* [RFC PATCH 4/6] mm/mremap: Use mmu gather interface instead of flush_tlb_range
From: Aneesh Kumar K.V @ 2021-02-02 9:11 UTC (permalink / raw)
To: linux-mm, akpm; +Cc: peterz, kaleshsingh, Aneesh Kumar K.V, joel, linuxppc-dev
In-Reply-To: <20210202091116.196134-1-aneesh.kumar@linux.ibm.com>
Some architectures do have the concept of page walk cache and only mmu gather
interface supports flushing them. A fast mremap that involves moving page
table pages instead of copying pte entries should flush page walk cache since
the old translation cache is no more valid. Hence switch to mm gather to flush
TLB and mark tlb.freed_tables = 1. No page table pages need to be freed here.
With this the tlb flush is done outside page table lock (ptl).
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
mm/mremap.c | 33 +++++++++++++++++++++++++++++----
1 file changed, 29 insertions(+), 4 deletions(-)
diff --git a/mm/mremap.c b/mm/mremap.c
index 54fd2302b99d..14778d215011 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -217,6 +217,7 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
{
spinlock_t *old_ptl, *new_ptl;
struct mm_struct *mm = vma->vm_mm;
+ struct mmu_gather tlb;
pmd_t pmd;
/*
@@ -245,11 +246,12 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
if (WARN_ON_ONCE(!pmd_none(*new_pmd)))
return false;
+ tlb_gather_mmu(&tlb, mm, old_addr, PMD_SIZE);
/*
* We don't have to worry about the ordering of src and dst
* ptlocks because exclusive mmap_lock prevents deadlock.
*/
- old_ptl = pmd_lock(vma->vm_mm, old_pmd);
+ old_ptl = pmd_lock(mm, old_pmd);
new_ptl = pmd_lockptr(mm, new_pmd);
if (new_ptl != old_ptl)
spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
@@ -258,13 +260,23 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
pmd = *old_pmd;
pmd_clear(old_pmd);
+ /*
+ * Mark the range. We are not freeing page table pages nor
+ * regular pages. Hence we don't need to call tlb_remove_table()
+ * or tlb_remove_page().
+ */
+ tlb_flush_pte_range(&tlb, old_addr, PMD_SIZE);
+ tlb.freed_tables = 1;
VM_BUG_ON(!pmd_none(*new_pmd));
pmd_populate(mm, new_pmd, (pgtable_t)pmd_page_vaddr(pmd));
- flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
if (new_ptl != old_ptl)
spin_unlock(new_ptl);
spin_unlock(old_ptl);
+ /*
+ * This will invalidate both the old TLB and page table walk caches.
+ */
+ tlb_finish_mmu(&tlb, old_addr, PMD_SIZE);
return true;
}
@@ -283,6 +295,7 @@ static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
{
spinlock_t *old_ptl, *new_ptl;
struct mm_struct *mm = vma->vm_mm;
+ struct mmu_gather tlb;
pud_t pud;
/*
@@ -292,11 +305,12 @@ static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
if (WARN_ON_ONCE(!pud_none(*new_pud)))
return false;
+ tlb_gather_mmu(&tlb, mm, old_addr, PUD_SIZE);
/*
* We don't have to worry about the ordering of src and dst
* ptlocks because exclusive mmap_lock prevents deadlock.
*/
- old_ptl = pud_lock(vma->vm_mm, old_pud);
+ old_ptl = pud_lock(mm, old_pud);
new_ptl = pud_lockptr(mm, new_pud);
if (new_ptl != old_ptl)
spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
@@ -305,14 +319,25 @@ static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
pud = *old_pud;
pud_clear(old_pud);
+ /*
+ * Mark the range. We are not freeing page table pages nor
+ * regular pages. Hence we don't need to call tlb_remove_table()
+ * or tlb_remove_page().
+ */
+ tlb_flush_pte_range(&tlb, old_addr, PUD_SIZE);
+ tlb.freed_tables = 1;
VM_BUG_ON(!pud_none(*new_pud));
pud_populate(mm, new_pud, (pmd_t *)pud_page_vaddr(pud));
- flush_tlb_range(vma, old_addr, old_addr + PUD_SIZE);
+
if (new_ptl != old_ptl)
spin_unlock(new_ptl);
spin_unlock(old_ptl);
+ /*
+ * This will invalidate both the old TLB and page table walk caches.
+ */
+ tlb_finish_mmu(&tlb, old_addr, PUD_SIZE);
return true;
}
#else
--
2.29.2
^ permalink raw reply related
* [RFC PATCH 2/6] selftest/mremap_test: Avoid crash with static build
From: Aneesh Kumar K.V @ 2021-02-02 9:11 UTC (permalink / raw)
To: linux-mm, akpm; +Cc: peterz, kaleshsingh, Aneesh Kumar K.V, joel, linuxppc-dev
In-Reply-To: <20210202091116.196134-1-aneesh.kumar@linux.ibm.com>
With a large mmap map size, we can overlap with the text area and using
MAP_FIXED results in unmapping that area. Switch to MAP_FIXED_NOREPLACE
and handle the EEXIST error.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
tools/testing/selftests/vm/mremap_test.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c
index c9a5461eb786..0624d1bd71b5 100644
--- a/tools/testing/selftests/vm/mremap_test.c
+++ b/tools/testing/selftests/vm/mremap_test.c
@@ -75,9 +75,10 @@ static void *get_source_mapping(struct config c)
retry:
addr += c.src_alignment;
src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANONYMOUS | MAP_SHARED, -1, 0);
+ MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED,
+ -1, 0);
if (src_addr == MAP_FAILED) {
- if (errno == EPERM)
+ if (errno == EPERM || errno == EEXIST)
goto retry;
goto error;
}
--
2.29.2
^ permalink raw reply related
* [RFC PATCH 5/6] mm/mremap: Allow arch runtime override
From: Aneesh Kumar K.V @ 2021-02-02 9:11 UTC (permalink / raw)
To: linux-mm, akpm; +Cc: peterz, kaleshsingh, Aneesh Kumar K.V, joel, linuxppc-dev
In-Reply-To: <20210202091116.196134-1-aneesh.kumar@linux.ibm.com>
Architectures like ppc64 can only support faster mremap only with radix
translation. Hence allow a runtime check w.r.t support for fast mremap.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/arm64/include/asm/tlb.h | 6 ++++++
arch/powerpc/include/asm/tlb.h | 6 ++++++
arch/x86/include/asm/tlb.h | 5 +++++
mm/mremap.c | 14 +++++++++++++-
4 files changed, 30 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 61c97d3b58c7..fe209efc6a10 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -94,4 +94,10 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
}
#endif
+#define arch_supports_page_tables_move arch_supports_page_tables_move
+static inline bool arch_supports_page_tables_move(void)
+{
+ return true;
+}
+
#endif
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index 160422a439aa..058918a7cd3c 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -83,5 +83,11 @@ static inline int mm_is_thread_local(struct mm_struct *mm)
}
#endif
+#define arch_supports_page_tables_move arch_supports_page_tables_move
+static inline bool arch_supports_page_tables_move(void)
+{
+ return radix_enabled();
+}
+
#endif /* __KERNEL__ */
#endif /* __ASM_POWERPC_TLB_H */
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 820082bd6880..62827553afd8 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -38,4 +38,9 @@ static inline void __tlb_remove_table(void *table)
free_page_and_swap_cache(table);
}
+#define arch_supports_page_tables_move arch_supports_page_tables_move
+static inline bool arch_supports_page_tables_move(void)
+{
+ return true;
+}
#endif /* _ASM_X86_TLB_H */
diff --git a/mm/mremap.c b/mm/mremap.c
index 14778d215011..dd1244a410bb 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -26,7 +26,7 @@
#include <linux/userfaultfd_k.h>
#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
+#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"
@@ -211,6 +211,14 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
drop_rmap_locks(vma);
}
+#ifndef arch_supports_page_tables_move
+#define arch_supports_page_tables_move arch_supports_page_tables_move
+static inline bool arch_supports_page_tables_move(void)
+{
+ return false;
+}
+#endif
+
#ifdef CONFIG_HAVE_MOVE_PMD
static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd)
@@ -220,6 +228,8 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
struct mmu_gather tlb;
pmd_t pmd;
+ if (!arch_supports_page_tables_move())
+ return false;
/*
* The destination pmd shouldn't be established, free_pgtables()
* should have released it.
@@ -298,6 +308,8 @@ static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
struct mmu_gather tlb;
pud_t pud;
+ if (!arch_supports_page_tables_move())
+ return false;
/*
* The destination pud shouldn't be established, free_pgtables()
* should have released it.
--
2.29.2
^ permalink raw reply related
* [RFC PATCH 6/6] powerpc/mm: Enable move pmd/pud
From: Aneesh Kumar K.V @ 2021-02-02 9:11 UTC (permalink / raw)
To: linux-mm, akpm; +Cc: peterz, kaleshsingh, Aneesh Kumar K.V, joel, linuxppc-dev
In-Reply-To: <20210202091116.196134-1-aneesh.kumar@linux.ibm.com>
mremap HAVE_MOVE_PMD/PUD optimization time comparison for 1GB region:
1GB mremap - Source PTE-aligned, Destination PTE-aligned
mremap time: 1114318ns
1GB mremap - Source PMD-aligned, Destination PMD-aligned
mremap time: 1097715ns
1GB mremap - Source PUD-aligned, Destination PUD-aligned
mremap time: 26851ns
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/powerpc/platforms/Kconfig.cputype | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 3ce907523b1e..2e666e569fdf 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -97,6 +97,8 @@ config PPC_BOOK3S_64
select PPC_HAVE_PMU_SUPPORT
select SYS_SUPPORTS_HUGETLBFS
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ select HAVE_MOVE_PMD
+ select HAVE_MOVE_PUD
select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
select ARCH_SUPPORTS_NUMA_BALANCING
select IRQ_WORK
--
2.29.2
^ permalink raw reply related
* [PATCH kernel] powerpc/uaccess: Skip might_fault() when user access is enabled
From: Alexey Kardashevskiy @ 2021-02-02 9:14 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Alexey Kardashevskiy, Nicholas Piggin
The amount of code executed with enabled user space access (unlocked KUAP)
should be minimal. However with CONFIG_PROVE_LOCKING or
CONFIG_DEBUG_ATOMIC_SLEEP enabled, might_fault() may end up replaying
interrupts which in turn may access the user space and forget to restore
the KUAP state.
The problem places are strncpy_from_user (and similar) which unlock KUAP
and call unsafe_get_user -> __get_user_allowed -> __get_user_nocheck()
with do_allow=false to skip KUAP as the caller took care of it.
This changes __get_user_nocheck() to look at @do_allow to decide whether
to skip might_fault(). Since strncpy_from_user/etc call might_fault()
anyway before unlocking KUAP, there should be no visible change.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
This an attempt to fix that KUAP restore problem from
"powerpc/kuap: Restore AMR after replaying soft interrupts".
---
arch/powerpc/include/asm/uaccess.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 501c9a79038c..cd6c0427a9e2 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -313,7 +313,7 @@ do { \
__typeof__(size) __gu_size = (size); \
\
__chk_user_ptr(__gu_addr); \
- if (!is_kernel_addr((unsigned long)__gu_addr)) \
+ if (!do_allow && !is_kernel_addr((unsigned long)__gu_addr)) \
might_fault(); \
barrier_nospec(); \
if (do_allow) \
--
2.17.1
^ permalink raw reply related
* [PATCH kernel] powerpc/kuap: Restore AMR after replaying soft interrupts
From: Alexey Kardashevskiy @ 2021-02-02 9:15 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Alexey Kardashevskiy, Nicholas Piggin
Since de78a9c "powerpc: Add a framework for Kernel Userspace Access
Protection", user access helpers call user_{read|write}_access_{begin|end}
when user space access is allowed.
890274c "powerpc/64s: Implement KUAP for Radix MMU" made the mentioned
helpers program a AMR special register to allow such access for a short
period of time, most of the time AMR is expected to block user memory
access by the kernel.
Since the code accesses the user space memory, unsafe_get_user()
calls might_fault() which calls arch_local_irq_restore() if either
CONFIG_PROVE_LOCKING or CONFIG_DEBUG_ATOMIC_SLEEP is enabled.
arch_local_irq_restore() then attempts to replay pending soft interrupts
as KUAP regions have hardware interrupts enabled.
If a pending interrupt happens to do user access (performance interrupts
do that), it enables access for a short period of time so after returning
from the replay, the user access state remains blocked and if a user page
fault happens - "Bug: Read fault blocked by AMR!" appears and SIGSEGV is
sent.
This saves/restores AMR when replaying interrupts.
This adds a check if AMR was not blocked when before replaying interrupts.
Found by syzkaller. The call stack for the bug is:
copy_from_user_nofault+0xf8/0x250
perf_callchain_user_64+0x3d8/0x8d0
perf_callchain_user+0x38/0x50
get_perf_callchain+0x28c/0x300
perf_callchain+0xb0/0x130
perf_prepare_sample+0x364/0xbf0
perf_event_output_forward+0xe0/0x280
__perf_event_overflow+0xa4/0x240
perf_swevent_hrtimer+0x1d4/0x1f0
__hrtimer_run_queues+0x328/0x900
hrtimer_interrupt+0x128/0x350
timer_interrupt+0x180/0x600
replay_soft_interrupts+0x21c/0x4f0
arch_local_irq_restore+0x94/0x150
lock_is_held_type+0x140/0x200
___might_sleep+0x220/0x330
__might_fault+0x88/0x120
do_strncpy_from_user+0x108/0x2b0
strncpy_from_user+0x1d0/0x2a0
getname_flags+0x88/0x2c0
do_sys_openat2+0x2d4/0x5f0
do_sys_open+0xcc/0x140
system_call_exception+0x160/0x240
system_call_common+0xf0/0x27c
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
---
Changes:
v3:
* do not block/unblock if AMR was blocked
* reverted move of AMR_KUAP_***
* added pr_warn
v2:
* fixed compile on hash
* moved get/set to arch_local_irq_restore
* block KUAP before replaying
---
This is an example:
------------[ cut here ]------------
Bug: Read fault blocked by AMR!
WARNING: CPU: 0 PID: 1603 at /home/aik/p/kernel/arch/powerpc/include/asm/book3s/64/kup-radix.h:145 __do_page_fau
Modules linked in:
CPU: 0 PID: 1603 Comm: amr Not tainted 5.10.0-rc6_v5.10-rc6_a+fstn1 #24
NIP: c00000000009ece8 LR: c00000000009ece4 CTR: 0000000000000000
REGS: c00000000dc63560 TRAP: 0700 Not tainted (5.10.0-rc6_v5.10-rc6_a+fstn1)
MSR: 8000000000021033 <SF,ME,IR,DR,RI,LE> CR: 28002888 XER: 20040000
CFAR: c0000000001fa928 IRQMASK: 1
GPR00: c00000000009ece4 c00000000dc637f0 c000000002397600 000000000000001f
GPR04: c0000000020eb318 0000000000000000 c00000000dc63494 0000000000000027
GPR08: c00000007fe4de68 c00000000dfe9180 0000000000000000 0000000000000001
GPR12: 0000000000002000 c0000000030a0000 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000000 bfffffffffffffff
GPR20: 0000000000000000 c0000000134a4020 c0000000019c2218 0000000000000fe0
GPR24: 0000000000000000 0000000000000000 c00000000d106200 0000000040000000
GPR28: 0000000000000000 0000000000000300 c00000000dc63910 c000000001946730
NIP [c00000000009ece8] __do_page_fault+0xb38/0xde0
LR [c00000000009ece4] __do_page_fault+0xb34/0xde0
Call Trace:
[c00000000dc637f0] [c00000000009ece4] __do_page_fault+0xb34/0xde0 (unreliable)
[c00000000dc638a0] [c00000000000c968] handle_page_fault+0x10/0x2c
--- interrupt: 300 at strncpy_from_user+0x290/0x440
LR = strncpy_from_user+0x284/0x440
[c00000000dc63ba0] [c000000000c3dcb0] strncpy_from_user+0x2f0/0x440 (unreliable)
[c00000000dc63c30] [c00000000068b888] getname_flags+0x88/0x2c0
[c00000000dc63c90] [c000000000662a44] do_sys_openat2+0x2d4/0x5f0
[c00000000dc63d30] [c00000000066560c] do_sys_open+0xcc/0x140
[c00000000dc63dc0] [c000000000045e10] system_call_exception+0x160/0x240
[c00000000dc63e20] [c00000000000da60] system_call_common+0xf0/0x27c
Instruction dump:
409c0048 3fe2ff5b 3bfff128 fac10060 fae10068 482f7a85 60000000 3c62ff5b
7fe4fb78 3863f250 4815bbd9 60000000 <0fe00000> 3c62ff5b 3863f2b8 4815c8b5
irq event stamp: 254
hardirqs last enabled at (253): [<c000000000019550>] arch_local_irq_restore+0xa0/0x150
hardirqs last disabled at (254): [<c000000000008a10>] data_access_common_virt+0x1b0/0x1d0
softirqs last enabled at (0): [<c0000000001f6d5c>] copy_process+0x78c/0x2120
softirqs last disabled at (0): [<0000000000000000>] 0x0
---[ end trace ba98aec5151f3aeb ]---
---
arch/powerpc/kernel/irq.c | 27 ++++++++++++++++++++++++++-
1 file changed, 26 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index cc7a6271b6b4..592abc798826 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -269,6 +269,23 @@ void replay_soft_interrupts(void)
}
}
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP)
+static inline void replay_soft_interrupts_irqrestore(void)
+{
+ unsigned long kuap_state = get_kuap();
+
+ if (kuap_state != AMR_KUAP_BLOCKED)
+ set_kuap(AMR_KUAP_BLOCKED);
+
+ replay_soft_interrupts();
+
+ if (kuap_state != AMR_KUAP_BLOCKED)
+ set_kuap(kuap_state);
+}
+#else
+#define replay_soft_interrupts_irqrestore() replay_soft_interrupts()
+#endif
+
notrace void arch_local_irq_restore(unsigned long mask)
{
unsigned char irq_happened;
@@ -278,6 +295,14 @@ notrace void arch_local_irq_restore(unsigned long mask)
if (mask)
return;
+ /*
+ * It fires if anything calls local_irq_enable or restore when
+ * KUAP is enabled, and the code handles that just fine by saving
+ * and re-locking AMR but we would like to remove those calls,
+ * hence the warning.
+ */
+ kuap_check_amr();
+
/*
* From this point onward, we can take interrupts, preempt,
* etc... unless we got hard-disabled. We check if an event
@@ -332,7 +357,7 @@ notrace void arch_local_irq_restore(unsigned long mask)
irq_soft_mask_set(IRQS_ALL_DISABLED);
trace_hardirqs_off();
- replay_soft_interrupts();
+ replay_soft_interrupts_irqrestore();
local_paca->irq_happened = 0;
trace_hardirqs_on();
--
2.17.1
^ permalink raw reply related
* Re: [RFC 11/20] mm/tlb: remove arch-specific tlb_start/end_vma()
From: Peter Zijlstra @ 2021-02-02 9:31 UTC (permalink / raw)
To: Nadav Amit
Cc: Andrea Arcangeli, linux-s390, X86 ML, Yu Zhao, Will Deacon,
Dave Hansen, LKML, linux-csky@vger.kernel.org, Linux-MM,
Nicholas Piggin, Andy Lutomirski, Andrew Morton, linuxppc-dev,
Thomas Gleixner
In-Reply-To: <F1C67840-C62F-4583-8593-B621706034F6@vmware.com>
On Tue, Feb 02, 2021 at 07:20:55AM +0000, Nadav Amit wrote:
> Arm does not define tlb_end_vma, and consequently it flushes the TLB after
> each VMA. I suspect it is not intentional.
ARM is one of those that look at the VM_EXEC bit to explicitly flush
ITLB IIRC, so it has to.
^ permalink raw reply
* Re: [PATCH] powerpc/fault: fix wrong KUAP fault for IO_URING
From: Nicholas Piggin @ 2021-02-02 9:49 UTC (permalink / raw)
To: Aneesh Kumar K.V, Christophe Leroy, Michael Ellerman, Zorro Lang
Cc: Jens Axboe, linuxppc-dev
In-Reply-To: <e2dfb7ec-a4d4-579d-a79b-6709df6e9e50@linux.ibm.com>
Excerpts from Aneesh Kumar K.V's message of February 2, 2021 4:30 pm:
> On 2/2/21 11:50 AM, Christophe Leroy wrote:
>>
>>
>> Le 02/02/2021 à 07:16, Aneesh Kumar K.V a écrit :
>>> On 2/2/21 11:32 AM, Christophe Leroy wrote:
>>>>
>>>>
>>>> Le 02/02/2021 à 06:55, Aneesh Kumar K.V a écrit :
>>>>> Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> writes:
>>>>>
>>>>>> Nicholas Piggin <npiggin@gmail.com> writes:
>>>>>>
>>>>>>> Excerpts from Michael Ellerman's message of January 30, 2021 9:22 pm:
>>>>>>>> Christophe Leroy <christophe.leroy@csgroup.eu> writes:
>>>>>>>>> +Aneesh
>>>>>>>>>
>>>>>>>>> Le 29/01/2021 à 07:52, Zorro Lang a écrit :
>>>>>>>> ..
>>>>>>>>>> [ 96.200296] ------------[ cut here ]------------
>>>>>>>>>> [ 96.200304] Bug: Read fault blocked by KUAP!
>>>>>>>>>> [ 96.200309] WARNING: CPU: 3 PID: 1876 at
>>>>>>>>>> arch/powerpc/mm/fault.c:229 bad_kernel_fault+0x180/0x310
>>>>>>>>>
>>>>>>>>>> [ 96.200734] NIP [c000000000849424]
>>>>>>>>>> fault_in_pages_readable+0x104/0x350
>>>>>>>>>> [ 96.200741] LR [c00000000084952c]
>>>>>>>>>> fault_in_pages_readable+0x20c/0x350
>>>>>>>>>> [ 96.200747] --- interrupt: 300
>>>>>>>>>
>>>>>>>>>
>>>>>>>>> Problem happens in a section where userspace access is supposed
>>>>>>>>> to be granted, so the patch you
>>>>>>>>> proposed is definitely not the right fix.
>>>>>>>>>
>>>>>>>>> c000000000849408: 2c 01 00 4c isync
>>>>>>>>> c00000000084940c: a6 03 3d 7d mtspr 29,r9 <== granting
>>>>>>>>> userspace access permission
>>>>>>>>> c000000000849410: 2c 01 00 4c isync
>>>>>>>>> c000000000849414: 00 00 36 e9 ld r9,0(r22)
>>>>>>>>> c000000000849418: 20 00 29 81 lwz r9,32(r9)
>>>>>>>>> c00000000084941c: 00 02 29 71 andi. r9,r9,512
>>>>>>>>> c000000000849420: 78 d3 5e 7f mr r30,r26
>>>>>>>>> ==> c000000000849424: 00 00 bf 8b lbz r29,0(r31) <==
>>>>>>>>> accessing userspace
>>>>>>>>> c000000000849428: 10 00 82 41 beq c000000000849438
>>>>>>>>> <fault_in_pages_readable+0x118>
>>>>>>>>> c00000000084942c: 2c 01 00 4c isync
>>>>>>>>> c000000000849430: a6 03 bd 7e mtspr 29,r21 <==
>>>>>>>>> clearing userspace access permission
>>>>>>>>> c000000000849434: 2c 01 00 4c isync
>>>>>>>>>
>>>>>>>>> My first guess is that the problem is linked to the following
>>>>>>>>> function, see the comment
>>>>>>>>>
>>>>>>>>> /*
>>>>>>>>> * For kernel thread that doesn't have thread.regs return
>>>>>>>>> * default AMR/IAMR values.
>>>>>>>>> */
>>>>>>>>> static inline u64 current_thread_amr(void)
>>>>>>>>> {
>>>>>>>>> if (current->thread.regs)
>>>>>>>>> return current->thread.regs->amr;
>>>>>>>>> return AMR_KUAP_BLOCKED;
>>>>>>>>> }
>>>>>>>>>
>>>>>>>>> Above function was introduced by commit 48a8ab4eeb82
>>>>>>>>> ("powerpc/book3s64/pkeys: Don't update SPRN_AMR
>>>>>>>>> when in kernel mode")
>>>>>>>>
>>>>>>>> Yeah that's a bit of a curly one.
>>>>>>>>
>>>>>>>> At some point io_uring did kthread_use_mm(), which is supposed to
>>>>>>>> mean
>>>>>>>> the kthread can operate on behalf of the original process that
>>>>>>>> submitted
>>>>>>>> the IO.
>>>>>>>>
>>>>>>>> But because KUAP is implemented using memory protection keys, it
>>>>>>>> depends
>>>>>>>> on the value of the AMR register, which is not part of the mm,
>>>>>>>> it's in
>>>>>>>> thread.regs->amr.
>>>>>>>>
>>>>>>>> And what's worse by the time we're in kthread_use_mm() we no
>>>>>>>> longer have
>>>>>>>> access to the thread.regs->amr of the original process that
>>>>>>>> submitted
>>>>>>>> the IO.
>>>>>>>>
>>>>>>>> We also can't simply move the AMR into the mm, precisely because
>>>>>>>> it's
>>>>>>>> per thread, not per mm.
>>>>>>>>
>>>>>>>> So TBH I don't know how we're going to fix this.
>>>>>>>>
>>>>>>>> I guess we could return AMR=unblocked for kernel threads, but that's
>>>>>>>> arguably a bug because it allows a process to circumvent memory
>>>>>>>> keys by
>>>>>>>> asking the kernel to do the access.
>>>>>>>
>>>>>>> We shouldn't need to inherit AMR should we? We only need it to be
>>>>>>> locked
>>>>>>> for kernel threads until it's explicitly unlocked -- nothing mm
>>>>>>> specific
>>>>>>> there. I think current_thread_amr could return 0 for kernel
>>>>>>> threads? Or
>>>>>>> I would even avoid using that function for allow_user_access and open
>>>>>>> code the kthread case and remove it from current_thread_amr().
>>>>>>>
>>>>>>> Thanks,
>>>>>>> Nick
>>>>>>
>>>>>
>>>>> updated one
>>>>>
>>>>> From 8fdb0680f983940d61f91da8252b13c8d3e8ebee Mon Sep 17 00:00:00 2001
>>>>> From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
>>>>> Date: Tue, 2 Feb 2021 09:23:38 +0530
>>>>> Subject: [PATCH v2] powerpc/kuap: Allow kernel thread to access
>>>>> userspace
>>>>> after kthread_use_mm
>>>>>
>>>>> This fix the bad fault reported by KUAP when io_wqe_worker access
>>>>> userspace.
>>>>>
>>>>> Bug: Read fault blocked by KUAP!
>>>>> WARNING: CPU: 1 PID: 101841 at arch/powerpc/mm/fault.c:229
>>>>> __do_page_fault+0x6b4/0xcd0
>>>>> NIP [c00000000009e7e4] __do_page_fault+0x6b4/0xcd0
>>>>> LR [c00000000009e7e0] __do_page_fault+0x6b0/0xcd0
>>>>> ..........
>>>>> Call Trace:
>>>>> [c000000016367330] [c00000000009e7e0] __do_page_fault+0x6b0/0xcd0
>>>>> (unreliable)
>>>>> [c0000000163673e0] [c00000000009ee3c] do_page_fault+0x3c/0x120
>>>>> [c000000016367430] [c00000000000c848] handle_page_fault+0x10/0x2c
>>>>> --- interrupt: 300 at iov_iter_fault_in_readable+0x148/0x6f0
>>>>> ..........
>>>>> NIP [c0000000008e8228] iov_iter_fault_in_readable+0x148/0x6f0
>>>>> LR [c0000000008e834c] iov_iter_fault_in_readable+0x26c/0x6f0
>>>>> interrupt: 300
>>>>> [c0000000163677e0] [c0000000007154a0] iomap_write_actor+0xc0/0x280
>>>>> [c000000016367880] [c00000000070fc94] iomap_apply+0x1c4/0x780
>>>>> [c000000016367990] [c000000000710330]
>>>>> iomap_file_buffered_write+0xa0/0x120
>>>>> [c0000000163679e0] [c00800000040791c]
>>>>> xfs_file_buffered_aio_write+0x314/0x5e0 [xfs]
>>>>> [c000000016367a90] [c0000000006d74bc] io_write+0x10c/0x460
>>>>> [c000000016367bb0] [c0000000006d80e4] io_issue_sqe+0x8d4/0x1200
>>>>> [c000000016367c70] [c0000000006d8ad0] io_wq_submit_work+0xc0/0x250
>>>>> [c000000016367cb0] [c0000000006e2578]
>>>>> io_worker_handle_work+0x498/0x800
>>>>> [c000000016367d40] [c0000000006e2cdc] io_wqe_worker+0x3fc/0x4f0
>>>>> [c000000016367da0] [c0000000001cb0a4] kthread+0x1c4/0x1d0
>>>>> [c000000016367e10] [c00000000000dbf0]
>>>>> ret_from_kernel_thread+0x5c/0x6c
>>>>>
>>>>> The kernel consider thread AMR value for kernel thread to be
>>>>> AMR_KUAP_BLOCKED. Hence access to userspace is denied. This
>>>>> of course not correct and we should allow userspace access after
>>>>> kthread_use_mm(). To be precise, kthread_use_mm() should inherit the
>>>>> AMR value of the operating address space. But, the AMR value is
>>>>> thread-specific and we inherit the address space and not thread
>>>>> access restrictions. Because of this ignore AMR value when accessing
>>>>> userspace via kernel thread.
>>>>>
>>>>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
>>>>> ---
>>>>> Changes from v1:
>>>>> * Address review feedback from Nick
>>>>>
>>>>> arch/powerpc/include/asm/book3s/64/kup.h | 8 +++++++-
>>>>> 1 file changed, 7 insertions(+), 1 deletion(-)
>>>>>
>>>>> diff --git a/arch/powerpc/include/asm/book3s/64/kup.h
>>>>> b/arch/powerpc/include/asm/book3s/64/kup.h
>>>>> index f50f72e535aa..95f4df99249e 100644
>>>>> --- a/arch/powerpc/include/asm/book3s/64/kup.h
>>>>> +++ b/arch/powerpc/include/asm/book3s/64/kup.h
>>>>> @@ -384,7 +384,13 @@ static __always_inline void
>>>>> allow_user_access(void __user *to, const void __user
>>>>> // This is written so we can resolve to a single case at build
>>>>> time
>>>>> BUILD_BUG_ON(!__builtin_constant_p(dir));
>>>>> - if (mmu_has_feature(MMU_FTR_PKEY))
>>>>> + /*
>>>>> + * if it is a kthread that did kthread_use_mm() don't
>>>>> + * use current_thread_amr().
>>>>
>>>> According to include/linux/sched.h, PF_KTHREAD means /* I am a kernel
>>>> thread */
>>>> It doesn't seem to be related to kthread_use_mm()
>>>
>>> That should be a sufficient check here. if we did reach here without
>>> calling kthread_user_mm, we will crash on access because we don't have
>>> a mm attached to the current process. a kernel thread with
>>> kthread_use_mm has
>>
>> Ok but then the comment doesn't match the check.
>
>
> I was trying to be explict in the comment that we expect the thread to
> have done kthread_use_mm().
I would avoid making it sound conditional. There is no way for a kernel
thread to ever access user without having done so.
/*
* Kernel threads may access user mm with kthread_use_mm() but
* can't use current_thread_amr because they have thread.regs==NULL,
* but they have no pkeys.
*/
>
>>
>> And also the comment in current_thread_amr() is then misleading.
>>
>> Why not do the current->flags & PF_KTHREAD check in current_thread_amr()
>> and return 0 in that case instead of BLOCKED ?
>
> In my view currrent_thread_amr() is more generic and we want to be
> explicit there that a kernel thread AMR is KUAP_BLOCKED. Only when we
> call allow user access, we relax the AMR value.
current_thread_amr() shouldn't be used by kernel threads ever
(after the patch). It's just confusing. The user access or the
check could have a test and warning for !current->mm if there
is a concern about it (maybe there already is one somehwere).
Thanks,
Nick
^ permalink raw reply
* Re: [RFC 11/20] mm/tlb: remove arch-specific tlb_start/end_vma()
From: Nadav Amit @ 2021-02-02 9:54 UTC (permalink / raw)
To: Peter Zijlstra
Cc: Andrea Arcangeli, linux-s390, X86 ML, Yu Zhao, Will Deacon,
Dave Hansen, LKML, linux-csky@vger.kernel.org, Linux-MM,
Nicholas Piggin, Andy Lutomirski, Andrew Morton, linuxppc-dev,
Thomas Gleixner
In-Reply-To: <YBkb8yKSUKTPJvxk@hirez.programming.kicks-ass.net>
> On Feb 2, 2021, at 1:31 AM, Peter Zijlstra <peterz@infradead.org> wrote:
>
> On Tue, Feb 02, 2021 at 07:20:55AM +0000, Nadav Amit wrote:
>> Arm does not define tlb_end_vma, and consequently it flushes the TLB after
>> each VMA. I suspect it is not intentional.
>
> ARM is one of those that look at the VM_EXEC bit to explicitly flush
> ITLB IIRC, so it has to.
Hmm… I don’t think Arm is doing that. At least arm64 does not use the
default tlb_flush(), and it does not seem to consider VM_EXEC (at least in
this path):
static inline void tlb_flush(struct mmu_gather *tlb)
{
struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
bool last_level = !tlb->freed_tables;
unsigned long stride = tlb_get_unmap_size(tlb);
int tlb_level = tlb_get_level(tlb);
/*
* If we're tearing down the address space then we only care about
* invalidating the walk-cache, since the ASID allocator won't
* reallocate our ASID without invalidating the entire TLB.
*/
if (tlb->mm_exiting) {
if (!last_level)
flush_tlb_mm(tlb->mm);
return;
}
__flush_tlb_range(&vma, tlb->start, tlb->end, stride,
last_level, tlb_level);
}
^ permalink raw reply
* Re: [PATCH v11 01/13] mm/vmalloc: fix HUGE_VMAP regression by enabling huge pages in vmalloc_to_page
From: Nicholas Piggin @ 2021-02-02 10:22 UTC (permalink / raw)
To: Andrew Morton, Ding Tianhong, linux-mm
Cc: linux-arch, linux-kernel, Christoph Hellwig, Jonathan Cameron,
Rick Edgecombe, linuxppc-dev, Christoph Hellwig
In-Reply-To: <2dcbe2c9-c968-4895-fc43-c40dfe9f06d3@huawei.com>
Excerpts from Ding Tianhong's message of January 28, 2021 1:13 pm:
> On 2021/1/26 12:44, Nicholas Piggin wrote:
>> vmalloc_to_page returns NULL for addresses mapped by larger pages[*].
>> Whether or not a vmap is huge depends on the architecture details,
>> alignments, boot options, etc., which the caller can not be expected
>> to know. Therefore HUGE_VMAP is a regression for vmalloc_to_page.
>>
>> This change teaches vmalloc_to_page about larger pages, and returns
>> the struct page that corresponds to the offset within the large page.
>> This makes the API agnostic to mapping implementation details.
>>
>> [*] As explained by commit 029c54b095995 ("mm/vmalloc.c: huge-vmap:
>> fail gracefully on unexpected huge vmap mappings")
>>
>> Reviewed-by: Christoph Hellwig <hch@lst.de>
>> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
>> ---
>> mm/vmalloc.c | 41 ++++++++++++++++++++++++++---------------
>> 1 file changed, 26 insertions(+), 15 deletions(-)
>>
>> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
>> index e6f352bf0498..62372f9e0167 100644
>> --- a/mm/vmalloc.c
>> +++ b/mm/vmalloc.c
>> @@ -34,7 +34,7 @@
>> #include <linux/bitops.h>
>> #include <linux/rbtree_augmented.h>
>> #include <linux/overflow.h>
>> -
>> +#include <linux/pgtable.h>
>> #include <linux/uaccess.h>
>> #include <asm/tlbflush.h>
>> #include <asm/shmparam.h>
>> @@ -343,7 +343,9 @@ int is_vmalloc_or_module_addr(const void *x)
>> }
>>
>> /*
>> - * Walk a vmap address to the struct page it maps.
>> + * Walk a vmap address to the struct page it maps. Huge vmap mappings will
>> + * return the tail page that corresponds to the base page address, which
>> + * matches small vmap mappings.
>> */
>> struct page *vmalloc_to_page(const void *vmalloc_addr)
>> {
>> @@ -363,25 +365,33 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
>>
>> if (pgd_none(*pgd))
>> return NULL;
>> + if (WARN_ON_ONCE(pgd_leaf(*pgd)))
>> + return NULL; /* XXX: no allowance for huge pgd */
>> + if (WARN_ON_ONCE(pgd_bad(*pgd)))
>> + return NULL;
>> +
>> p4d = p4d_offset(pgd, addr);
>> if (p4d_none(*p4d))
>> return NULL;
>> - pud = pud_offset(p4d, addr);
>> + if (p4d_leaf(*p4d))
>> + return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT);
>> + if (WARN_ON_ONCE(p4d_bad(*p4d)))
>> + return NULL;
>>
>> - /*
>> - * Don't dereference bad PUD or PMD (below) entries. This will also
>> - * identify huge mappings, which we may encounter on architectures
>> - * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be
>> - * identified as vmalloc addresses by is_vmalloc_addr(), but are
>> - * not [unambiguously] associated with a struct page, so there is
>> - * no correct value to return for them.
>> - */
>> - WARN_ON_ONCE(pud_bad(*pud));
>> - if (pud_none(*pud) || pud_bad(*pud))
>> + pud = pud_offset(p4d, addr);
>> + if (pud_none(*pud))
>> + return NULL;
>> + if (pud_leaf(*pud))
>> + return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
>
> Hi Nicho:
>
> /builds/1mzfdQzleCy69KZFb5qHNSEgabZ/mm/vmalloc.c: In function 'vmalloc_to_page':
> /builds/1mzfdQzleCy69KZFb5qHNSEgabZ/include/asm-generic/pgtable-nop4d-hack.h:48:27: error: implicit declaration of function 'pud_page'; did you mean 'put_page'? [-Werror=implicit-function-declaration]
> 48 | #define pgd_page(pgd) (pud_page((pud_t){ pgd }))
> | ^~~~~~~~
>
> the pug_page is not defined for aarch32 when enabling 2-level page config, it break the system building.
Hey thanks for finding that, not sure why that didn't trigger any CI.
Anyway newer kernels don't have the ptable-*-hack.h headers, but even so
it still breaks upstream. arm is using some hand-rolled 2-level folding
of its own (which is fair enough because most 32-bit archs were 2 level
at the time I added pgtable-nopud.h header).
This patch seems to at least make it build.
Thanks,
Nick
---
arch/arm/include/asm/pgtable-3level.h | 2 --
arch/arm/include/asm/pgtable.h | 3 +++
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 2b85d175e999..d4edab51a77c 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -186,8 +186,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
#define pmd_write(pmd) (pmd_isclear((pmd), L_PMD_SECT_RDONLY))
#define pmd_dirty(pmd) (pmd_isset((pmd), L_PMD_SECT_DIRTY))
-#define pud_page(pud) pmd_page(__pmd(pud_val(pud)))
-#define pud_write(pud) pmd_write(__pmd(pud_val(pud)))
#define pmd_hugewillfault(pmd) (!pmd_young(pmd) || !pmd_write(pmd))
#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd))
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index c02f24400369..d63a5bb6bd0c 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -166,6 +166,9 @@ extern struct page *empty_zero_page;
extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+#define pud_page(pud) pmd_page(__pmd(pud_val(pud)))
+#define pud_write(pud) pmd_write(__pmd(pud_val(pud)))
+
#define pmd_none(pmd) (!pmd_val(pmd))
static inline pte_t *pmd_page_vaddr(pmd_t pmd)
--
2.23.0
^ permalink raw reply related
* Re: [PATCH v7 42/42] powerpc/64s: power4 nap fixup in C
From: Michael Ellerman @ 2021-02-02 10:31 UTC (permalink / raw)
To: Nicholas Piggin, linuxppc-dev; +Cc: Athira Rajeev, Nicholas Piggin
In-Reply-To: <20210130130852.2952424-43-npiggin@gmail.com>
Nicholas Piggin <npiggin@gmail.com> writes:
> There is no need for this to be in asm, use the new intrrupt entry wrapper.
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
> ---
> arch/powerpc/include/asm/interrupt.h | 15 +++++++++
> arch/powerpc/include/asm/processor.h | 1 +
> arch/powerpc/include/asm/thread_info.h | 6 ++++
> arch/powerpc/kernel/exceptions-64s.S | 45 --------------------------
> arch/powerpc/kernel/idle_book3s.S | 4 +++
> 5 files changed, 26 insertions(+), 45 deletions(-)
Something in here is making my G5 not boot.
I don't know what the problem is because that machine is in the office,
and I am not, and it has no serial console.
I tried turning on pstore but it doesn't record anything :/
cheers
^ permalink raw reply
* Re: [PATCH 05/13] kallsyms: refactor {,module_}kallsyms_on_each_symbol
From: Miroslav Benes @ 2021-02-02 10:45 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Petr Mladek, Jiri Kosina, Andrew Donnellan, linux-kbuild,
David Airlie, Masahiro Yamada, Josh Poimboeuf, Maarten Lankhorst,
linux-kernel, Maxime Ripard, live-patching, Michal Marek,
Joe Lawrence, dri-devel, Thomas Zimmermann, Jessica Yu,
Frederic Barrat, Daniel Vetter, linuxppc-dev
In-Reply-To: <20210201162842.GB7276@lst.de>
On Mon, 1 Feb 2021, Christoph Hellwig wrote:
> On Mon, Feb 01, 2021 at 02:37:12PM +0100, Miroslav Benes wrote:
> > > > This change is not needed. (objname == NULL) means that we are
> > > > interested only in symbols in "vmlinux".
> > > >
> > > > module_kallsyms_on_each_symbol(klp_find_callback, &args)
> > > > will always fail when objname == NULL.
> > >
> > > I just tried to keep the old behavior. I can respin it with your
> > > recommended change noting the change in behavior, though.
> >
> > Yes, please. It would be cleaner that way.
>
> Let me know if this works for you:
>
> ---
> >From 18af41e88d088cfb8680d1669fcae2bc2ede5328 Mon Sep 17 00:00:00 2001
> From: Christoph Hellwig <hch@lst.de>
> Date: Wed, 20 Jan 2021 16:23:16 +0100
> Subject: kallsyms: refactor {,module_}kallsyms_on_each_symbol
>
> Require an explicit call to module_kallsyms_on_each_symbol to look
> for symbols in modules instead of the call from kallsyms_on_each_symbol,
> and acquire module_mutex inside of module_kallsyms_on_each_symbol instead
> of leaving that up to the caller. Note that this slightly changes the
> behavior for the livepatch code in that the symbols from vmlinux are not
> iterated anymore if objname is set, but that actually is the desired
> behavior in this case.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Miroslav Benes <mbenes@suse.cz>
Thanks Christoph
M
^ permalink raw reply
* Re: [RFC PATCH 3/6] mm/mremap: Use pmd/pud_poplulate to update page table entries
From: Peter Zijlstra @ 2021-02-02 10:47 UTC (permalink / raw)
To: Aneesh Kumar K.V; +Cc: linux-mm, kaleshsingh, joel, akpm, linuxppc-dev
In-Reply-To: <20210202091116.196134-3-aneesh.kumar@linux.ibm.com>
On Tue, Feb 02, 2021 at 02:41:13PM +0530, Aneesh Kumar K.V wrote:
> pmd/pud_populate is the right interface to be used to set the respective
> page table entries. Some architectures do assume that set_pmd/pud_at
> can only be used to set a hugepage PTE. Since we are not setting up a hugepage
> PTE here, use the pmd/pud_populate interface.
Since you did the audit, it might be nice to record which architectures
that are. Also, how much work to fix them?
^ permalink raw reply
* Re: [RFC 11/20] mm/tlb: remove arch-specific tlb_start/end_vma()
From: Peter Zijlstra @ 2021-02-02 11:04 UTC (permalink / raw)
To: Nadav Amit
Cc: Andrea Arcangeli, linux-s390, X86 ML, Yu Zhao, Will Deacon,
Dave Hansen, LKML, linux-csky@vger.kernel.org, Linux-MM,
Nicholas Piggin, Andy Lutomirski, Andrew Morton, linuxppc-dev,
Thomas Gleixner
In-Reply-To: <9100B8AE-129A-4E13-8F01-7B9C14C98B4C@vmware.com>
On Tue, Feb 02, 2021 at 09:54:36AM +0000, Nadav Amit wrote:
> > On Feb 2, 2021, at 1:31 AM, Peter Zijlstra <peterz@infradead.org> wrote:
> >
> > On Tue, Feb 02, 2021 at 07:20:55AM +0000, Nadav Amit wrote:
> >> Arm does not define tlb_end_vma, and consequently it flushes the TLB after
> >> each VMA. I suspect it is not intentional.
> >
> > ARM is one of those that look at the VM_EXEC bit to explicitly flush
> > ITLB IIRC, so it has to.
>
> Hmm… I don’t think Arm is doing that. At least arm64 does not use the
> default tlb_flush(), and it does not seem to consider VM_EXEC (at least in
> this path):
>
ARM != ARM64. ARM certainly does, but you're right, I don't think ARM64
does this.
^ permalink raw reply
* [PATCH v12 00/14] huge vmalloc mappings
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Ding Tianhong, linux-kernel, Nicholas Piggin,
Christoph Hellwig, Jonathan Cameron, Rick Edgecombe, linuxppc-dev
Should be getting close now. No doubt there will be a few more
things but I can do incremental fixes for small things if this gets
into -mm.
Thanks,
Nick
Since v11:
- ARM compile fix (patch 1)
- debug_vm_pgtable compile fix
Since v10:
- Fixed code style, most > 80 colums, tweak patch titles, etc [thanks Christoph]
- Made huge vmalloc code and data structure compile away if unselected
[Christoph]
- Archs only have to provide arch_vmap_p?d_supported for levels they
implement [Christoph]
Since v9:
- Fixed intermediate build breakage on x86-32 !PAE [thanks Ding]
- Fixed small page fallback case vm_struct double-free [thanks Ding]
Since v8:
- Fixed nommu compile.
- Added Kconfig option help text
- Added VM_NOHUGE which should help archs implement it [suggested by Rick]
Since v7:
- Rebase, added some acks, compile fix
- Removed "order=" from vmallocinfo, it's a bit confusing (nr_pages
is in small page size for compatibility).
- Added arch_vmap_pmd_supported() test before starting to allocate
the large page, rather than only testing it when doing the map, to
avoid unsupported configs trying to allocate huge pages for no
reason.
Since v6:
- Fixed a false positive warning introduced in patch 2, found by
kbuild test robot.
Since v5:
- Split arch changes out better and make the constant folding work
- Avoid most of the 80 column wrap, fix a reference to lib/ioremap.c
- Fix compile error on some archs
Since v4:
- Fixed an off-by-page-order bug in v4
- Several minor cleanups.
- Added page order to /proc/vmallocinfo
- Added hugepage to alloc_large_system_hage output.
- Made an architecture config option, powerpc only for now.
Since v3:
- Fixed an off-by-one bug in a loop
- Fix !CONFIG_HAVE_ARCH_HUGE_VMAP build fail
Nicholas Piggin (14):
ARM: mm: add missing pud_page define to 2-level page tables
mm/vmalloc: fix HUGE_VMAP regression by enabling huge pages in
vmalloc_to_page
mm: apply_to_pte_range warn and fail if a large pte is encountered
mm/vmalloc: rename vmap_*_range vmap_pages_*_range
mm/ioremap: rename ioremap_*_range to vmap_*_range
mm: HUGE_VMAP arch support cleanup
powerpc: inline huge vmap supported functions
arm64: inline huge vmap supported functions
x86: inline huge vmap supported functions
mm/vmalloc: provide fallback arch huge vmap support functions
mm: Move vmap_range from mm/ioremap.c to mm/vmalloc.c
mm/vmalloc: add vmap_range_noflush variant
mm/vmalloc: Hugepage vmalloc mappings
powerpc/64s/radix: Enable huge vmalloc mappings
.../admin-guide/kernel-parameters.txt | 2 +
arch/Kconfig | 11 +
arch/arm/include/asm/pgtable-3level.h | 2 -
arch/arm/include/asm/pgtable.h | 3 +
arch/arm64/include/asm/vmalloc.h | 24 +
arch/arm64/mm/mmu.c | 26 -
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/vmalloc.h | 20 +
arch/powerpc/kernel/module.c | 21 +-
arch/powerpc/mm/book3s64/radix_pgtable.c | 21 -
arch/x86/include/asm/vmalloc.h | 20 +
arch/x86/mm/ioremap.c | 19 -
arch/x86/mm/pgtable.c | 13 -
include/linux/io.h | 9 -
include/linux/vmalloc.h | 46 ++
init/main.c | 1 -
mm/debug_vm_pgtable.c | 4 +-
mm/ioremap.c | 225 +-------
mm/memory.c | 66 ++-
mm/page_alloc.c | 5 +-
mm/vmalloc.c | 484 +++++++++++++++---
21 files changed, 619 insertions(+), 404 deletions(-)
--
2.23.0
^ permalink raw reply
* [PATCH v12 01/14] ARM: mm: add missing pud_page define to 2-level page tables
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Ding Tianhong, linux-kernel, Nicholas Piggin,
Russell King, Christoph Hellwig, Jonathan Cameron, Rick Edgecombe,
linuxppc-dev, linux-arm-kernel
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
ARM uses its own PMD folding scheme which is missing pud_page which
should just pass through to pmd_page. Move this from the 3-level
page table to common header.
Cc: Russell King <linux@armlinux.org.uk>
Cc: Ding Tianhong <dingtianhong@huawei.com>
Cc: linux-arm-kernel@lists.infradead.org
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/arm/include/asm/pgtable-3level.h | 2 --
arch/arm/include/asm/pgtable.h | 3 +++
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 2b85d175e999..d4edab51a77c 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -186,8 +186,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
#define pmd_write(pmd) (pmd_isclear((pmd), L_PMD_SECT_RDONLY))
#define pmd_dirty(pmd) (pmd_isset((pmd), L_PMD_SECT_DIRTY))
-#define pud_page(pud) pmd_page(__pmd(pud_val(pud)))
-#define pud_write(pud) pmd_write(__pmd(pud_val(pud)))
#define pmd_hugewillfault(pmd) (!pmd_young(pmd) || !pmd_write(pmd))
#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd))
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index c02f24400369..d63a5bb6bd0c 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -166,6 +166,9 @@ extern struct page *empty_zero_page;
extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+#define pud_page(pud) pmd_page(__pmd(pud_val(pud)))
+#define pud_write(pud) pmd_write(__pmd(pud_val(pud)))
+
#define pmd_none(pmd) (!pmd_val(pmd))
static inline pte_t *pmd_page_vaddr(pmd_t pmd)
--
2.23.0
^ permalink raw reply related
* [PATCH v12 02/14] mm/vmalloc: fix HUGE_VMAP regression by enabling huge pages in vmalloc_to_page
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Miaohe Lin, Ding Tianhong, linux-kernel,
Nicholas Piggin, Christoph Hellwig, Jonathan Cameron,
Rick Edgecombe, linuxppc-dev, Christoph Hellwig
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
vmalloc_to_page returns NULL for addresses mapped by larger pages[*].
Whether or not a vmap is huge depends on the architecture details,
alignments, boot options, etc., which the caller can not be expected
to know. Therefore HUGE_VMAP is a regression for vmalloc_to_page.
This change teaches vmalloc_to_page about larger pages, and returns
the struct page that corresponds to the offset within the large page.
This makes the API agnostic to mapping implementation details.
[*] As explained by commit 029c54b095995 ("mm/vmalloc.c: huge-vmap:
fail gracefully on unexpected huge vmap mappings")
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
mm/vmalloc.c | 41 ++++++++++++++++++++++++++---------------
1 file changed, 26 insertions(+), 15 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e6f352bf0498..62372f9e0167 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -34,7 +34,7 @@
#include <linux/bitops.h>
#include <linux/rbtree_augmented.h>
#include <linux/overflow.h>
-
+#include <linux/pgtable.h>
#include <linux/uaccess.h>
#include <asm/tlbflush.h>
#include <asm/shmparam.h>
@@ -343,7 +343,9 @@ int is_vmalloc_or_module_addr(const void *x)
}
/*
- * Walk a vmap address to the struct page it maps.
+ * Walk a vmap address to the struct page it maps. Huge vmap mappings will
+ * return the tail page that corresponds to the base page address, which
+ * matches small vmap mappings.
*/
struct page *vmalloc_to_page(const void *vmalloc_addr)
{
@@ -363,25 +365,33 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
if (pgd_none(*pgd))
return NULL;
+ if (WARN_ON_ONCE(pgd_leaf(*pgd)))
+ return NULL; /* XXX: no allowance for huge pgd */
+ if (WARN_ON_ONCE(pgd_bad(*pgd)))
+ return NULL;
+
p4d = p4d_offset(pgd, addr);
if (p4d_none(*p4d))
return NULL;
- pud = pud_offset(p4d, addr);
+ if (p4d_leaf(*p4d))
+ return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT);
+ if (WARN_ON_ONCE(p4d_bad(*p4d)))
+ return NULL;
- /*
- * Don't dereference bad PUD or PMD (below) entries. This will also
- * identify huge mappings, which we may encounter on architectures
- * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be
- * identified as vmalloc addresses by is_vmalloc_addr(), but are
- * not [unambiguously] associated with a struct page, so there is
- * no correct value to return for them.
- */
- WARN_ON_ONCE(pud_bad(*pud));
- if (pud_none(*pud) || pud_bad(*pud))
+ pud = pud_offset(p4d, addr);
+ if (pud_none(*pud))
+ return NULL;
+ if (pud_leaf(*pud))
+ return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+ if (WARN_ON_ONCE(pud_bad(*pud)))
return NULL;
+
pmd = pmd_offset(pud, addr);
- WARN_ON_ONCE(pmd_bad(*pmd));
- if (pmd_none(*pmd) || pmd_bad(*pmd))
+ if (pmd_none(*pmd))
+ return NULL;
+ if (pmd_leaf(*pmd))
+ return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+ if (WARN_ON_ONCE(pmd_bad(*pmd)))
return NULL;
ptep = pte_offset_map(pmd, addr);
@@ -389,6 +399,7 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
if (pte_present(pte))
page = pte_page(pte);
pte_unmap(ptep);
+
return page;
}
EXPORT_SYMBOL(vmalloc_to_page);
--
2.23.0
^ permalink raw reply related
* [PATCH v12 03/14] mm: apply_to_pte_range warn and fail if a large pte is encountered
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Miaohe Lin, Ding Tianhong, linux-kernel,
Nicholas Piggin, Christoph Hellwig, Jonathan Cameron,
Rick Edgecombe, linuxppc-dev, Christoph Hellwig
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
apply_to_pte_range might mistake a large pte for bad, or treat it as a
page table, resulting in a crash or corruption. Add a test to warn and
return error if large entries are found.
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
mm/memory.c | 66 +++++++++++++++++++++++++++++++++++++++--------------
1 file changed, 49 insertions(+), 17 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index feff48e1465a..672e39a72788 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2440,13 +2440,21 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
}
do {
next = pmd_addr_end(addr, end);
- if (create || !pmd_none_or_clear_bad(pmd)) {
- err = apply_to_pte_range(mm, pmd, addr, next, fn, data,
- create, mask);
- if (err)
- break;
+ if (pmd_none(*pmd) && !create)
+ continue;
+ if (WARN_ON_ONCE(pmd_leaf(*pmd)))
+ return -EINVAL;
+ if (!pmd_none(*pmd) && WARN_ON_ONCE(pmd_bad(*pmd))) {
+ if (!create)
+ continue;
+ pmd_clear_bad(pmd);
}
+ err = apply_to_pte_range(mm, pmd, addr, next,
+ fn, data, create, mask);
+ if (err)
+ break;
} while (pmd++, addr = next, addr != end);
+
return err;
}
@@ -2468,13 +2476,21 @@ static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
}
do {
next = pud_addr_end(addr, end);
- if (create || !pud_none_or_clear_bad(pud)) {
- err = apply_to_pmd_range(mm, pud, addr, next, fn, data,
- create, mask);
- if (err)
- break;
+ if (pud_none(*pud) && !create)
+ continue;
+ if (WARN_ON_ONCE(pud_leaf(*pud)))
+ return -EINVAL;
+ if (!pud_none(*pud) && WARN_ON_ONCE(pud_bad(*pud))) {
+ if (!create)
+ continue;
+ pud_clear_bad(pud);
}
+ err = apply_to_pmd_range(mm, pud, addr, next,
+ fn, data, create, mask);
+ if (err)
+ break;
} while (pud++, addr = next, addr != end);
+
return err;
}
@@ -2496,13 +2512,21 @@ static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
}
do {
next = p4d_addr_end(addr, end);
- if (create || !p4d_none_or_clear_bad(p4d)) {
- err = apply_to_pud_range(mm, p4d, addr, next, fn, data,
- create, mask);
- if (err)
- break;
+ if (p4d_none(*p4d) && !create)
+ continue;
+ if (WARN_ON_ONCE(p4d_leaf(*p4d)))
+ return -EINVAL;
+ if (!p4d_none(*p4d) && WARN_ON_ONCE(p4d_bad(*p4d))) {
+ if (!create)
+ continue;
+ p4d_clear_bad(p4d);
}
+ err = apply_to_pud_range(mm, p4d, addr, next,
+ fn, data, create, mask);
+ if (err)
+ break;
} while (p4d++, addr = next, addr != end);
+
return err;
}
@@ -2522,9 +2546,17 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
pgd = pgd_offset(mm, addr);
do {
next = pgd_addr_end(addr, end);
- if (!create && pgd_none_or_clear_bad(pgd))
+ if (pgd_none(*pgd) && !create)
continue;
- err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask);
+ if (WARN_ON_ONCE(pgd_leaf(*pgd)))
+ return -EINVAL;
+ if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) {
+ if (!create)
+ continue;
+ pgd_clear_bad(pgd);
+ }
+ err = apply_to_p4d_range(mm, pgd, addr, next,
+ fn, data, create, &mask);
if (err)
break;
} while (pgd++, addr = next, addr != end);
--
2.23.0
^ permalink raw reply related
* [PATCH v12 04/14] mm/vmalloc: rename vmap_*_range vmap_pages_*_range
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Miaohe Lin, Ding Tianhong, linux-kernel,
Nicholas Piggin, Christoph Hellwig, Jonathan Cameron,
Rick Edgecombe, linuxppc-dev, Christoph Hellwig
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
The vmalloc mapper operates on a struct page * array rather than a
linear physical address, re-name it to make this distinction clear.
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
mm/vmalloc.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 62372f9e0167..7f2f36116980 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -189,7 +189,7 @@ void unmap_kernel_range_noflush(unsigned long start, unsigned long size)
arch_sync_kernel_mappings(start, end);
}
-static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
+static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr,
pgtbl_mod_mask *mask)
{
@@ -217,7 +217,7 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
return 0;
}
-static int vmap_pmd_range(pud_t *pud, unsigned long addr,
+static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr,
pgtbl_mod_mask *mask)
{
@@ -229,13 +229,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr,
return -ENOMEM;
do {
next = pmd_addr_end(addr, end);
- if (vmap_pte_range(pmd, addr, next, prot, pages, nr, mask))
+ if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask))
return -ENOMEM;
} while (pmd++, addr = next, addr != end);
return 0;
}
-static int vmap_pud_range(p4d_t *p4d, unsigned long addr,
+static int vmap_pages_pud_range(p4d_t *p4d, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr,
pgtbl_mod_mask *mask)
{
@@ -247,13 +247,13 @@ static int vmap_pud_range(p4d_t *p4d, unsigned long addr,
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
- if (vmap_pmd_range(pud, addr, next, prot, pages, nr, mask))
+ if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}
-static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
+static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr,
pgtbl_mod_mask *mask)
{
@@ -265,7 +265,7 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
return -ENOMEM;
do {
next = p4d_addr_end(addr, end);
- if (vmap_pud_range(p4d, addr, next, prot, pages, nr, mask))
+ if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask))
return -ENOMEM;
} while (p4d++, addr = next, addr != end);
return 0;
@@ -306,7 +306,7 @@ int map_kernel_range_noflush(unsigned long addr, unsigned long size,
next = pgd_addr_end(addr, end);
if (pgd_bad(*pgd))
mask |= PGTBL_PGD_MODIFIED;
- err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr, &mask);
+ err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask);
if (err)
return err;
} while (pgd++, addr = next, addr != end);
--
2.23.0
^ permalink raw reply related
* [PATCH v12 05/14] mm/ioremap: rename ioremap_*_range to vmap_*_range
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Miaohe Lin, Ding Tianhong, linux-kernel,
Nicholas Piggin, Christoph Hellwig, Jonathan Cameron,
Rick Edgecombe, linuxppc-dev, Christoph Hellwig
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
This will be used as a generic kernel virtual mapping function, so
re-name it in preparation.
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
mm/ioremap.c | 64 +++++++++++++++++++++++++++-------------------------
1 file changed, 33 insertions(+), 31 deletions(-)
diff --git a/mm/ioremap.c b/mm/ioremap.c
index 5fa1ab41d152..3f4d36f9745a 100644
--- a/mm/ioremap.c
+++ b/mm/ioremap.c
@@ -61,9 +61,9 @@ static inline int ioremap_pud_enabled(void) { return 0; }
static inline int ioremap_pmd_enabled(void) { return 0; }
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
-static int ioremap_pte_range(pmd_t *pmd, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ pgtbl_mod_mask *mask)
{
pte_t *pte;
u64 pfn;
@@ -81,9 +81,8 @@ static int ioremap_pte_range(pmd_t *pmd, unsigned long addr,
return 0;
}
-static int ioremap_try_huge_pmd(pmd_t *pmd, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr,
- pgprot_t prot)
+static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot)
{
if (!ioremap_pmd_enabled())
return 0;
@@ -103,9 +102,9 @@ static int ioremap_try_huge_pmd(pmd_t *pmd, unsigned long addr,
return pmd_set_huge(pmd, phys_addr, prot);
}
-static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ pgtbl_mod_mask *mask)
{
pmd_t *pmd;
unsigned long next;
@@ -116,20 +115,19 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
do {
next = pmd_addr_end(addr, end);
- if (ioremap_try_huge_pmd(pmd, addr, next, phys_addr, prot)) {
+ if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot)) {
*mask |= PGTBL_PMD_MODIFIED;
continue;
}
- if (ioremap_pte_range(pmd, addr, next, phys_addr, prot, mask))
+ if (vmap_pte_range(pmd, addr, next, phys_addr, prot, mask))
return -ENOMEM;
} while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
}
-static int ioremap_try_huge_pud(pud_t *pud, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr,
- pgprot_t prot)
+static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot)
{
if (!ioremap_pud_enabled())
return 0;
@@ -149,9 +147,9 @@ static int ioremap_try_huge_pud(pud_t *pud, unsigned long addr,
return pud_set_huge(pud, phys_addr, prot);
}
-static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ pgtbl_mod_mask *mask)
{
pud_t *pud;
unsigned long next;
@@ -162,20 +160,19 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
do {
next = pud_addr_end(addr, end);
- if (ioremap_try_huge_pud(pud, addr, next, phys_addr, prot)) {
+ if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot)) {
*mask |= PGTBL_PUD_MODIFIED;
continue;
}
- if (ioremap_pmd_range(pud, addr, next, phys_addr, prot, mask))
+ if (vmap_pmd_range(pud, addr, next, phys_addr, prot, mask))
return -ENOMEM;
} while (pud++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
}
-static int ioremap_try_huge_p4d(p4d_t *p4d, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr,
- pgprot_t prot)
+static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot)
{
if (!ioremap_p4d_enabled())
return 0;
@@ -195,9 +192,9 @@ static int ioremap_try_huge_p4d(p4d_t *p4d, unsigned long addr,
return p4d_set_huge(p4d, phys_addr, prot);
}
-static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ pgtbl_mod_mask *mask)
{
p4d_t *p4d;
unsigned long next;
@@ -208,19 +205,19 @@ static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
do {
next = p4d_addr_end(addr, end);
- if (ioremap_try_huge_p4d(p4d, addr, next, phys_addr, prot)) {
+ if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot)) {
*mask |= PGTBL_P4D_MODIFIED;
continue;
}
- if (ioremap_pud_range(p4d, addr, next, phys_addr, prot, mask))
+ if (vmap_pud_range(p4d, addr, next, phys_addr, prot, mask))
return -ENOMEM;
} while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
}
-int ioremap_page_range(unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
+static int vmap_range(unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot)
{
pgd_t *pgd;
unsigned long start;
@@ -235,8 +232,7 @@ int ioremap_page_range(unsigned long addr,
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
- err = ioremap_p4d_range(pgd, addr, next, phys_addr, prot,
- &mask);
+ err = vmap_p4d_range(pgd, addr, next, phys_addr, prot, &mask);
if (err)
break;
} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
@@ -249,6 +245,12 @@ int ioremap_page_range(unsigned long addr,
return err;
}
+int ioremap_page_range(unsigned long addr,
+ unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
+{
+ return vmap_range(addr, end, phys_addr, prot);
+}
+
#ifdef CONFIG_GENERIC_IOREMAP
void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot)
{
--
2.23.0
^ permalink raw reply related
* [PATCH v12 06/14] mm: HUGE_VMAP arch support cleanup
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, x86, H. Peter Anvin, Will Deacon, Catalin Marinas,
Ding Tianhong, linux-kernel, Nicholas Piggin, Christoph Hellwig,
Ingo Molnar, Borislav Petkov, Jonathan Cameron, Thomas Gleixner,
Rick Edgecombe, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
This changes the awkward approach where architectures provide init
functions to determine which levels they can provide large mappings for,
to one where the arch is queried for each call.
This removes code and indirection, and allows constant-folding of dead
code for unsupported levels.
This also adds a prot argument to the arch query. This is unused
currently but could help with some architectures (e.g., some powerpc
processors can't map uncacheable memory with large pages).
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: x86@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Reviewed-by: Ding Tianhong <dingtianhong@huawei.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com> [arm64]
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/arm64/include/asm/vmalloc.h | 8 ++
arch/arm64/mm/mmu.c | 10 +--
arch/powerpc/include/asm/vmalloc.h | 8 ++
arch/powerpc/mm/book3s64/radix_pgtable.c | 8 +-
arch/x86/include/asm/vmalloc.h | 7 ++
arch/x86/mm/ioremap.c | 12 +--
include/linux/io.h | 9 ---
include/linux/vmalloc.h | 6 ++
init/main.c | 1 -
mm/debug_vm_pgtable.c | 4 +-
mm/ioremap.c | 94 ++++++++++--------------
11 files changed, 87 insertions(+), 80 deletions(-)
diff --git a/arch/arm64/include/asm/vmalloc.h b/arch/arm64/include/asm/vmalloc.h
index 2ca708ab9b20..597b40405319 100644
--- a/arch/arm64/include/asm/vmalloc.h
+++ b/arch/arm64/include/asm/vmalloc.h
@@ -1,4 +1,12 @@
#ifndef _ASM_ARM64_VMALLOC_H
#define _ASM_ARM64_VMALLOC_H
+#include <asm/page.h>
+
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+bool arch_vmap_p4d_supported(pgprot_t prot);
+bool arch_vmap_pud_supported(pgprot_t prot);
+bool arch_vmap_pmd_supported(pgprot_t prot);
+#endif
+
#endif /* _ASM_ARM64_VMALLOC_H */
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index ae0c3d023824..1613d290cbd1 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1313,12 +1313,12 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
return dt_virt;
}
-int __init arch_ioremap_p4d_supported(void)
+bool arch_vmap_p4d_supported(pgprot_t prot)
{
- return 0;
+ return false;
}
-int __init arch_ioremap_pud_supported(void)
+bool arch_vmap_pud_supported(pgprot_t prot)
{
/*
* Only 4k granule supports level 1 block mappings.
@@ -1328,9 +1328,9 @@ int __init arch_ioremap_pud_supported(void)
!IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
}
-int __init arch_ioremap_pmd_supported(void)
+bool arch_vmap_pmd_supported(pgprot_t prot)
{
- /* See arch_ioremap_pud_supported() */
+ /* See arch_vmap_pud_supported() */
return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
}
diff --git a/arch/powerpc/include/asm/vmalloc.h b/arch/powerpc/include/asm/vmalloc.h
index b992dfaaa161..105abb73f075 100644
--- a/arch/powerpc/include/asm/vmalloc.h
+++ b/arch/powerpc/include/asm/vmalloc.h
@@ -1,4 +1,12 @@
#ifndef _ASM_POWERPC_VMALLOC_H
#define _ASM_POWERPC_VMALLOC_H
+#include <asm/page.h>
+
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+bool arch_vmap_p4d_supported(pgprot_t prot);
+bool arch_vmap_pud_supported(pgprot_t prot);
+bool arch_vmap_pmd_supported(pgprot_t prot);
+#endif
+
#endif /* _ASM_POWERPC_VMALLOC_H */
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 98f0b243c1ab..743807fc210f 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -1082,13 +1082,13 @@ void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
set_pte_at(mm, addr, ptep, pte);
}
-int __init arch_ioremap_pud_supported(void)
+bool arch_vmap_pud_supported(pgprot_t prot)
{
/* HPT does not cope with large pages in the vmalloc area */
return radix_enabled();
}
-int __init arch_ioremap_pmd_supported(void)
+bool arch_vmap_pmd_supported(pgprot_t prot)
{
return radix_enabled();
}
@@ -1182,7 +1182,7 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
return 1;
}
-int __init arch_ioremap_p4d_supported(void)
+bool arch_vmap_p4d_supported(pgprot_t prot)
{
- return 0;
+ return false;
}
diff --git a/arch/x86/include/asm/vmalloc.h b/arch/x86/include/asm/vmalloc.h
index 29837740b520..094ea2b565f3 100644
--- a/arch/x86/include/asm/vmalloc.h
+++ b/arch/x86/include/asm/vmalloc.h
@@ -1,6 +1,13 @@
#ifndef _ASM_X86_VMALLOC_H
#define _ASM_X86_VMALLOC_H
+#include <asm/page.h>
#include <asm/pgtable_areas.h>
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+bool arch_vmap_p4d_supported(pgprot_t prot);
+bool arch_vmap_pud_supported(pgprot_t prot);
+bool arch_vmap_pmd_supported(pgprot_t prot);
+#endif
+
#endif /* _ASM_X86_VMALLOC_H */
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 9e5ccc56f8e0..fbaf0c447986 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -481,24 +481,26 @@ void iounmap(volatile void __iomem *addr)
}
EXPORT_SYMBOL(iounmap);
-int __init arch_ioremap_p4d_supported(void)
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+bool arch_vmap_p4d_supported(pgprot_t prot)
{
- return 0;
+ return false;
}
-int __init arch_ioremap_pud_supported(void)
+bool arch_vmap_pud_supported(pgprot_t prot)
{
#ifdef CONFIG_X86_64
return boot_cpu_has(X86_FEATURE_GBPAGES);
#else
- return 0;
+ return false;
#endif
}
-int __init arch_ioremap_pmd_supported(void)
+bool arch_vmap_pmd_supported(pgprot_t prot)
{
return boot_cpu_has(X86_FEATURE_PSE);
}
+#endif
/*
* Convert a physical pointer to a virtual kernel pointer for /dev/mem
diff --git a/include/linux/io.h b/include/linux/io.h
index 8394c56babc2..f1effd4d7a3c 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -31,15 +31,6 @@ static inline int ioremap_page_range(unsigned long addr, unsigned long end,
}
#endif
-#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-void __init ioremap_huge_init(void);
-int arch_ioremap_p4d_supported(void);
-int arch_ioremap_pud_supported(void);
-int arch_ioremap_pmd_supported(void);
-#else
-static inline void ioremap_huge_init(void) { }
-#endif
-
/*
* Managed iomap interface
*/
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 80c0181c411d..00bd62bd701e 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -83,6 +83,12 @@ struct vmap_area {
};
};
+#ifndef CONFIG_HAVE_ARCH_HUGE_VMAP
+static inline bool arch_vmap_p4d_supported(pgprot_t prot) { return false; }
+static inline bool arch_vmap_pud_supported(pgprot_t prot) { return false; }
+static inline bool arch_vmap_pmd_supported(pgprot_t prot) { return false; }
+#endif
+
/*
* Highlevel APIs for driver use
*/
diff --git a/init/main.c b/init/main.c
index c68d784376ca..bf9389e5b2e4 100644
--- a/init/main.c
+++ b/init/main.c
@@ -834,7 +834,6 @@ static void __init mm_init(void)
pgtable_init();
debug_objects_mem_init();
vmalloc_init();
- ioremap_huge_init();
/* Should be run before the first non-init thread is created */
init_espfix_bsp();
/* Should be run after espfix64 is set up. */
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index c05d9dcf7891..38345e76bd26 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -218,7 +218,7 @@ static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot)
{
pmd_t pmd;
- if (!arch_ioremap_pmd_supported())
+ if (!arch_vmap_pmd_supported())
return;
pr_debug("Validating PMD huge\n");
@@ -340,7 +340,7 @@ static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot)
{
pud_t pud;
- if (!arch_ioremap_pud_supported())
+ if (!arch_vmap_pud_supported())
return;
pr_debug("Validating PUD huge\n");
diff --git a/mm/ioremap.c b/mm/ioremap.c
index 3f4d36f9745a..3264d0203785 100644
--- a/mm/ioremap.c
+++ b/mm/ioremap.c
@@ -16,49 +16,16 @@
#include "pgalloc-track.h"
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-static int __read_mostly ioremap_p4d_capable;
-static int __read_mostly ioremap_pud_capable;
-static int __read_mostly ioremap_pmd_capable;
-static int __read_mostly ioremap_huge_disabled;
+static bool __ro_after_init iomap_max_page_shift = PAGE_SHIFT;
static int __init set_nohugeiomap(char *str)
{
- ioremap_huge_disabled = 1;
+ iomap_max_page_shift = P4D_SHIFT;
return 0;
}
early_param("nohugeiomap", set_nohugeiomap);
-
-void __init ioremap_huge_init(void)
-{
- if (!ioremap_huge_disabled) {
- if (arch_ioremap_p4d_supported())
- ioremap_p4d_capable = 1;
- if (arch_ioremap_pud_supported())
- ioremap_pud_capable = 1;
- if (arch_ioremap_pmd_supported())
- ioremap_pmd_capable = 1;
- }
-}
-
-static inline int ioremap_p4d_enabled(void)
-{
- return ioremap_p4d_capable;
-}
-
-static inline int ioremap_pud_enabled(void)
-{
- return ioremap_pud_capable;
-}
-
-static inline int ioremap_pmd_enabled(void)
-{
- return ioremap_pmd_capable;
-}
-
-#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */
-static inline int ioremap_p4d_enabled(void) { return 0; }
-static inline int ioremap_pud_enabled(void) { return 0; }
-static inline int ioremap_pmd_enabled(void) { return 0; }
+#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */
+static const bool iomap_max_page_shift = PAGE_SHIFT;
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
@@ -82,9 +49,13 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
}
static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot)
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
{
- if (!ioremap_pmd_enabled())
+ if (max_page_shift < PMD_SHIFT)
+ return 0;
+
+ if (!arch_vmap_pmd_supported(prot))
return 0;
if ((end - addr) != PMD_SIZE)
@@ -104,7 +75,7 @@ static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+ unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
pmd_t *pmd;
unsigned long next;
@@ -115,7 +86,8 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
do {
next = pmd_addr_end(addr, end);
- if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot)) {
+ if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot,
+ max_page_shift)) {
*mask |= PGTBL_PMD_MODIFIED;
continue;
}
@@ -127,9 +99,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
}
static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot)
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
{
- if (!ioremap_pud_enabled())
+ if (max_page_shift < PUD_SHIFT)
+ return 0;
+
+ if (!arch_vmap_pud_supported(prot))
return 0;
if ((end - addr) != PUD_SIZE)
@@ -149,7 +125,7 @@ static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+ unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
pud_t *pud;
unsigned long next;
@@ -160,21 +136,27 @@ static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
do {
next = pud_addr_end(addr, end);
- if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot)) {
+ if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot,
+ max_page_shift)) {
*mask |= PGTBL_PUD_MODIFIED;
continue;
}
- if (vmap_pmd_range(pud, addr, next, phys_addr, prot, mask))
+ if (vmap_pmd_range(pud, addr, next, phys_addr, prot,
+ max_page_shift, mask))
return -ENOMEM;
} while (pud++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
}
static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot)
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
{
- if (!ioremap_p4d_enabled())
+ if (max_page_shift < P4D_SHIFT)
+ return 0;
+
+ if (!arch_vmap_p4d_supported(prot))
return 0;
if ((end - addr) != P4D_SIZE)
@@ -194,7 +176,7 @@ static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+ unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
p4d_t *p4d;
unsigned long next;
@@ -205,19 +187,22 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
do {
next = p4d_addr_end(addr, end);
- if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot)) {
+ if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot,
+ max_page_shift)) {
*mask |= PGTBL_P4D_MODIFIED;
continue;
}
- if (vmap_pud_range(p4d, addr, next, phys_addr, prot, mask))
+ if (vmap_pud_range(p4d, addr, next, phys_addr, prot,
+ max_page_shift, mask))
return -ENOMEM;
} while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
}
static int vmap_range(unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot)
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
{
pgd_t *pgd;
unsigned long start;
@@ -232,7 +217,8 @@ static int vmap_range(unsigned long addr, unsigned long end,
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
- err = vmap_p4d_range(pgd, addr, next, phys_addr, prot, &mask);
+ err = vmap_p4d_range(pgd, addr, next, phys_addr, prot,
+ max_page_shift, &mask);
if (err)
break;
} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
@@ -248,7 +234,7 @@ static int vmap_range(unsigned long addr, unsigned long end,
int ioremap_page_range(unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
- return vmap_range(addr, end, phys_addr, prot);
+ return vmap_range(addr, end, phys_addr, prot, iomap_max_page_shift);
}
#ifdef CONFIG_GENERIC_IOREMAP
--
2.23.0
^ permalink raw reply related
* [PATCH v12 07/14] powerpc: inline huge vmap supported functions
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Ding Tianhong, linux-kernel, Nicholas Piggin,
Christoph Hellwig, Jonathan Cameron, Rick Edgecombe, linuxppc-dev
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
This allows unsupported levels to be constant folded away, and so
p4d_free_pud_page can be removed because it's no longer linked to.
Cc: linuxppc-dev@lists.ozlabs.org
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/vmalloc.h | 19 ++++++++++++++++---
arch/powerpc/mm/book3s64/radix_pgtable.c | 21 ---------------------
2 files changed, 16 insertions(+), 24 deletions(-)
diff --git a/arch/powerpc/include/asm/vmalloc.h b/arch/powerpc/include/asm/vmalloc.h
index 105abb73f075..3f0c153befb0 100644
--- a/arch/powerpc/include/asm/vmalloc.h
+++ b/arch/powerpc/include/asm/vmalloc.h
@@ -1,12 +1,25 @@
#ifndef _ASM_POWERPC_VMALLOC_H
#define _ASM_POWERPC_VMALLOC_H
+#include <asm/mmu.h>
#include <asm/page.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-bool arch_vmap_p4d_supported(pgprot_t prot);
-bool arch_vmap_pud_supported(pgprot_t prot);
-bool arch_vmap_pmd_supported(pgprot_t prot);
+static inline bool arch_vmap_p4d_supported(pgprot_t prot)
+{
+ return false;
+}
+
+static inline bool arch_vmap_pud_supported(pgprot_t prot)
+{
+ /* HPT does not cope with large pages in the vmalloc area */
+ return radix_enabled();
+}
+
+static inline bool arch_vmap_pmd_supported(pgprot_t prot)
+{
+ return radix_enabled();
+}
#endif
#endif /* _ASM_POWERPC_VMALLOC_H */
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 743807fc210f..8da62afccee5 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -1082,22 +1082,6 @@ void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
set_pte_at(mm, addr, ptep, pte);
}
-bool arch_vmap_pud_supported(pgprot_t prot)
-{
- /* HPT does not cope with large pages in the vmalloc area */
- return radix_enabled();
-}
-
-bool arch_vmap_pmd_supported(pgprot_t prot)
-{
- return radix_enabled();
-}
-
-int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
-{
- return 0;
-}
-
int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
{
pte_t *ptep = (pte_t *)pud;
@@ -1181,8 +1165,3 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
return 1;
}
-
-bool arch_vmap_p4d_supported(pgprot_t prot)
-{
- return false;
-}
--
2.23.0
^ permalink raw reply related
* [PATCH v12 08/14] arm64: inline huge vmap supported functions
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Will Deacon, Catalin Marinas, Ding Tianhong,
linux-kernel, Nicholas Piggin, Christoph Hellwig,
Jonathan Cameron, Rick Edgecombe, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
This allows unsupported levels to be constant folded away, and so
p4d_free_pud_page can be removed because it's no longer linked to.
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/arm64/include/asm/vmalloc.h | 23 ++++++++++++++++++++---
arch/arm64/mm/mmu.c | 26 --------------------------
2 files changed, 20 insertions(+), 29 deletions(-)
diff --git a/arch/arm64/include/asm/vmalloc.h b/arch/arm64/include/asm/vmalloc.h
index 597b40405319..fc9a12d6cc1a 100644
--- a/arch/arm64/include/asm/vmalloc.h
+++ b/arch/arm64/include/asm/vmalloc.h
@@ -4,9 +4,26 @@
#include <asm/page.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-bool arch_vmap_p4d_supported(pgprot_t prot);
-bool arch_vmap_pud_supported(pgprot_t prot);
-bool arch_vmap_pmd_supported(pgprot_t prot);
+static inline bool arch_vmap_p4d_supported(pgprot_t prot)
+{
+ return false;
+}
+
+static inline bool arch_vmap_pud_supported(pgprot_t prot)
+{
+ /*
+ * Only 4k granule supports level 1 block mappings.
+ * SW table walks can't handle removal of intermediate entries.
+ */
+ return IS_ENABLED(CONFIG_ARM64_4K_PAGES) &&
+ !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
+}
+
+static inline bool arch_vmap_pmd_supported(pgprot_t prot)
+{
+ /* See arch_vmap_pud_supported() */
+ return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
+}
#endif
#endif /* _ASM_ARM64_VMALLOC_H */
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 1613d290cbd1..ab9ba7c36dae 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1313,27 +1313,6 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
return dt_virt;
}
-bool arch_vmap_p4d_supported(pgprot_t prot)
-{
- return false;
-}
-
-bool arch_vmap_pud_supported(pgprot_t prot)
-{
- /*
- * Only 4k granule supports level 1 block mappings.
- * SW table walks can't handle removal of intermediate entries.
- */
- return IS_ENABLED(CONFIG_ARM64_4K_PAGES) &&
- !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
-}
-
-bool arch_vmap_pmd_supported(pgprot_t prot)
-{
- /* See arch_vmap_pud_supported() */
- return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
-}
-
int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
{
pud_t new_pud = pfn_pud(__phys_to_pfn(phys), mk_pud_sect_prot(prot));
@@ -1425,11 +1404,6 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr)
return 1;
}
-int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
-{
- return 0; /* Don't attempt a block mapping */
-}
-
#ifdef CONFIG_MEMORY_HOTPLUG
static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
{
--
2.23.0
^ permalink raw reply related
* [PATCH v12 09/14] x86: inline huge vmap supported functions
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, x86, H. Peter Anvin, Ding Tianhong, linux-kernel,
Nicholas Piggin, Christoph Hellwig, Ingo Molnar, Borislav Petkov,
Jonathan Cameron, Thomas Gleixner, Rick Edgecombe, linuxppc-dev
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
This allows unsupported levels to be constant folded away, and so
p4d_free_pud_page can be removed because it's no longer linked to.
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: x86@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/x86/include/asm/vmalloc.h | 22 +++++++++++++++++++---
arch/x86/mm/ioremap.c | 21 ---------------------
arch/x86/mm/pgtable.c | 13 -------------
3 files changed, 19 insertions(+), 37 deletions(-)
diff --git a/arch/x86/include/asm/vmalloc.h b/arch/x86/include/asm/vmalloc.h
index 094ea2b565f3..e714b00fc0ca 100644
--- a/arch/x86/include/asm/vmalloc.h
+++ b/arch/x86/include/asm/vmalloc.h
@@ -1,13 +1,29 @@
#ifndef _ASM_X86_VMALLOC_H
#define _ASM_X86_VMALLOC_H
+#include <asm/cpufeature.h>
#include <asm/page.h>
#include <asm/pgtable_areas.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-bool arch_vmap_p4d_supported(pgprot_t prot);
-bool arch_vmap_pud_supported(pgprot_t prot);
-bool arch_vmap_pmd_supported(pgprot_t prot);
+static inline bool arch_vmap_p4d_supported(pgprot_t prot)
+{
+ return false;
+}
+
+static inline bool arch_vmap_pud_supported(pgprot_t prot)
+{
+#ifdef CONFIG_X86_64
+ return boot_cpu_has(X86_FEATURE_GBPAGES);
+#else
+ return false;
+#endif
+}
+
+static inline bool arch_vmap_pmd_supported(pgprot_t prot)
+{
+ return boot_cpu_has(X86_FEATURE_PSE);
+}
#endif
#endif /* _ASM_X86_VMALLOC_H */
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index fbaf0c447986..12c686c65ea9 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -481,27 +481,6 @@ void iounmap(volatile void __iomem *addr)
}
EXPORT_SYMBOL(iounmap);
-#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-bool arch_vmap_p4d_supported(pgprot_t prot)
-{
- return false;
-}
-
-bool arch_vmap_pud_supported(pgprot_t prot)
-{
-#ifdef CONFIG_X86_64
- return boot_cpu_has(X86_FEATURE_GBPAGES);
-#else
- return false;
-#endif
-}
-
-bool arch_vmap_pmd_supported(pgprot_t prot)
-{
- return boot_cpu_has(X86_FEATURE_PSE);
-}
-#endif
-
/*
* Convert a physical pointer to a virtual kernel pointer for /dev/mem
* access
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index f6a9e2e36642..d27cf69e811d 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -780,14 +780,6 @@ int pmd_clear_huge(pmd_t *pmd)
return 0;
}
-/*
- * Until we support 512GB pages, skip them in the vmap area.
- */
-int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
-{
- return 0;
-}
-
#ifdef CONFIG_X86_64
/**
* pud_free_pmd_page - Clear pud entry and free pmd page.
@@ -861,11 +853,6 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
#else /* !CONFIG_X86_64 */
-int pud_free_pmd_page(pud_t *pud, unsigned long addr)
-{
- return pud_none(*pud);
-}
-
/*
* Disable free page handling on x86-PAE. This assures that ioremap()
* does not update sync'd pmd entries. See vmalloc_sync_one().
--
2.23.0
^ permalink raw reply related
* [PATCH v12 10/14] mm/vmalloc: provide fallback arch huge vmap support functions
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Ding Tianhong, linux-kernel, Nicholas Piggin,
Christoph Hellwig, Jonathan Cameron, Rick Edgecombe, linuxppc-dev,
Christoph Hellwig
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
If an architecture doesn't support a particular page table level as
a huge vmap page size then allow it to skip defining the support
query function.
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/arm64/include/asm/vmalloc.h | 7 +++----
arch/powerpc/include/asm/vmalloc.h | 7 +++----
arch/x86/include/asm/vmalloc.h | 13 +++++--------
include/linux/vmalloc.h | 24 ++++++++++++++++++++----
4 files changed, 31 insertions(+), 20 deletions(-)
diff --git a/arch/arm64/include/asm/vmalloc.h b/arch/arm64/include/asm/vmalloc.h
index fc9a12d6cc1a..7a22aeea9bb5 100644
--- a/arch/arm64/include/asm/vmalloc.h
+++ b/arch/arm64/include/asm/vmalloc.h
@@ -4,11 +4,8 @@
#include <asm/page.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-static inline bool arch_vmap_p4d_supported(pgprot_t prot)
-{
- return false;
-}
+#define arch_vmap_pud_supported arch_vmap_pud_supported
static inline bool arch_vmap_pud_supported(pgprot_t prot)
{
/*
@@ -19,11 +16,13 @@ static inline bool arch_vmap_pud_supported(pgprot_t prot)
!IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
}
+#define arch_vmap_pmd_supported arch_vmap_pmd_supported
static inline bool arch_vmap_pmd_supported(pgprot_t prot)
{
/* See arch_vmap_pud_supported() */
return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
}
+
#endif
#endif /* _ASM_ARM64_VMALLOC_H */
diff --git a/arch/powerpc/include/asm/vmalloc.h b/arch/powerpc/include/asm/vmalloc.h
index 3f0c153befb0..4c69ece52a31 100644
--- a/arch/powerpc/include/asm/vmalloc.h
+++ b/arch/powerpc/include/asm/vmalloc.h
@@ -5,21 +5,20 @@
#include <asm/page.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-static inline bool arch_vmap_p4d_supported(pgprot_t prot)
-{
- return false;
-}
+#define arch_vmap_pud_supported arch_vmap_pud_supported
static inline bool arch_vmap_pud_supported(pgprot_t prot)
{
/* HPT does not cope with large pages in the vmalloc area */
return radix_enabled();
}
+#define arch_vmap_pmd_supported arch_vmap_pmd_supported
static inline bool arch_vmap_pmd_supported(pgprot_t prot)
{
return radix_enabled();
}
+
#endif
#endif /* _ASM_POWERPC_VMALLOC_H */
diff --git a/arch/x86/include/asm/vmalloc.h b/arch/x86/include/asm/vmalloc.h
index e714b00fc0ca..49ce331f3ac6 100644
--- a/arch/x86/include/asm/vmalloc.h
+++ b/arch/x86/include/asm/vmalloc.h
@@ -6,24 +6,21 @@
#include <asm/pgtable_areas.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-static inline bool arch_vmap_p4d_supported(pgprot_t prot)
-{
- return false;
-}
+#ifdef CONFIG_X86_64
+#define arch_vmap_pud_supported arch_vmap_pud_supported
static inline bool arch_vmap_pud_supported(pgprot_t prot)
{
-#ifdef CONFIG_X86_64
return boot_cpu_has(X86_FEATURE_GBPAGES);
-#else
- return false;
-#endif
}
+#endif
+#define arch_vmap_pmd_supported arch_vmap_pmd_supported
static inline bool arch_vmap_pmd_supported(pgprot_t prot)
{
return boot_cpu_has(X86_FEATURE_PSE);
}
+
#endif
#endif /* _ASM_X86_VMALLOC_H */
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 00bd62bd701e..9f7b8b00101b 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -83,10 +83,26 @@ struct vmap_area {
};
};
-#ifndef CONFIG_HAVE_ARCH_HUGE_VMAP
-static inline bool arch_vmap_p4d_supported(pgprot_t prot) { return false; }
-static inline bool arch_vmap_pud_supported(pgprot_t prot) { return false; }
-static inline bool arch_vmap_pmd_supported(pgprot_t prot) { return false; }
+/* archs that select HAVE_ARCH_HUGE_VMAP should override one or more of these */
+#ifndef arch_vmap_p4d_supported
+static inline bool arch_vmap_p4d_supported(pgprot_t prot)
+{
+ return false;
+}
+#endif
+
+#ifndef arch_vmap_pud_supported
+static inline bool arch_vmap_pud_supported(pgprot_t prot)
+{
+ return false;
+}
+#endif
+
+#ifndef arch_vmap_pmd_supported
+static inline bool arch_vmap_pmd_supported(pgprot_t prot)
+{
+ return false;
+}
#endif
/*
--
2.23.0
^ 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