| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1457469802-11850-18-git-send-email-jglisse@redhat.com>
Date: Tue, 8 Mar 2016 15:43:10 -0500
From: Jérôme Glisse <jglisse@...hat.com>
To: akpm@...ux-foundation.org, <linux-kernel@...r.kernel.org>,
linux-mm@...ck.org
Cc: Linus Torvalds <torvalds@...ux-foundation.org>, <joro@...tes.org>,
Mel Gorman <mgorman@...e.de>, "H. Peter Anvin" <hpa@...or.com>,
Peter Zijlstra <peterz@...radead.org>,
Andrea Arcangeli <aarcange@...hat.com>,
Johannes Weiner <jweiner@...hat.com>,
Larry Woodman <lwoodman@...hat.com>,
Rik van Riel <riel@...hat.com>,
Dave Airlie <airlied@...hat.com>,
Brendan Conoboy <blc@...hat.com>,
Joe Donohue <jdonohue@...hat.com>,
Christophe Harle <charle@...dia.com>,
Duncan Poole <dpoole@...dia.com>,
Sherry Cheung <SCheung@...dia.com>,
Subhash Gutti <sgutti@...dia.com>,
John Hubbard <jhubbard@...dia.com>,
Mark Hairgrove <mhairgrove@...dia.com>,
Lucien Dunning <ldunning@...dia.com>,
Cameron Buschardt <cabuschardt@...dia.com>,
Arvind Gopalakrishnan <arvindg@...dia.com>,
Haggai Eran <haggaie@...lanox.com>,
Shachar Raindel <raindel@...lanox.com>,
Liran Liss <liranl@...lanox.com>,
Roland Dreier <roland@...estorage.com>,
Ben Sander <ben.sander@....com>,
Greg Stoner <Greg.Stoner@....com>,
John Bridgman <John.Bridgman@....com>,
Michael Mantor <Michael.Mantor@....com>,
Paul Blinzer <Paul.Blinzer@....com>,
Leonid Shamis <Leonid.Shamis@....com>,
Laurent Morichetti <Laurent.Morichetti@....com>,
Alexander Deucher <Alexander.Deucher@....com>,
Jerome Glisse <jglisse@...hat.com>,
Jatin Kumar <jakumar@...dia.com>
Subject: [PATCH v12 17/29] HMM: add special swap filetype for memory migrated to device v2.
From: Jerome Glisse <jglisse@...hat.com>
When migrating anonymous memory from system memory to device memory
CPU pte are replaced with special HMM swap entry so that page fault,
get user page (gup), fork, ... are properly redirected to HMM helpers.
This patch only add the new swap type entry and hooks HMM helpers
functions inside the page fault and fork code path.
Changed since v1:
- Fix name when of HMM CPU page fault function.
Signed-off-by: Jérôme Glisse <jglisse@...hat.com>
Signed-off-by: Sherry Cheung <SCheung@...dia.com>
Signed-off-by: Subhash Gutti <sgutti@...dia.com>
Signed-off-by: Mark Hairgrove <mhairgrove@...dia.com>
Signed-off-by: John Hubbard <jhubbard@...dia.com>
Signed-off-by: Jatin Kumar <jakumar@...dia.com>
---
include/linux/hmm.h | 34 ++++++++++++++++++++++++++++++++++
include/linux/swap.h | 13 ++++++++++++-
include/linux/swapops.h | 43 ++++++++++++++++++++++++++++++++++++++++++-
mm/hmm.c | 21 +++++++++++++++++++++
mm/memory.c | 22 ++++++++++++++++++++++
5 files changed, 131 insertions(+), 2 deletions(-)
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 4bc132a..7c66513 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -272,6 +272,40 @@ void hmm_mirror_range_dirty(struct hmm_mirror *mirror,
unsigned long start,
unsigned long end);
+int hmm_handle_cpu_fault(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ pmd_t *pmdp, unsigned long addr,
+ unsigned flags, pte_t orig_pte);
+
+int hmm_mm_fork(struct mm_struct *src_mm,
+ struct mm_struct *dst_mm,
+ struct vm_area_struct *dst_vma,
+ pmd_t *dst_pmd,
+ unsigned long start,
+ unsigned long end);
+
+#else /* CONFIG_HMM */
+
+static inline int hmm_handle_cpu_fault(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ pmd_t *pmdp, unsigned long addr,
+ unsigned flags, pte_t orig_pte)
+{
+ return VM_FAULT_SIGBUS;
+}
+
+static inline int hmm_mm_fork(struct mm_struct *src_mm,
+ struct mm_struct *dst_mm,
+ struct vm_area_struct *dst_vma,
+ pmd_t *dst_pmd,
+ unsigned long start,
+ unsigned long end)
+{
+ BUG();
+ return -ENOMEM;
+}
#endif /* CONFIG_HMM */
+
+
#endif
diff --git a/include/linux/swap.h b/include/linux/swap.h
index b14a2bb..336e0a1 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -70,8 +70,19 @@ static inline int current_is_kswapd(void)
#define SWP_HWPOISON_NUM 0
#endif
+/*
+ * HMM (heterogeneous memory management) used when data is in remote memory.
+ */
+#ifdef CONFIG_HMM
+#define SWP_HMM_NUM 1
+#define SWP_HMM (MAX_SWAPFILES + SWP_MIGRATION_NUM + SWP_HWPOISON_NUM)
+#else
+#define SWP_HMM_NUM 0
+#endif
+
#define MAX_SWAPFILES \
- ((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM)
+ ((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - \
+ SWP_HWPOISON_NUM - SWP_HMM_NUM)
/*
* Magic header for a swap area. The first part of the union is
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 5c3a5f3..8c6ba9f 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -227,7 +227,7 @@ static inline void num_poisoned_pages_inc(void)
}
#endif
-#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION)
+#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || defined(CONFIG_HMM)
static inline int non_swap_entry(swp_entry_t entry)
{
return swp_type(entry) >= MAX_SWAPFILES;
@@ -239,4 +239,45 @@ static inline int non_swap_entry(swp_entry_t entry)
}
#endif
+#ifdef CONFIG_HMM
+static inline swp_entry_t make_hmm_entry(void)
+{
+ /* We do not store anything inside the CPU page table entry (pte). */
+ return swp_entry(SWP_HMM, 0);
+}
+
+static inline swp_entry_t make_hmm_entry_locked(void)
+{
+ /* We do not store anything inside the CPU page table entry (pte). */
+ return swp_entry(SWP_HMM, 1);
+}
+
+static inline swp_entry_t make_hmm_entry_poisonous(void)
+{
+ /* We do not store anything inside the CPU page table entry (pte). */
+ return swp_entry(SWP_HMM, 2);
+}
+
+static inline int is_hmm_entry(swp_entry_t entry)
+{
+ return (swp_type(entry) == SWP_HMM);
+}
+
+static inline int is_hmm_entry_locked(swp_entry_t entry)
+{
+ return (swp_type(entry) == SWP_HMM) && (swp_offset(entry) == 1);
+}
+
+static inline int is_hmm_entry_poisonous(swp_entry_t entry)
+{
+ return (swp_type(entry) == SWP_HMM) && (swp_offset(entry) == 2);
+}
+#else /* CONFIG_HMM */
+static inline int is_hmm_entry(swp_entry_t swp)
+{
+ return 0;
+}
+#endif /* CONFIG_HMM */
+
+
#endif /* _LINUX_SWAPOPS_H */
diff --git a/mm/hmm.c b/mm/hmm.c
index ad44325..4c0d2c0 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -419,6 +419,27 @@ static struct mmu_notifier_ops hmm_notifier_ops = {
};
+int hmm_handle_cpu_fault(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ pmd_t *pmdp, unsigned long addr,
+ unsigned flags, pte_t orig_pte)
+{
+ return VM_FAULT_SIGBUS;
+}
+EXPORT_SYMBOL(hmm_handle_cpu_fault);
+
+int hmm_mm_fork(struct mm_struct *src_mm,
+ struct mm_struct *dst_mm,
+ struct vm_area_struct *dst_vma,
+ pmd_t *dst_pmd,
+ unsigned long start,
+ unsigned long end)
+{
+ return -ENOMEM;
+}
+EXPORT_SYMBOL(hmm_mm_fork);
+
+
struct mm_pt_iter {
struct mm_struct *mm;
pte_t *ptep;
diff --git a/mm/memory.c b/mm/memory.c
index 19de9ba..3cb3653 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -54,6 +54,7 @@
#include <linux/writeback.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
+#include <linux/hmm.h>
#include <linux/kallsyms.h>
#include <linux/swapops.h>
#include <linux/elf.h>
@@ -882,9 +883,11 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte_t *orig_src_pte, *orig_dst_pte;
pte_t *src_pte, *dst_pte;
spinlock_t *src_ptl, *dst_ptl;
+ unsigned cnt_hmm_entry = 0;
int progress = 0;
int rss[NR_MM_COUNTERS];
swp_entry_t entry = (swp_entry_t){0};
+ unsigned long start;
again:
init_rss_vec(rss);
@@ -898,6 +901,7 @@ again:
orig_src_pte = src_pte;
orig_dst_pte = dst_pte;
arch_enter_lazy_mmu_mode();
+ start = addr;
do {
/*
@@ -914,6 +918,12 @@ again:
progress++;
continue;
}
+ if (unlikely(!pte_present(*src_pte))) {
+ entry = pte_to_swp_entry(*src_pte);
+
+ if (is_hmm_entry(entry))
+ cnt_hmm_entry++;
+ }
entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
vma, addr, rss);
if (entry.val)
@@ -928,6 +938,15 @@ again:
pte_unmap_unlock(orig_dst_pte, dst_ptl);
cond_resched();
+ if (cnt_hmm_entry) {
+ int ret;
+
+ ret = hmm_mm_fork(src_mm, dst_mm, dst_vma,
+ dst_pmd, start, end);
+ if (ret)
+ return ret;
+ }
+
if (entry.val) {
if (add_swap_count_continuation(entry, GFP_KERNEL) < 0)
return -ENOMEM;
@@ -2489,6 +2508,9 @@ int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
migration_entry_wait(mm, pmd, address);
} else if (is_hwpoison_entry(entry)) {
ret = VM_FAULT_HWPOISON;
+ } else if (is_hmm_entry(entry)) {
+ ret = hmm_handle_cpu_fault(mm, vma, pmd, address,
+ flags, orig_pte);
} else {
print_bad_pte(vma, address, orig_pte, NULL);
ret = VM_FAULT_SIGBUS;
--
2.4.3
Powered by blists - more mailing lists