b/arch/xtensa/include/asm/syscall.h
@@ -14,7 +14,7 @@
#include <asm/ptrace.h>
#include <uapi/linux/audit.h>
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_XTENSA;
}
diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
index 0c938a4354f6..e0d060b43321 100644
--- a/include/asm-generic/syscall.h
+++ b/include/asm-generic/syscall.h
@@ -144,14 +144,15 @@ void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
/**
* syscall_get_arch - return the AUDIT_ARCH for the current system call
+ * @task: task of interest, must be blocked
*
* Returns the AUDIT_ARCH_* based on the system call convention in use.
*
- * It's only valid to call this when current is stopped on entry to a system
+ * It's only valid to call this when @task is stopped on entry to a system
* call, due to %TIF_SYSCALL_TRACE, %TIF_SYSCALL_AUDIT, or %TIF_SECCOMP.
*
* Architectures which permit CONFIG_HAVE_ARCH_SECCOMP_FILTER must
* provide an implementation of this.
*/
-int syscall_get_arch(void);
+int syscall_get_arch(struct task_struct *task);
#endif /* _ASM_SYSCALL_H */
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index d1eab1d4a930..28f868239f0c 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1628,7 +1628,7 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2,
return;
}
- context->arch = syscall_get_arch();
+ context->arch = syscall_get_arch(current);
context->major = major;
context->argv[0] = a1;
context->argv[1] = a2;
@@ -2580,7 +2580,7 @@ void audit_seccomp(unsigned long syscall, long signr, int code)
return;
audit_log_task(ab);
audit_log_format(ab, " sig=%ld arch=%x syscall=%ld compat=%d ip=0x%lx code=0x%x",
- signr, syscall_get_arch(), syscall,
+ signr, syscall_get_arch(current), syscall,
in_compat_syscall(), KSTK_EIP(current), code);
audit_log_end(ab);
}
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 54a0347ca812..36f36ab00f48 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -148,7 +148,7 @@ static void populate_seccomp_data(struct seccomp_data *sd)
unsigned long args[6];
sd->nr = syscall_get_nr(task, regs);
- sd->arch = syscall_get_arch();
+ sd->arch = syscall_get_arch(task);
syscall_get_arguments(task, regs, 0, 6, args);
sd->args[0] = args[0];
sd->args[1] = args[1];
@@ -591,7 +591,7 @@ static void seccomp_init_siginfo(kernel_siginfo_t *info, int syscall, int reason
info->si_code = SYS_SECCOMP;
info->si_call_addr = (void __user *)KSTK_EIP(current);
info->si_errno = reason;
- info->si_arch = syscall_get_arch();
+ info->si_arch = syscall_get_arch(current);
info->si_syscall = syscall;
}
--
ldv
^ permalink raw reply related
* [RESEND PATCH v2] powerpc: mute unused-but-set-variable warnings
From: Qian Cai @ 2019-03-17 22:05 UTC (permalink / raw)
To: mpe, benh, paulus; +Cc: Qian Cai, linuxppc-dev, linux-kernel
pte_unmap() compiles away on some powerpc platforms, so silence the
warnings below by making it a static inline function.
mm/memory.c: In function 'copy_pte_range':
mm/memory.c:820:24: warning: variable 'orig_dst_pte' set but not used
[-Wunused-but-set-variable]
mm/memory.c:820:9: warning: variable 'orig_src_pte' set but not used
[-Wunused-but-set-variable]
mm/madvise.c: In function 'madvise_free_pte_range':
mm/madvise.c:318:9: warning: variable 'orig_pte' set but not used
[-Wunused-but-set-variable]
mm/swap_state.c: In function 'swap_ra_info':
mm/swap_state.c:634:15: warning: variable 'orig_pte' set but not used
[-Wunused-but-set-variable]
Suggested-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by:: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Qian Cai <cai@lca.pw>
---
v2: make it a static inline function.
arch/powerpc/include/asm/book3s/64/pgtable.h | 3 ++-
arch/powerpc/include/asm/nohash/64/pgtable.h | 3 ++-
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 868fcaf56f6b..d798e33a0c86 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1006,7 +1006,8 @@ extern struct page *pgd_page(pgd_t pgd);
(((pte_t *) pmd_page_vaddr(*(dir))) + pte_index(addr))
#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr))
-#define pte_unmap(pte) do { } while(0)
+
+static inline void pte_unmap(pte_t *pte) { }
/* to find an entry in a kernel page-table-directory */
/* This now only contains the vmalloc pages */
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index e77ed9761632..0384a3302fb6 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -205,7 +205,8 @@ static inline void pgd_set(pgd_t *pgdp, unsigned long val)
(((pte_t *) pmd_page_vaddr(*(dir))) + (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)))
#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr))
-#define pte_unmap(pte) do { } while(0)
+
+static inline void pte_unmap(pte_t *pte) { }
/* to find an entry in a kernel page-table-directory */
/* This now only contains the vmalloc pages */
--
2.17.2 (Apple Git-113)
^ permalink raw reply related
* Re: [PATCH v7 4/4] hugetlb: allow to free gigantic pages regardless of the configuration
From: christophe leroy @ 2019-03-17 18:31 UTC (permalink / raw)
To: Alexandre Ghiti, aneesh.kumar, mpe, Andrew Morton,
Vlastimil Babka, Catalin Marinas, Will Deacon,
Benjamin Herrenschmidt, Paul Mackerras, Martin Schwidefsky,
Heiko Carstens, Yoshinori Sato, Rich Felker, David S . Miller,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, H . Peter Anvin,
x86, Dave Hansen, Andy Lutomirski, Peter Zijlstra, Mike Kravetz,
linux-arm-kernel, linux-kernel, linuxppc-dev, linux-s390,
linux-sh, sparclinux, linux-mm
In-Reply-To: <20190317162847.14107-5-alex@ghiti.fr>
Le 17/03/2019 à 17:28, Alexandre Ghiti a écrit :
> On systems without CONTIG_ALLOC activated but that support gigantic pages,
> boottime reserved gigantic pages can not be freed at all. This patch
> simply enables the possibility to hand back those pages to memory
> allocator.
>
> Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
> Acked-by: David S. Miller <davem@davemloft.net> [sparc]
> ---
> arch/arm64/Kconfig | 2 +-
> arch/arm64/include/asm/hugetlb.h | 4 --
> arch/powerpc/include/asm/book3s/64/hugetlb.h | 7 ---
> arch/powerpc/platforms/Kconfig.cputype | 2 +-
> arch/s390/Kconfig | 2 +-
> arch/s390/include/asm/hugetlb.h | 3 --
> arch/sh/Kconfig | 2 +-
> arch/sparc/Kconfig | 2 +-
> arch/x86/Kconfig | 2 +-
> arch/x86/include/asm/hugetlb.h | 4 --
> include/asm-generic/hugetlb.h | 14 +++++
> include/linux/gfp.h | 2 +-
> mm/hugetlb.c | 54 ++++++++++++++------
> mm/page_alloc.c | 4 +-
> 14 files changed, 61 insertions(+), 43 deletions(-)
>
[...]
> diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
> index 71d7b77eea50..aaf14974ee5f 100644
> --- a/include/asm-generic/hugetlb.h
> +++ b/include/asm-generic/hugetlb.h
> @@ -126,4 +126,18 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
> }
> #endif
>
> +#ifndef __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
> +#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
> +static inline bool gigantic_page_runtime_supported(void)
> +{
> + return true;
> +}
> +#else
> +static inline bool gigantic_page_runtime_supported(void)
> +{
> + return false;
> +}
> +#endif /* CONFIG_ARCH_HAS_GIGANTIC_PAGE */
What about the following instead:
static inline bool gigantic_page_runtime_supported(void)
{
return IS_ENABLED(CONFIG_ARCH_HAS_GIGANTIC_PAGE);
}
> +#endif /* __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED */
> +
> #endif /* _ASM_GENERIC_HUGETLB_H */
> diff --git a/include/linux/gfp.h b/include/linux/gfp.h
> index 1f1ad9aeebb9..58ea44bf75de 100644
> --- a/include/linux/gfp.h
> +++ b/include/linux/gfp.h
> @@ -589,8 +589,8 @@ static inline bool pm_suspended_storage(void)
> /* The below functions must be run on a range from a single zone. */
> extern int alloc_contig_range(unsigned long start, unsigned long end,
> unsigned migratetype, gfp_t gfp_mask);
> -extern void free_contig_range(unsigned long pfn, unsigned nr_pages);
> #endif
> +extern void free_contig_range(unsigned long pfn, unsigned int nr_pages);
'extern' is unneeded and should be avoided (iaw checkpatch)
Christophe
>
> #ifdef CONFIG_CMA
> /* CMA stuff */
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index afef61656c1e..4e55aa38704f 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -1058,6 +1058,7 @@ static void free_gigantic_page(struct page *page, unsigned int order)
> free_contig_range(page_to_pfn(page), 1 << order);
> }
>
> +#ifdef CONFIG_CONTIG_ALLOC
> static int __alloc_gigantic_page(unsigned long start_pfn,
> unsigned long nr_pages, gfp_t gfp_mask)
> {
> @@ -1142,11 +1143,20 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
>
> static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
> static void prep_compound_gigantic_page(struct page *page, unsigned int order);
> +#else /* !CONFIG_CONTIG_ALLOC */
> +static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
> + int nid, nodemask_t *nodemask)
> +{
> + return NULL;
> +}
> +#endif /* CONFIG_CONTIG_ALLOC */
>
> #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */
> -static inline bool gigantic_page_supported(void) { return false; }
> static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
> - int nid, nodemask_t *nodemask) { return NULL; }
> + int nid, nodemask_t *nodemask)
> +{
> + return NULL;
> +}
> static inline void free_gigantic_page(struct page *page, unsigned int order) { }
> static inline void destroy_compound_gigantic_page(struct page *page,
> unsigned int order) { }
> @@ -1156,7 +1166,7 @@ static void update_and_free_page(struct hstate *h, struct page *page)
> {
> int i;
>
> - if (hstate_is_gigantic(h) && !gigantic_page_supported())
> + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
> return;
>
> h->nr_huge_pages--;
> @@ -2276,13 +2286,27 @@ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
> }
>
> #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
> -static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
> - nodemask_t *nodes_allowed)
> +static int set_max_huge_pages(struct hstate *h, unsigned long count,
> + nodemask_t *nodes_allowed)
> {
> unsigned long min_count, ret;
>
> - if (hstate_is_gigantic(h) && !gigantic_page_supported())
> - return h->max_huge_pages;
> + spin_lock(&hugetlb_lock);
> +
> + /*
> + * Gigantic pages runtime allocation depend on the capability for large
> + * page range allocation.
> + * If the system does not provide this feature, return an error when
> + * the user tries to allocate gigantic pages but let the user free the
> + * boottime allocated gigantic pages.
> + */
> + if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) {
> + if (count > persistent_huge_pages(h)) {
> + spin_unlock(&hugetlb_lock);
> + return -EINVAL;
> + }
> + /* Fall through to decrease pool */
> + }
>
> /*
> * Increase the pool size
> @@ -2295,7 +2319,6 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
> * pool might be one hugepage larger than it needs to be, but
> * within all the constraints specified by the sysctls.
> */
> - spin_lock(&hugetlb_lock);
> while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
> if (!adjust_pool_surplus(h, nodes_allowed, -1))
> break;
> @@ -2350,9 +2373,10 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
> break;
> }
> out:
> - ret = persistent_huge_pages(h);
> + h->max_huge_pages = persistent_huge_pages(h);
> spin_unlock(&hugetlb_lock);
> - return ret;
> +
> + return 0;
> }
>
> #define HSTATE_ATTR_RO(_name) \
> @@ -2404,7 +2428,7 @@ static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
> int err;
> NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY);
>
> - if (hstate_is_gigantic(h) && !gigantic_page_supported()) {
> + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) {
> err = -EINVAL;
> goto out;
> }
> @@ -2428,15 +2452,13 @@ static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
> } else
> nodes_allowed = &node_states[N_MEMORY];
>
> - h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed);
> + err = set_max_huge_pages(h, count, nodes_allowed);
>
> +out:
> if (nodes_allowed != &node_states[N_MEMORY])
> NODEMASK_FREE(nodes_allowed);
>
> - return len;
> -out:
> - NODEMASK_FREE(nodes_allowed);
> - return err;
> + return err ? err : len;
> }
>
> static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index ac9c45ffb344..a4547d90fa7a 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -8234,8 +8234,9 @@ int alloc_contig_range(unsigned long start, unsigned long end,
> pfn_max_align_up(end), migratetype);
> return ret;
> }
> +#endif /* CONFIG_CONTIG_ALLOC */
>
> -void free_contig_range(unsigned long pfn, unsigned nr_pages)
> +void free_contig_range(unsigned long pfn, unsigned int nr_pages)
> {
> unsigned int count = 0;
>
> @@ -8247,7 +8248,6 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
> }
> WARN(count != 0, "%d pages are still in use!\n", count);
> }
> -#endif
>
> #ifdef CONFIG_MEMORY_HOTPLUG
> /*
>
---
L'absence de virus dans ce courrier électronique a été vérifiée par le logiciel antivirus Avast.
https://www.avast.com/antivirus
^ permalink raw reply
* Re: Mac Mini G4 hang on boot with git master
From: Mark Cave-Ayland @ 2019-03-17 18:29 UTC (permalink / raw)
To: christophe leroy, linuxppc-dev; +Cc: paulus
In-Reply-To: <926e0e0b-c54c-13ed-f2ec-be22bef92538@c-s.fr>
On 17/03/2019 16:25, christophe leroy wrote:
>> This was a weird one: bisecting directly from git master gave a nonsense result,
>> however by manually rebasing Michael's PR onto my last known good commit from master
>> I was able to finally pin it down to this commit:
>>
>>
>> 7a0d6955f3f7a4250da63d528bfff7a9c91b5725 is the first bad commit
>> commit 7a0d6955f3f7a4250da63d528bfff7a9c91b5725
>> Author: Christophe Leroy <christophe.leroy@c-s.fr>
>> Date: Thu Feb 21 10:37:55 2019 +0000
>>
>> powerpc/6xx: Store PGDIR physical address in a SPRG
>>
>> Use SPRN_SPRG2 to store the current thread PGDIR and
>> avoid reading thread_struct.pgdir at every TLB miss.
>>
>> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
>> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
>>
>>
>
> Hi,
>
> The fix is there:
>
> https://patchwork.ozlabs.org/patch/1053385/
>
> Christophe
Hi Christophe,
Thank you! I've tried the patch here and have confirmed that it fixes the problem
with the hang on boot.
ATB,
Mark.
^ permalink raw reply
* [PATCH v7 4/4] hugetlb: allow to free gigantic pages regardless of the configuration
From: Alexandre Ghiti @ 2019-03-17 16:28 UTC (permalink / raw)
To: aneesh.kumar, mpe, Andrew Morton, Vlastimil Babka,
Catalin Marinas, Will Deacon, Benjamin Herrenschmidt,
Paul Mackerras, Martin Schwidefsky, Heiko Carstens,
Yoshinori Sato, Rich Felker, David S . Miller, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, H . Peter Anvin, x86, Dave Hansen,
Andy Lutomirski, Peter Zijlstra, Mike Kravetz, linux-arm-kernel,
linux-kernel, linuxppc-dev, linux-s390, linux-sh, sparclinux,
linux-mm
Cc: Alexandre Ghiti
In-Reply-To: <20190317162847.14107-1-alex@ghiti.fr>
On systems without CONTIG_ALLOC activated but that support gigantic pages,
boottime reserved gigantic pages can not be freed at all. This patch
simply enables the possibility to hand back those pages to memory
allocator.
Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
Acked-by: David S. Miller <davem@davemloft.net> [sparc]
---
arch/arm64/Kconfig | 2 +-
arch/arm64/include/asm/hugetlb.h | 4 --
arch/powerpc/include/asm/book3s/64/hugetlb.h | 7 ---
arch/powerpc/platforms/Kconfig.cputype | 2 +-
arch/s390/Kconfig | 2 +-
arch/s390/include/asm/hugetlb.h | 3 --
arch/sh/Kconfig | 2 +-
arch/sparc/Kconfig | 2 +-
arch/x86/Kconfig | 2 +-
arch/x86/include/asm/hugetlb.h | 4 --
include/asm-generic/hugetlb.h | 14 +++++
include/linux/gfp.h | 2 +-
mm/hugetlb.c | 54 ++++++++++++++------
mm/page_alloc.c | 4 +-
14 files changed, 61 insertions(+), 43 deletions(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 091a513b93e9..af687eff884a 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -18,7 +18,7 @@ config ARM64
select ARCH_HAS_FAST_MULTIPLIER
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
- select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
+ select ARCH_HAS_GIGANTIC_PAGE
select ARCH_HAS_KCOV
select ARCH_HAS_MEMBARRIER_SYNC_CORE
select ARCH_HAS_PTE_SPECIAL
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index fb6609875455..59893e766824 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -65,8 +65,4 @@ extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
#include <asm-generic/hugetlb.h>
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void) { return true; }
-#endif
-
#endif /* __ASM_HUGETLB_H */
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index 5b0177733994..d04a0bcc2f1c 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -32,13 +32,6 @@ static inline int hstate_get_psize(struct hstate *hstate)
}
}
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void)
-{
- return true;
-}
-#endif
-
/* hugepd entry valid bit */
#define HUGEPD_VAL_BITS (0x8000000000000000UL)
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index f677c8974212..dc0328de20cd 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -319,7 +319,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
config PPC_RADIX_MMU
bool "Radix MMU Support"
depends on PPC_BOOK3S_64
- select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
+ select ARCH_HAS_GIGANTIC_PAGE
default y
help
Enable support for the Power ISA 3.0 Radix style MMU. Currently this
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 1c57b83c76f5..d84e536796b1 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -69,7 +69,7 @@ config S390
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
- select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
+ select ARCH_HAS_GIGANTIC_PAGE
select ARCH_HAS_KCOV
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_SET_MEMORY
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 2d1afa58a4b6..bd191560efcf 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -116,7 +116,4 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
return pte_modify(pte, newprot);
}
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void) { return true; }
-#endif
#endif /* _ASM_S390_HUGETLB_H */
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index c7266302691c..404b12a0d871 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -53,7 +53,7 @@ config SUPERH
select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_NMI
select NEED_SG_DMA_LENGTH
- select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
+ select ARCH_HAS_GIGANTIC_PAGE
help
The SuperH is a RISC processor targeted for use in embedded systems
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index ca33c80870e2..234a6bd46e89 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -90,7 +90,7 @@ config SPARC64
select ARCH_CLOCKSOURCE_DATA
select ARCH_HAS_PTE_SPECIAL
select PCI_DOMAINS if PCI
- select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
+ select ARCH_HAS_GIGANTIC_PAGE
config ARCH_DEFCONFIG
string
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8ba90f3e0038..ff24eaeef211 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -23,7 +23,7 @@ config X86_64
def_bool y
depends on 64BIT
# Options that are inherently 64-bit kernel only:
- select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
+ select ARCH_HAS_GIGANTIC_PAGE
select ARCH_SUPPORTS_INT128
select ARCH_USE_CMPXCHG_LOCKREF
select HAVE_ARCH_SOFT_DIRTY
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 7469d321f072..f65cfb48cfdd 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -17,8 +17,4 @@ static inline void arch_clear_hugepage_flags(struct page *page)
{
}
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void) { return true; }
-#endif
-
#endif /* _ASM_X86_HUGETLB_H */
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 71d7b77eea50..aaf14974ee5f 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -126,4 +126,18 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
}
#endif
+#ifndef __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
+#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
+static inline bool gigantic_page_runtime_supported(void)
+{
+ return true;
+}
+#else
+static inline bool gigantic_page_runtime_supported(void)
+{
+ return false;
+}
+#endif /* CONFIG_ARCH_HAS_GIGANTIC_PAGE */
+#endif /* __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED */
+
#endif /* _ASM_GENERIC_HUGETLB_H */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 1f1ad9aeebb9..58ea44bf75de 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -589,8 +589,8 @@ static inline bool pm_suspended_storage(void)
/* The below functions must be run on a range from a single zone. */
extern int alloc_contig_range(unsigned long start, unsigned long end,
unsigned migratetype, gfp_t gfp_mask);
-extern void free_contig_range(unsigned long pfn, unsigned nr_pages);
#endif
+extern void free_contig_range(unsigned long pfn, unsigned int nr_pages);
#ifdef CONFIG_CMA
/* CMA stuff */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index afef61656c1e..4e55aa38704f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1058,6 +1058,7 @@ static void free_gigantic_page(struct page *page, unsigned int order)
free_contig_range(page_to_pfn(page), 1 << order);
}
+#ifdef CONFIG_CONTIG_ALLOC
static int __alloc_gigantic_page(unsigned long start_pfn,
unsigned long nr_pages, gfp_t gfp_mask)
{
@@ -1142,11 +1143,20 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
static void prep_compound_gigantic_page(struct page *page, unsigned int order);
+#else /* !CONFIG_CONTIG_ALLOC */
+static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
+ int nid, nodemask_t *nodemask)
+{
+ return NULL;
+}
+#endif /* CONFIG_CONTIG_ALLOC */
#else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */
-static inline bool gigantic_page_supported(void) { return false; }
static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
- int nid, nodemask_t *nodemask) { return NULL; }
+ int nid, nodemask_t *nodemask)
+{
+ return NULL;
+}
static inline void free_gigantic_page(struct page *page, unsigned int order) { }
static inline void destroy_compound_gigantic_page(struct page *page,
unsigned int order) { }
@@ -1156,7 +1166,7 @@ static void update_and_free_page(struct hstate *h, struct page *page)
{
int i;
- if (hstate_is_gigantic(h) && !gigantic_page_supported())
+ if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
return;
h->nr_huge_pages--;
@@ -2276,13 +2286,27 @@ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
}
#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
-static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
- nodemask_t *nodes_allowed)
+static int set_max_huge_pages(struct hstate *h, unsigned long count,
+ nodemask_t *nodes_allowed)
{
unsigned long min_count, ret;
- if (hstate_is_gigantic(h) && !gigantic_page_supported())
- return h->max_huge_pages;
+ spin_lock(&hugetlb_lock);
+
+ /*
+ * Gigantic pages runtime allocation depend on the capability for large
+ * page range allocation.
+ * If the system does not provide this feature, return an error when
+ * the user tries to allocate gigantic pages but let the user free the
+ * boottime allocated gigantic pages.
+ */
+ if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) {
+ if (count > persistent_huge_pages(h)) {
+ spin_unlock(&hugetlb_lock);
+ return -EINVAL;
+ }
+ /* Fall through to decrease pool */
+ }
/*
* Increase the pool size
@@ -2295,7 +2319,6 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
* pool might be one hugepage larger than it needs to be, but
* within all the constraints specified by the sysctls.
*/
- spin_lock(&hugetlb_lock);
while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
if (!adjust_pool_surplus(h, nodes_allowed, -1))
break;
@@ -2350,9 +2373,10 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
break;
}
out:
- ret = persistent_huge_pages(h);
+ h->max_huge_pages = persistent_huge_pages(h);
spin_unlock(&hugetlb_lock);
- return ret;
+
+ return 0;
}
#define HSTATE_ATTR_RO(_name) \
@@ -2404,7 +2428,7 @@ static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
int err;
NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY);
- if (hstate_is_gigantic(h) && !gigantic_page_supported()) {
+ if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) {
err = -EINVAL;
goto out;
}
@@ -2428,15 +2452,13 @@ static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
} else
nodes_allowed = &node_states[N_MEMORY];
- h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed);
+ err = set_max_huge_pages(h, count, nodes_allowed);
+out:
if (nodes_allowed != &node_states[N_MEMORY])
NODEMASK_FREE(nodes_allowed);
- return len;
-out:
- NODEMASK_FREE(nodes_allowed);
- return err;
+ return err ? err : len;
}
static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ac9c45ffb344..a4547d90fa7a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8234,8 +8234,9 @@ int alloc_contig_range(unsigned long start, unsigned long end,
pfn_max_align_up(end), migratetype);
return ret;
}
+#endif /* CONFIG_CONTIG_ALLOC */
-void free_contig_range(unsigned long pfn, unsigned nr_pages)
+void free_contig_range(unsigned long pfn, unsigned int nr_pages)
{
unsigned int count = 0;
@@ -8247,7 +8248,6 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
}
WARN(count != 0, "%d pages are still in use!\n", count);
}
-#endif
#ifdef CONFIG_MEMORY_HOTPLUG
/*
--
2.20.1
^ permalink raw reply related
* [PATCH v7 3/4] mm: Simplify MEMORY_ISOLATION && COMPACTION || CMA into CONTIG_ALLOC
From: Alexandre Ghiti @ 2019-03-17 16:28 UTC (permalink / raw)
To: aneesh.kumar, mpe, Andrew Morton, Vlastimil Babka,
Catalin Marinas, Will Deacon, Benjamin Herrenschmidt,
Paul Mackerras, Martin Schwidefsky, Heiko Carstens,
Yoshinori Sato, Rich Felker, David S . Miller, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, H . Peter Anvin, x86, Dave Hansen,
Andy Lutomirski, Peter Zijlstra, Mike Kravetz, linux-arm-kernel,
linux-kernel, linuxppc-dev, linux-s390, linux-sh, sparclinux,
linux-mm
Cc: Alexandre Ghiti
In-Reply-To: <20190317162847.14107-1-alex@ghiti.fr>
This condition allows to define alloc_contig_range, so simplify
it into a more accurate naming.
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
arch/arm64/Kconfig | 2 +-
arch/powerpc/platforms/Kconfig.cputype | 2 +-
arch/s390/Kconfig | 2 +-
arch/sh/Kconfig | 2 +-
arch/sparc/Kconfig | 2 +-
arch/x86/Kconfig | 2 +-
arch/x86/mm/hugetlbpage.c | 2 +-
include/linux/gfp.h | 2 +-
mm/Kconfig | 3 +++
mm/page_alloc.c | 3 +--
10 files changed, 12 insertions(+), 10 deletions(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a4168d366127..091a513b93e9 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -18,7 +18,7 @@ config ARM64
select ARCH_HAS_FAST_MULTIPLIER
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
- select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+ select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
select ARCH_HAS_KCOV
select ARCH_HAS_MEMBARRIER_SYNC_CORE
select ARCH_HAS_PTE_SPECIAL
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 8c7464c3f27f..f677c8974212 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -319,7 +319,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
config PPC_RADIX_MMU
bool "Radix MMU Support"
depends on PPC_BOOK3S_64
- select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+ select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
default y
help
Enable support for the Power ISA 3.0 Radix style MMU. Currently this
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index ed554b09eb3f..1c57b83c76f5 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -69,7 +69,7 @@ config S390
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
- select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+ select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
select ARCH_HAS_KCOV
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_SET_MEMORY
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 299a17bed67c..c7266302691c 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -53,7 +53,7 @@ config SUPERH
select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_NMI
select NEED_SG_DMA_LENGTH
- select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+ select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
help
The SuperH is a RISC processor targeted for use in embedded systems
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 0b7f0e0fefa5..ca33c80870e2 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -90,7 +90,7 @@ config SPARC64
select ARCH_CLOCKSOURCE_DATA
select ARCH_HAS_PTE_SPECIAL
select PCI_DOMAINS if PCI
- select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+ select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
config ARCH_DEFCONFIG
string
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 68261430fe6e..8ba90f3e0038 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -23,7 +23,7 @@ config X86_64
def_bool y
depends on 64BIT
# Options that are inherently 64-bit kernel only:
- select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+ select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
select ARCH_SUPPORTS_INT128
select ARCH_USE_CMPXCHG_LOCKREF
select HAVE_ARCH_SOFT_DIRTY
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 92e4c4b85bba..fab095362c50 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -203,7 +203,7 @@ static __init int setup_hugepagesz(char *opt)
}
__setup("hugepagesz=", setup_hugepagesz);
-#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
+#ifdef CONFIG_CONTIG_ALLOC
static __init int gigantic_pages_init(void)
{
/* With compaction or CMA we can allocate gigantic pages at runtime */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 5f5e25fd6149..1f1ad9aeebb9 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -585,7 +585,7 @@ static inline bool pm_suspended_storage(void)
}
#endif /* CONFIG_PM_SLEEP */
-#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
+#ifdef CONFIG_CONTIG_ALLOC
/* The below functions must be run on a range from a single zone. */
extern int alloc_contig_range(unsigned long start, unsigned long end,
unsigned migratetype, gfp_t gfp_mask);
diff --git a/mm/Kconfig b/mm/Kconfig
index 25c71eb8a7db..137eadc18732 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -258,6 +258,9 @@ config ARCH_ENABLE_HUGEPAGE_MIGRATION
config ARCH_ENABLE_THP_MIGRATION
bool
+config CONTIG_ALLOC
+ def_bool (MEMORY_ISOLATION && COMPACTION) || CMA
+
config PHYS_ADDR_T_64BIT
def_bool 64BIT
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 35fdde041f5c..ac9c45ffb344 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8024,8 +8024,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
return true;
}
-#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
-
+#ifdef CONFIG_CONTIG_ALLOC
static unsigned long pfn_max_align_down(unsigned long pfn)
{
return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES,
--
2.20.1
^ permalink raw reply related
* [PATCH v7 2/4] sparc: Advertise gigantic page support
From: Alexandre Ghiti @ 2019-03-17 16:28 UTC (permalink / raw)
To: aneesh.kumar, mpe, Andrew Morton, Vlastimil Babka,
Catalin Marinas, Will Deacon, Benjamin Herrenschmidt,
Paul Mackerras, Martin Schwidefsky, Heiko Carstens,
Yoshinori Sato, Rich Felker, David S . Miller, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, H . Peter Anvin, x86, Dave Hansen,
Andy Lutomirski, Peter Zijlstra, Mike Kravetz, linux-arm-kernel,
linux-kernel, linuxppc-dev, linux-s390, linux-sh, sparclinux,
linux-mm
Cc: Alexandre Ghiti
In-Reply-To: <20190317162847.14107-1-alex@ghiti.fr>
sparc actually supports gigantic pages and selecting
ARCH_HAS_GIGANTIC_PAGE allows it to allocate and free
gigantic pages at runtime.
sparc allows configuration such as huge pages of 16GB,
pages of 8KB and MAX_ORDER = 13 (default):
HPAGE_SHIFT (34) - PAGE_SHIFT (13) = 21 >= MAX_ORDER (13)
Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
Acked-by: David S. Miller <davem@davemloft.net>
---
arch/sparc/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index d5dd652fb8cc..0b7f0e0fefa5 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -90,6 +90,7 @@ config SPARC64
select ARCH_CLOCKSOURCE_DATA
select ARCH_HAS_PTE_SPECIAL
select PCI_DOMAINS if PCI
+ select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
config ARCH_DEFCONFIG
string
--
2.20.1
^ permalink raw reply related
* [PATCH v7 1/4] sh: Advertise gigantic page support
From: Alexandre Ghiti @ 2019-03-17 16:28 UTC (permalink / raw)
To: aneesh.kumar, mpe, Andrew Morton, Vlastimil Babka,
Catalin Marinas, Will Deacon, Benjamin Herrenschmidt,
Paul Mackerras, Martin Schwidefsky, Heiko Carstens,
Yoshinori Sato, Rich Felker, David S . Miller, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, H . Peter Anvin, x86, Dave Hansen,
Andy Lutomirski, Peter Zijlstra, Mike Kravetz, linux-arm-kernel,
linux-kernel, linuxppc-dev, linux-s390, linux-sh, sparclinux,
linux-mm
Cc: Alexandre Ghiti
In-Reply-To: <20190317162847.14107-1-alex@ghiti.fr>
sh actually supports gigantic pages and selecting
ARCH_HAS_GIGANTIC_PAGE allows it to allocate and free
gigantic pages at runtime.
At least sdk7786_defconfig exposes such a configuration with
huge pages of 64MB, pages of 4KB and MAX_ORDER = 11:
HPAGE_SHIFT (26) - PAGE_SHIFT (12) = 14 >= MAX_ORDER (11)
Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
---
arch/sh/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index a9c36f95744a..299a17bed67c 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -53,6 +53,7 @@ config SUPERH
select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_NMI
select NEED_SG_DMA_LENGTH
+ select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
help
The SuperH is a RISC processor targeted for use in embedded systems
--
2.20.1
^ permalink raw reply related
* [PATCH v7 0/4] Fix free/allocation of runtime gigantic pages
From: Alexandre Ghiti @ 2019-03-17 16:28 UTC (permalink / raw)
To: aneesh.kumar, mpe, Andrew Morton, Vlastimil Babka,
Catalin Marinas, Will Deacon, Benjamin Herrenschmidt,
Paul Mackerras, Martin Schwidefsky, Heiko Carstens,
Yoshinori Sato, Rich Felker, David S . Miller, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, H . Peter Anvin, x86, Dave Hansen,
Andy Lutomirski, Peter Zijlstra, Mike Kravetz, linux-arm-kernel,
linux-kernel, linuxppc-dev, linux-s390, linux-sh, sparclinux,
linux-mm
Cc: Alexandre Ghiti
his series fixes sh and sparc that did not advertise their gigantic page
support and then were not able to allocate and free those pages at runtime.
It renames MEMORY_ISOLATION && COMPACTION || CMA condition into the more
accurate CONTIG_ALLOC, since it allows the definition of alloc_contig_range
function.
Finally, it then fixes the wrong definition of ARCH_HAS_GIGANTIC_PAGE config
that, without MEMORY_ISOLATION && COMPACTION || CMA defined, did not allow
architectures to free boottime allocated gigantic pages although unrelated.
Changes in v7:
I thought gigantic page support was settled at compile time, but Aneesh
and Michael have just come up with a patch proving me wrong for
powerpc: https://patchwork.ozlabs.org/patch/1047003/. So this version:
- reintroduces gigantic_page_supported renamed into
gigantic_page_runtime_supported
- reintroduces gigantic page page support corresponding checks (not
everywhere though: set_max_huge_pages check was redundant with
__nr_hugepages_store_common)
- introduces the possibility for arch to override this function
by using asm-generic/hugetlb.h current semantics although Aneesh
proposed something else.
Changes in v6:
- Remove unnecessary goto since the fallthrough path does the same and is
the 'normal' behaviour, as suggested by Dave Hensen
- Be more explicit in comment in set_max_huge_page: we return an error
if alloc_contig_range is not defined and the user tries to allocate a
gigantic page (we keep the same behaviour as before this patch), but we
now let her free boottime gigantic page, as suggested by Dave Hensen
- Add Acked-by, thanks.
Changes in v5:
- Fix bug in previous version thanks to Mike Kravetz
- Fix block comments that did not respect coding style thanks to Dave Hensen
- Define ARCH_HAS_GIGANTIC_PAGE only for sparc64 as advised by David Miller
- Factorize "def_bool" and "depends on" thanks to Vlastimil Babka
Changes in v4 as suggested by Dave Hensen:
- Split previous version into small patches
- Do not compile alloc_gigantic** functions for architectures that do not
support those pages
- Define correct ARCH_HAS_GIGANTIC_PAGE in all arch that support them to avoid
useless runtime check
- Add comment in set_max_huge_pages to explain that freeing is possible even
without CONTIG_ALLOC defined
- Remove gigantic_page_supported function across all archs
Changes in v3 as suggested by Vlastimil Babka and Dave Hansen:
- config definition was wrong and is now in mm/Kconfig
- COMPACTION_CORE was renamed in CONTIG_ALLOC
Changes in v2 as suggested by Vlastimil Babka:
- Get rid of ARCH_HAS_GIGANTIC_PAGE
- Get rid of architecture specific gigantic_page_supported
- Factorize CMA or (MEMORY_ISOLATION && COMPACTION) into COMPACTION_CORE
Alexandre Ghiti (4):
sh: Advertise gigantic page support
sparc: Advertise gigantic page support
mm: Simplify MEMORY_ISOLATION && COMPACTION || CMA into CONTIG_ALLOC
hugetlb: allow to free gigantic pages regardless of the configuration
arch/arm64/Kconfig | 2 +-
arch/arm64/include/asm/hugetlb.h | 4 --
arch/powerpc/include/asm/book3s/64/hugetlb.h | 7 ---
arch/powerpc/platforms/Kconfig.cputype | 2 +-
arch/s390/Kconfig | 2 +-
arch/s390/include/asm/hugetlb.h | 3 --
arch/sh/Kconfig | 1 +
arch/sparc/Kconfig | 1 +
arch/x86/Kconfig | 2 +-
arch/x86/include/asm/hugetlb.h | 4 --
arch/x86/mm/hugetlbpage.c | 2 +-
include/asm-generic/hugetlb.h | 14 +++++
include/linux/gfp.h | 4 +-
mm/Kconfig | 3 ++
mm/hugetlb.c | 54 ++++++++++++++------
mm/page_alloc.c | 7 ++-
16 files changed, 67 insertions(+), 45 deletions(-)
--
2.20.1
^ permalink raw reply
* Re: Mac Mini G4 hang on boot with git master
From: christophe leroy @ 2019-03-17 16:25 UTC (permalink / raw)
To: Mark Cave-Ayland, linuxppc-dev; +Cc: paulus
In-Reply-To: <f5ded479-7008-7b81-a5d9-84f4b3724fe9@ilande.co.uk>
Le 17/03/2019 à 15:15, Mark Cave-Ayland a écrit :
> On 15/03/2019 13:37, Mark Cave-Ayland wrote:
>
>> Hi all,
>>
>> I've just done a git pull and rebuilt master on my Mac Mini G4 in order to test
>> Michael's merge of my KVM PR fix, and unfortunately my kernel now hangs on boot :(
>>
>> My last working git checkout was somewhere around the 5.0-rc stage, so I suspect it's
>> something that's been merged for 5.1.
>>
>> The hang occurs just after the boot console is disabled which makes me wonder if
>> something is going wrong during PCI bus enumeration. Does anyone have an idea as to
>> what may be causing this? I can obviously bisect it down, but on slow hardware it can
>> take some time...
>
> This was a weird one: bisecting directly from git master gave a nonsense result,
> however by manually rebasing Michael's PR onto my last known good commit from master
> I was able to finally pin it down to this commit:
>
>
> 7a0d6955f3f7a4250da63d528bfff7a9c91b5725 is the first bad commit
> commit 7a0d6955f3f7a4250da63d528bfff7a9c91b5725
> Author: Christophe Leroy <christophe.leroy@c-s.fr>
> Date: Thu Feb 21 10:37:55 2019 +0000
>
> powerpc/6xx: Store PGDIR physical address in a SPRG
>
> Use SPRN_SPRG2 to store the current thread PGDIR and
> avoid reading thread_struct.pgdir at every TLB miss.
>
> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
>
>
Hi,
The fix is there:
https://patchwork.ozlabs.org/patch/1053385/
Christophe
---
L'absence de virus dans ce courrier électronique a été vérifiée par le logiciel antivirus Avast.
https://www.avast.com/antivirus
^ permalink raw reply
* [PATCH v2 5/5] powerpc/mm/hash: Simplify the region id calculation.
From: Aneesh Kumar K.V @ 2019-03-17 15:48 UTC (permalink / raw)
To: npiggin, benh, paulus, mpe; +Cc: Aneesh Kumar K.V, linuxppc-dev
In-Reply-To: <20190317154827.9188-1-aneesh.kumar@linux.ibm.com>
This reduces multiple comparisons in get_region_id to a bit shift operation.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/powerpc/include/asm/book3s/64/hash-4k.h | 4 ++-
arch/powerpc/include/asm/book3s/64/hash-64k.h | 1 +
arch/powerpc/include/asm/book3s/64/hash.h | 31 +++++++++----------
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 2 +-
4 files changed, 20 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 0dd62287f56c..64eaf187f891 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -13,12 +13,14 @@
*/
#define MAX_EA_BITS_PER_CONTEXT 46
+#define REGION_SHIFT (MAX_EA_BITS_PER_CONTEXT - 2)
+
/*
* Our page table limit us to 64TB. Hence for the kernel mapping,
* each MAP area is limited to 16 TB.
* The four map areas are: linear mapping, vmap, IO and vmemmap
*/
-#define H_KERN_MAP_SIZE (ASM_CONST(1) << (MAX_EA_BITS_PER_CONTEXT - 2))
+#define H_KERN_MAP_SIZE (ASM_CONST(1) << REGION_SHIFT)
/*
* Define the address range of the kernel non-linear virtual area
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index e392cf17b457..24ca63beba14 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -12,6 +12,7 @@
* is handled in the hotpath.
*/
#define MAX_EA_BITS_PER_CONTEXT 49
+#define REGION_SHIFT MAX_EA_BITS_PER_CONTEXT
/*
* We use one context for each MAP area.
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 523b9191a1e2..d1f0d7332b84 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -87,26 +87,26 @@
#define H_VMEMMAP_SIZE H_KERN_MAP_SIZE
#define H_VMEMMAP_END (H_VMEMMAP_START + H_VMEMMAP_SIZE)
+#define REGION_ID(ea) ((((unsigned long)ea - H_KERN_VIRT_START) >> REGION_SHIFT) + 2)
+
/*
* Region IDs
*/
-#define USER_REGION_ID 1
-#define KERNEL_REGION_ID 2
-#define VMALLOC_REGION_ID 3
-#define IO_REGION_ID 4
-#define VMEMMAP_REGION_ID 5
+#define USER_REGION_ID 0
+#define KERNEL_REGION_ID 1
+#define VMALLOC_REGION_ID REGION_ID(H_VMALLOC_START)
+#define IO_REGION_ID REGION_ID(H_KERN_IO_START)
+#define VMEMMAP_REGION_ID REGION_ID(H_VMEMMAP_START)
/*
* Defines the address of the vmemap area, in its own region on
* hash table CPUs.
*/
-
#ifdef CONFIG_PPC_MM_SLICES
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
#endif /* CONFIG_PPC_MM_SLICES */
-
/* PTEIDX nibble */
#define _PTEIDX_SECONDARY 0x8
#define _PTEIDX_GROUP_IX 0x7
@@ -117,22 +117,21 @@
#ifndef __ASSEMBLY__
static inline int get_region_id(unsigned long ea)
{
+ int region_id;
int id = (ea >> 60UL);
if (id == 0)
return USER_REGION_ID;
- VM_BUG_ON(id != 0xc);
- VM_BUG_ON(ea >= H_VMEMMAP_END);
+ if (ea < H_KERN_VIRT_START)
+ return KERNEL_REGION_ID;
- if (ea >= H_VMEMMAP_START)
- return VMEMMAP_REGION_ID;
- else if (ea >= H_KERN_IO_START)
- return IO_REGION_ID;
- else if (ea >= H_VMALLOC_START)
- return VMALLOC_REGION_ID;
+ VM_BUG_ON(id != 0xc);
+ BUILD_BUG_ON(REGION_ID(H_VMALLOC_START) != 2);
- return KERNEL_REGION_ID;
+ region_id = REGION_ID(ea);
+ VM_BUG_ON(region_id > VMEMMAP_REGION_ID);
+ return region_id;
}
#define hash__pmd_bad(pmd) (pmd_val(pmd) & H_PMD_BAD_BITS)
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index b3f256c042aa..b146448109fd 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -794,7 +794,7 @@ static inline unsigned long get_kernel_context(unsigned long ea)
*/
ctx = 1 + ((ea & EA_MASK) >> MAX_EA_BITS_PER_CONTEXT);
} else
- ctx = region_id + MAX_KERNEL_CTX_CNT - 2;
+ ctx = region_id + MAX_KERNEL_CTX_CNT - 1;
return ctx;
}
--
2.20.1
^ permalink raw reply related
* [PATCH v2 4/5] powerpc/mm: Drop the unnecessary region check
From: Aneesh Kumar K.V @ 2019-03-17 15:48 UTC (permalink / raw)
To: npiggin, benh, paulus, mpe; +Cc: Aneesh Kumar K.V, linuxppc-dev
In-Reply-To: <20190317154827.9188-1-aneesh.kumar@linux.ibm.com>
All the regions are now mapped with top nibble 0xc. Hence the region id
check is not needed for virt_addr_valid()
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/powerpc/include/asm/page.h | 12 ------------
1 file changed, 12 deletions(-)
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 918228f2205b..748f5db2e2b7 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -132,19 +132,7 @@ static inline bool pfn_valid(unsigned long pfn)
#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr))
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
-#ifdef CONFIG_PPC_BOOK3S_64
-/*
- * On hash the vmalloc and other regions alias to the kernel region when passed
- * through __pa(), which virt_to_pfn() uses. That means virt_addr_valid() can
- * return true for some vmalloc addresses, which is incorrect. So explicitly
- * check that the address is in the kernel region.
- */
-/* may be can drop get_region_id */
-#define virt_addr_valid(kaddr) (get_region_id((unsigned long)kaddr) == KERNEL_REGION_ID && \
- pfn_valid(virt_to_pfn(kaddr)))
-#else
#define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr))
-#endif
/*
* On Book-E parts we need __va to parse the device tree and we can't
--
2.20.1
^ permalink raw reply related
* [PATCH v2 3/5] powerpc/mm: Validate address values against different region limits
From: Aneesh Kumar K.V @ 2019-03-17 15:48 UTC (permalink / raw)
To: npiggin, benh, paulus, mpe; +Cc: Aneesh Kumar K.V, linuxppc-dev
In-Reply-To: <20190317154827.9188-1-aneesh.kumar@linux.ibm.com>
This adds an explicit check in various functions.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/powerpc/mm/hash_utils_64.c | 18 +++++++++++++++---
arch/powerpc/mm/pgtable-hash64.c | 13 ++++++++++---
arch/powerpc/mm/pgtable-radix.c | 16 ++++++++++++++++
arch/powerpc/mm/pgtable_64.c | 5 +++++
4 files changed, 46 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index c6b39e7694ba..ef0ca3bf555d 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -786,9 +786,16 @@ void resize_hpt_for_hotplug(unsigned long new_mem_size)
int hash__create_section_mapping(unsigned long start, unsigned long end, int nid)
{
- int rc = htab_bolt_mapping(start, end, __pa(start),
- pgprot_val(PAGE_KERNEL), mmu_linear_psize,
- mmu_kernel_ssize);
+ int rc;
+
+ if (end >= H_VMALLOC_START) {
+ pr_warn("Outisde the supported range\n");
+ return -1;
+ }
+
+ rc = htab_bolt_mapping(start, end, __pa(start),
+ pgprot_val(PAGE_KERNEL), mmu_linear_psize,
+ mmu_kernel_ssize);
if (rc < 0) {
int rc2 = htab_remove_mapping(start, end, mmu_linear_psize,
@@ -929,6 +936,11 @@ static void __init htab_initialize(void)
DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",
base, size, prot);
+ if ((base + size) >= H_VMALLOC_START) {
+ pr_warn("Outisde the supported range\n");
+ continue;
+ }
+
BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
prot, mmu_linear_psize, mmu_kernel_ssize));
}
diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c
index c08d49046a96..d934de4e2b3a 100644
--- a/arch/powerpc/mm/pgtable-hash64.c
+++ b/arch/powerpc/mm/pgtable-hash64.c
@@ -112,9 +112,16 @@ int __meminit hash__vmemmap_create_mapping(unsigned long start,
unsigned long page_size,
unsigned long phys)
{
- int rc = htab_bolt_mapping(start, start + page_size, phys,
- pgprot_val(PAGE_KERNEL),
- mmu_vmemmap_psize, mmu_kernel_ssize);
+ int rc;
+
+ if ((start + page_size) >= H_VMEMMAP_END) {
+ pr_warn("Outisde the supported range\n");
+ return -1;
+ }
+
+ rc = htab_bolt_mapping(start, start + page_size, phys,
+ pgprot_val(PAGE_KERNEL),
+ mmu_vmemmap_psize, mmu_kernel_ssize);
if (rc < 0) {
int rc2 = htab_remove_mapping(start, start + page_size,
mmu_vmemmap_psize,
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index ba485fbd81f1..c9b24bf78819 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -334,6 +334,12 @@ void __init radix_init_pgtable(void)
* page tables will be allocated within the range. No
* need or a node (which we don't have yet).
*/
+
+ if ((reg->base + reg->size) >= RADIX_VMALLOC_START) {
+ pr_warn("Outisde the supported range\n");
+ continue;
+ }
+
WARN_ON(create_physical_mapping(reg->base,
reg->base + reg->size,
-1));
@@ -866,6 +872,11 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end)
int __meminit radix__create_section_mapping(unsigned long start, unsigned long end, int nid)
{
+ if (end >= RADIX_VMALLOC_START) {
+ pr_warn("Outisde the supported range\n");
+ return -1;
+ }
+
return create_physical_mapping(start, end, nid);
}
@@ -893,6 +904,11 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start,
int nid = early_pfn_to_nid(phys >> PAGE_SHIFT);
int ret;
+ if ((start + page_size) >= RADIX_VMEMMAP_END) {
+ pr_warn("Outisde the supported range\n");
+ return -1;
+ }
+
ret = __map_kernel_page_nid(start, phys, __pgprot(flags), page_size, nid);
BUG_ON(ret);
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 56068cac2a3c..72f58c076e26 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -121,6 +121,11 @@ void __iomem *__ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_
if (pgprot_val(prot) & H_PAGE_4K_PFN)
return NULL;
+ if ((ea + size) >= (void *)IOREMAP_END) {
+ pr_warn("Outisde the supported range\n");
+ return NULL;
+ }
+
WARN_ON(pa & ~PAGE_MASK);
WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
WARN_ON(size & ~PAGE_MASK);
--
2.20.1
^ permalink raw reply related
* [PATCH v2 2/5] powerpc/mm/hash64: Map all the kernel regions in the same 0xc range
From: Aneesh Kumar K.V @ 2019-03-17 15:48 UTC (permalink / raw)
To: npiggin, benh, paulus, mpe; +Cc: Aneesh Kumar K.V, linuxppc-dev
In-Reply-To: <20190317154827.9188-1-aneesh.kumar@linux.ibm.com>
This patch maps vmap, IO and vmemap regions in the 0xc address range
instead of the current 0xd and 0xf range. This brings the mapping closer
to radix translation mode.
With hash 64K page size each of this region is 512TB whereas with 4K config
we are limited by the max page table range of 64TB and hence there regions
are of 16TB size.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/powerpc/include/asm/book3s/64/hash-4k.h | 13 +++
arch/powerpc/include/asm/book3s/64/hash-64k.h | 11 +++
arch/powerpc/include/asm/book3s/64/hash.h | 95 ++++++++++++-------
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 31 +++---
arch/powerpc/include/asm/book3s/64/pgtable.h | 1 -
arch/powerpc/include/asm/book3s/64/radix.h | 41 ++++----
arch/powerpc/include/asm/page.h | 3 +-
arch/powerpc/kvm/book3s_hv_rm_xics.c | 2 +-
arch/powerpc/mm/copro_fault.c | 14 ++-
arch/powerpc/mm/hash_utils_64.c | 26 ++---
arch/powerpc/mm/pgtable-radix.c | 3 +-
arch/powerpc/mm/pgtable_64.c | 2 -
arch/powerpc/mm/ptdump/hashpagetable.c | 2 +-
arch/powerpc/mm/ptdump/ptdump.c | 3 +-
arch/powerpc/mm/slb.c | 22 +++--
arch/powerpc/platforms/cell/spu_base.c | 4 +-
drivers/misc/cxl/fault.c | 2 +-
drivers/misc/ocxl/link.c | 2 +-
18 files changed, 170 insertions(+), 107 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index cf5ba5254299..0dd62287f56c 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -13,6 +13,19 @@
*/
#define MAX_EA_BITS_PER_CONTEXT 46
+/*
+ * Our page table limit us to 64TB. Hence for the kernel mapping,
+ * each MAP area is limited to 16 TB.
+ * The four map areas are: linear mapping, vmap, IO and vmemmap
+ */
+#define H_KERN_MAP_SIZE (ASM_CONST(1) << (MAX_EA_BITS_PER_CONTEXT - 2))
+
+/*
+ * Define the address range of the kernel non-linear virtual area
+ * 16TB
+ */
+#define H_KERN_VIRT_START ASM_CONST(0xc000100000000000)
+
#ifndef __ASSEMBLY__
#define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE)
#define H_PMD_TABLE_SIZE (sizeof(pmd_t) << H_PMD_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index f82ee8a3b561..e392cf17b457 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -13,6 +13,17 @@
*/
#define MAX_EA_BITS_PER_CONTEXT 49
+/*
+ * We use one context for each MAP area.
+ */
+#define H_KERN_MAP_SIZE (1UL << MAX_EA_BITS_PER_CONTEXT)
+
+/*
+ * Define the address range of the kernel non-linear virtual area
+ * 2PB
+ */
+#define H_KERN_VIRT_START ASM_CONST(0xc008000000000000)
+
/*
* 64k aligned address free up few of the lower bits of RPN for us
* We steal that here. For more deatils look at pte_pfn/pfn_pte()
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 8cbc4106d449..523b9191a1e2 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -29,6 +29,10 @@
#define H_PGTABLE_EADDR_SIZE (H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + \
H_PUD_INDEX_SIZE + H_PGD_INDEX_SIZE + PAGE_SHIFT)
#define H_PGTABLE_RANGE (ASM_CONST(1) << H_PGTABLE_EADDR_SIZE)
+/*
+ * Top 2 bits are ignored in page table walk.
+ */
+#define EA_MASK (~(0xcUL << 60))
/*
* We store the slot details in the second half of page table.
@@ -42,53 +46,60 @@
#endif
/*
- * Define the address range of the kernel non-linear virtual area. In contrast
- * to the linear mapping, this is managed using the kernel page tables and then
- * inserted into the hash page table to actually take effect, similarly to user
- * mappings.
+ * One context each will be used for vmap, IO and vmemmap
*/
-#define H_KERN_VIRT_START ASM_CONST(0xD000000000000000)
-
+#define H_KERN_VIRT_SIZE (H_KERN_MAP_SIZE * 3)
/*
- * Allow virtual mapping of one context size.
- * 512TB for 64K page size
- * 64TB for 4K page size
+ * +------------------------------+
+ * | |
+ * | |
+ * | |
+ * +------------------------------+ Kernel virtual map end (0xc00e000000000000)
+ * | |
+ * | |
+ * | 512TB/16TB of vmemmap |
+ * | |
+ * | |
+ * +------------------------------+ Kernel vmemmap start
+ * | |
+ * | 512TB/16TB of IO map |
+ * | |
+ * +------------------------------+ Kernel IO map start
+ * | |
+ * | 512TB/16TB of vmap |
+ * | |
+ * +------------------------------+ Kernel virt start (0xc008000000000000)
+ * | |
+ * | |
+ * | |
+ * +------------------------------+ Kernel linear (0xc.....)
*/
-#define H_KERN_VIRT_SIZE (1UL << MAX_EA_BITS_PER_CONTEXT)
-/*
- * 8TB IO mapping size
- */
-#define H_KERN_IO_SIZE ASM_CONST(0x80000000000) /* 8T */
+#define H_VMALLOC_START H_KERN_VIRT_START
+#define H_VMALLOC_SIZE H_KERN_MAP_SIZE
+#define H_VMALLOC_END (H_VMALLOC_START + H_VMALLOC_SIZE)
-/*
- * The vmalloc space starts at the beginning of the kernel non-linear virtual
- * region, and occupies 504T (64K) or 56T (4K)
- */
-#define H_VMALLOC_START H_KERN_VIRT_START
-#define H_VMALLOC_SIZE (H_KERN_VIRT_SIZE - H_KERN_IO_SIZE)
-#define H_VMALLOC_END (H_VMALLOC_START + H_VMALLOC_SIZE)
+#define H_KERN_IO_START H_VMALLOC_END
+#define H_KERN_IO_SIZE H_KERN_MAP_SIZE
+#define H_KERN_IO_END (H_KERN_IO_START + H_KERN_IO_SIZE)
-#define H_KERN_IO_START H_VMALLOC_END
-#define H_KERN_IO_END (H_KERN_VIRT_START + H_KERN_VIRT_SIZE)
+#define H_VMEMMAP_START H_KERN_IO_END
+#define H_VMEMMAP_SIZE H_KERN_MAP_SIZE
+#define H_VMEMMAP_END (H_VMEMMAP_START + H_VMEMMAP_SIZE)
/*
* Region IDs
*/
-#define REGION_SHIFT 60UL
-#define REGION_MASK (0xfUL << REGION_SHIFT)
-#define REGION_ID(ea) (((unsigned long)(ea)) >> REGION_SHIFT)
-
-#define VMALLOC_REGION_ID (REGION_ID(H_VMALLOC_START))
-#define KERNEL_REGION_ID (REGION_ID(PAGE_OFFSET))
-#define VMEMMAP_REGION_ID (0xfUL) /* Server only */
-#define USER_REGION_ID (0UL)
+#define USER_REGION_ID 1
+#define KERNEL_REGION_ID 2
+#define VMALLOC_REGION_ID 3
+#define IO_REGION_ID 4
+#define VMEMMAP_REGION_ID 5
/*
* Defines the address of the vmemap area, in its own region on
* hash table CPUs.
*/
-#define H_VMEMMAP_BASE (VMEMMAP_REGION_ID << REGION_SHIFT)
#ifdef CONFIG_PPC_MM_SLICES
#define HAVE_ARCH_UNMAPPED_AREA
@@ -104,6 +115,26 @@
#define H_PUD_BAD_BITS (PMD_TABLE_SIZE-1)
#ifndef __ASSEMBLY__
+static inline int get_region_id(unsigned long ea)
+{
+ int id = (ea >> 60UL);
+
+ if (id == 0)
+ return USER_REGION_ID;
+
+ VM_BUG_ON(id != 0xc);
+ VM_BUG_ON(ea >= H_VMEMMAP_END);
+
+ if (ea >= H_VMEMMAP_START)
+ return VMEMMAP_REGION_ID;
+ else if (ea >= H_KERN_IO_START)
+ return IO_REGION_ID;
+ else if (ea >= H_VMALLOC_START)
+ return VMALLOC_REGION_ID;
+
+ return KERNEL_REGION_ID;
+}
+
#define hash__pmd_bad(pmd) (pmd_val(pmd) & H_PMD_BAD_BITS)
#define hash__pud_bad(pud) (pud_val(pud) & H_PUD_BAD_BITS)
static inline int hash__pgd_bad(pgd_t pgd)
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index a28a28079edb..b3f256c042aa 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -588,7 +588,8 @@ extern void slb_set_size(u16 size);
#endif
#define MAX_VMALLOC_CTX_CNT 1
-#define MAX_MEMMAP_CTX_CNT 1
+#define MAX_IO_CTX_CNT 1
+#define MAX_VMEMMAP_CTX_CNT 1
/*
* 256MB segment
@@ -601,13 +602,10 @@ extern void slb_set_size(u16 size);
* would give a protovsid of 0x1fffffffff. That will result in a VSID 0
* because of the modulo operation in vsid scramble.
*
- * We add one extra context to MIN_USER_CONTEXT so that we can map kernel
- * context easily. The +1 is to map the unused 0xe region mapping.
*/
#define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 2)
#define MIN_USER_CONTEXT (MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \
- MAX_MEMMAP_CTX_CNT + 2)
-
+ MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT)
/*
* For platforms that support on 65bit VA we limit the context bits
*/
@@ -747,7 +745,7 @@ static inline unsigned long get_vsid(unsigned long context, unsigned long ea,
/*
* Bad address. We return VSID 0 for that
*/
- if ((ea & ~REGION_MASK) >= H_PGTABLE_RANGE)
+ if ((ea & EA_MASK) >= H_PGTABLE_RANGE)
return 0;
if (!mmu_has_feature(MMU_FTR_68_BIT_VA))
@@ -774,28 +772,29 @@ static inline unsigned long get_vsid(unsigned long context, unsigned long ea,
* 0x00002 - [ 0xc002000000000000 - 0xc003ffffffffffff]
* 0x00003 - [ 0xc004000000000000 - 0xc005ffffffffffff]
* 0x00004 - [ 0xc006000000000000 - 0xc007ffffffffffff]
-
- * 0x00005 - [ 0xd000000000000000 - 0xd001ffffffffffff ]
- * 0x00006 - Not used - Can map 0xe000000000000000 range.
- * 0x00007 - [ 0xf000000000000000 - 0xf001ffffffffffff ]
*
- * So we can compute the context from the region (top nibble) by
- * subtracting 11, or 0xc - 1.
+ * vmap, IO, vmemap
+ *
+ * 0x00005 - [ 0xc008000000000000 - 0xc009ffffffffffff]
+ * 0x00006 - [ 0xc00a000000000000 - 0xc00bffffffffffff]
+ * 0x00007 - [ 0xc00c000000000000 - 0xc00dffffffffffff]
+ *
*/
static inline unsigned long get_kernel_context(unsigned long ea)
{
- unsigned long region_id = REGION_ID(ea);
+ unsigned long region_id = get_region_id(ea);
unsigned long ctx;
/*
- * For linear mapping we do support multiple context
+ * Depending on Kernel config, kernel region can have one context
+ * or more.
*/
if (region_id == KERNEL_REGION_ID) {
/*
* We already verified ea to be not beyond the addr limit.
*/
- ctx = 1 + ((ea & ~REGION_MASK) >> MAX_EA_BITS_PER_CONTEXT);
+ ctx = 1 + ((ea & EA_MASK) >> MAX_EA_BITS_PER_CONTEXT);
} else
- ctx = (region_id - 0xc) + MAX_KERNEL_CTX_CNT;
+ ctx = region_id + MAX_KERNEL_CTX_CNT - 2;
return ctx;
}
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 51190a6d1c8a..8c156c5b4cd5 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -279,7 +279,6 @@ extern unsigned long __kernel_virt_size;
extern unsigned long __kernel_io_start;
extern unsigned long __kernel_io_end;
#define KERN_VIRT_START __kernel_virt_start
-#define KERN_VIRT_SIZE __kernel_virt_size
#define KERN_IO_START __kernel_io_start
#define KERN_IO_END __kernel_io_end
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 6d760a083d62..b43e12457fea 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -72,19 +72,17 @@
* | |
* | |
* | |
- * +------------------------------+ Kernel IO map end (0xc010000000000000)
+ * +------------------------------+ Kernel vmemmap end (0xc010000000000000)
* | |
+ * | 512TB |
* | |
- * | 1/2 of virtual map |
+ * +------------------------------+ Kernel IO map end/vmemap start
* | |
+ * | 512TB |
* | |
- * +------------------------------+ Kernel IO map start
+ * +------------------------------+ Kernel vmap end/ IO map start
* | |
- * | 1/4 of virtual map |
- * | |
- * +------------------------------+ Kernel vmemap start
- * | |
- * | 1/4 of virtual map |
+ * | 512TB |
* | |
* +------------------------------+ Kernel virt start (0xc008000000000000)
* | |
@@ -93,25 +91,24 @@
* +------------------------------+ Kernel linear (0xc.....)
*/
-#define RADIX_KERN_VIRT_START ASM_CONST(0xc008000000000000)
-#define RADIX_KERN_VIRT_SIZE ASM_CONST(0x0008000000000000)
-
+#define RADIX_KERN_VIRT_START ASM_CONST(0xc008000000000000)
/*
- * The vmalloc space starts at the beginning of that region, and
- * occupies a quarter of it on radix config.
- * (we keep a quarter for the virtual memmap)
+ * We use MAX_EA_BITS_PER_CONTEXT(hash specific) here just to make sure we pick
+ * the same value as hash.
*/
+#define RADIX_KERN_MAP_SIZE (1UL << MAX_EA_BITS_PER_CONTEXT)
+
#define RADIX_VMALLOC_START RADIX_KERN_VIRT_START
-#define RADIX_VMALLOC_SIZE (RADIX_KERN_VIRT_SIZE >> 2)
+#define RADIX_VMALLOC_SIZE RADIX_KERN_MAP_SIZE
#define RADIX_VMALLOC_END (RADIX_VMALLOC_START + RADIX_VMALLOC_SIZE)
-/*
- * Defines the address of the vmemap area, in its own region on
- * hash table CPUs.
- */
-#define RADIX_VMEMMAP_BASE (RADIX_VMALLOC_END)
-#define RADIX_KERN_IO_START (RADIX_KERN_VIRT_START + (RADIX_KERN_VIRT_SIZE >> 1))
-#define RADIX_KERN_IO_END (RADIX_KERN_VIRT_START + RADIX_KERN_VIRT_SIZE)
+#define RADIX_KERN_IO_START RADIX_VMALLOC_END
+#define RADIX_KERN_IO_SIZE RADIX_KERN_MAP_SIZE
+#define RADIX_KERN_IO_END (RADIX_KERN_IO_START + RADIX_KERN_IO_SIZE)
+
+#define RADIX_VMEMMAP_START RADIX_KERN_IO_END
+#define RADIX_VMEMMAP_SIZE RADIX_KERN_MAP_SIZE
+#define RADIX_VMEMMAP_END (RADIX_VMEMMAP_START + RADIX_VMEMMAP_SIZE)
#ifndef __ASSEMBLY__
#define RADIX_PTE_TABLE_SIZE (sizeof(pte_t) << RADIX_PTE_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index ed870468ef6f..918228f2205b 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -139,7 +139,8 @@ static inline bool pfn_valid(unsigned long pfn)
* return true for some vmalloc addresses, which is incorrect. So explicitly
* check that the address is in the kernel region.
*/
-#define virt_addr_valid(kaddr) (REGION_ID(kaddr) == KERNEL_REGION_ID && \
+/* may be can drop get_region_id */
+#define virt_addr_valid(kaddr) (get_region_id((unsigned long)kaddr) == KERNEL_REGION_ID && \
pfn_valid(virt_to_pfn(kaddr)))
#else
#define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr))
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 3b9662a4207e..085509148d95 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -822,7 +822,7 @@ static inline void this_cpu_inc_rm(unsigned int __percpu *addr)
raddr = per_cpu_ptr(addr, cpu);
l = (unsigned long)raddr;
- if (REGION_ID(l) == VMALLOC_REGION_ID) {
+ if (get_region_id(l) == VMALLOC_REGION_ID) {
l = vmalloc_to_phys(raddr);
raddr = (unsigned int *)l;
}
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index c8da352e8686..0da84a03388c 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -105,7 +105,7 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
u64 vsid, vsidkey;
int psize, ssize;
- switch (REGION_ID(ea)) {
+ switch (get_region_id(ea)) {
case USER_REGION_ID:
pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea);
if (mm == NULL)
@@ -117,14 +117,18 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
break;
case VMALLOC_REGION_ID:
pr_devel("%s: 0x%llx -- VMALLOC_REGION_ID\n", __func__, ea);
- if (ea < VMALLOC_END)
- psize = mmu_vmalloc_psize;
- else
- psize = mmu_io_psize;
+ psize = mmu_vmalloc_psize;
ssize = mmu_kernel_ssize;
vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
vsidkey = SLB_VSID_KERNEL;
break;
+
+ case IO_REGION_ID:
+ pr_devel("%s: 0x%llx -- IO_REGION_ID\n", __func__, ea);
+ psize = mmu_io_psize;
+ ssize = mmu_kernel_ssize;
+ vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+ vsidkey = SLB_VSID_KERNEL;
case KERNEL_REGION_ID:
pr_devel("%s: 0x%llx -- KERNEL_REGION_ID\n", __func__, ea);
psize = mmu_linear_psize;
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 394dd969002f..c6b39e7694ba 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1013,12 +1013,11 @@ void __init hash__early_init_mmu(void)
__pgd_val_bits = HASH_PGD_VAL_BITS;
__kernel_virt_start = H_KERN_VIRT_START;
- __kernel_virt_size = H_KERN_VIRT_SIZE;
__vmalloc_start = H_VMALLOC_START;
__vmalloc_end = H_VMALLOC_END;
__kernel_io_start = H_KERN_IO_START;
__kernel_io_end = H_KERN_IO_END;
- vmemmap = (struct page *)H_VMEMMAP_BASE;
+ vmemmap = (struct page *)H_VMEMMAP_START;
ioremap_bot = IOREMAP_BASE;
#ifdef CONFIG_PCI
@@ -1239,7 +1238,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
trace_hash_fault(ea, access, trap);
/* Get region & vsid */
- switch (REGION_ID(ea)) {
+ switch (get_region_id(ea)) {
case USER_REGION_ID:
user_region = 1;
if (! mm) {
@@ -1253,10 +1252,13 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
break;
case VMALLOC_REGION_ID:
vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
- if (ea < VMALLOC_END)
- psize = mmu_vmalloc_psize;
- else
- psize = mmu_io_psize;
+ psize = mmu_vmalloc_psize;
+ ssize = mmu_kernel_ssize;
+ break;
+
+ case IO_REGION_ID:
+ vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+ psize = mmu_io_psize;
ssize = mmu_kernel_ssize;
break;
default:
@@ -1422,7 +1424,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
unsigned long flags = 0;
struct mm_struct *mm = current->mm;
- if (REGION_ID(ea) == VMALLOC_REGION_ID)
+ if ((get_region_id(ea) == VMALLOC_REGION_ID) ||
+ (get_region_id(ea) == IO_REGION_ID))
mm = &init_mm;
if (dsisr & DSISR_NOHPTE)
@@ -1438,8 +1441,9 @@ int __hash_page(unsigned long ea, unsigned long msr, unsigned long trap,
unsigned long access = _PAGE_PRESENT | _PAGE_READ;
unsigned long flags = 0;
struct mm_struct *mm = current->mm;
+ unsigned int region_id = get_region_id(ea);
- if (REGION_ID(ea) == VMALLOC_REGION_ID)
+ if ((region_id == VMALLOC_REGION_ID) || (region_id == IO_REGION_ID))
mm = &init_mm;
if (dsisr & DSISR_NOHPTE)
@@ -1456,7 +1460,7 @@ int __hash_page(unsigned long ea, unsigned long msr, unsigned long trap,
* 2) user space access kernel space.
*/
access |= _PAGE_PRIVILEGED;
- if ((msr & MSR_PR) || (REGION_ID(ea) == USER_REGION_ID))
+ if ((msr & MSR_PR) || (region_id == USER_REGION_ID))
access &= ~_PAGE_PRIVILEGED;
if (trap == 0x400)
@@ -1500,7 +1504,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
int rc, ssize, update_flags = 0;
unsigned long access = _PAGE_PRESENT | _PAGE_READ | (is_exec ? _PAGE_EXEC : 0);
- BUG_ON(REGION_ID(ea) != USER_REGION_ID);
+ BUG_ON(get_region_id(ea) != USER_REGION_ID);
if (!should_hash_preload(mm, ea))
return;
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index bca1bf66c56e..ba485fbd81f1 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -574,12 +574,11 @@ void __init radix__early_init_mmu(void)
__pgd_val_bits = RADIX_PGD_VAL_BITS;
__kernel_virt_start = RADIX_KERN_VIRT_START;
- __kernel_virt_size = RADIX_KERN_VIRT_SIZE;
__vmalloc_start = RADIX_VMALLOC_START;
__vmalloc_end = RADIX_VMALLOC_END;
__kernel_io_start = RADIX_KERN_IO_START;
__kernel_io_end = RADIX_KERN_IO_END;
- vmemmap = (struct page *)RADIX_VMEMMAP_BASE;
+ vmemmap = (struct page *)RADIX_VMEMMAP_START;
ioremap_bot = IOREMAP_BASE;
#ifdef CONFIG_PCI
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 7cea39bdf05f..56068cac2a3c 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -90,8 +90,6 @@ unsigned long __pgd_val_bits;
EXPORT_SYMBOL(__pgd_val_bits);
unsigned long __kernel_virt_start;
EXPORT_SYMBOL(__kernel_virt_start);
-unsigned long __kernel_virt_size;
-EXPORT_SYMBOL(__kernel_virt_size);
unsigned long __vmalloc_start;
EXPORT_SYMBOL(__vmalloc_start);
unsigned long __vmalloc_end;
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index b430e4e08af6..b9bda0105841 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -500,7 +500,7 @@ static void populate_markers(void)
address_markers[7].start_address = IOREMAP_BASE;
address_markers[8].start_address = IOREMAP_END;
#ifdef CONFIG_PPC_BOOK3S_64
- address_markers[9].start_address = H_VMEMMAP_BASE;
+ address_markers[9].start_address = H_VMEMMAP_START;
#else
address_markers[9].start_address = VMEMMAP_BASE;
#endif
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 37138428ab55..63fc56feea15 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -303,8 +303,9 @@ static void populate_markers(void)
address_markers[i++].start_address = PHB_IO_END;
address_markers[i++].start_address = IOREMAP_BASE;
address_markers[i++].start_address = IOREMAP_END;
+ /* What is the ifdef about? */
#ifdef CONFIG_PPC_BOOK3S_64
- address_markers[i++].start_address = H_VMEMMAP_BASE;
+ address_markers[i++].start_address = H_VMEMMAP_START;
#else
address_markers[i++].start_address = VMEMMAP_BASE;
#endif
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 5986df48359b..a0c37f428d60 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -694,7 +694,7 @@ static long slb_allocate_kernel(unsigned long ea, unsigned long id)
if (id == KERNEL_REGION_ID) {
/* We only support upto MAX_PHYSMEM_BITS */
- if ((ea & ~REGION_MASK) > (1UL << MAX_PHYSMEM_BITS))
+ if ((ea & EA_MASK) > (1UL << MAX_PHYSMEM_BITS))
return -EFAULT;
flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_linear_psize].sllp;
@@ -702,20 +702,25 @@ static long slb_allocate_kernel(unsigned long ea, unsigned long id)
#ifdef CONFIG_SPARSEMEM_VMEMMAP
} else if (id == VMEMMAP_REGION_ID) {
- if ((ea & ~REGION_MASK) >= (1ULL << MAX_EA_BITS_PER_CONTEXT))
+ if (ea >= H_VMEMMAP_END)
return -EFAULT;
flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_vmemmap_psize].sllp;
#endif
} else if (id == VMALLOC_REGION_ID) {
- if ((ea & ~REGION_MASK) >= (1ULL << MAX_EA_BITS_PER_CONTEXT))
+ if (ea >= H_VMALLOC_END)
return -EFAULT;
- if (ea < H_VMALLOC_END)
- flags = local_paca->vmalloc_sllp;
- else
- flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_io_psize].sllp;
+ flags = local_paca->vmalloc_sllp;
+
+ } else if (id == IO_REGION_ID) {
+
+ if (ea >= H_KERN_IO_END)
+ return -EFAULT;
+
+ flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_io_psize].sllp;
+
} else {
return -EFAULT;
}
@@ -725,6 +730,7 @@ static long slb_allocate_kernel(unsigned long ea, unsigned long id)
ssize = MMU_SEGSIZE_256M;
context = get_kernel_context(ea);
+
return slb_insert_entry(ea, context, flags, ssize, true);
}
@@ -761,7 +767,7 @@ static long slb_allocate_user(struct mm_struct *mm, unsigned long ea)
long do_slb_fault(struct pt_regs *regs, unsigned long ea)
{
- unsigned long id = REGION_ID(ea);
+ unsigned long id = get_region_id(ea);
/* IRQs are not reconciled here, so can't check irqs_disabled */
VM_WARN_ON(mfmsr() & MSR_EE);
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index 7f12c7b78c0f..4770cce1bfe2 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -194,7 +194,7 @@ static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr)
* faults need to be deferred to process context.
*/
if ((dsisr & MFC_DSISR_PTE_NOT_FOUND) &&
- (REGION_ID(ea) != USER_REGION_ID)) {
+ (get_region_id(ea) != USER_REGION_ID)) {
spin_unlock(&spu->register_lock);
ret = hash_page(ea,
@@ -224,7 +224,7 @@ static void __spu_kernel_slb(void *addr, struct copro_slb *slb)
unsigned long ea = (unsigned long)addr;
u64 llp;
- if (REGION_ID(ea) == KERNEL_REGION_ID)
+ if (get_region_id(ea) == KERNEL_REGION_ID)
llp = mmu_psize_defs[mmu_linear_psize].sllp;
else
llp = mmu_psize_defs[mmu_virtual_psize].sllp;
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index dc7b34174f85..a4d17a5a9763 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -168,7 +168,7 @@ int cxl_handle_mm_fault(struct mm_struct *mm, u64 dsisr, u64 dar)
if (dsisr & CXL_PSL_DSISR_An_S)
access |= _PAGE_WRITE;
- if (!mm && (REGION_ID(dar) != USER_REGION_ID))
+ if (!mm && (get_region_id(dar) != USER_REGION_ID))
access |= _PAGE_PRIVILEGED;
if (dsisr & DSISR_NOHPTE)
diff --git a/drivers/misc/ocxl/link.c b/drivers/misc/ocxl/link.c
index d50b861d7e57..04ec3d74f828 100644
--- a/drivers/misc/ocxl/link.c
+++ b/drivers/misc/ocxl/link.c
@@ -163,7 +163,7 @@ static void xsl_fault_handler_bh(struct work_struct *fault_work)
if (fault->dsisr & SPA_XSL_S)
access |= _PAGE_WRITE;
- if (REGION_ID(fault->dar) != USER_REGION_ID)
+ if (get_region_id(fault->dar) != USER_REGION_ID)
access |= _PAGE_PRIVILEGED;
local_irq_save(flags);
--
2.20.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox