[Linux-stable-mirror] Patch "x86/kaiser: Reenable PARAVIRT" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
x86/kaiser: Reenable PARAVIRT
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
x86-kaiser-reenable-paravirt.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Borislav Petkov <bp(a)suse.de>
Date: Tue, 2 Jan 2018 14:19:49 +0100
Subject: x86/kaiser: Reenable PARAVIRT
From: Borislav Petkov <bp(a)suse.de>
Now that the required bits have been addressed, reenable
PARAVIRT.
Signed-off-by: Borislav Petkov <bp(a)suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
security/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -34,7 +34,7 @@ config SECURITY
config KAISER
bool "Remove the kernel mapping in user mode"
default y
- depends on X86_64 && SMP && !PARAVIRT
+ depends on X86_64 && SMP
help
This enforces a strict kernel and user space isolation, in order
to close hardware side channels on kernel address information.
Patches currently in stable-queue which might be from bp(a)suse.de are
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/x86-kaiser-reenable-paravirt.patch
queue-4.9/x86-kaiser-rename-and-simplify-x86_feature_kaiser-handling.patch
queue-4.9/x86-kaiser-check-boottime-cmdline-params.patch
queue-4.9/x86-kaiser-move-feature-detection-up.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "x86/kaiser: Move feature detection up" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
x86/kaiser: Move feature detection up
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
x86-kaiser-move-feature-detection-up.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Borislav Petkov <bp(a)suse.de>
Date: Mon, 25 Dec 2017 13:57:16 +0100
Subject: x86/kaiser: Move feature detection up
From: Borislav Petkov <bp(a)suse.de>
... before the first use of kaiser_enabled as otherwise funky
things happen:
about to get started...
(XEN) d0v0 Unhandled page fault fault/trap [#14, ec=0000]
(XEN) Pagetable walk from ffff88022a449090:
(XEN) L4[0x110] = 0000000229e0e067 0000000000001e0e
(XEN) L3[0x008] = 0000000000000000 ffffffffffffffff
(XEN) domain_crash_sync called from entry.S: fault at ffff82d08033fd08
entry.o#create_bounce_frame+0x135/0x14d
(XEN) Domain 0 (vcpu#0) crashed on cpu#0:
(XEN) ----[ Xen-4.9.1_02-3.21 x86_64 debug=n Not tainted ]----
(XEN) CPU: 0
(XEN) RIP: e033:[<ffffffff81007460>]
(XEN) RFLAGS: 0000000000000286 EM: 1 CONTEXT: pv guest (d0v0)
Signed-off-by: Borislav Petkov <bp(a)suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/kaiser.h | 2 ++
arch/x86/kernel/setup.c | 7 +++++++
arch/x86/mm/kaiser.c | 2 --
3 files changed, 9 insertions(+), 2 deletions(-)
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -96,8 +96,10 @@ DECLARE_PER_CPU(unsigned long, x86_cr3_p
extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
extern int kaiser_enabled;
+extern void __init kaiser_check_boottime_disable(void);
#else
#define kaiser_enabled 0
+static inline void __init kaiser_check_boottime_disable(void) {}
#endif /* CONFIG_KAISER */
/*
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -114,6 +114,7 @@
#include <asm/microcode.h>
#include <asm/mmu_context.h>
#include <asm/kaslr.h>
+#include <asm/kaiser.h>
/*
* max_low_pfn_mapped: highest direct mapped pfn under 4GB
@@ -1019,6 +1020,12 @@ void __init setup_arch(char **cmdline_p)
*/
init_hypervisor_platform();
+ /*
+ * This needs to happen right after XENPV is set on xen and
+ * kaiser_enabled is checked below in cleanup_highmap().
+ */
+ kaiser_check_boottime_disable();
+
x86_init.resources.probe_roms();
/* after parse_early_param, so could debug it */
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -310,8 +310,6 @@ void __init kaiser_init(void)
{
int cpu;
- kaiser_check_boottime_disable();
-
if (!kaiser_enabled)
return;
Patches currently in stable-queue which might be from bp(a)suse.de are
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/x86-kaiser-reenable-paravirt.patch
queue-4.9/x86-kaiser-rename-and-simplify-x86_feature_kaiser-handling.patch
queue-4.9/x86-kaiser-check-boottime-cmdline-params.patch
queue-4.9/x86-kaiser-move-feature-detection-up.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 27 Aug 2017 16:24:27 -0700
Subject: kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user
From: Hugh Dickins <hughd(a)google.com>
Mostly this commit is just unshouting X86_CR3_PCID_KERN_VAR and
X86_CR3_PCID_USER_VAR: we usually name variables in lower-case.
But why does x86_cr3_pcid_noflush need to be __aligned(PAGE_SIZE)?
Ah, it's a leftover from when kaiser_add_user_map() once complained
about mapping the same page twice. Make it __read_mostly instead.
(I'm a little uneasy about all the unrelated data which shares its
page getting user-mapped too, but that was so before, and not a big
deal: though we call it user-mapped, it's not mapped with _PAGE_USER.)
And there is a little change around the two calls to do_nmi().
Previously they set the NOFLUSH bit (if PCID supported) when
forcing to kernel context before do_nmi(); now they also have the
NOFLUSH bit set (if PCID supported) when restoring context after:
nothing done in do_nmi() should require a TLB to be flushed here.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 8 ++++----
arch/x86/include/asm/kaiser.h | 11 +++++------
arch/x86/mm/kaiser.c | 13 +++++++------
3 files changed, 16 insertions(+), 16 deletions(-)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1316,11 +1316,11 @@ ENTRY(nmi)
/* Unconditionally use kernel CR3 for do_nmi() */
/* %rax is saved above, so OK to clobber here */
movq %cr3, %rax
+ /* If PCID enabled, NOFLUSH now and NOFLUSH on return */
+ orq x86_cr3_pcid_noflush, %rax
pushq %rax
/* mask off "user" bit of pgd address and 12 PCID bits: */
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
- /* Add back kernel PCID and "no flush" bit */
- orq X86_CR3_PCID_KERN_VAR, %rax
movq %rax, %cr3
#endif
call do_nmi
@@ -1560,11 +1560,11 @@ end_repeat_nmi:
/* Unconditionally use kernel CR3 for do_nmi() */
/* %rax is saved above, so OK to clobber here */
movq %cr3, %rax
+ /* If PCID enabled, NOFLUSH now and NOFLUSH on return */
+ orq x86_cr3_pcid_noflush, %rax
pushq %rax
/* mask off "user" bit of pgd address and 12 PCID bits: */
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
- /* Add back kernel PCID and "no flush" bit */
- orq X86_CR3_PCID_KERN_VAR, %rax
movq %rax, %cr3
#endif
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -25,7 +25,7 @@
.macro _SWITCH_TO_KERNEL_CR3 reg
movq %cr3, \reg
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
-orq X86_CR3_PCID_KERN_VAR, \reg
+orq x86_cr3_pcid_noflush, \reg
movq \reg, %cr3
.endm
@@ -37,11 +37,10 @@ movq \reg, %cr3
* not enabled): so that the one register can update both memory and cr3.
*/
movq %cr3, \reg
-andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
-orq PER_CPU_VAR(X86_CR3_PCID_USER_VAR), \reg
+orq PER_CPU_VAR(x86_cr3_pcid_user), \reg
js 9f
/* FLUSH this time, reset to NOFLUSH for next time (if PCID enabled) */
-movb \regb, PER_CPU_VAR(X86_CR3_PCID_USER_VAR+7)
+movb \regb, PER_CPU_VAR(x86_cr3_pcid_user+7)
9:
movq \reg, %cr3
.endm
@@ -94,8 +93,8 @@ movq PER_CPU_VAR(unsafe_stack_register_b
*/
DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
-extern unsigned long X86_CR3_PCID_KERN_VAR;
-DECLARE_PER_CPU(unsigned long, X86_CR3_PCID_USER_VAR);
+extern unsigned long x86_cr3_pcid_noflush;
+DECLARE_PER_CPU(unsigned long, x86_cr3_pcid_user);
extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -28,8 +28,8 @@ DEFINE_PER_CPU_USER_MAPPED(unsigned long
* This is also handy because systems that do not support PCIDs
* just end up or'ing a 0 into their CR3, which does no harm.
*/
-__aligned(PAGE_SIZE) unsigned long X86_CR3_PCID_KERN_VAR;
-DEFINE_PER_CPU(unsigned long, X86_CR3_PCID_USER_VAR);
+unsigned long x86_cr3_pcid_noflush __read_mostly;
+DEFINE_PER_CPU(unsigned long, x86_cr3_pcid_user);
/*
* At runtime, the only things we map are some things for CPU
@@ -303,7 +303,8 @@ void __init kaiser_init(void)
sizeof(gate_desc) * NR_VECTORS,
__PAGE_KERNEL);
- kaiser_add_user_map_early(&X86_CR3_PCID_KERN_VAR, PAGE_SIZE,
+ kaiser_add_user_map_early(&x86_cr3_pcid_noflush,
+ sizeof(x86_cr3_pcid_noflush),
__PAGE_KERNEL);
}
@@ -381,8 +382,8 @@ void kaiser_setup_pcid(void)
* These variables are used by the entry/exit
* code to change PCID and pgd and TLB flushing.
*/
- X86_CR3_PCID_KERN_VAR = kern_cr3;
- this_cpu_write(X86_CR3_PCID_USER_VAR, user_cr3);
+ x86_cr3_pcid_noflush = kern_cr3;
+ this_cpu_write(x86_cr3_pcid_user, user_cr3);
}
/*
@@ -392,7 +393,7 @@ void kaiser_setup_pcid(void)
*/
void kaiser_flush_tlb_on_return_to_user(void)
{
- this_cpu_write(X86_CR3_PCID_USER_VAR,
+ this_cpu_write(x86_cr3_pcid_user,
X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET);
}
EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user);
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "x86/kaiser: Check boottime cmdline params" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
x86/kaiser: Check boottime cmdline params
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
x86-kaiser-check-boottime-cmdline-params.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Borislav Petkov <bp(a)suse.de>
Date: Tue, 2 Jan 2018 14:19:48 +0100
Subject: x86/kaiser: Check boottime cmdline params
From: Borislav Petkov <bp(a)suse.de>
AMD (and possibly other vendors) are not affected by the leak
KAISER is protecting against.
Keep the "nopti" for traditional reasons and add pti=<on|off|auto>
like upstream.
Signed-off-by: Borislav Petkov <bp(a)suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
Documentation/kernel-parameters.txt | 6 +++
arch/x86/mm/kaiser.c | 59 +++++++++++++++++++++++++-----------
2 files changed, 47 insertions(+), 18 deletions(-)
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3327,6 +3327,12 @@ bytes respectively. Such letter suffixes
pt. [PARIDE]
See Documentation/blockdev/paride.txt.
+ pti= [X86_64]
+ Control KAISER user/kernel address space isolation:
+ on - enable
+ off - disable
+ auto - default setting
+
pty.legacy_count=
[KNL] Number of legacy pty's. Overwrites compiled-in
default number.
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -15,6 +15,7 @@
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/desc.h>
+#include <asm/cmdline.h>
int kaiser_enabled __read_mostly = 1;
EXPORT_SYMBOL(kaiser_enabled); /* for inlined TLB flush functions */
@@ -263,6 +264,43 @@ static void __init kaiser_init_all_pgds(
WARN_ON(__ret); \
} while (0)
+void __init kaiser_check_boottime_disable(void)
+{
+ bool enable = true;
+ char arg[5];
+ int ret;
+
+ ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
+ if (ret > 0) {
+ if (!strncmp(arg, "on", 2))
+ goto enable;
+
+ if (!strncmp(arg, "off", 3))
+ goto disable;
+
+ if (!strncmp(arg, "auto", 4))
+ goto skip;
+ }
+
+ if (cmdline_find_option_bool(boot_command_line, "nopti"))
+ goto disable;
+
+skip:
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ goto disable;
+
+enable:
+ if (enable)
+ setup_force_cpu_cap(X86_FEATURE_KAISER);
+
+ return;
+
+disable:
+ pr_info("Kernel/User page tables isolation: disabled\n");
+ kaiser_enabled = 0;
+ setup_clear_cpu_cap(X86_FEATURE_KAISER);
+}
+
/*
* If anything in here fails, we will likely die on one of the
* first kernel->user transitions and init will die. But, we
@@ -274,12 +312,10 @@ void __init kaiser_init(void)
{
int cpu;
- if (!kaiser_enabled) {
- setup_clear_cpu_cap(X86_FEATURE_KAISER);
- return;
- }
+ kaiser_check_boottime_disable();
- setup_force_cpu_cap(X86_FEATURE_KAISER);
+ if (!kaiser_enabled)
+ return;
kaiser_init_all_pgds();
@@ -423,16 +459,3 @@ void kaiser_flush_tlb_on_return_to_user(
X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET);
}
EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user);
-
-static int __init x86_nokaiser_setup(char *s)
-{
- /* nopti doesn't accept parameters */
- if (s)
- return -EINVAL;
-
- kaiser_enabled = 0;
- pr_info("Kernel/User page tables isolation: disabled\n");
-
- return 0;
-}
-early_param("nopti", x86_nokaiser_setup);
Patches currently in stable-queue which might be from bp(a)suse.de are
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/x86-kaiser-reenable-paravirt.patch
queue-4.9/x86-kaiser-rename-and-simplify-x86_feature_kaiser-handling.patch
queue-4.9/x86-kaiser-check-boottime-cmdline-params.patch
queue-4.9/x86-kaiser-move-feature-detection-up.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: vmstat show NR_KAISERTABLE as nr_overhead" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: vmstat show NR_KAISERTABLE as nr_overhead
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sat, 9 Sep 2017 21:27:32 -0700
Subject: kaiser: vmstat show NR_KAISERTABLE as nr_overhead
From: Hugh Dickins <hughd(a)google.com>
The kaiser update made an interesting choice, never to free any shadow
page tables. Contention on global spinlock was worrying, particularly
with it held across page table scans when freeing. Something had to be
done: I was going to add refcounting; but simply never to free them is
an appealing choice, minimizing contention without complicating the code
(the more a page table is found already, the less the spinlock is used).
But leaking pages in this way is also a worry: can we get away with it?
At the very least, we need a count to show how bad it actually gets:
in principle, one might end up wasting about 1/256 of memory that way
(1/512 for when direct-mapped pages have to be user-mapped, plus 1/512
for when they are user-mapped from the vmalloc area on another occasion
(but we don't have vmalloc'ed stacks, so only large ldts are vmalloc'ed).
Add per-cpu stat NR_KAISERTABLE: including 256 at startup for the
shared pgd entries, and 1 for each intermediate page table added
thereafter for user-mapping - but leave out the 1 per mm, for its
shadow pgd, because that distracts from the monotonic increase.
Shown in /proc/vmstat as nr_overhead (0 if kaiser not enabled).
In practice, it doesn't look so bad so far: more like 1/12000 after
nine hours of gtests below; and movable pageblock segregation should
tend to cluster the kaiser tables into a subset of the address space
(if not, they will be bad for compaction too). But production may
tell a different story: keep an eye on this number, and bring back
lighter freeing if it gets out of control (maybe a shrinker).
["nr_overhead" should of course say "nr_kaisertable", if it needs
to stay; but for the moment we are being coy, preferring that when
Joe Blow notices a new line in his /proc/vmstat, he does not get
too curious about what this "kaiser" stuff might be.]
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/kaiser.c | 16 +++++++++++-----
include/linux/mmzone.h | 3 ++-
mm/vmstat.c | 1 +
3 files changed, 14 insertions(+), 6 deletions(-)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -121,9 +121,11 @@ static pte_t *kaiser_pagetable_walk(unsi
if (!new_pmd_page)
return NULL;
spin_lock(&shadow_table_allocation_lock);
- if (pud_none(*pud))
+ if (pud_none(*pud)) {
set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
- else
+ __inc_zone_page_state(virt_to_page((void *)
+ new_pmd_page), NR_KAISERTABLE);
+ } else
free_page(new_pmd_page);
spin_unlock(&shadow_table_allocation_lock);
}
@@ -139,9 +141,11 @@ static pte_t *kaiser_pagetable_walk(unsi
if (!new_pte_page)
return NULL;
spin_lock(&shadow_table_allocation_lock);
- if (pmd_none(*pmd))
+ if (pmd_none(*pmd)) {
set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page)));
- else
+ __inc_zone_page_state(virt_to_page((void *)
+ new_pte_page), NR_KAISERTABLE);
+ } else
free_page(new_pte_page);
spin_unlock(&shadow_table_allocation_lock);
}
@@ -205,11 +209,13 @@ static void __init kaiser_init_all_pgds(
pgd = native_get_shadow_pgd(pgd_offset_k((unsigned long )0));
for (i = PTRS_PER_PGD / 2; i < PTRS_PER_PGD; i++) {
pgd_t new_pgd;
- pud_t *pud = pud_alloc_one(&init_mm, PAGE_OFFSET + i * PGDIR_SIZE);
+ pud_t *pud = pud_alloc_one(&init_mm,
+ PAGE_OFFSET + i * PGDIR_SIZE);
if (!pud) {
WARN_ON(1);
break;
}
+ inc_zone_page_state(virt_to_page(pud), NR_KAISERTABLE);
new_pgd = __pgd(_KERNPG_TABLE |__pa(pud));
/*
* Make sure not to stomp on some other pgd entry.
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -124,8 +124,9 @@ enum zone_stat_item {
NR_SLAB_UNRECLAIMABLE,
NR_PAGETABLE, /* used for pagetables */
NR_KERNEL_STACK_KB, /* measured in KiB */
- /* Second 128 byte cacheline */
+ NR_KAISERTABLE,
NR_BOUNCE,
+ /* Second 128 byte cacheline */
#if IS_ENABLED(CONFIG_ZSMALLOC)
NR_ZSPAGES, /* allocated in zsmalloc */
#endif
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -932,6 +932,7 @@ const char * const vmstat_text[] = {
"nr_slab_unreclaimable",
"nr_page_table_pages",
"nr_kernel_stack",
+ "nr_overhead",
"nr_bounce",
#if IS_ENABLED(CONFIG_ZSMALLOC)
"nr_zspages",
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: use ALTERNATIVE instead of x86_cr3_pcid_noflush" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: use ALTERNATIVE instead of x86_cr3_pcid_noflush
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Tue, 3 Oct 2017 20:49:04 -0700
Subject: kaiser: use ALTERNATIVE instead of x86_cr3_pcid_noflush
From: Hugh Dickins <hughd(a)google.com>
Now that we're playing the ALTERNATIVE game, use that more efficient
method: instead of user-mapping an extra page, and reading an extra
cacheline each time for x86_cr3_pcid_noflush.
Neel has found that __stringify(bts $X86_CR3_PCID_NOFLUSH_BIT, %rax)
is a working substitute for the "bts $63, %rax" in these ALTERNATIVEs;
but the one line with $63 in looks clearer, so let's stick with that.
Worried about what happens with an ALTERNATIVE between the jump and
jump label in another ALTERNATIVE? I was, but have checked the
combinations in SWITCH_KERNEL_CR3_NO_STACK at entry_SYSCALL_64,
and it does a good job.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 7 ++++---
arch/x86/include/asm/kaiser.h | 6 +++---
arch/x86/mm/kaiser.c | 11 +----------
3 files changed, 8 insertions(+), 16 deletions(-)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1084,7 +1084,8 @@ ENTRY(paranoid_entry)
jz 2f
orl $2, %ebx
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
- orq x86_cr3_pcid_noflush, %rax
+ /* If PCID enabled, set X86_CR3_PCID_NOFLUSH_BIT */
+ ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID
movq %rax, %cr3
2:
#endif
@@ -1344,7 +1345,7 @@ ENTRY(nmi)
/* %rax is saved above, so OK to clobber here */
ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER
/* If PCID enabled, NOFLUSH now and NOFLUSH on return */
- orq x86_cr3_pcid_noflush, %rax
+ ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID
pushq %rax
/* mask off "user" bit of pgd address and 12 PCID bits: */
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
@@ -1588,7 +1589,7 @@ end_repeat_nmi:
/* %rax is saved above, so OK to clobber here */
ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER
/* If PCID enabled, NOFLUSH now and NOFLUSH on return */
- orq x86_cr3_pcid_noflush, %rax
+ ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID
pushq %rax
/* mask off "user" bit of pgd address and 12 PCID bits: */
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -25,7 +25,8 @@
.macro _SWITCH_TO_KERNEL_CR3 reg
movq %cr3, \reg
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
-orq x86_cr3_pcid_noflush, \reg
+/* If PCID enabled, set X86_CR3_PCID_NOFLUSH_BIT */
+ALTERNATIVE "", "bts $63, \reg", X86_FEATURE_PCID
movq \reg, %cr3
.endm
@@ -39,7 +40,7 @@ movq \reg, %cr3
movq %cr3, \reg
orq PER_CPU_VAR(x86_cr3_pcid_user), \reg
js 9f
-/* FLUSH this time, reset to NOFLUSH for next time (if PCID enabled) */
+/* If PCID enabled, FLUSH this time, reset to NOFLUSH for next time */
movb \regb, PER_CPU_VAR(x86_cr3_pcid_user+7)
9:
movq \reg, %cr3
@@ -90,7 +91,6 @@ movq PER_CPU_VAR(unsafe_stack_register_b
*/
DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
-extern unsigned long x86_cr3_pcid_noflush;
DECLARE_PER_CPU(unsigned long, x86_cr3_pcid_user);
extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -31,7 +31,6 @@ DEFINE_PER_CPU_USER_MAPPED(unsigned long
* This is also handy because systems that do not support PCIDs
* just end up or'ing a 0 into their CR3, which does no harm.
*/
-unsigned long x86_cr3_pcid_noflush __read_mostly;
DEFINE_PER_CPU(unsigned long, x86_cr3_pcid_user);
/*
@@ -356,10 +355,6 @@ void __init kaiser_init(void)
kaiser_add_user_map_early(&debug_idt_table,
sizeof(gate_desc) * NR_VECTORS,
__PAGE_KERNEL);
-
- kaiser_add_user_map_early(&x86_cr3_pcid_noflush,
- sizeof(x86_cr3_pcid_noflush),
- __PAGE_KERNEL);
}
/* Add a mapping to the shadow mapping, and synchronize the mappings */
@@ -433,18 +428,14 @@ pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp,
void kaiser_setup_pcid(void)
{
- unsigned long kern_cr3 = 0;
unsigned long user_cr3 = KAISER_SHADOW_PGD_OFFSET;
- if (this_cpu_has(X86_FEATURE_PCID)) {
- kern_cr3 |= X86_CR3_PCID_KERN_NOFLUSH;
+ if (this_cpu_has(X86_FEATURE_PCID))
user_cr3 |= X86_CR3_PCID_USER_NOFLUSH;
- }
/*
* These variables are used by the entry/exit
* code to change PCID and pgd and TLB flushing.
*/
- x86_cr3_pcid_noflush = kern_cr3;
this_cpu_write(x86_cr3_pcid_user, user_cr3);
}
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: tidied up kaiser_add/remove_mapping slightly" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: tidied up kaiser_add/remove_mapping slightly
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 3 Sep 2017 19:23:08 -0700
Subject: kaiser: tidied up kaiser_add/remove_mapping slightly
From: Hugh Dickins <hughd(a)google.com>
Yes, unmap_pud_range_nofree()'s declaration ought to be in a
header file really, but I'm not sure we want to use it anyway:
so for now just declare it inside kaiser_remove_mapping().
And there doesn't seem to be such a thing as unmap_p4d_range(),
even in a 5-level paging tree.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/kaiser.c | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -285,8 +285,7 @@ void __init kaiser_init(void)
__PAGE_KERNEL);
}
-extern void unmap_pud_range_nofree(pgd_t *pgd, unsigned long start, unsigned long end);
-// add a mapping to the shadow-mapping, and synchronize the mappings
+/* Add a mapping to the shadow mapping, and synchronize the mappings */
int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags)
{
return kaiser_add_user_map((const void *)addr, size, flags);
@@ -294,15 +293,13 @@ int kaiser_add_mapping(unsigned long add
void kaiser_remove_mapping(unsigned long start, unsigned long size)
{
+ extern void unmap_pud_range_nofree(pgd_t *pgd,
+ unsigned long start, unsigned long end);
unsigned long end = start + size;
unsigned long addr;
for (addr = start; addr < end; addr += PGDIR_SIZE) {
pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(addr));
- /*
- * unmap_p4d_range() handles > P4D_SIZE unmaps,
- * so no need to trim 'end'.
- */
unmap_pud_range_nofree(pgd, addr, end);
}
}
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: tidied up asm/kaiser.h somewhat" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: tidied up asm/kaiser.h somewhat
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-tidied-up-asm-kaiser.h-somewhat.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 3 Sep 2017 19:18:07 -0700
Subject: kaiser: tidied up asm/kaiser.h somewhat
From: Hugh Dickins <hughd(a)google.com>
Mainly deleting a surfeit of blank lines, and reflowing header comment.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/kaiser.h | 32 +++++++++++++-------------------
1 file changed, 13 insertions(+), 19 deletions(-)
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -1,15 +1,17 @@
#ifndef _ASM_X86_KAISER_H
#define _ASM_X86_KAISER_H
-
-/* This file includes the definitions for the KAISER feature.
- * KAISER is a counter measure against x86_64 side channel attacks on the kernel virtual memory.
- * It has a shodow-pgd for every process. the shadow-pgd has a minimalistic kernel-set mapped,
- * but includes the whole user memory. Within a kernel context switch, or when an interrupt is handled,
- * the pgd is switched to the normal one. When the system switches to user mode, the shadow pgd is enabled.
- * By this, the virtual memory chaches are freed, and the user may not attack the whole kernel memory.
+/*
+ * This file includes the definitions for the KAISER feature.
+ * KAISER is a counter measure against x86_64 side channel attacks on
+ * the kernel virtual memory. It has a shadow pgd for every process: the
+ * shadow pgd has a minimalistic kernel-set mapped, but includes the whole
+ * user memory. Within a kernel context switch, or when an interrupt is handled,
+ * the pgd is switched to the normal one. When the system switches to user mode,
+ * the shadow pgd is enabled. By this, the virtual memory caches are freed,
+ * and the user may not attack the whole kernel memory.
*
- * A minimalistic kernel mapping holds the parts needed to be mapped in user mode, as the entry/exit functions
- * of the user space, or the stacks.
+ * A minimalistic kernel mapping holds the parts needed to be mapped in user
+ * mode, such as the entry/exit functions of the user space, or the stacks.
*/
#ifdef __ASSEMBLY__
#ifdef CONFIG_KAISER
@@ -48,13 +50,10 @@ _SWITCH_TO_KERNEL_CR3 %rax
movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
.endm
-
.macro SWITCH_USER_CR3_NO_STACK
-
movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)
_SWITCH_TO_USER_CR3 %rax
movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
-
.endm
#else /* CONFIG_KAISER */
@@ -72,7 +71,6 @@ movq PER_CPU_VAR(unsafe_stack_register_b
#else /* __ASSEMBLY__ */
-
#ifdef CONFIG_KAISER
/*
* Upon kernel/user mode switch, it may happen that the address
@@ -80,7 +78,6 @@ movq PER_CPU_VAR(unsafe_stack_register_b
* stored. To change the address space, another register is
* needed. A register therefore has to be stored/restored.
*/
-
DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
/**
@@ -95,7 +92,6 @@ DECLARE_PER_CPU_USER_MAPPED(unsigned lon
*/
extern int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags);
-
/**
* kaiser_remove_mapping - unmap a virtual memory part of the shadow mapping
* @addr: the start address of the range
@@ -104,12 +100,12 @@ extern int kaiser_add_mapping(unsigned l
extern void kaiser_remove_mapping(unsigned long start, unsigned long size);
/**
- * kaiser_initialize_mapping - Initalize the shadow mapping
+ * kaiser_init - Initialize the shadow mapping
*
* Most parts of the shadow mapping can be mapped upon boot
* time. Only per-process things like the thread stacks
* or a new LDT have to be mapped at runtime. These boot-
- * time mappings are permanent and nevertunmapped.
+ * time mappings are permanent and never unmapped.
*/
extern void kaiser_init(void);
@@ -117,6 +113,4 @@ extern void kaiser_init(void);
#endif /* __ASSEMBLY */
-
-
#endif /* _ASM_X86_KAISER_H */
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-stack-map-page_size-at-thread_size-page_size.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 3 Sep 2017 18:57:03 -0700
Subject: kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE
From: Hugh Dickins <hughd(a)google.com>
Kaiser only needs to map one page of the stack; and
kernel/fork.c did not build on powerpc (no __PAGE_KERNEL).
It's all cleaner if linux/kaiser.h provides kaiser_map_thread_stack()
and kaiser_unmap_thread_stack() wrappers around asm/kaiser.h's
kaiser_add_mapping() and kaiser_remove_mapping(). And use
linux/kaiser.h in init/main.c to avoid the #ifdefs there.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
include/linux/kaiser.h | 40 +++++++++++++++++++++++++++++++++-------
init/main.c | 6 +-----
kernel/fork.c | 7 ++-----
3 files changed, 36 insertions(+), 17 deletions(-)
--- a/include/linux/kaiser.h
+++ b/include/linux/kaiser.h
@@ -1,26 +1,52 @@
-#ifndef _INCLUDE_KAISER_H
-#define _INCLUDE_KAISER_H
+#ifndef _LINUX_KAISER_H
+#define _LINUX_KAISER_H
#ifdef CONFIG_KAISER
#include <asm/kaiser.h>
+
+static inline int kaiser_map_thread_stack(void *stack)
+{
+ /*
+ * Map that page of kernel stack on which we enter from user context.
+ */
+ return kaiser_add_mapping((unsigned long)stack +
+ THREAD_SIZE - PAGE_SIZE, PAGE_SIZE, __PAGE_KERNEL);
+}
+
+static inline void kaiser_unmap_thread_stack(void *stack)
+{
+ /*
+ * Note: may be called even when kaiser_map_thread_stack() failed.
+ */
+ kaiser_remove_mapping((unsigned long)stack +
+ THREAD_SIZE - PAGE_SIZE, PAGE_SIZE);
+}
#else
/*
* These stubs are used whenever CONFIG_KAISER is off, which
- * includes architectures that support KAISER, but have it
- * disabled.
+ * includes architectures that support KAISER, but have it disabled.
*/
static inline void kaiser_init(void)
{
}
-static inline void kaiser_remove_mapping(unsigned long start, unsigned long size)
+static inline int kaiser_add_mapping(unsigned long addr,
+ unsigned long size, unsigned long flags)
+{
+ return 0;
+}
+static inline void kaiser_remove_mapping(unsigned long start,
+ unsigned long size)
{
}
-static inline int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags)
+static inline int kaiser_map_thread_stack(void *stack)
{
return 0;
}
+static inline void kaiser_unmap_thread_stack(void *stack)
+{
+}
#endif /* !CONFIG_KAISER */
-#endif /* _INCLUDE_KAISER_H */
+#endif /* _LINUX_KAISER_H */
--- a/init/main.c
+++ b/init/main.c
@@ -80,15 +80,13 @@
#include <linux/integrity.h>
#include <linux/proc_ns.h>
#include <linux/io.h>
+#include <linux/kaiser.h>
#include <asm/io.h>
#include <asm/bugs.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>
-#ifdef CONFIG_KAISER
-#include <asm/kaiser.h>
-#endif
static int kernel_init(void *);
@@ -476,9 +474,7 @@ static void __init mm_init(void)
pgtable_init();
vmalloc_init();
ioremap_huge_init();
-#ifdef CONFIG_KAISER
kaiser_init();
-#endif
}
asmlinkage __visible void __init start_kernel(void)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -212,12 +212,9 @@ static unsigned long *alloc_thread_stack
#endif
}
-extern void kaiser_remove_mapping(unsigned long start_addr, unsigned long size);
static inline void free_thread_stack(struct task_struct *tsk)
{
-#ifdef CONFIG_KAISER
- kaiser_remove_mapping((unsigned long)tsk->stack, THREAD_SIZE);
-#endif
+ kaiser_unmap_thread_stack(tsk->stack);
#ifdef CONFIG_VMAP_STACK
if (task_stack_vm_area(tsk)) {
unsigned long flags;
@@ -501,7 +498,7 @@ static struct task_struct *dup_task_stru
*/
tsk->stack = stack;
- err= kaiser_add_mapping((unsigned long)tsk->stack, THREAD_SIZE, __PAGE_KERNEL);
+ err= kaiser_map_thread_stack(tsk->stack);
if (err)
goto free_stack;
#ifdef CONFIG_VMAP_STACK
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: PCID 0 for kernel and 128 for user" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: PCID 0 for kernel and 128 for user
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-pcid-0-for-kernel-and-128-for-user.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Fri, 8 Sep 2017 19:26:30 -0700
Subject: kaiser: PCID 0 for kernel and 128 for user
From: Hugh Dickins <hughd(a)google.com>
Why was 4 chosen for kernel PCID and 6 for user PCID?
No good reason in a backport where PCIDs are only used for Kaiser.
If we continue with those, then we shall need to add Andy Lutomirski's
4.13 commit 6c690ee1039b ("x86/mm: Split read_cr3() into read_cr3_pa()
and __read_cr3()"), which deals with the problem of read_cr3() callers
finding stray bits in the cr3 that they expected to be page-aligned;
and for hibernation, his 4.14 commit f34902c5c6c0 ("x86/hibernate/64:
Mask off CR3's PCID bits in the saved CR3").
But if 0 is used for kernel PCID, then there's no need to add in those
commits - whenever the kernel looks, it sees 0 in the lower bits; and
0 for kernel seems an obvious choice.
And I naughtily propose 128 for user PCID. Because there's a place
in _SWITCH_TO_USER_CR3 where it takes note of the need for TLB FLUSH,
but needs to reset that to NOFLUSH for the next occasion. Currently
it does so with a "movb $(0x80)" into the high byte of the per-cpu
quadword, but that will cause a machine without PCID support to crash.
Now, if %al just happened to have 0x80 in it at that point, on a
machine with PCID support, but 0 on a machine without PCID support...
(That will go badly wrong once the pgd can be at a physical address
above 2^56, but even with 5-level paging, physical goes up to 2^52.)
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/kaiser.h | 19 ++++++++++++-------
arch/x86/include/asm/pgtable_types.h | 7 ++++---
arch/x86/mm/tlb.c | 3 +++
3 files changed, 19 insertions(+), 10 deletions(-)
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -29,14 +29,19 @@ orq X86_CR3_PCID_KERN_VAR, \reg
movq \reg, %cr3
.endm
-.macro _SWITCH_TO_USER_CR3 reg
+.macro _SWITCH_TO_USER_CR3 reg regb
+/*
+ * regb must be the low byte portion of reg: because we have arranged
+ * for the low byte of the user PCID to serve as the high byte of NOFLUSH
+ * (0x80 for each when PCID is enabled, or 0x00 when PCID and NOFLUSH are
+ * not enabled): so that the one register can update both memory and cr3.
+ */
movq %cr3, \reg
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
orq PER_CPU_VAR(X86_CR3_PCID_USER_VAR), \reg
js 9f
-// FLUSH this time, reset to NOFLUSH for next time
-// But if nopcid? Consider using 0x80 for user pcid?
-movb $(0x80), PER_CPU_VAR(X86_CR3_PCID_USER_VAR+7)
+/* FLUSH this time, reset to NOFLUSH for next time (if PCID enabled) */
+movb \regb, PER_CPU_VAR(X86_CR3_PCID_USER_VAR+7)
9:
movq \reg, %cr3
.endm
@@ -49,7 +54,7 @@ popq %rax
.macro SWITCH_USER_CR3
pushq %rax
-_SWITCH_TO_USER_CR3 %rax
+_SWITCH_TO_USER_CR3 %rax %al
popq %rax
.endm
@@ -61,7 +66,7 @@ movq PER_CPU_VAR(unsafe_stack_register_b
.macro SWITCH_USER_CR3_NO_STACK
movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)
-_SWITCH_TO_USER_CR3 %rax
+_SWITCH_TO_USER_CR3 %rax %al
movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
.endm
@@ -69,7 +74,7 @@ movq PER_CPU_VAR(unsafe_stack_register_b
.macro SWITCH_KERNEL_CR3 reg
.endm
-.macro SWITCH_USER_CR3 reg
+.macro SWITCH_USER_CR3 reg regb
.endm
.macro SWITCH_USER_CR3_NO_STACK
.endm
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -146,16 +146,17 @@
/* Mask for all the PCID-related bits in CR3: */
#define X86_CR3_PCID_MASK (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_MASK)
+#define X86_CR3_PCID_ASID_KERN (_AC(0x0,UL))
+
#if defined(CONFIG_KAISER) && defined(CONFIG_X86_64)
-#define X86_CR3_PCID_ASID_KERN (_AC(0x4,UL))
-#define X86_CR3_PCID_ASID_USER (_AC(0x6,UL))
+/* Let X86_CR3_PCID_ASID_USER be usable for the X86_CR3_PCID_NOFLUSH bit */
+#define X86_CR3_PCID_ASID_USER (_AC(0x80,UL))
#define X86_CR3_PCID_KERN_FLUSH (X86_CR3_PCID_ASID_KERN)
#define X86_CR3_PCID_USER_FLUSH (X86_CR3_PCID_ASID_USER)
#define X86_CR3_PCID_KERN_NOFLUSH (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_KERN)
#define X86_CR3_PCID_USER_NOFLUSH (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_USER)
#else
-#define X86_CR3_PCID_ASID_KERN (_AC(0x0,UL))
#define X86_CR3_PCID_ASID_USER (_AC(0x0,UL))
/*
* PCIDs are unsupported on 32-bit and none of these bits can be
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -50,6 +50,9 @@ static void load_new_mm_cr3(pgd_t *pgdir
* invpcid_flush_single_context(X86_CR3_PCID_ASID_USER) could
* do it here, but can only be used if X86_FEATURE_INVPCID is
* available - and many machines support pcid without invpcid.
+ *
+ * The line below is a no-op: X86_CR3_PCID_KERN_FLUSH is now 0;
+ * but keep that line in there in case something changes.
*/
new_mm_cr3 |= X86_CR3_PCID_KERN_FLUSH;
kaiser_flush_tlb_on_return_to_user();
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: paranoid_entry pass cr3 need to paranoid_exit" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: paranoid_entry pass cr3 need to paranoid_exit
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Tue, 26 Sep 2017 18:43:07 -0700
Subject: kaiser: paranoid_entry pass cr3 need to paranoid_exit
From: Hugh Dickins <hughd(a)google.com>
Neel Natu points out that paranoid_entry() was wrong to assume that
an entry that did not need swapgs would not need SWITCH_KERNEL_CR3:
paranoid_entry (used for debug breakpoint, int3, double fault or MCE;
though I think it's only the MCE case that is cause for concern here)
can break in at an awkward time, between cr3 switch and swapgs, but
its handling always needs kernel gs and kernel cr3.
Easy to fix in itself, but paranoid_entry() also needs to convey to
paranoid_exit() (and my reading of macro idtentry says paranoid_entry
and paranoid_exit are always paired) how to restore the prior state.
The swapgs state is already conveyed by %ebx (0 or 1), so extend that
also to convey when SWITCH_USER_CR3 will be needed (2 or 3).
(Yes, I'd much prefer that 0 meant no swapgs, whereas it's the other
way round: and a convention shared with error_entry() and error_exit(),
which I don't want to touch. Perhaps I should have inverted the bit
for switch cr3 too, but did not.)
paranoid_exit() would be straightforward, except for TRACE_IRQS: it
did TRACE_IRQS_IRETQ when doing swapgs, but TRACE_IRQS_IRETQ_DEBUG
when not: which is it supposed to use when SWITCH_USER_CR3 is split
apart from that? As best as I can determine, commit 5963e317b1e9
("ftrace/x86: Do not change stacks in DEBUG when calling lockdep")
missed the swapgs case, and should have used TRACE_IRQS_IRETQ_DEBUG
there too (the discrepancy has nothing to do with the liberal use
of _NO_STACK and _UNSAFE_STACK hereabouts: TRACE_IRQS_OFF_DEBUG has
just been used in all cases); discrepancy lovingly preserved across
several paranoid_exit() cleanups, but I'm now removing it.
Neel further indicates that to use SWITCH_USER_CR3_NO_STACK there in
paranoid_exit() is now not only unnecessary but unsafe: might corrupt
syscall entry's unsafe_stack_register_backup of %rax. Just use
SWITCH_USER_CR3: and delete SWITCH_USER_CR3_NO_STACK altogether,
before we make the mistake of using it again.
hughd adds: this commit fixes an issue in the Kaiser-without-PCIDs
part of the series, and ought to be moved earlier, if you decided
to make a release of Kaiser-without-PCIDs.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 46 ++++++++++++++++++++++++++++++---------
arch/x86/entry/entry_64_compat.S | 2 -
arch/x86/include/asm/kaiser.h | 8 ------
3 files changed, 37 insertions(+), 19 deletions(-)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1053,7 +1053,11 @@ idtentry machine_check has_error_cod
/*
* Save all registers in pt_regs, and switch gs if needed.
* Use slow, but surefire "are we in kernel?" check.
- * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
+ *
+ * Return: ebx=0: needs swapgs but not SWITCH_USER_CR3 in paranoid_exit
+ * ebx=1: needs neither swapgs nor SWITCH_USER_CR3 in paranoid_exit
+ * ebx=2: needs both swapgs and SWITCH_USER_CR3 in paranoid_exit
+ * ebx=3: needs SWITCH_USER_CR3 but not swapgs in paranoid_exit
*/
ENTRY(paranoid_entry)
cld
@@ -1065,9 +1069,26 @@ ENTRY(paranoid_entry)
testl %edx, %edx
js 1f /* negative -> in kernel */
SWAPGS
- SWITCH_KERNEL_CR3
xorl %ebx, %ebx
-1: ret
+1:
+#ifdef CONFIG_KAISER
+ /*
+ * We might have come in between a swapgs and a SWITCH_KERNEL_CR3
+ * on entry, or between a SWITCH_USER_CR3 and a swapgs on exit.
+ * Do a conditional SWITCH_KERNEL_CR3: this could safely be done
+ * unconditionally, but we need to find out whether the reverse
+ * should be done on return (conveyed to paranoid_exit in %ebx).
+ */
+ movq %cr3, %rax
+ testl $KAISER_SHADOW_PGD_OFFSET, %eax
+ jz 2f
+ orl $2, %ebx
+ andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
+ orq x86_cr3_pcid_noflush, %rax
+ movq %rax, %cr3
+2:
+#endif
+ ret
END(paranoid_entry)
/*
@@ -1080,20 +1101,25 @@ END(paranoid_entry)
* be complicated. Fortunately, we there's no good reason
* to try to handle preemption here.
*
- * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
+ * On entry: ebx=0: needs swapgs but not SWITCH_USER_CR3
+ * ebx=1: needs neither swapgs nor SWITCH_USER_CR3
+ * ebx=2: needs both swapgs and SWITCH_USER_CR3
+ * ebx=3: needs SWITCH_USER_CR3 but not swapgs
*/
ENTRY(paranoid_exit)
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF_DEBUG
- testl %ebx, %ebx /* swapgs needed? */
+ TRACE_IRQS_IRETQ_DEBUG
+#ifdef CONFIG_KAISER
+ testl $2, %ebx /* SWITCH_USER_CR3 needed? */
+ jz paranoid_exit_no_switch
+ SWITCH_USER_CR3
+paranoid_exit_no_switch:
+#endif
+ testl $1, %ebx /* swapgs needed? */
jnz paranoid_exit_no_swapgs
- TRACE_IRQS_IRETQ
- SWITCH_USER_CR3_NO_STACK
SWAPGS_UNSAFE_STACK
- jmp paranoid_exit_restore
paranoid_exit_no_swapgs:
- TRACE_IRQS_IRETQ_DEBUG
-paranoid_exit_restore:
RESTORE_EXTRA_REGS
RESTORE_C_REGS
REMOVE_PT_GPREGS_FROM_STACK 8
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -343,7 +343,7 @@ ENTRY(entry_INT80_compat)
/* Go back to user mode. */
TRACE_IRQS_ON
- SWITCH_USER_CR3_NO_STACK
+ SWITCH_USER_CR3
SWAPGS
jmp restore_regs_and_iret
END(entry_INT80_compat)
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -63,20 +63,12 @@ _SWITCH_TO_KERNEL_CR3 %rax
movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
.endm
-.macro SWITCH_USER_CR3_NO_STACK
-movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)
-_SWITCH_TO_USER_CR3 %rax %al
-movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
-.endm
-
#else /* CONFIG_KAISER */
.macro SWITCH_KERNEL_CR3 reg
.endm
.macro SWITCH_USER_CR3 reg regb
.endm
-.macro SWITCH_USER_CR3_NO_STACK
-.endm
.macro SWITCH_KERNEL_CR3_NO_STACK
.endm
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: name that 0x1000 KAISER_SHADOW_PGD_OFFSET" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: name that 0x1000 KAISER_SHADOW_PGD_OFFSET
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sat, 9 Sep 2017 17:31:18 -0700
Subject: kaiser: name that 0x1000 KAISER_SHADOW_PGD_OFFSET
From: Hugh Dickins <hughd(a)google.com>
There's a 0x1000 in various places, which looks better with a name.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 4 ++--
arch/x86/include/asm/kaiser.h | 7 +++++--
2 files changed, 7 insertions(+), 4 deletions(-)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1318,7 +1318,7 @@ ENTRY(nmi)
movq %cr3, %rax
pushq %rax
#ifdef CONFIG_KAISER_REAL_SWITCH
- andq $(~0x1000), %rax
+ andq $(~KAISER_SHADOW_PGD_OFFSET), %rax
#endif
movq %rax, %cr3
#endif
@@ -1561,7 +1561,7 @@ end_repeat_nmi:
movq %cr3, %rax
pushq %rax
#ifdef CONFIG_KAISER_REAL_SWITCH
- andq $(~0x1000), %rax
+ andq $(~KAISER_SHADOW_PGD_OFFSET), %rax
#endif
movq %rax, %cr3
#endif
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -13,13 +13,16 @@
* A minimalistic kernel mapping holds the parts needed to be mapped in user
* mode, such as the entry/exit functions of the user space, or the stacks.
*/
+
+#define KAISER_SHADOW_PGD_OFFSET 0x1000
+
#ifdef __ASSEMBLY__
#ifdef CONFIG_KAISER
.macro _SWITCH_TO_KERNEL_CR3 reg
movq %cr3, \reg
#ifdef CONFIG_KAISER_REAL_SWITCH
-andq $(~0x1000), \reg
+andq $(~KAISER_SHADOW_PGD_OFFSET), \reg
#endif
movq \reg, %cr3
.endm
@@ -27,7 +30,7 @@ movq \reg, %cr3
.macro _SWITCH_TO_USER_CR3 reg
movq %cr3, \reg
#ifdef CONFIG_KAISER_REAL_SWITCH
-orq $(0x1000), \reg
+orq $(KAISER_SHADOW_PGD_OFFSET), \reg
#endif
movq \reg, %cr3
.endm
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: load_new_mm_cr3() let SWITCH_USER_CR3 flush user" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: load_new_mm_cr3() let SWITCH_USER_CR3 flush user
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Thu, 17 Aug 2017 15:00:37 -0700
Subject: kaiser: load_new_mm_cr3() let SWITCH_USER_CR3 flush user
From: Hugh Dickins <hughd(a)google.com>
We have many machines (Westmere, Sandybridge, Ivybridge) supporting
PCID but not INVPCID: on these load_new_mm_cr3() simply crashed.
Flushing user context inside load_new_mm_cr3() without the use of
invpcid is difficult: momentarily switch from kernel to user context
and back to do so? I'm not sure whether that can be safely done at
all, and would risk polluting user context with kernel internals,
and kernel context with stale user externals.
Instead, follow the hint in the comment that was there: change
X86_CR3_PCID_USER_VAR to be a per-cpu variable, then load_new_mm_cr3()
can leave a note in it, for SWITCH_USER_CR3 on return to userspace to
flush user context TLB, instead of default X86_CR3_PCID_USER_NOFLUSH.
Which works well enough that there's no need to do it this way only
when invpcid is unsupported: it's a good alternative to invpcid here.
But there's a couple of inlines in asm/tlbflush.h that need to do the
same trick, so it's best to localize all this per-cpu business in
mm/kaiser.c: moving that part of the initialization from setup_pcid()
to kaiser_setup_pcid(); with kaiser_flush_tlb_on_return_to_user() the
function for noting an X86_CR3_PCID_USER_FLUSH. And let's keep a
KAISER_SHADOW_PGD_OFFSET in there, to avoid the extra OR on exit.
I did try to make the feature tests in asm/tlbflush.h more consistent
with each other: there seem to be far too many ways of performing such
tests, and I don't have a good grasp of their differences. At first
I converted them all to be static_cpu_has(): but that proved to be a
mistake, as the comment in __native_flush_tlb_single() hints; so then
I reversed and made them all this_cpu_has(). Probably all gratuitous
change, but that's the way it's working at present.
I am slightly bothered by the way non-per-cpu X86_CR3_PCID_KERN_VAR
gets re-initialized by each cpu (before and after these changes):
no problem when (as usual) all cpus on a machine have the same
features, but in principle incorrect. However, my experiment
to per-cpu-ify that one did not end well...
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/kaiser.h | 18 +++++++-----
arch/x86/include/asm/tlbflush.h | 56 +++++++++++++++++++++++++++-------------
arch/x86/kernel/cpu/common.c | 22 ---------------
arch/x86/mm/kaiser.c | 50 +++++++++++++++++++++++++++++++----
arch/x86/mm/tlb.c | 46 ++++++++++++--------------------
5 files changed, 113 insertions(+), 79 deletions(-)
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -32,13 +32,12 @@ movq \reg, %cr3
.macro _SWITCH_TO_USER_CR3 reg
movq %cr3, \reg
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
-/*
- * This can obviously be one instruction by putting the
- * KAISER_SHADOW_PGD_OFFSET bit in the X86_CR3_PCID_USER_VAR.
- * But, just leave it now for simplicity.
- */
-orq X86_CR3_PCID_USER_VAR, \reg
-orq $(KAISER_SHADOW_PGD_OFFSET), \reg
+orq PER_CPU_VAR(X86_CR3_PCID_USER_VAR), \reg
+js 9f
+// FLUSH this time, reset to NOFLUSH for next time
+// But if nopcid? Consider using 0x80 for user pcid?
+movb $(0x80), PER_CPU_VAR(X86_CR3_PCID_USER_VAR+7)
+9:
movq \reg, %cr3
.endm
@@ -90,6 +89,11 @@ movq PER_CPU_VAR(unsafe_stack_register_b
*/
DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
+extern unsigned long X86_CR3_PCID_KERN_VAR;
+DECLARE_PER_CPU(unsigned long, X86_CR3_PCID_USER_VAR);
+
+extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
+
/**
* kaiser_add_mapping - map a virtual memory part to the shadow (user) mapping
* @addr: the start address of the range
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -13,6 +13,7 @@ static inline void __invpcid(unsigned lo
unsigned long type)
{
struct { u64 d[2]; } desc = { { pcid, addr } };
+
/*
* The memory clobber is because the whole point is to invalidate
* stale TLB entries and, especially if we're flushing global
@@ -131,27 +132,42 @@ static inline void cr4_set_bits_and_upda
cr4_set_bits(mask);
}
+/*
+ * Declare a couple of kaiser interfaces here for convenience,
+ * to avoid the need for asm/kaiser.h in unexpected places.
+ */
+#ifdef CONFIG_KAISER
+extern void kaiser_setup_pcid(void);
+extern void kaiser_flush_tlb_on_return_to_user(void);
+#else
+static inline void kaiser_setup_pcid(void)
+{
+}
+static inline void kaiser_flush_tlb_on_return_to_user(void)
+{
+}
+#endif
+
static inline void __native_flush_tlb(void)
{
- if (!cpu_feature_enabled(X86_FEATURE_INVPCID)) {
+ if (this_cpu_has(X86_FEATURE_INVPCID)) {
/*
- * If current->mm == NULL then we borrow a mm which may change during a
- * task switch and therefore we must not be preempted while we write CR3
- * back:
+ * Note, this works with CR4.PCIDE=0 or 1.
*/
- preempt_disable();
- native_write_cr3(native_read_cr3());
- preempt_enable();
+ invpcid_flush_all_nonglobals();
return;
}
+
/*
- * We are no longer using globals with KAISER, so a
- * "nonglobals" flush would work too. But, this is more
- * conservative.
- *
- * Note, this works with CR4.PCIDE=0 or 1.
+ * If current->mm == NULL then we borrow a mm which may change during a
+ * task switch and therefore we must not be preempted while we write CR3
+ * back:
*/
- invpcid_flush_all();
+ preempt_disable();
+ if (this_cpu_has(X86_FEATURE_PCID))
+ kaiser_flush_tlb_on_return_to_user();
+ native_write_cr3(native_read_cr3());
+ preempt_enable();
}
static inline void __native_flush_tlb_global_irq_disabled(void)
@@ -167,9 +183,13 @@ static inline void __native_flush_tlb_gl
static inline void __native_flush_tlb_global(void)
{
+#ifdef CONFIG_KAISER
+ /* Globals are not used at all */
+ __native_flush_tlb();
+#else
unsigned long flags;
- if (static_cpu_has(X86_FEATURE_INVPCID)) {
+ if (this_cpu_has(X86_FEATURE_INVPCID)) {
/*
* Using INVPCID is considerably faster than a pair of writes
* to CR4 sandwiched inside an IRQ flag save/restore.
@@ -186,10 +206,9 @@ static inline void __native_flush_tlb_gl
* be called from deep inside debugging code.)
*/
raw_local_irq_save(flags);
-
__native_flush_tlb_global_irq_disabled();
-
raw_local_irq_restore(flags);
+#endif
}
static inline void __native_flush_tlb_single(unsigned long addr)
@@ -200,9 +219,12 @@ static inline void __native_flush_tlb_si
*
* The ASIDs used below are hard-coded. But, we must not
* call invpcid(type=1/2) before CR4.PCIDE=1. Just call
- * invpcid in the case we are called early.
+ * invlpg in the case we are called early.
*/
+
if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) {
+ if (this_cpu_has(X86_FEATURE_PCID))
+ kaiser_flush_tlb_on_return_to_user();
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
return;
}
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -324,33 +324,12 @@ static __always_inline void setup_smap(s
}
}
-/*
- * These can have bit 63 set, so we can not just use a plain "or"
- * instruction to get their value or'd into CR3. It would take
- * another register. So, we use a memory reference to these
- * instead.
- *
- * This is also handy because systems that do not support
- * PCIDs just end up or'ing a 0 into their CR3, which does
- * no harm.
- */
-__aligned(PAGE_SIZE) unsigned long X86_CR3_PCID_KERN_VAR = 0;
-__aligned(PAGE_SIZE) unsigned long X86_CR3_PCID_USER_VAR = 0;
-
static void setup_pcid(struct cpuinfo_x86 *c)
{
if (cpu_has(c, X86_FEATURE_PCID)) {
if (cpu_has(c, X86_FEATURE_PGE)) {
cr4_set_bits(X86_CR4_PCIDE);
/*
- * These variables are used by the entry/exit
- * code to change PCIDs.
- */
-#ifdef CONFIG_KAISER
- X86_CR3_PCID_KERN_VAR = X86_CR3_PCID_KERN_NOFLUSH;
- X86_CR3_PCID_USER_VAR = X86_CR3_PCID_USER_NOFLUSH;
-#endif
- /*
* INVPCID has two "groups" of types:
* 1/2: Invalidate an individual address
* 3/4: Invalidate all contexts
@@ -375,6 +354,7 @@ static void setup_pcid(struct cpuinfo_x8
clear_cpu_cap(c, X86_FEATURE_PCID);
}
}
+ kaiser_setup_pcid();
}
/*
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -11,12 +11,26 @@
#include <linux/uaccess.h>
#include <asm/kaiser.h>
+#include <asm/tlbflush.h> /* to verify its kaiser declarations */
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/desc.h>
+
#ifdef CONFIG_KAISER
+__visible
+DEFINE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
+
+/*
+ * These can have bit 63 set, so we can not just use a plain "or"
+ * instruction to get their value or'd into CR3. It would take
+ * another register. So, we use a memory reference to these instead.
+ *
+ * This is also handy because systems that do not support PCIDs
+ * just end up or'ing a 0 into their CR3, which does no harm.
+ */
+__aligned(PAGE_SIZE) unsigned long X86_CR3_PCID_KERN_VAR;
+DEFINE_PER_CPU(unsigned long, X86_CR3_PCID_USER_VAR);
-__visible DEFINE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
/*
* At runtime, the only things we map are some things for CPU
* hotplug, and stacks for new processes. No two CPUs will ever
@@ -238,9 +252,6 @@ static void __init kaiser_init_all_pgds(
WARN_ON(__ret); \
} while (0)
-extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
-extern unsigned long X86_CR3_PCID_KERN_VAR;
-extern unsigned long X86_CR3_PCID_USER_VAR;
/*
* If anything in here fails, we will likely die on one of the
* first kernel->user transitions and init will die. But, we
@@ -294,8 +305,6 @@ void __init kaiser_init(void)
kaiser_add_user_map_early(&X86_CR3_PCID_KERN_VAR, PAGE_SIZE,
__PAGE_KERNEL);
- kaiser_add_user_map_early(&X86_CR3_PCID_USER_VAR, PAGE_SIZE,
- __PAGE_KERNEL);
}
/* Add a mapping to the shadow mapping, and synchronize the mappings */
@@ -358,4 +367,33 @@ pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp,
}
return pgd;
}
+
+void kaiser_setup_pcid(void)
+{
+ unsigned long kern_cr3 = 0;
+ unsigned long user_cr3 = KAISER_SHADOW_PGD_OFFSET;
+
+ if (this_cpu_has(X86_FEATURE_PCID)) {
+ kern_cr3 |= X86_CR3_PCID_KERN_NOFLUSH;
+ user_cr3 |= X86_CR3_PCID_USER_NOFLUSH;
+ }
+ /*
+ * These variables are used by the entry/exit
+ * code to change PCID and pgd and TLB flushing.
+ */
+ X86_CR3_PCID_KERN_VAR = kern_cr3;
+ this_cpu_write(X86_CR3_PCID_USER_VAR, user_cr3);
+}
+
+/*
+ * Make a note that this cpu will need to flush USER tlb on return to user.
+ * Caller checks whether this_cpu_has(X86_FEATURE_PCID) before calling:
+ * if cpu does not, then the NOFLUSH bit will never have been set.
+ */
+void kaiser_flush_tlb_on_return_to_user(void)
+{
+ this_cpu_write(X86_CR3_PCID_USER_VAR,
+ X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET);
+}
+EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user);
#endif /* CONFIG_KAISER */
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -6,13 +6,14 @@
#include <linux/interrupt.h>
#include <linux/export.h>
#include <linux/cpu.h>
+#include <linux/debugfs.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/cache.h>
#include <asm/apic.h>
#include <asm/uv/uv.h>
-#include <linux/debugfs.h>
+#include <asm/kaiser.h>
/*
* TLB flushing, formerly SMP-only
@@ -38,34 +39,23 @@ static void load_new_mm_cr3(pgd_t *pgdir
{
unsigned long new_mm_cr3 = __pa(pgdir);
- /*
- * KAISER, plus PCIDs needs some extra work here. But,
- * if either of features is not present, we need no
- * PCIDs here and just do a normal, full TLB flush with
- * the write_cr3()
- */
- if (!IS_ENABLED(CONFIG_KAISER) ||
- !cpu_feature_enabled(X86_FEATURE_PCID))
- goto out_set_cr3;
- /*
- * We reuse the same PCID for different tasks, so we must
- * flush all the entires for the PCID out when we change
- * tasks.
- */
- new_mm_cr3 = X86_CR3_PCID_KERN_FLUSH | __pa(pgdir);
-
- /*
- * The flush from load_cr3() may leave old TLB entries
- * for userspace in place. We must flush that context
- * separately. We can theoretically delay doing this
- * until we actually load up the userspace CR3, but
- * that's a bit tricky. We have to have the "need to
- * flush userspace PCID" bit per-cpu and check it in the
- * exit-to-userspace paths.
- */
- invpcid_flush_single_context(X86_CR3_PCID_ASID_USER);
+#ifdef CONFIG_KAISER
+ if (this_cpu_has(X86_FEATURE_PCID)) {
+ /*
+ * We reuse the same PCID for different tasks, so we must
+ * flush all the entries for the PCID out when we change tasks.
+ * Flush KERN below, flush USER when returning to userspace in
+ * kaiser's SWITCH_USER_CR3 (_SWITCH_TO_USER_CR3) macro.
+ *
+ * invpcid_flush_single_context(X86_CR3_PCID_ASID_USER) could
+ * do it here, but can only be used if X86_FEATURE_INVPCID is
+ * available - and many machines support pcid without invpcid.
+ */
+ new_mm_cr3 |= X86_CR3_PCID_KERN_FLUSH;
+ kaiser_flush_tlb_on_return_to_user();
+ }
+#endif /* CONFIG_KAISER */
-out_set_cr3:
/*
* Caution: many callers of this function expect
* that load_cr3() is serializing and orders TLB
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: kaiser_flush_tlb_on_return_to_user() check PCID" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: kaiser_flush_tlb_on_return_to_user() check PCID
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sat, 4 Nov 2017 18:43:06 -0700
Subject: kaiser: kaiser_flush_tlb_on_return_to_user() check PCID
From: Hugh Dickins <hughd(a)google.com>
Let kaiser_flush_tlb_on_return_to_user() do the X86_FEATURE_PCID
check, instead of each caller doing it inline first: nobody needs
to optimize for the noPCID case, it's clearer this way, and better
suits later changes. Replace those no-op X86_CR3_PCID_KERN_FLUSH lines
by a BUILD_BUG_ON() in load_new_mm_cr3(), in case something changes.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/tlbflush.h | 4 ++--
arch/x86/mm/kaiser.c | 6 +++---
arch/x86/mm/tlb.c | 8 ++++----
3 files changed, 9 insertions(+), 9 deletions(-)
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -158,7 +158,7 @@ static inline void __native_flush_tlb(vo
* back:
*/
preempt_disable();
- if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID))
+ if (kaiser_enabled)
kaiser_flush_tlb_on_return_to_user();
native_write_cr3(native_read_cr3());
preempt_enable();
@@ -217,7 +217,7 @@ static inline void __native_flush_tlb_si
*/
if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) {
- if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID))
+ if (kaiser_enabled)
kaiser_flush_tlb_on_return_to_user();
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
return;
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -435,12 +435,12 @@ void kaiser_setup_pcid(void)
/*
* Make a note that this cpu will need to flush USER tlb on return to user.
- * Caller checks whether this_cpu_has(X86_FEATURE_PCID) before calling:
- * if cpu does not, then the NOFLUSH bit will never have been set.
+ * If cpu does not have PCID, then the NOFLUSH bit will never have been set.
*/
void kaiser_flush_tlb_on_return_to_user(void)
{
- this_cpu_write(x86_cr3_pcid_user,
+ if (this_cpu_has(X86_FEATURE_PCID))
+ this_cpu_write(x86_cr3_pcid_user,
X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET);
}
EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user);
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -39,7 +39,7 @@ static void load_new_mm_cr3(pgd_t *pgdir
{
unsigned long new_mm_cr3 = __pa(pgdir);
- if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID)) {
+ if (kaiser_enabled) {
/*
* We reuse the same PCID for different tasks, so we must
* flush all the entries for the PCID out when we change tasks.
@@ -50,10 +50,10 @@ static void load_new_mm_cr3(pgd_t *pgdir
* do it here, but can only be used if X86_FEATURE_INVPCID is
* available - and many machines support pcid without invpcid.
*
- * The line below is a no-op: X86_CR3_PCID_KERN_FLUSH is now 0;
- * but keep that line in there in case something changes.
+ * If X86_CR3_PCID_KERN_FLUSH actually added something, then it
+ * would be needed in the write_cr3() below - if PCIDs enabled.
*/
- new_mm_cr3 |= X86_CR3_PCID_KERN_FLUSH;
+ BUILD_BUG_ON(X86_CR3_PCID_KERN_FLUSH);
kaiser_flush_tlb_on_return_to_user();
}
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: kaiser_remove_mapping() move along the pgd" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: kaiser_remove_mapping() move along the pgd
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Mon, 2 Oct 2017 10:57:24 -0700
Subject: kaiser: kaiser_remove_mapping() move along the pgd
From: Hugh Dickins <hughd(a)google.com>
When removing the bogus comment from kaiser_remove_mapping(),
I really ought to have checked the extent of its bogosity: as
Neel points out, there is nothing to stop unmap_pud_range_nofree()
from continuing beyond the end of a pud (and starting in the wrong
position on the next).
Fix kaiser_remove_mapping() to constrain the extent and advance pgd
pointer correctly: use pgd_addr_end() macro as used throughout base
mm (but don't assume page-rounded start and size in this case).
But this bug was very unlikely to trigger in this backport: since
any buddy allocation is contained within a single pud extent, and
we are not using vmapped stacks (and are only mapping one page of
stack anyway): the only way to hit this bug here would be when
freeing a large modified ldt.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/kaiser.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -319,11 +319,13 @@ void kaiser_remove_mapping(unsigned long
extern void unmap_pud_range_nofree(pgd_t *pgd,
unsigned long start, unsigned long end);
unsigned long end = start + size;
- unsigned long addr;
+ unsigned long addr, next;
+ pgd_t *pgd;
- for (addr = start; addr < end; addr += PGDIR_SIZE) {
- pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(addr));
- unmap_pud_range_nofree(pgd, addr, end);
+ pgd = native_get_shadow_pgd(pgd_offset_k(start));
+ for (addr = start; addr < end; pgd++, addr = next) {
+ next = pgd_addr_end(addr, end);
+ unmap_pud_range_nofree(pgd, addr, next);
}
}
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: fix unlikely error in alloc_ldt_struct()" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: fix unlikely error in alloc_ldt_struct()
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Mon, 4 Dec 2017 20:13:35 -0800
Subject: kaiser: fix unlikely error in alloc_ldt_struct()
From: Hugh Dickins <hughd(a)google.com>
An error from kaiser_add_mapping() here is not at all likely, but
Eric Biggers rightly points out that __free_ldt_struct() relies on
new_ldt->size being initialized: move that up.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/kernel/ldt.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -79,11 +79,11 @@ static struct ldt_struct *alloc_ldt_stru
ret = kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size,
__PAGE_KERNEL);
+ new_ldt->size = size;
if (ret) {
__free_ldt_struct(new_ldt);
return NULL;
}
- new_ldt->size = size;
return new_ldt;
}
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: fix regs to do_nmi() ifndef CONFIG_KAISER" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: fix regs to do_nmi() ifndef CONFIG_KAISER
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Thu, 21 Sep 2017 20:39:56 -0700
Subject: kaiser: fix regs to do_nmi() ifndef CONFIG_KAISER
From: Hugh Dickins <hughd(a)google.com>
pjt has observed that nmi's second (nmi_from_kernel) call to do_nmi()
adjusted the %rdi regs arg, rightly when CONFIG_KAISER, but wrongly
when not CONFIG_KAISER.
Although the minimal change is to add an #ifdef CONFIG_KAISER around
the addq line, that looks cluttered, and I prefer how the first call
to do_nmi() handled it: prepare args in %rdi and %rsi before getting
into the CONFIG_KAISER block, since it does not touch them at all.
And while we're here, place the "#ifdef CONFIG_KAISER" that follows
each, to enclose the "Unconditionally restore CR3" comment: matching
how the "Unconditionally use kernel CR3" comment above is enclosed.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1323,12 +1323,13 @@ ENTRY(nmi)
movq %rax, %cr3
#endif
call do_nmi
+
+#ifdef CONFIG_KAISER
/*
* Unconditionally restore CR3. I know we return to
* kernel code that needs user CR3, but do we ever return
* to "user mode" where we need the kernel CR3?
*/
-#ifdef CONFIG_KAISER
popq %rax
mov %rax, %cr3
#endif
@@ -1552,6 +1553,8 @@ end_repeat_nmi:
SWAPGS
xorl %ebx, %ebx
1:
+ movq %rsp, %rdi
+ movq $-1, %rsi
#ifdef CONFIG_KAISER
/* Unconditionally use kernel CR3 for do_nmi() */
/* %rax is saved above, so OK to clobber here */
@@ -1564,16 +1567,14 @@ end_repeat_nmi:
#endif
/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
- movq %rsp, %rdi
- addq $8, %rdi /* point %rdi at ptregs, fixed up for CR3 */
- movq $-1, %rsi
call do_nmi
+
+#ifdef CONFIG_KAISER
/*
* Unconditionally restore CR3. We might be returning to
* kernel code that needs user CR3, like just just before
* a sysret.
*/
-#ifdef CONFIG_KAISER
popq %rax
mov %rax, %cr3
#endif
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: KAISER depends on SMP" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: KAISER depends on SMP
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-kaiser-depends-on-smp.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Wed, 13 Sep 2017 14:03:10 -0700
Subject: kaiser: KAISER depends on SMP
From: Hugh Dickins <hughd(a)google.com>
It is absurd that KAISER should depend on SMP, but apparently nobody
has tried a UP build before: which breaks on implicit declaration of
function 'per_cpu_offset' in arch/x86/mm/kaiser.c.
Now, you would expect that to be trivially fixed up; but looking at
the System.map when that block is #ifdef'ed out of kaiser_init(),
I see that in a UP build __per_cpu_user_mapped_end is precisely at
__per_cpu_user_mapped_start, and the items carefully gathered into
that section for user-mapping on SMP, dispersed elsewhere on UP.
So, some other kind of section assignment will be needed on UP,
but implementing that is not a priority: just make KAISER depend
on SMP for now.
Also inserted a blank line before the option, tidied up the
brief Kconfig help message, and added an "If unsure, Y".
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
security/Kconfig | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -30,14 +30,16 @@ config SECURITY
model will be used.
If you are unsure how to answer this question, answer N.
+
config KAISER
bool "Remove the kernel mapping in user mode"
default y
- depends on X86_64
- depends on !PARAVIRT
+ depends on X86_64 && SMP && !PARAVIRT
help
- This enforces a strict kernel and user space isolation in order to close
- hardware side channels on kernel address information.
+ This enforces a strict kernel and user space isolation, in order
+ to close hardware side channels on kernel address information.
+
+ If you are unsure how to answer this question, answer Y.
config KAISER_REAL_SWITCH
bool "KAISER: actually switch page tables"
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: fix perf crashes" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: fix perf crashes
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-fix-perf-crashes.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Wed, 23 Aug 2017 14:21:14 -0700
Subject: kaiser: fix perf crashes
From: Hugh Dickins <hughd(a)google.com>
Avoid perf crashes: place debug_store in the user-mapped per-cpu area
instead of allocating, and use page allocator plus kaiser_add_mapping()
to keep the BTS and PEBS buffers user-mapped (that is, present in the
user mapping, though visible only to kernel and hardware). The PEBS
fixup buffer does not need this treatment.
The need for a user-mapped struct debug_store showed up before doing
any conscious perf testing: in a couple of kernel paging oopses on
Westmere, implicating the debug_store offset of the per-cpu area.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/events/intel/ds.c | 57 +++++++++++++++++++++++++++++++++++----------
1 file changed, 45 insertions(+), 12 deletions(-)
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -2,11 +2,15 @@
#include <linux/types.h>
#include <linux/slab.h>
+#include <asm/kaiser.h>
#include <asm/perf_event.h>
#include <asm/insn.h>
#include "../perf_event.h"
+static
+DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct debug_store, cpu_debug_store);
+
/* The size of a BTS record in bytes: */
#define BTS_RECORD_SIZE 24
@@ -268,6 +272,39 @@ void fini_debug_store_on_cpu(int cpu)
static DEFINE_PER_CPU(void *, insn_buffer);
+static void *dsalloc(size_t size, gfp_t flags, int node)
+{
+#ifdef CONFIG_KAISER
+ unsigned int order = get_order(size);
+ struct page *page;
+ unsigned long addr;
+
+ page = __alloc_pages_node(node, flags | __GFP_ZERO, order);
+ if (!page)
+ return NULL;
+ addr = (unsigned long)page_address(page);
+ if (kaiser_add_mapping(addr, size, __PAGE_KERNEL) < 0) {
+ __free_pages(page, order);
+ addr = 0;
+ }
+ return (void *)addr;
+#else
+ return kmalloc_node(size, flags | __GFP_ZERO, node);
+#endif
+}
+
+static void dsfree(const void *buffer, size_t size)
+{
+#ifdef CONFIG_KAISER
+ if (!buffer)
+ return;
+ kaiser_remove_mapping((unsigned long)buffer, size);
+ free_pages((unsigned long)buffer, get_order(size));
+#else
+ kfree(buffer);
+#endif
+}
+
static int alloc_pebs_buffer(int cpu)
{
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -278,7 +315,7 @@ static int alloc_pebs_buffer(int cpu)
if (!x86_pmu.pebs)
return 0;
- buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
+ buffer = dsalloc(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
if (unlikely(!buffer))
return -ENOMEM;
@@ -289,7 +326,7 @@ static int alloc_pebs_buffer(int cpu)
if (x86_pmu.intel_cap.pebs_format < 2) {
ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
if (!ibuffer) {
- kfree(buffer);
+ dsfree(buffer, x86_pmu.pebs_buffer_size);
return -ENOMEM;
}
per_cpu(insn_buffer, cpu) = ibuffer;
@@ -315,7 +352,8 @@ static void release_pebs_buffer(int cpu)
kfree(per_cpu(insn_buffer, cpu));
per_cpu(insn_buffer, cpu) = NULL;
- kfree((void *)(unsigned long)ds->pebs_buffer_base);
+ dsfree((void *)(unsigned long)ds->pebs_buffer_base,
+ x86_pmu.pebs_buffer_size);
ds->pebs_buffer_base = 0;
}
@@ -329,7 +367,7 @@ static int alloc_bts_buffer(int cpu)
if (!x86_pmu.bts)
return 0;
- buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+ buffer = dsalloc(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
if (unlikely(!buffer)) {
WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
return -ENOMEM;
@@ -355,19 +393,15 @@ static void release_bts_buffer(int cpu)
if (!ds || !x86_pmu.bts)
return;
- kfree((void *)(unsigned long)ds->bts_buffer_base);
+ dsfree((void *)(unsigned long)ds->bts_buffer_base, BTS_BUFFER_SIZE);
ds->bts_buffer_base = 0;
}
static int alloc_ds_buffer(int cpu)
{
- int node = cpu_to_node(cpu);
- struct debug_store *ds;
-
- ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
- if (unlikely(!ds))
- return -ENOMEM;
+ struct debug_store *ds = per_cpu_ptr(&cpu_debug_store, cpu);
+ memset(ds, 0, sizeof(*ds));
per_cpu(cpu_hw_events, cpu).ds = ds;
return 0;
@@ -381,7 +415,6 @@ static void release_ds_buffer(int cpu)
return;
per_cpu(cpu_hw_events, cpu).ds = NULL;
- kfree(ds);
}
void release_ds_buffers(void)
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: ENOMEM if kaiser_pagetable_walk() NULL" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: ENOMEM if kaiser_pagetable_walk() NULL
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-enomem-if-kaiser_pagetable_walk-null.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 3 Sep 2017 18:48:02 -0700
Subject: kaiser: ENOMEM if kaiser_pagetable_walk() NULL
From: Hugh Dickins <hughd(a)google.com>
kaiser_add_user_map() took no notice when kaiser_pagetable_walk() failed.
And avoid its might_sleep() when atomic (though atomic at present unused).
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/kaiser.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -98,11 +98,11 @@ static pte_t *kaiser_pagetable_walk(unsi
pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(address));
gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
- might_sleep();
if (is_atomic) {
gfp &= ~GFP_KERNEL;
gfp |= __GFP_HIGH | __GFP_ATOMIC;
- }
+ } else
+ might_sleep();
if (pgd_none(*pgd)) {
WARN_ONCE(1, "All shadow pgds should have been populated");
@@ -159,13 +159,17 @@ int kaiser_add_user_map(const void *__st
unsigned long end_addr = PAGE_ALIGN(start_addr + size);
unsigned long target_address;
- for (;address < end_addr; address += PAGE_SIZE) {
+ for (; address < end_addr; address += PAGE_SIZE) {
target_address = get_pa_from_mapping(address);
if (target_address == -1) {
ret = -EIO;
break;
}
pte = kaiser_pagetable_walk(address, false);
+ if (!pte) {
+ ret = -ENOMEM;
+ break;
+ }
if (pte_none(*pte)) {
set_pte(pte, __pte(flags | target_address));
} else {
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: enhanced by kernel and user PCIDs" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: enhanced by kernel and user PCIDs
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-enhanced-by-kernel-and-user-pcids.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Wed, 30 Aug 2017 16:23:00 -0700
Subject: kaiser: enhanced by kernel and user PCIDs
From: Hugh Dickins <hughd(a)google.com>
Merged performance improvements to Kaiser, using distinct kernel
and user Process Context Identifiers to minimize the TLB flushing.
[This work actually all from Dave Hansen 2017-08-30:
still omitting trackswitch mods, and KAISER_REAL_SWITCH deleted.]
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 10 ++++-
arch/x86/entry/entry_64_compat.S | 1
arch/x86/include/asm/cpufeatures.h | 1
arch/x86/include/asm/kaiser.h | 15 ++++++-
arch/x86/include/asm/pgtable_types.h | 26 +++++++++++++
arch/x86/include/asm/tlbflush.h | 54 +++++++++++++++++++++++-----
arch/x86/include/uapi/asm/processor-flags.h | 3 +
arch/x86/kernel/cpu/common.c | 34 +++++++++++++++++
arch/x86/kvm/x86.c | 3 +
arch/x86/mm/kaiser.c | 7 +++
arch/x86/mm/tlb.c | 46 ++++++++++++++++++++++-
11 files changed, 182 insertions(+), 18 deletions(-)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1317,7 +1317,10 @@ ENTRY(nmi)
/* %rax is saved above, so OK to clobber here */
movq %cr3, %rax
pushq %rax
- andq $(~KAISER_SHADOW_PGD_OFFSET), %rax
+ /* mask off "user" bit of pgd address and 12 PCID bits: */
+ andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
+ /* Add back kernel PCID and "no flush" bit */
+ orq X86_CR3_PCID_KERN_VAR, %rax
movq %rax, %cr3
#endif
call do_nmi
@@ -1558,7 +1561,10 @@ end_repeat_nmi:
/* %rax is saved above, so OK to clobber here */
movq %cr3, %rax
pushq %rax
- andq $(~KAISER_SHADOW_PGD_OFFSET), %rax
+ /* mask off "user" bit of pgd address and 12 PCID bits: */
+ andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
+ /* Add back kernel PCID and "no flush" bit */
+ orq X86_CR3_PCID_KERN_VAR, %rax
movq %rax, %cr3
#endif
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -13,6 +13,7 @@
#include <asm/irqflags.h>
#include <asm/asm.h>
#include <asm/smap.h>
+#include <asm/pgtable_types.h>
#include <asm/kaiser.h>
#include <linux/linkage.h>
#include <linux/err.h>
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -189,6 +189,7 @@
#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */
#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 4) /* Effectively INVPCID && CR4.PCIDE=1 */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -1,5 +1,8 @@
#ifndef _ASM_X86_KAISER_H
#define _ASM_X86_KAISER_H
+
+#include <uapi/asm/processor-flags.h> /* For PCID constants */
+
/*
* This file includes the definitions for the KAISER feature.
* KAISER is a counter measure against x86_64 side channel attacks on
@@ -21,13 +24,21 @@
.macro _SWITCH_TO_KERNEL_CR3 reg
movq %cr3, \reg
-andq $(~KAISER_SHADOW_PGD_OFFSET), \reg
+andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
+orq X86_CR3_PCID_KERN_VAR, \reg
movq \reg, %cr3
.endm
.macro _SWITCH_TO_USER_CR3 reg
movq %cr3, \reg
-orq $(KAISER_SHADOW_PGD_OFFSET), \reg
+andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
+/*
+ * This can obviously be one instruction by putting the
+ * KAISER_SHADOW_PGD_OFFSET bit in the X86_CR3_PCID_USER_VAR.
+ * But, just leave it now for simplicity.
+ */
+orq X86_CR3_PCID_USER_VAR, \reg
+orq $(KAISER_SHADOW_PGD_OFFSET), \reg
movq \reg, %cr3
.endm
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -141,6 +141,32 @@
_PAGE_SOFT_DIRTY)
#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
+/* The ASID is the lower 12 bits of CR3 */
+#define X86_CR3_PCID_ASID_MASK (_AC((1<<12)-1,UL))
+
+/* Mask for all the PCID-related bits in CR3: */
+#define X86_CR3_PCID_MASK (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_MASK)
+#if defined(CONFIG_KAISER) && defined(CONFIG_X86_64)
+#define X86_CR3_PCID_ASID_KERN (_AC(0x4,UL))
+#define X86_CR3_PCID_ASID_USER (_AC(0x6,UL))
+
+#define X86_CR3_PCID_KERN_FLUSH (X86_CR3_PCID_ASID_KERN)
+#define X86_CR3_PCID_USER_FLUSH (X86_CR3_PCID_ASID_USER)
+#define X86_CR3_PCID_KERN_NOFLUSH (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_KERN)
+#define X86_CR3_PCID_USER_NOFLUSH (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_USER)
+#else
+#define X86_CR3_PCID_ASID_KERN (_AC(0x0,UL))
+#define X86_CR3_PCID_ASID_USER (_AC(0x0,UL))
+/*
+ * PCIDs are unsupported on 32-bit and none of these bits can be
+ * set in CR3:
+ */
+#define X86_CR3_PCID_KERN_FLUSH (0)
+#define X86_CR3_PCID_USER_FLUSH (0)
+#define X86_CR3_PCID_KERN_NOFLUSH (0)
+#define X86_CR3_PCID_USER_NOFLUSH (0)
+#endif
+
/*
* The cache modes defined here are used to translate between pure SW usage
* and the HW defined cache mode bits and/or PAT entries.
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -13,7 +13,6 @@ static inline void __invpcid(unsigned lo
unsigned long type)
{
struct { u64 d[2]; } desc = { { pcid, addr } };
-
/*
* The memory clobber is because the whole point is to invalidate
* stale TLB entries and, especially if we're flushing global
@@ -134,14 +133,25 @@ static inline void cr4_set_bits_and_upda
static inline void __native_flush_tlb(void)
{
+ if (!cpu_feature_enabled(X86_FEATURE_INVPCID)) {
+ /*
+ * If current->mm == NULL then we borrow a mm which may change during a
+ * task switch and therefore we must not be preempted while we write CR3
+ * back:
+ */
+ preempt_disable();
+ native_write_cr3(native_read_cr3());
+ preempt_enable();
+ return;
+ }
/*
- * If current->mm == NULL then we borrow a mm which may change during a
- * task switch and therefore we must not be preempted while we write CR3
- * back:
- */
- preempt_disable();
- native_write_cr3(native_read_cr3());
- preempt_enable();
+ * We are no longer using globals with KAISER, so a
+ * "nonglobals" flush would work too. But, this is more
+ * conservative.
+ *
+ * Note, this works with CR4.PCIDE=0 or 1.
+ */
+ invpcid_flush_all();
}
static inline void __native_flush_tlb_global_irq_disabled(void)
@@ -163,6 +173,8 @@ static inline void __native_flush_tlb_gl
/*
* Using INVPCID is considerably faster than a pair of writes
* to CR4 sandwiched inside an IRQ flag save/restore.
+ *
+ * Note, this works with CR4.PCIDE=0 or 1.
*/
invpcid_flush_all();
return;
@@ -182,7 +194,31 @@ static inline void __native_flush_tlb_gl
static inline void __native_flush_tlb_single(unsigned long addr)
{
- asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+ /*
+ * SIMICS #GP's if you run INVPCID with type 2/3
+ * and X86_CR4_PCIDE clear. Shame!
+ *
+ * The ASIDs used below are hard-coded. But, we must not
+ * call invpcid(type=1/2) before CR4.PCIDE=1. Just call
+ * invpcid in the case we are called early.
+ */
+ if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) {
+ asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+ return;
+ }
+ /* Flush the address out of both PCIDs. */
+ /*
+ * An optimization here might be to determine addresses
+ * that are only kernel-mapped and only flush the kernel
+ * ASID. But, userspace flushes are probably much more
+ * important performance-wise.
+ *
+ * Make sure to do only a single invpcid when KAISER is
+ * disabled and we have only a single ASID.
+ */
+ if (X86_CR3_PCID_ASID_KERN != X86_CR3_PCID_ASID_USER)
+ invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr);
+ invpcid_flush_one(X86_CR3_PCID_ASID_USER, addr);
}
static inline void __flush_tlb_all(void)
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -77,7 +77,8 @@
#define X86_CR3_PWT _BITUL(X86_CR3_PWT_BIT)
#define X86_CR3_PCD_BIT 4 /* Page Cache Disable */
#define X86_CR3_PCD _BITUL(X86_CR3_PCD_BIT)
-#define X86_CR3_PCID_MASK _AC(0x00000fff,UL) /* PCID Mask */
+#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */
+#define X86_CR3_PCID_NOFLUSH _BITULL(X86_CR3_PCID_NOFLUSH_BIT)
/*
* Intel CPU features in CR4
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -324,11 +324,45 @@ static __always_inline void setup_smap(s
}
}
+/*
+ * These can have bit 63 set, so we can not just use a plain "or"
+ * instruction to get their value or'd into CR3. It would take
+ * another register. So, we use a memory reference to these
+ * instead.
+ *
+ * This is also handy because systems that do not support
+ * PCIDs just end up or'ing a 0 into their CR3, which does
+ * no harm.
+ */
+__aligned(PAGE_SIZE) unsigned long X86_CR3_PCID_KERN_VAR = 0;
+__aligned(PAGE_SIZE) unsigned long X86_CR3_PCID_USER_VAR = 0;
+
static void setup_pcid(struct cpuinfo_x86 *c)
{
if (cpu_has(c, X86_FEATURE_PCID)) {
if (cpu_has(c, X86_FEATURE_PGE)) {
cr4_set_bits(X86_CR4_PCIDE);
+ /*
+ * These variables are used by the entry/exit
+ * code to change PCIDs.
+ */
+#ifdef CONFIG_KAISER
+ X86_CR3_PCID_KERN_VAR = X86_CR3_PCID_KERN_NOFLUSH;
+ X86_CR3_PCID_USER_VAR = X86_CR3_PCID_USER_NOFLUSH;
+#endif
+ /*
+ * INVPCID has two "groups" of types:
+ * 1/2: Invalidate an individual address
+ * 3/4: Invalidate all contexts
+ *
+ * 1/2 take a PCID, but 3/4 do not. So, 3/4
+ * ignore the PCID argument in the descriptor.
+ * But, we have to be careful not to call 1/2
+ * with an actual non-zero PCID in them before
+ * we do the above cr4_set_bits().
+ */
+ if (cpu_has(c, X86_FEATURE_INVPCID))
+ set_cpu_cap(c, X86_FEATURE_INVPCID_SINGLE);
} else {
/*
* flush_tlb_all(), as currently implemented, won't
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -773,7 +773,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, u
return 1;
/* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */
- if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu))
+ if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_ASID_MASK) ||
+ !is_long_mode(vcpu))
return 1;
}
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -239,6 +239,8 @@ static void __init kaiser_init_all_pgds(
} while (0)
extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
+extern unsigned long X86_CR3_PCID_KERN_VAR;
+extern unsigned long X86_CR3_PCID_USER_VAR;
/*
* If anything in here fails, we will likely die on one of the
* first kernel->user transitions and init will die. But, we
@@ -289,6 +291,11 @@ void __init kaiser_init(void)
kaiser_add_user_map_early(&debug_idt_table,
sizeof(gate_desc) * NR_VECTORS,
__PAGE_KERNEL);
+
+ kaiser_add_user_map_early(&X86_CR3_PCID_KERN_VAR, PAGE_SIZE,
+ __PAGE_KERNEL);
+ kaiser_add_user_map_early(&X86_CR3_PCID_USER_VAR, PAGE_SIZE,
+ __PAGE_KERNEL);
}
/* Add a mapping to the shadow mapping, and synchronize the mappings */
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -34,6 +34,46 @@ struct flush_tlb_info {
unsigned long flush_end;
};
+static void load_new_mm_cr3(pgd_t *pgdir)
+{
+ unsigned long new_mm_cr3 = __pa(pgdir);
+
+ /*
+ * KAISER, plus PCIDs needs some extra work here. But,
+ * if either of features is not present, we need no
+ * PCIDs here and just do a normal, full TLB flush with
+ * the write_cr3()
+ */
+ if (!IS_ENABLED(CONFIG_KAISER) ||
+ !cpu_feature_enabled(X86_FEATURE_PCID))
+ goto out_set_cr3;
+ /*
+ * We reuse the same PCID for different tasks, so we must
+ * flush all the entires for the PCID out when we change
+ * tasks.
+ */
+ new_mm_cr3 = X86_CR3_PCID_KERN_FLUSH | __pa(pgdir);
+
+ /*
+ * The flush from load_cr3() may leave old TLB entries
+ * for userspace in place. We must flush that context
+ * separately. We can theoretically delay doing this
+ * until we actually load up the userspace CR3, but
+ * that's a bit tricky. We have to have the "need to
+ * flush userspace PCID" bit per-cpu and check it in the
+ * exit-to-userspace paths.
+ */
+ invpcid_flush_single_context(X86_CR3_PCID_ASID_USER);
+
+out_set_cr3:
+ /*
+ * Caution: many callers of this function expect
+ * that load_cr3() is serializing and orders TLB
+ * fills with respect to the mm_cpumask writes.
+ */
+ write_cr3(new_mm_cr3);
+}
+
/*
* We cannot call mmdrop() because we are in interrupt context,
* instead update mm->cpu_vm_mask.
@@ -45,7 +85,7 @@ void leave_mm(int cpu)
BUG();
if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) {
cpumask_clear_cpu(cpu, mm_cpumask(active_mm));
- load_cr3(swapper_pg_dir);
+ load_new_mm_cr3(swapper_pg_dir);
/*
* This gets called in the idle path where RCU
* functions differently. Tracing normally
@@ -120,7 +160,7 @@ void switch_mm_irqs_off(struct mm_struct
* ordering guarantee we need.
*
*/
- load_cr3(next->pgd);
+ load_new_mm_cr3(next->pgd);
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
@@ -167,7 +207,7 @@ void switch_mm_irqs_off(struct mm_struct
* As above, load_cr3() is serializing and orders TLB
* fills with respect to the mm_cpumask write.
*/
- load_cr3(next->pgd);
+ load_new_mm_cr3(next->pgd);
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
load_mm_cr4(next);
load_mm_ldt(next);
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: drop is_atomic arg to kaiser_pagetable_walk()" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: drop is_atomic arg to kaiser_pagetable_walk()
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 29 Oct 2017 11:36:19 -0700
Subject: kaiser: drop is_atomic arg to kaiser_pagetable_walk()
From: Hugh Dickins <hughd(a)google.com>
I have not observed a might_sleep() warning from setup_fixmap_gdt()'s
use of kaiser_add_mapping() in our tree (why not?), but like upstream
we have not provided a way for that to pass is_atomic true down to
kaiser_pagetable_walk(), and at startup it's far from a likely source
of trouble: so just delete the walk's is_atomic arg and might_sleep().
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/kaiser.c | 10 ++--------
1 file changed, 2 insertions(+), 8 deletions(-)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -107,19 +107,13 @@ static inline unsigned long get_pa_from_
*
* Returns a pointer to a PTE on success, or NULL on failure.
*/
-static pte_t *kaiser_pagetable_walk(unsigned long address, bool is_atomic)
+static pte_t *kaiser_pagetable_walk(unsigned long address)
{
pmd_t *pmd;
pud_t *pud;
pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(address));
gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
- if (is_atomic) {
- gfp &= ~GFP_KERNEL;
- gfp |= __GFP_HIGH | __GFP_ATOMIC;
- } else
- might_sleep();
-
if (pgd_none(*pgd)) {
WARN_ONCE(1, "All shadow pgds should have been populated");
return NULL;
@@ -194,7 +188,7 @@ static int kaiser_add_user_map(const voi
ret = -EIO;
break;
}
- pte = kaiser_pagetable_walk(address, false);
+ pte = kaiser_pagetable_walk(address);
if (!pte) {
ret = -ENOMEM;
break;
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: fix build and FIXME in alloc_ldt_struct()" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: fix build and FIXME in alloc_ldt_struct()
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 3 Sep 2017 17:09:44 -0700
Subject: kaiser: fix build and FIXME in alloc_ldt_struct()
From: Hugh Dickins <hughd(a)google.com>
Include linux/kaiser.h instead of asm/kaiser.h to build ldt.c without
CONFIG_KAISER. kaiser_add_mapping() does already return an error code,
so fix the FIXME.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/kernel/ldt.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -16,9 +16,9 @@
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
+#include <linux/kaiser.h>
#include <asm/ldt.h>
-#include <asm/kaiser.h>
#include <asm/desc.h>
#include <asm/mmu_context.h>
#include <asm/syscalls.h>
@@ -49,7 +49,7 @@ static struct ldt_struct *alloc_ldt_stru
{
struct ldt_struct *new_ldt;
int alloc_size;
- int ret = 0;
+ int ret;
if (size > LDT_ENTRIES)
return NULL;
@@ -77,10 +77,8 @@ static struct ldt_struct *alloc_ldt_stru
return NULL;
}
- // FIXME: make kaiser_add_mapping() return an error code
- // when it fails
- kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size,
- __PAGE_KERNEL);
+ ret = kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size,
+ __PAGE_KERNEL);
if (ret) {
__free_ldt_struct(new_ldt);
return NULL;
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: do not set _PAGE_NX on pgd_none" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: do not set _PAGE_NX on pgd_none
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-do-not-set-_page_nx-on-pgd_none.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Tue, 5 Sep 2017 12:05:01 -0700
Subject: kaiser: do not set _PAGE_NX on pgd_none
From: Hugh Dickins <hughd(a)google.com>
native_pgd_clear() uses native_set_pgd(), so native_set_pgd() must
avoid setting the _PAGE_NX bit on an otherwise pgd_none() entry:
usually that just generated a warning on exit, but sometimes
more mysterious and damaging failures (our production machines
could not complete booting).
The original fix to this just avoided adding _PAGE_NX to
an empty entry; but eventually more problems surfaced with kexec,
and EFI mapping expected to be a problem too. So now instead
change native_set_pgd() to update shadow only if _PAGE_USER:
A few places (kernel/machine_kexec_64.c, platform/efi/efi_64.c for sure)
use set_pgd() to set up a temporary internal virtual address space, with
physical pages remapped at what Kaiser regards as userspace addresses:
Kaiser then assumes a shadow pgd follows, which it will try to corrupt.
This appears to be responsible for the recent kexec and kdump failures;
though it's unclear how those did not manifest as a problem before.
Ah, the shadow pgd will only be assumed to "follow" if the requested
pgd is on an even-numbered page: so I suppose it was going wrong 50%
of the time all along.
What we need is a flag to set_pgd(), to tell it we're dealing with
userspace. Er, isn't that what the pgd's _PAGE_USER bit is saying?
Add a test for that. But we cannot do the same for pgd_clear()
(which may be called to clear corrupted entries - set aside the
question of "corrupt in which pgd?" until later), so there just
rely on pgd_clear() not being called in the problematic cases -
with a WARN_ON_ONCE() which should fire half the time if it is.
But this is getting too big for an inline function: move it into
arch/x86/mm/kaiser.c (which then demands a boot/compressed mod);
and de-void and de-space native_get_shadow/normal_pgd() while here.
Also make an unnecessary change to KASLR's init_trampoline(): it was
using set_pgd() to assign a pgd-value to a global variable (not in a
pg directory page), which was rather scary given Kaiser's previous
set_pgd() implementation: not a problem now, but too scary to leave
as was, it could easily blow up if we have to change set_pgd() again.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/boot/compressed/misc.h | 1
arch/x86/include/asm/pgtable_64.h | 51 +++++++++-----------------------------
arch/x86/mm/kaiser.c | 42 +++++++++++++++++++++++++++++++
arch/x86/mm/kaslr.c | 4 +-
4 files changed, 58 insertions(+), 40 deletions(-)
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -9,6 +9,7 @@
*/
#undef CONFIG_PARAVIRT
#undef CONFIG_PARAVIRT_SPINLOCKS
+#undef CONFIG_KAISER
#undef CONFIG_KASAN
#include <linux/linkage.h>
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -107,61 +107,36 @@ static inline void native_pud_clear(pud_
}
#ifdef CONFIG_KAISER
-static inline pgd_t * native_get_shadow_pgd(pgd_t *pgdp)
+extern pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd);
+
+static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp)
{
- return (pgd_t *)(void*)((unsigned long)(void*)pgdp | (unsigned long)PAGE_SIZE);
+ return (pgd_t *)((unsigned long)pgdp | (unsigned long)PAGE_SIZE);
}
-static inline pgd_t * native_get_normal_pgd(pgd_t *pgdp)
+static inline pgd_t *native_get_normal_pgd(pgd_t *pgdp)
{
- return (pgd_t *)(void*)((unsigned long)(void*)pgdp & ~(unsigned long)PAGE_SIZE);
+ return (pgd_t *)((unsigned long)pgdp & ~(unsigned long)PAGE_SIZE);
}
#else
-static inline pgd_t * native_get_shadow_pgd(pgd_t *pgdp)
+static inline pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ return pgd;
+}
+static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp)
{
BUILD_BUG_ON(1);
return NULL;
}
-static inline pgd_t * native_get_normal_pgd(pgd_t *pgdp)
+static inline pgd_t *native_get_normal_pgd(pgd_t *pgdp)
{
return pgdp;
}
#endif /* CONFIG_KAISER */
-/*
- * Page table pages are page-aligned. The lower half of the top
- * level is used for userspace and the top half for the kernel.
- * This returns true for user pages that need to get copied into
- * both the user and kernel copies of the page tables, and false
- * for kernel pages that should only be in the kernel copy.
- */
-static inline bool is_userspace_pgd(void *__ptr)
-{
- unsigned long ptr = (unsigned long)__ptr;
-
- return ((ptr % PAGE_SIZE) < (PAGE_SIZE / 2));
-}
-
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
-#ifdef CONFIG_KAISER
- pteval_t extra_kern_pgd_flags = 0;
- /* Do we need to also populate the shadow pgd? */
- if (is_userspace_pgd(pgdp)) {
- native_get_shadow_pgd(pgdp)->pgd = pgd.pgd;
- /*
- * Even if the entry is *mapping* userspace, ensure
- * that userspace can not use it. This way, if we
- * get out to userspace running on the kernel CR3,
- * userspace will crash instead of running.
- */
- extra_kern_pgd_flags = _PAGE_NX;
- }
- pgdp->pgd = pgd.pgd;
- pgdp->pgd |= extra_kern_pgd_flags;
-#else /* CONFIG_KAISER */
- *pgdp = pgd;
-#endif
+ *pgdp = kaiser_set_shadow_pgd(pgdp, pgd);
}
static inline void native_pgd_clear(pgd_t *pgd)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -302,4 +302,46 @@ void kaiser_remove_mapping(unsigned long
unmap_pud_range_nofree(pgd, addr, end);
}
}
+
+/*
+ * Page table pages are page-aligned. The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ * This returns true for user pages that need to get copied into
+ * both the user and kernel copies of the page tables, and false
+ * for kernel pages that should only be in the kernel copy.
+ */
+static inline bool is_userspace_pgd(pgd_t *pgdp)
+{
+ return ((unsigned long)pgdp % PAGE_SIZE) < (PAGE_SIZE / 2);
+}
+
+pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ /*
+ * Do we need to also populate the shadow pgd? Check _PAGE_USER to
+ * skip cases like kexec and EFI which make temporary low mappings.
+ */
+ if (pgd.pgd & _PAGE_USER) {
+ if (is_userspace_pgd(pgdp)) {
+ native_get_shadow_pgd(pgdp)->pgd = pgd.pgd;
+ /*
+ * Even if the entry is *mapping* userspace, ensure
+ * that userspace can not use it. This way, if we
+ * get out to userspace running on the kernel CR3,
+ * userspace will crash instead of running.
+ */
+ pgd.pgd |= _PAGE_NX;
+ }
+ } else if (!pgd.pgd) {
+ /*
+ * pgd_clear() cannot check _PAGE_USER, and is even used to
+ * clear corrupted pgd entries: so just rely on cases like
+ * kexec and EFI never to be using pgd_clear().
+ */
+ if (!WARN_ON_ONCE((unsigned long)pgdp & PAGE_SIZE) &&
+ is_userspace_pgd(pgdp))
+ native_get_shadow_pgd(pgdp)->pgd = pgd.pgd;
+ }
+ return pgd;
+}
#endif /* CONFIG_KAISER */
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -189,6 +189,6 @@ void __meminit init_trampoline(void)
*pud_tramp = *pud;
}
- set_pgd(&trampoline_pgd_entry,
- __pgd(_KERNPG_TABLE | __pa(pud_page_tramp)));
+ /* Avoid set_pgd(), in case it's complicated by CONFIG_KAISER */
+ trampoline_pgd_entry = __pgd(_KERNPG_TABLE | __pa(pud_page_tramp));
}
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: disabled on Xen PV" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: disabled on Xen PV
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-disabled-on-xen-pv.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Jiri Kosina <jkosina(a)suse.cz>
Date: Tue, 2 Jan 2018 14:19:49 +0100
Subject: kaiser: disabled on Xen PV
From: Jiri Kosina <jkosina(a)suse.cz>
Kaiser cannot be used on paravirtualized MMUs (namely reading and writing CR3).
This does not work with KAISER as the CR3 switch from and to user space PGD
would require to map the whole XEN_PV machinery into both.
More importantly, enabling KAISER on Xen PV doesn't make too much sense, as PV
guests use distinct %cr3 values for kernel and user already.
Signed-off-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/kaiser.c | 5 +++++
1 file changed, 5 insertions(+)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -263,6 +263,9 @@ void __init kaiser_check_boottime_disabl
char arg[5];
int ret;
+ if (boot_cpu_has(X86_FEATURE_XENPV))
+ goto silent_disable;
+
ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
if (ret > 0) {
if (!strncmp(arg, "on", 2))
@@ -290,6 +293,8 @@ enable:
disable:
pr_info("Kernel/User page tables isolation: disabled\n");
+
+silent_disable:
kaiser_enabled = 0;
setup_clear_cpu_cap(X86_FEATURE_KAISER);
}
Patches currently in stable-queue which might be from jkosina(a)suse.cz are
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-disabled-on-xen-pv.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: asm/tlbflush.h handle noPGE at lower level" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: asm/tlbflush.h handle noPGE at lower level
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sat, 4 Nov 2017 18:23:24 -0700
Subject: kaiser: asm/tlbflush.h handle noPGE at lower level
From: Hugh Dickins <hughd(a)google.com>
I found asm/tlbflush.h too twisty, and think it safer not to avoid
__native_flush_tlb_global_irq_disabled() in the kaiser_enabled case,
but instead let it handle kaiser_enabled along with cr3: it can just
use __native_flush_tlb() for that, no harm in re-disabling preemption.
(This is not the same change as Kirill and Dave have suggested for
upstream, flipping PGE in cr4: that's neat, but needs a cpu_has_pge
check; cr3 is enough for kaiser, and thought to be cheaper than cr4.)
Also delete the X86_FEATURE_INVPCID invpcid_flush_all_nonglobals()
preference from __native_flush_tlb(): unlike the invpcid_flush_all()
preference in __native_flush_tlb_global(), it's not seen in upstream
4.14, and was recently reported to be surprisingly slow.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/tlbflush.h | 27 +++------------------------
1 file changed, 3 insertions(+), 24 deletions(-)
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -152,14 +152,6 @@ static inline void kaiser_flush_tlb_on_r
static inline void __native_flush_tlb(void)
{
- if (this_cpu_has(X86_FEATURE_INVPCID)) {
- /*
- * Note, this works with CR4.PCIDE=0 or 1.
- */
- invpcid_flush_all_nonglobals();
- return;
- }
-
/*
* If current->mm == NULL then we borrow a mm which may change during a
* task switch and therefore we must not be preempted while we write CR3
@@ -183,11 +175,8 @@ static inline void __native_flush_tlb_gl
/* restore PGE as it was before */
native_write_cr4(cr4);
} else {
- /*
- * x86_64 microcode update comes this way when CR4.PGE is not
- * enabled, and it's safer for all callers to allow this case.
- */
- native_write_cr3(native_read_cr3());
+ /* do it with cr3, letting kaiser flush user PCID */
+ __native_flush_tlb();
}
}
@@ -195,12 +184,6 @@ static inline void __native_flush_tlb_gl
{
unsigned long flags;
- if (kaiser_enabled) {
- /* Globals are not used at all */
- __native_flush_tlb();
- return;
- }
-
if (this_cpu_has(X86_FEATURE_INVPCID)) {
/*
* Using INVPCID is considerably faster than a pair of writes
@@ -256,11 +239,7 @@ static inline void __native_flush_tlb_si
static inline void __flush_tlb_all(void)
{
- if (boot_cpu_has(X86_FEATURE_PGE))
- __flush_tlb_global();
- else
- __flush_tlb();
-
+ __flush_tlb_global();
/*
* Note: if we somehow had PCID but not PGE, then this wouldn't work --
* we'd end up flushing kernel translations for the current ASID but
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: delete KAISER_REAL_SWITCH option" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: delete KAISER_REAL_SWITCH option
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-delete-kaiser_real_switch-option.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 3 Sep 2017 18:30:43 -0700
Subject: kaiser: delete KAISER_REAL_SWITCH option
From: Hugh Dickins <hughd(a)google.com>
We fail to see what CONFIG_KAISER_REAL_SWITCH is for: it seems to be
left over from early development, and now just obscures tricky parts
of the code. Delete it before adding PCIDs, or nokaiser boot option.
(Or if there is some good reason to keep the option, then it needs
a help text - and a "depends on KAISER", so that all those without
KAISER are not asked the question. But we'd much rather delete it.)
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 4 ----
arch/x86/include/asm/kaiser.h | 4 ----
security/Kconfig | 4 ----
3 files changed, 12 deletions(-)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1317,9 +1317,7 @@ ENTRY(nmi)
/* %rax is saved above, so OK to clobber here */
movq %cr3, %rax
pushq %rax
-#ifdef CONFIG_KAISER_REAL_SWITCH
andq $(~KAISER_SHADOW_PGD_OFFSET), %rax
-#endif
movq %rax, %cr3
#endif
call do_nmi
@@ -1560,9 +1558,7 @@ end_repeat_nmi:
/* %rax is saved above, so OK to clobber here */
movq %cr3, %rax
pushq %rax
-#ifdef CONFIG_KAISER_REAL_SWITCH
andq $(~KAISER_SHADOW_PGD_OFFSET), %rax
-#endif
movq %rax, %cr3
#endif
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -21,17 +21,13 @@
.macro _SWITCH_TO_KERNEL_CR3 reg
movq %cr3, \reg
-#ifdef CONFIG_KAISER_REAL_SWITCH
andq $(~KAISER_SHADOW_PGD_OFFSET), \reg
-#endif
movq \reg, %cr3
.endm
.macro _SWITCH_TO_USER_CR3 reg
movq %cr3, \reg
-#ifdef CONFIG_KAISER_REAL_SWITCH
orq $(KAISER_SHADOW_PGD_OFFSET), \reg
-#endif
movq \reg, %cr3
.endm
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -41,10 +41,6 @@ config KAISER
If you are unsure how to answer this question, answer Y.
-config KAISER_REAL_SWITCH
- bool "KAISER: actually switch page tables"
- default y
-
config SECURITYFS
bool "Enable the securityfs filesystem"
help
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: cleanups while trying for gold link" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: cleanups while trying for gold link
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-cleanups-while-trying-for-gold-link.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Mon, 21 Aug 2017 20:11:43 -0700
Subject: kaiser: cleanups while trying for gold link
From: Hugh Dickins <hughd(a)google.com>
While trying to get our gold link to work, four cleanups:
matched the gdt_page declaration to its definition;
in fiddling unsuccessfully with PERCPU_INPUT(), lined up backslashes;
lined up the backslashes according to convention in percpu-defs.h;
deleted the unused irq_stack_pointer addition to irq_stack_union.
Sad to report that aligning backslashes does not appear to help gold
align to 8192: but while these did not help, they are worth keeping.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/desc.h | 2 +-
arch/x86/include/asm/processor.h | 5 -----
include/asm-generic/vmlinux.lds.h | 18 ++++++++----------
include/linux/percpu-defs.h | 24 ++++++++++++------------
4 files changed, 21 insertions(+), 28 deletions(-)
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -43,7 +43,7 @@ struct gdt_page {
struct desc_struct gdt[GDT_ENTRIES];
} __attribute__((aligned(PAGE_SIZE)));
-DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
+DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page);
static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
{
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -335,11 +335,6 @@ union irq_stack_union {
char gs_base[40];
unsigned long stack_canary;
};
-
- struct {
- char irq_stack_pointer[64];
- char unused[IRQ_STACK_SIZE - 64];
- };
};
DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible;
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -778,16 +778,14 @@
*/
#define PERCPU_INPUT(cacheline) \
VMLINUX_SYMBOL(__per_cpu_start) = .; \
- \
- VMLINUX_SYMBOL(__per_cpu_user_mapped_start) = .; \
- *(.data..percpu..first) \
- . = ALIGN(cacheline); \
- *(.data..percpu..user_mapped) \
- *(.data..percpu..user_mapped..shared_aligned) \
- . = ALIGN(PAGE_SIZE); \
- *(.data..percpu..user_mapped..page_aligned) \
- VMLINUX_SYMBOL(__per_cpu_user_mapped_end) = .; \
- \
+ VMLINUX_SYMBOL(__per_cpu_user_mapped_start) = .; \
+ *(.data..percpu..first) \
+ . = ALIGN(cacheline); \
+ *(.data..percpu..user_mapped) \
+ *(.data..percpu..user_mapped..shared_aligned) \
+ . = ALIGN(PAGE_SIZE); \
+ *(.data..percpu..user_mapped..page_aligned) \
+ VMLINUX_SYMBOL(__per_cpu_user_mapped_end) = .; \
. = ALIGN(PAGE_SIZE); \
*(.data..percpu..page_aligned) \
. = ALIGN(cacheline); \
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -121,10 +121,10 @@
#define DEFINE_PER_CPU(type, name) \
DEFINE_PER_CPU_SECTION(type, name, "")
-#define DECLARE_PER_CPU_USER_MAPPED(type, name) \
+#define DECLARE_PER_CPU_USER_MAPPED(type, name) \
DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION)
-#define DEFINE_PER_CPU_USER_MAPPED(type, name) \
+#define DEFINE_PER_CPU_USER_MAPPED(type, name) \
DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION)
/*
@@ -156,11 +156,11 @@
DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
____cacheline_aligned_in_smp
-#define DECLARE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \
+#define DECLARE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \
DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION PER_CPU_SHARED_ALIGNED_SECTION) \
____cacheline_aligned_in_smp
-#define DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \
+#define DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \
DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION PER_CPU_SHARED_ALIGNED_SECTION) \
____cacheline_aligned_in_smp
@@ -185,18 +185,18 @@
/*
* Declaration/definition used for per-CPU variables that must be page aligned and need to be mapped in user mode.
*/
-#define DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \
- DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \
- __aligned(PAGE_SIZE)
-
-#define DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \
- DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \
- __aligned(PAGE_SIZE)
+#define DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \
+ DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \
+ __aligned(PAGE_SIZE)
+
+#define DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \
+ DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \
+ __aligned(PAGE_SIZE)
/*
* Declaration/definition used for per-CPU variables that must be read mostly.
*/
-#define DECLARE_PER_CPU_READ_MOSTLY(type, name) \
+#define DECLARE_PER_CPU_READ_MOSTLY(type, name) \
DECLARE_PER_CPU_SECTION(type, name, "..read_mostly")
#define DEFINE_PER_CPU_READ_MOSTLY(type, name) \
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: align addition to x86/mm/Makefile" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: align addition to x86/mm/Makefile
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-align-addition-to-x86-mm-makefile.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 3 Sep 2017 19:51:10 -0700
Subject: kaiser: align addition to x86/mm/Makefile
From: Hugh Dickins <hughd(a)google.com>
Use tab not space so they line up properly, kaslr.o also.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/Makefile | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -37,5 +37,5 @@ obj-$(CONFIG_NUMA_EMU) += numa_emulatio
obj-$(CONFIG_X86_INTEL_MPX) += mpx.o
obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o
-obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o
-obj-$(CONFIG_KAISER) += kaiser.o
+obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o
+obj-$(CONFIG_KAISER) += kaiser.o
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: add "nokaiser" boot option, using ALTERNATIVE" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: add "nokaiser" boot option, using ALTERNATIVE
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-add-nokaiser-boot-option-using-alternative.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 24 Sep 2017 16:59:49 -0700
Subject: kaiser: add "nokaiser" boot option, using ALTERNATIVE
From: Hugh Dickins <hughd(a)google.com>
Added "nokaiser" boot option: an early param like "noinvpcid".
Most places now check int kaiser_enabled (#defined 0 when not
CONFIG_KAISER) instead of #ifdef CONFIG_KAISER; but entry_64.S
and entry_64_compat.S are using the ALTERNATIVE technique, which
patches in the preferred instructions at runtime. That technique
is tied to x86 cpu features, so X86_FEATURE_KAISER is fabricated.
Prior to "nokaiser", Kaiser #defined _PAGE_GLOBAL 0: revert that,
but be careful with both _PAGE_GLOBAL and CR4.PGE: setting them when
nokaiser like when !CONFIG_KAISER, but not setting either when kaiser -
neither matters on its own, but it's hard to be sure that _PAGE_GLOBAL
won't get set in some obscure corner, or something add PGE into CR4.
By omitting _PAGE_GLOBAL from __supported_pte_mask when kaiser_enabled,
all page table setup which uses pte_pfn() masks it out of the ptes.
It's slightly shameful that the same declaration versus definition of
kaiser_enabled appears in not one, not two, but in three header files
(asm/kaiser.h, asm/pgtable.h, asm/tlbflush.h). I felt safer that way,
than with #including any of those in any of the others; and did not
feel it worth an asm/kaiser_enabled.h - kernel/cpu/common.c includes
them all, so we shall hear about it if they get out of synch.
Cleanups while in the area: removed the silly #ifdef CONFIG_KAISER
from kaiser.c; removed the unused native_get_normal_pgd(); removed
the spurious reg clutter from SWITCH_*_CR3 macro stubs; corrected some
comments. But more interestingly, set CR4.PSE in secondary_startup_64:
the manual is clear that it does not matter whether it's 0 or 1 when
4-level-pts are enabled, but I was distracted to find cr4 different on
BSP and auxiliaries - BSP alone was adding PSE, in probe_page_size_mask().
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
Documentation/kernel-parameters.txt | 2 +
arch/x86/entry/entry_64.S | 15 ++++++-----
arch/x86/include/asm/cpufeatures.h | 3 ++
arch/x86/include/asm/kaiser.h | 27 +++++++++++++++------
arch/x86/include/asm/pgtable.h | 20 +++++++++++----
arch/x86/include/asm/pgtable_64.h | 13 +++-------
arch/x86/include/asm/pgtable_types.h | 4 ---
arch/x86/include/asm/tlbflush.h | 39 +++++++++++++++++++------------
arch/x86/kernel/cpu/common.c | 28 +++++++++++++++++++++-
arch/x86/kernel/espfix_64.c | 3 +-
arch/x86/kernel/head_64.S | 4 +--
arch/x86/mm/init.c | 2 -
arch/x86/mm/init_64.c | 10 +++++++
arch/x86/mm/kaiser.c | 26 +++++++++++++++++---
arch/x86/mm/pgtable.c | 8 +-----
arch/x86/mm/tlb.c | 4 ---
tools/arch/x86/include/asm/cpufeatures.h | 3 ++
17 files changed, 146 insertions(+), 65 deletions(-)
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2763,6 +2763,8 @@ bytes respectively. Such letter suffixes
nojitter [IA-64] Disables jitter checking for ITC timers.
+ nokaiser [X86-64] Disable KAISER isolation of kernel from user.
+
no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver
no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1079,7 +1079,7 @@ ENTRY(paranoid_entry)
* unconditionally, but we need to find out whether the reverse
* should be done on return (conveyed to paranoid_exit in %ebx).
*/
- movq %cr3, %rax
+ ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER
testl $KAISER_SHADOW_PGD_OFFSET, %eax
jz 2f
orl $2, %ebx
@@ -1111,6 +1111,7 @@ ENTRY(paranoid_exit)
TRACE_IRQS_OFF_DEBUG
TRACE_IRQS_IRETQ_DEBUG
#ifdef CONFIG_KAISER
+ /* No ALTERNATIVE for X86_FEATURE_KAISER: paranoid_entry sets %ebx */
testl $2, %ebx /* SWITCH_USER_CR3 needed? */
jz paranoid_exit_no_switch
SWITCH_USER_CR3
@@ -1341,13 +1342,14 @@ ENTRY(nmi)
#ifdef CONFIG_KAISER
/* Unconditionally use kernel CR3 for do_nmi() */
/* %rax is saved above, so OK to clobber here */
- movq %cr3, %rax
+ ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER
/* If PCID enabled, NOFLUSH now and NOFLUSH on return */
orq x86_cr3_pcid_noflush, %rax
pushq %rax
/* mask off "user" bit of pgd address and 12 PCID bits: */
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
movq %rax, %cr3
+2:
#endif
call do_nmi
@@ -1357,8 +1359,7 @@ ENTRY(nmi)
* kernel code that needs user CR3, but do we ever return
* to "user mode" where we need the kernel CR3?
*/
- popq %rax
- mov %rax, %cr3
+ ALTERNATIVE "", "popq %rax; movq %rax, %cr3", X86_FEATURE_KAISER
#endif
/*
@@ -1585,13 +1586,14 @@ end_repeat_nmi:
#ifdef CONFIG_KAISER
/* Unconditionally use kernel CR3 for do_nmi() */
/* %rax is saved above, so OK to clobber here */
- movq %cr3, %rax
+ ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER
/* If PCID enabled, NOFLUSH now and NOFLUSH on return */
orq x86_cr3_pcid_noflush, %rax
pushq %rax
/* mask off "user" bit of pgd address and 12 PCID bits: */
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
movq %rax, %cr3
+2:
#endif
/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
@@ -1603,8 +1605,7 @@ end_repeat_nmi:
* kernel code that needs user CR3, like just just before
* a sysret.
*/
- popq %rax
- mov %rax, %cr3
+ ALTERNATIVE "", "popq %rax; movq %rax, %cr3", X86_FEATURE_KAISER
#endif
testl %ebx, %ebx /* swapgs needed? */
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -198,6 +198,9 @@
#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
+/* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
+#define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_KAISER w/o nokaiser */
+
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -46,28 +46,33 @@ movq \reg, %cr3
.endm
.macro SWITCH_KERNEL_CR3
-pushq %rax
+ALTERNATIVE "jmp 8f", "pushq %rax", X86_FEATURE_KAISER
_SWITCH_TO_KERNEL_CR3 %rax
popq %rax
+8:
.endm
.macro SWITCH_USER_CR3
-pushq %rax
+ALTERNATIVE "jmp 8f", "pushq %rax", X86_FEATURE_KAISER
_SWITCH_TO_USER_CR3 %rax %al
popq %rax
+8:
.endm
.macro SWITCH_KERNEL_CR3_NO_STACK
-movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)
+ALTERNATIVE "jmp 8f", \
+ __stringify(movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)), \
+ X86_FEATURE_KAISER
_SWITCH_TO_KERNEL_CR3 %rax
movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
+8:
.endm
#else /* CONFIG_KAISER */
-.macro SWITCH_KERNEL_CR3 reg
+.macro SWITCH_KERNEL_CR3
.endm
-.macro SWITCH_USER_CR3 reg regb
+.macro SWITCH_USER_CR3
.endm
.macro SWITCH_KERNEL_CR3_NO_STACK
.endm
@@ -90,6 +95,16 @@ DECLARE_PER_CPU(unsigned long, x86_cr3_p
extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
+extern int kaiser_enabled;
+#else
+#define kaiser_enabled 0
+#endif /* CONFIG_KAISER */
+
+/*
+ * Kaiser function prototypes are needed even when CONFIG_KAISER is not set,
+ * so as to build with tests on kaiser_enabled instead of #ifdefs.
+ */
+
/**
* kaiser_add_mapping - map a virtual memory part to the shadow (user) mapping
* @addr: the start address of the range
@@ -119,8 +134,6 @@ extern void kaiser_remove_mapping(unsign
*/
extern void kaiser_init(void);
-#endif /* CONFIG_KAISER */
-
#endif /* __ASSEMBLY */
#endif /* _ASM_X86_KAISER_H */
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -18,6 +18,12 @@
#ifndef __ASSEMBLY__
#include <asm/x86_init.h>
+#ifdef CONFIG_KAISER
+extern int kaiser_enabled;
+#else
+#define kaiser_enabled 0
+#endif
+
void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
void ptdump_walk_pgd_level_checkwx(void);
@@ -697,7 +703,7 @@ static inline int pgd_bad(pgd_t pgd)
* page table by accident; it will fault on the first
* instruction it tries to run. See native_set_pgd().
*/
- if (IS_ENABLED(CONFIG_KAISER))
+ if (kaiser_enabled)
ignore_flags |= _PAGE_NX;
return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
@@ -913,12 +919,14 @@ static inline void pmdp_set_wrprotect(st
*/
static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
{
- memcpy(dst, src, count * sizeof(pgd_t));
+ memcpy(dst, src, count * sizeof(pgd_t));
#ifdef CONFIG_KAISER
- /* Clone the shadow pgd part as well */
- memcpy(native_get_shadow_pgd(dst),
- native_get_shadow_pgd(src),
- count * sizeof(pgd_t));
+ if (kaiser_enabled) {
+ /* Clone the shadow pgd part as well */
+ memcpy(native_get_shadow_pgd(dst),
+ native_get_shadow_pgd(src),
+ count * sizeof(pgd_t));
+ }
#endif
}
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -111,13 +111,12 @@ extern pgd_t kaiser_set_shadow_pgd(pgd_t
static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp)
{
+#ifdef CONFIG_DEBUG_VM
+ /* linux/mmdebug.h may not have been included at this point */
+ BUG_ON(!kaiser_enabled);
+#endif
return (pgd_t *)((unsigned long)pgdp | (unsigned long)PAGE_SIZE);
}
-
-static inline pgd_t *native_get_normal_pgd(pgd_t *pgdp)
-{
- return (pgd_t *)((unsigned long)pgdp & ~(unsigned long)PAGE_SIZE);
-}
#else
static inline pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
{
@@ -128,10 +127,6 @@ static inline pgd_t *native_get_shadow_p
BUILD_BUG_ON(1);
return NULL;
}
-static inline pgd_t *native_get_normal_pgd(pgd_t *pgdp)
-{
- return pgdp;
-}
#endif /* CONFIG_KAISER */
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -45,11 +45,7 @@
#define _PAGE_ACCESSED (_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
#define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
#define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE)
-#ifdef CONFIG_KAISER
-#define _PAGE_GLOBAL (_AT(pteval_t, 0))
-#else
#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
-#endif
#define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1)
#define _PAGE_SOFTW2 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2)
#define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT)
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -137,9 +137,11 @@ static inline void cr4_set_bits_and_upda
* to avoid the need for asm/kaiser.h in unexpected places.
*/
#ifdef CONFIG_KAISER
+extern int kaiser_enabled;
extern void kaiser_setup_pcid(void);
extern void kaiser_flush_tlb_on_return_to_user(void);
#else
+#define kaiser_enabled 0
static inline void kaiser_setup_pcid(void)
{
}
@@ -164,7 +166,7 @@ static inline void __native_flush_tlb(vo
* back:
*/
preempt_disable();
- if (this_cpu_has(X86_FEATURE_PCID))
+ if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID))
kaiser_flush_tlb_on_return_to_user();
native_write_cr3(native_read_cr3());
preempt_enable();
@@ -175,20 +177,30 @@ static inline void __native_flush_tlb_gl
unsigned long cr4;
cr4 = this_cpu_read(cpu_tlbstate.cr4);
- /* clear PGE */
- native_write_cr4(cr4 & ~X86_CR4_PGE);
- /* write old PGE again and flush TLBs */
- native_write_cr4(cr4);
+ if (cr4 & X86_CR4_PGE) {
+ /* clear PGE and flush TLB of all entries */
+ native_write_cr4(cr4 & ~X86_CR4_PGE);
+ /* restore PGE as it was before */
+ native_write_cr4(cr4);
+ } else {
+ /*
+ * x86_64 microcode update comes this way when CR4.PGE is not
+ * enabled, and it's safer for all callers to allow this case.
+ */
+ native_write_cr3(native_read_cr3());
+ }
}
static inline void __native_flush_tlb_global(void)
{
-#ifdef CONFIG_KAISER
- /* Globals are not used at all */
- __native_flush_tlb();
-#else
unsigned long flags;
+ if (kaiser_enabled) {
+ /* Globals are not used at all */
+ __native_flush_tlb();
+ return;
+ }
+
if (this_cpu_has(X86_FEATURE_INVPCID)) {
/*
* Using INVPCID is considerably faster than a pair of writes
@@ -208,7 +220,6 @@ static inline void __native_flush_tlb_gl
raw_local_irq_save(flags);
__native_flush_tlb_global_irq_disabled();
raw_local_irq_restore(flags);
-#endif
}
static inline void __native_flush_tlb_single(unsigned long addr)
@@ -223,7 +234,7 @@ static inline void __native_flush_tlb_si
*/
if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) {
- if (this_cpu_has(X86_FEATURE_PCID))
+ if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID))
kaiser_flush_tlb_on_return_to_user();
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
return;
@@ -238,9 +249,9 @@ static inline void __native_flush_tlb_si
* Make sure to do only a single invpcid when KAISER is
* disabled and we have only a single ASID.
*/
- if (X86_CR3_PCID_ASID_KERN != X86_CR3_PCID_ASID_USER)
- invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr);
- invpcid_flush_one(X86_CR3_PCID_ASID_USER, addr);
+ if (kaiser_enabled)
+ invpcid_flush_one(X86_CR3_PCID_ASID_USER, addr);
+ invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr);
}
static inline void __flush_tlb_all(void)
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -179,6 +179,20 @@ static int __init x86_pcid_setup(char *s
return 1;
}
__setup("nopcid", x86_pcid_setup);
+
+static int __init x86_nokaiser_setup(char *s)
+{
+ /* nokaiser doesn't accept parameters */
+ if (s)
+ return -EINVAL;
+#ifdef CONFIG_KAISER
+ kaiser_enabled = 0;
+ setup_clear_cpu_cap(X86_FEATURE_KAISER);
+ pr_info("nokaiser: KAISER feature disabled\n");
+#endif
+ return 0;
+}
+early_param("nokaiser", x86_nokaiser_setup);
#endif
static int __init x86_noinvpcid_setup(char *s)
@@ -327,7 +341,7 @@ static __always_inline void setup_smap(s
static void setup_pcid(struct cpuinfo_x86 *c)
{
if (cpu_has(c, X86_FEATURE_PCID)) {
- if (cpu_has(c, X86_FEATURE_PGE)) {
+ if (cpu_has(c, X86_FEATURE_PGE) || kaiser_enabled) {
cr4_set_bits(X86_CR4_PCIDE);
/*
* INVPCID has two "groups" of types:
@@ -799,6 +813,10 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
init_scattered_cpuid_features(c);
+#ifdef CONFIG_KAISER
+ if (kaiser_enabled)
+ set_cpu_cap(c, X86_FEATURE_KAISER);
+#endif
}
static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
@@ -1537,6 +1555,14 @@ void cpu_init(void)
* try to read it.
*/
cr4_init_shadow();
+ if (!kaiser_enabled) {
+ /*
+ * secondary_startup_64() deferred setting PGE in cr4:
+ * probe_page_size_mask() sets it on the boot cpu,
+ * but it needs to be set on each secondary cpu.
+ */
+ cr4_set_bits(X86_CR4_PGE);
+ }
/*
* Load microcode on this cpu if a valid microcode is available.
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -132,9 +132,10 @@ void __init init_espfix_bsp(void)
* area to ensure it is mapped into the shadow user page
* tables.
*/
- if (IS_ENABLED(CONFIG_KAISER))
+ if (kaiser_enabled) {
set_pgd(native_get_shadow_pgd(pgd_p),
__pgd(_KERNPG_TABLE | __pa((pud_t *)espfix_pud_page)));
+ }
/* Randomize the locations */
init_espfix_random();
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -190,8 +190,8 @@ ENTRY(secondary_startup_64)
movq $(init_level4_pgt - __START_KERNEL_map), %rax
1:
- /* Enable PAE mode and PGE */
- movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx
+ /* Enable PAE and PSE, but defer PGE until kaiser_enabled is decided */
+ movl $(X86_CR4_PAE | X86_CR4_PSE), %ecx
movq %rcx, %cr4
/* Setup early boot stage 4 level pagetables. */
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -177,7 +177,7 @@ static void __init probe_page_size_mask(
cr4_set_bits_and_update_boot(X86_CR4_PSE);
/* Enable PGE if available */
- if (boot_cpu_has(X86_FEATURE_PGE)) {
+ if (boot_cpu_has(X86_FEATURE_PGE) && !kaiser_enabled) {
cr4_set_bits_and_update_boot(X86_CR4_PGE);
__supported_pte_mask |= _PAGE_GLOBAL;
} else
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -324,6 +324,16 @@ void __init cleanup_highmap(void)
continue;
if (vaddr < (unsigned long) _text || vaddr > end)
set_pmd(pmd, __pmd(0));
+ else if (kaiser_enabled) {
+ /*
+ * level2_kernel_pgt is initialized with _PAGE_GLOBAL:
+ * clear that now. This is not important, so long as
+ * CR4.PGE remains clear, but it removes an anomaly.
+ * Physical mapping setup below avoids _PAGE_GLOBAL
+ * by use of massage_pgprot() inside pfn_pte() etc.
+ */
+ set_pmd(pmd, pmd_clear_flags(*pmd, _PAGE_GLOBAL));
+ }
}
}
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -16,7 +16,9 @@
#include <asm/pgalloc.h>
#include <asm/desc.h>
-#ifdef CONFIG_KAISER
+int kaiser_enabled __read_mostly = 1;
+EXPORT_SYMBOL(kaiser_enabled); /* for inlined TLB flush functions */
+
__visible
DEFINE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
@@ -167,8 +169,8 @@ static pte_t *kaiser_pagetable_walk(unsi
return pte_offset_kernel(pmd, address);
}
-int kaiser_add_user_map(const void *__start_addr, unsigned long size,
- unsigned long flags)
+static int kaiser_add_user_map(const void *__start_addr, unsigned long size,
+ unsigned long flags)
{
int ret = 0;
pte_t *pte;
@@ -177,6 +179,15 @@ int kaiser_add_user_map(const void *__st
unsigned long end_addr = PAGE_ALIGN(start_addr + size);
unsigned long target_address;
+ /*
+ * It is convenient for callers to pass in __PAGE_KERNEL etc,
+ * and there is no actual harm from setting _PAGE_GLOBAL, so
+ * long as CR4.PGE is not set. But it is nonetheless troubling
+ * to see Kaiser itself setting _PAGE_GLOBAL (now that "nokaiser"
+ * requires that not to be #defined to 0): so mask it off here.
+ */
+ flags &= ~_PAGE_GLOBAL;
+
for (; address < end_addr; address += PAGE_SIZE) {
target_address = get_pa_from_mapping(address);
if (target_address == -1) {
@@ -263,6 +274,8 @@ void __init kaiser_init(void)
{
int cpu;
+ if (!kaiser_enabled)
+ return;
kaiser_init_all_pgds();
for_each_possible_cpu(cpu) {
@@ -311,6 +324,8 @@ void __init kaiser_init(void)
/* Add a mapping to the shadow mapping, and synchronize the mappings */
int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags)
{
+ if (!kaiser_enabled)
+ return 0;
return kaiser_add_user_map((const void *)addr, size, flags);
}
@@ -322,6 +337,8 @@ void kaiser_remove_mapping(unsigned long
unsigned long addr, next;
pgd_t *pgd;
+ if (!kaiser_enabled)
+ return;
pgd = native_get_shadow_pgd(pgd_offset_k(start));
for (addr = start; addr < end; pgd++, addr = next) {
next = pgd_addr_end(addr, end);
@@ -343,6 +360,8 @@ static inline bool is_userspace_pgd(pgd_
pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
{
+ if (!kaiser_enabled)
+ return pgd;
/*
* Do we need to also populate the shadow pgd? Check _PAGE_USER to
* skip cases like kexec and EFI which make temporary low mappings.
@@ -399,4 +418,3 @@ void kaiser_flush_tlb_on_return_to_user(
X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET);
}
EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user);
-#endif /* CONFIG_KAISER */
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -345,16 +345,12 @@ static inline void _pgd_free(pgd_t *pgd)
}
#else
-#ifdef CONFIG_KAISER
/*
- * Instead of one pmd, we aquire two pmds. Being order-1, it is
+ * Instead of one pgd, Kaiser acquires two pgds. Being order-1, it is
* both 8k in size and 8k-aligned. That lets us just flip bit 12
* in a pointer to swap between the two 4k halves.
*/
-#define PGD_ALLOCATION_ORDER 1
-#else
-#define PGD_ALLOCATION_ORDER 0
-#endif
+#define PGD_ALLOCATION_ORDER kaiser_enabled
static inline pgd_t *_pgd_alloc(void)
{
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -39,8 +39,7 @@ static void load_new_mm_cr3(pgd_t *pgdir
{
unsigned long new_mm_cr3 = __pa(pgdir);
-#ifdef CONFIG_KAISER
- if (this_cpu_has(X86_FEATURE_PCID)) {
+ if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID)) {
/*
* We reuse the same PCID for different tasks, so we must
* flush all the entries for the PCID out when we change tasks.
@@ -57,7 +56,6 @@ static void load_new_mm_cr3(pgd_t *pgdir
new_mm_cr3 |= X86_CR3_PCID_KERN_FLUSH;
kaiser_flush_tlb_on_return_to_user();
}
-#endif /* CONFIG_KAISER */
/*
* Caution: many callers of this function expect
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -197,6 +197,9 @@
#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
+/* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
+#define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_KAISER w/o nokaiser */
+
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "x86/paravirt: Dont patch flush_tlb_single" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
x86/paravirt: Dont patch flush_tlb_single
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
x86-paravirt-dont-patch-flush_tlb_single.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Thomas Gleixner <tglx(a)linutronix.de>
Date: Mon, 4 Dec 2017 15:07:30 +0100
Subject: x86/paravirt: Dont patch flush_tlb_single
From: Thomas Gleixner <tglx(a)linutronix.de>
commit a035795499ca1c2bd1928808d1a156eda1420383 upstream
native_flush_tlb_single() will be changed with the upcoming
PAGE_TABLE_ISOLATION feature. This requires to have more code in
there than INVLPG.
Remove the paravirt patching for it.
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Reviewed-by: Josh Poimboeuf <jpoimboe(a)redhat.com>
Reviewed-by: Juergen Gross <jgross(a)suse.com>
Acked-by: Peter Zijlstra <peterz(a)infradead.org>
Cc: Andy Lutomirski <luto(a)kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky(a)oracle.com>
Cc: Borislav Petkov <bp(a)alien8.de>
Cc: Borislav Petkov <bpetkov(a)suse.de>
Cc: Brian Gerst <brgerst(a)gmail.com>
Cc: Dave Hansen <dave.hansen(a)intel.com>
Cc: Dave Hansen <dave.hansen(a)linux.intel.com>
Cc: David Laight <David.Laight(a)aculab.com>
Cc: Denys Vlasenko <dvlasenk(a)redhat.com>
Cc: Eduardo Valentin <eduval(a)amazon.com>
Cc: Greg KH <gregkh(a)linuxfoundation.org>
Cc: H. Peter Anvin <hpa(a)zytor.com>
Cc: Linus Torvalds <torvalds(a)linux-foundation.org>
Cc: Rik van Riel <riel(a)redhat.com>
Cc: Will Deacon <will.deacon(a)arm.com>
Cc: aliguori(a)amazon.com
Cc: daniel.gruss(a)iaik.tugraz.at
Cc: hughd(a)google.com
Cc: keescook(a)google.com
Cc: linux-mm(a)kvack.org
Cc: michael.schwarz(a)iaik.tugraz.at
Cc: moritz.lipp(a)iaik.tugraz.at
Cc: richard.fellner(a)student.tugraz.at
Link: https://lkml.kernel.org/r/20171204150606.828111617@linutronix.de
Signed-off-by: Ingo Molnar <mingo(a)kernel.org>
Acked-by: Borislav Petkov <bp(a)suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/kernel/paravirt_patch_64.c | 2 --
1 file changed, 2 deletions(-)
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -9,7 +9,6 @@ DEF_NATIVE(pv_irq_ops, save_fl, "pushfq;
DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
-DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)");
DEF_NATIVE(pv_cpu_ops, clts, "clts");
DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd");
@@ -62,7 +61,6 @@ unsigned native_patch(u8 type, u16 clobb
PATCH_SITE(pv_mmu_ops, read_cr3);
PATCH_SITE(pv_mmu_ops, write_cr3);
PATCH_SITE(pv_cpu_ops, clts);
- PATCH_SITE(pv_mmu_ops, flush_tlb_single);
PATCH_SITE(pv_cpu_ops, wbinvd);
#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
Patches currently in stable-queue which might be from tglx(a)linutronix.de are
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/x86-boot-add-early-cmdline-parsing-for-options-with-arguments.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "x86/kaiser: Move feature detection up" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
x86/kaiser: Move feature detection up
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
x86-kaiser-move-feature-detection-up.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Borislav Petkov <bp(a)suse.de>
Date: Mon, 25 Dec 2017 13:57:16 +0100
Subject: x86/kaiser: Move feature detection up
From: Borislav Petkov <bp(a)suse.de>
... before the first use of kaiser_enabled as otherwise funky
things happen:
about to get started...
(XEN) d0v0 Unhandled page fault fault/trap [#14, ec=0000]
(XEN) Pagetable walk from ffff88022a449090:
(XEN) L4[0x110] = 0000000229e0e067 0000000000001e0e
(XEN) L3[0x008] = 0000000000000000 ffffffffffffffff
(XEN) domain_crash_sync called from entry.S: fault at ffff82d08033fd08
entry.o#create_bounce_frame+0x135/0x14d
(XEN) Domain 0 (vcpu#0) crashed on cpu#0:
(XEN) ----[ Xen-4.9.1_02-3.21 x86_64 debug=n Not tainted ]----
(XEN) CPU: 0
(XEN) RIP: e033:[<ffffffff81007460>]
(XEN) RFLAGS: 0000000000000286 EM: 1 CONTEXT: pv guest (d0v0)
Signed-off-by: Borislav Petkov <bp(a)suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/kaiser.h | 2 ++
arch/x86/kernel/setup.c | 7 +++++++
arch/x86/mm/kaiser.c | 2 --
3 files changed, 9 insertions(+), 2 deletions(-)
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -96,8 +96,10 @@ DECLARE_PER_CPU(unsigned long, x86_cr3_p
extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
extern int kaiser_enabled;
+extern void __init kaiser_check_boottime_disable(void);
#else
#define kaiser_enabled 0
+static inline void __init kaiser_check_boottime_disable(void) {}
#endif /* CONFIG_KAISER */
/*
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -112,6 +112,7 @@
#include <asm/alternative.h>
#include <asm/prom.h>
#include <asm/microcode.h>
+#include <asm/kaiser.h>
/*
* max_low_pfn_mapped: highest direct mapped pfn under 4GB
@@ -1016,6 +1017,12 @@ void __init setup_arch(char **cmdline_p)
*/
init_hypervisor_platform();
+ /*
+ * This needs to happen right after XENPV is set on xen and
+ * kaiser_enabled is checked below in cleanup_highmap().
+ */
+ kaiser_check_boottime_disable();
+
x86_init.resources.probe_roms();
/* after parse_early_param, so could debug it */
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -311,8 +311,6 @@ void __init kaiser_init(void)
{
int cpu;
- kaiser_check_boottime_disable();
-
if (!kaiser_enabled)
return;
Patches currently in stable-queue which might be from bp(a)suse.de are
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/x86-kaiser-reenable-paravirt.patch
queue-4.4/x86-kaiser-rename-and-simplify-x86_feature_kaiser-handling.patch
queue-4.4/x86-kaiser-check-boottime-cmdline-params.patch
queue-4.4/x86-kaiser-move-feature-detection-up.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "x86/kaiser: Reenable PARAVIRT" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
x86/kaiser: Reenable PARAVIRT
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
x86-kaiser-reenable-paravirt.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Borislav Petkov <bp(a)suse.de>
Date: Tue, 2 Jan 2018 14:19:49 +0100
Subject: x86/kaiser: Reenable PARAVIRT
From: Borislav Petkov <bp(a)suse.de>
Now that the required bits have been addressed, reenable
PARAVIRT.
Signed-off-by: Borislav Petkov <bp(a)suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
security/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -34,7 +34,7 @@ config SECURITY
config KAISER
bool "Remove the kernel mapping in user mode"
default y
- depends on X86_64 && SMP && !PARAVIRT
+ depends on X86_64 && SMP
help
This enforces a strict kernel and user space isolation, in order
to close hardware side channels on kernel address information.
Patches currently in stable-queue which might be from bp(a)suse.de are
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/x86-kaiser-reenable-paravirt.patch
queue-4.4/x86-kaiser-rename-and-simplify-x86_feature_kaiser-handling.patch
queue-4.4/x86-kaiser-check-boottime-cmdline-params.patch
queue-4.4/x86-kaiser-move-feature-detection-up.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "x86/kaiser: Check boottime cmdline params" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
x86/kaiser: Check boottime cmdline params
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
x86-kaiser-check-boottime-cmdline-params.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Borislav Petkov <bp(a)suse.de>
Date: Tue, 2 Jan 2018 14:19:48 +0100
Subject: x86/kaiser: Check boottime cmdline params
From: Borislav Petkov <bp(a)suse.de>
AMD (and possibly other vendors) are not affected by the leak
KAISER is protecting against.
Keep the "nopti" for traditional reasons and add pti=<on|off|auto>
like upstream.
Signed-off-by: Borislav Petkov <bp(a)suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
Documentation/kernel-parameters.txt | 6 +++
arch/x86/mm/kaiser.c | 59 +++++++++++++++++++++++++-----------
2 files changed, 47 insertions(+), 18 deletions(-)
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3056,6 +3056,12 @@ bytes respectively. Such letter suffixes
pt. [PARIDE]
See Documentation/blockdev/paride.txt.
+ pti= [X86_64]
+ Control KAISER user/kernel address space isolation:
+ on - enable
+ off - disable
+ auto - default setting
+
pty.legacy_count=
[KNL] Number of legacy pty's. Overwrites compiled-in
default number.
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -16,6 +16,7 @@
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/desc.h>
+#include <asm/cmdline.h>
int kaiser_enabled __read_mostly = 1;
EXPORT_SYMBOL(kaiser_enabled); /* for inlined TLB flush functions */
@@ -264,6 +265,43 @@ static void __init kaiser_init_all_pgds(
WARN_ON(__ret); \
} while (0)
+void __init kaiser_check_boottime_disable(void)
+{
+ bool enable = true;
+ char arg[5];
+ int ret;
+
+ ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
+ if (ret > 0) {
+ if (!strncmp(arg, "on", 2))
+ goto enable;
+
+ if (!strncmp(arg, "off", 3))
+ goto disable;
+
+ if (!strncmp(arg, "auto", 4))
+ goto skip;
+ }
+
+ if (cmdline_find_option_bool(boot_command_line, "nopti"))
+ goto disable;
+
+skip:
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ goto disable;
+
+enable:
+ if (enable)
+ setup_force_cpu_cap(X86_FEATURE_KAISER);
+
+ return;
+
+disable:
+ pr_info("Kernel/User page tables isolation: disabled\n");
+ kaiser_enabled = 0;
+ setup_clear_cpu_cap(X86_FEATURE_KAISER);
+}
+
/*
* If anything in here fails, we will likely die on one of the
* first kernel->user transitions and init will die. But, we
@@ -275,12 +313,10 @@ void __init kaiser_init(void)
{
int cpu;
- if (!kaiser_enabled) {
- setup_clear_cpu_cap(X86_FEATURE_KAISER);
- return;
- }
+ kaiser_check_boottime_disable();
- setup_force_cpu_cap(X86_FEATURE_KAISER);
+ if (!kaiser_enabled)
+ return;
kaiser_init_all_pgds();
@@ -424,16 +460,3 @@ void kaiser_flush_tlb_on_return_to_user(
X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET);
}
EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user);
-
-static int __init x86_nokaiser_setup(char *s)
-{
- /* nopti doesn't accept parameters */
- if (s)
- return -EINVAL;
-
- kaiser_enabled = 0;
- pr_info("Kernel/User page tables isolation: disabled\n");
-
- return 0;
-}
-early_param("nopti", x86_nokaiser_setup);
Patches currently in stable-queue which might be from bp(a)suse.de are
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/x86-kaiser-reenable-paravirt.patch
queue-4.4/x86-kaiser-rename-and-simplify-x86_feature_kaiser-handling.patch
queue-4.4/x86-kaiser-check-boottime-cmdline-params.patch
queue-4.4/x86-kaiser-move-feature-detection-up.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 27 Aug 2017 16:24:27 -0700
Subject: kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user
From: Hugh Dickins <hughd(a)google.com>
Mostly this commit is just unshouting X86_CR3_PCID_KERN_VAR and
X86_CR3_PCID_USER_VAR: we usually name variables in lower-case.
But why does x86_cr3_pcid_noflush need to be __aligned(PAGE_SIZE)?
Ah, it's a leftover from when kaiser_add_user_map() once complained
about mapping the same page twice. Make it __read_mostly instead.
(I'm a little uneasy about all the unrelated data which shares its
page getting user-mapped too, but that was so before, and not a big
deal: though we call it user-mapped, it's not mapped with _PAGE_USER.)
And there is a little change around the two calls to do_nmi().
Previously they set the NOFLUSH bit (if PCID supported) when
forcing to kernel context before do_nmi(); now they also have the
NOFLUSH bit set (if PCID supported) when restoring context after:
nothing done in do_nmi() should require a TLB to be flushed here.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 8 ++++----
arch/x86/include/asm/kaiser.h | 11 +++++------
arch/x86/mm/kaiser.c | 13 +++++++------
3 files changed, 16 insertions(+), 16 deletions(-)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1290,11 +1290,11 @@ ENTRY(nmi)
/* Unconditionally use kernel CR3 for do_nmi() */
/* %rax is saved above, so OK to clobber here */
movq %cr3, %rax
+ /* If PCID enabled, NOFLUSH now and NOFLUSH on return */
+ orq x86_cr3_pcid_noflush, %rax
pushq %rax
/* mask off "user" bit of pgd address and 12 PCID bits: */
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
- /* Add back kernel PCID and "no flush" bit */
- orq X86_CR3_PCID_KERN_VAR, %rax
movq %rax, %cr3
#endif
call do_nmi
@@ -1534,11 +1534,11 @@ end_repeat_nmi:
/* Unconditionally use kernel CR3 for do_nmi() */
/* %rax is saved above, so OK to clobber here */
movq %cr3, %rax
+ /* If PCID enabled, NOFLUSH now and NOFLUSH on return */
+ orq x86_cr3_pcid_noflush, %rax
pushq %rax
/* mask off "user" bit of pgd address and 12 PCID bits: */
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
- /* Add back kernel PCID and "no flush" bit */
- orq X86_CR3_PCID_KERN_VAR, %rax
movq %rax, %cr3
#endif
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -25,7 +25,7 @@
.macro _SWITCH_TO_KERNEL_CR3 reg
movq %cr3, \reg
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
-orq X86_CR3_PCID_KERN_VAR, \reg
+orq x86_cr3_pcid_noflush, \reg
movq \reg, %cr3
.endm
@@ -37,11 +37,10 @@ movq \reg, %cr3
* not enabled): so that the one register can update both memory and cr3.
*/
movq %cr3, \reg
-andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
-orq PER_CPU_VAR(X86_CR3_PCID_USER_VAR), \reg
+orq PER_CPU_VAR(x86_cr3_pcid_user), \reg
js 9f
/* FLUSH this time, reset to NOFLUSH for next time (if PCID enabled) */
-movb \regb, PER_CPU_VAR(X86_CR3_PCID_USER_VAR+7)
+movb \regb, PER_CPU_VAR(x86_cr3_pcid_user+7)
9:
movq \reg, %cr3
.endm
@@ -94,8 +93,8 @@ movq PER_CPU_VAR(unsafe_stack_register_b
*/
DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
-extern unsigned long X86_CR3_PCID_KERN_VAR;
-DECLARE_PER_CPU(unsigned long, X86_CR3_PCID_USER_VAR);
+extern unsigned long x86_cr3_pcid_noflush;
+DECLARE_PER_CPU(unsigned long, x86_cr3_pcid_user);
extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -29,8 +29,8 @@ DEFINE_PER_CPU_USER_MAPPED(unsigned long
* This is also handy because systems that do not support PCIDs
* just end up or'ing a 0 into their CR3, which does no harm.
*/
-__aligned(PAGE_SIZE) unsigned long X86_CR3_PCID_KERN_VAR;
-DEFINE_PER_CPU(unsigned long, X86_CR3_PCID_USER_VAR);
+unsigned long x86_cr3_pcid_noflush __read_mostly;
+DEFINE_PER_CPU(unsigned long, x86_cr3_pcid_user);
/*
* At runtime, the only things we map are some things for CPU
@@ -304,7 +304,8 @@ void __init kaiser_init(void)
sizeof(gate_desc) * NR_VECTORS,
__PAGE_KERNEL);
- kaiser_add_user_map_early(&X86_CR3_PCID_KERN_VAR, PAGE_SIZE,
+ kaiser_add_user_map_early(&x86_cr3_pcid_noflush,
+ sizeof(x86_cr3_pcid_noflush),
__PAGE_KERNEL);
}
@@ -384,8 +385,8 @@ void kaiser_setup_pcid(void)
* These variables are used by the entry/exit
* code to change PCID and pgd and TLB flushing.
*/
- X86_CR3_PCID_KERN_VAR = kern_cr3;
- this_cpu_write(X86_CR3_PCID_USER_VAR, user_cr3);
+ x86_cr3_pcid_noflush = kern_cr3;
+ this_cpu_write(x86_cr3_pcid_user, user_cr3);
}
/*
@@ -395,7 +396,7 @@ void kaiser_setup_pcid(void)
*/
void kaiser_flush_tlb_on_return_to_user(void)
{
- this_cpu_write(X86_CR3_PCID_USER_VAR,
+ this_cpu_write(x86_cr3_pcid_user,
X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET);
}
EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user);
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: vmstat show NR_KAISERTABLE as nr_overhead" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: vmstat show NR_KAISERTABLE as nr_overhead
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sat, 9 Sep 2017 21:27:32 -0700
Subject: kaiser: vmstat show NR_KAISERTABLE as nr_overhead
From: Hugh Dickins <hughd(a)google.com>
The kaiser update made an interesting choice, never to free any shadow
page tables. Contention on global spinlock was worrying, particularly
with it held across page table scans when freeing. Something had to be
done: I was going to add refcounting; but simply never to free them is
an appealing choice, minimizing contention without complicating the code
(the more a page table is found already, the less the spinlock is used).
But leaking pages in this way is also a worry: can we get away with it?
At the very least, we need a count to show how bad it actually gets:
in principle, one might end up wasting about 1/256 of memory that way
(1/512 for when direct-mapped pages have to be user-mapped, plus 1/512
for when they are user-mapped from the vmalloc area on another occasion
(but we don't have vmalloc'ed stacks, so only large ldts are vmalloc'ed).
Add per-cpu stat NR_KAISERTABLE: including 256 at startup for the
shared pgd entries, and 1 for each intermediate page table added
thereafter for user-mapping - but leave out the 1 per mm, for its
shadow pgd, because that distracts from the monotonic increase.
Shown in /proc/vmstat as nr_overhead (0 if kaiser not enabled).
In practice, it doesn't look so bad so far: more like 1/12000 after
nine hours of gtests below; and movable pageblock segregation should
tend to cluster the kaiser tables into a subset of the address space
(if not, they will be bad for compaction too). But production may
tell a different story: keep an eye on this number, and bring back
lighter freeing if it gets out of control (maybe a shrinker).
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/kaiser.c | 16 +++++++++++-----
include/linux/mmzone.h | 3 ++-
mm/vmstat.c | 1 +
3 files changed, 14 insertions(+), 6 deletions(-)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -122,9 +122,11 @@ static pte_t *kaiser_pagetable_walk(unsi
if (!new_pmd_page)
return NULL;
spin_lock(&shadow_table_allocation_lock);
- if (pud_none(*pud))
+ if (pud_none(*pud)) {
set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
- else
+ __inc_zone_page_state(virt_to_page((void *)
+ new_pmd_page), NR_KAISERTABLE);
+ } else
free_page(new_pmd_page);
spin_unlock(&shadow_table_allocation_lock);
}
@@ -140,9 +142,11 @@ static pte_t *kaiser_pagetable_walk(unsi
if (!new_pte_page)
return NULL;
spin_lock(&shadow_table_allocation_lock);
- if (pmd_none(*pmd))
+ if (pmd_none(*pmd)) {
set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page)));
- else
+ __inc_zone_page_state(virt_to_page((void *)
+ new_pte_page), NR_KAISERTABLE);
+ } else
free_page(new_pte_page);
spin_unlock(&shadow_table_allocation_lock);
}
@@ -206,11 +210,13 @@ static void __init kaiser_init_all_pgds(
pgd = native_get_shadow_pgd(pgd_offset_k((unsigned long )0));
for (i = PTRS_PER_PGD / 2; i < PTRS_PER_PGD; i++) {
pgd_t new_pgd;
- pud_t *pud = pud_alloc_one(&init_mm, PAGE_OFFSET + i * PGDIR_SIZE);
+ pud_t *pud = pud_alloc_one(&init_mm,
+ PAGE_OFFSET + i * PGDIR_SIZE);
if (!pud) {
WARN_ON(1);
break;
}
+ inc_zone_page_state(virt_to_page(pud), NR_KAISERTABLE);
new_pgd = __pgd(_KERNPG_TABLE |__pa(pud));
/*
* Make sure not to stomp on some other pgd entry.
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -131,8 +131,9 @@ enum zone_stat_item {
NR_SLAB_RECLAIMABLE,
NR_SLAB_UNRECLAIMABLE,
NR_PAGETABLE, /* used for pagetables */
- NR_KERNEL_STACK,
/* Second 128 byte cacheline */
+ NR_KERNEL_STACK,
+ NR_KAISERTABLE,
NR_UNSTABLE_NFS, /* NFS unstable pages */
NR_BOUNCE,
NR_VMSCAN_WRITE,
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -736,6 +736,7 @@ const char * const vmstat_text[] = {
"nr_slab_unreclaimable",
"nr_page_table_pages",
"nr_kernel_stack",
+ "nr_overhead",
"nr_unstable",
"nr_bounce",
"nr_vmscan_write",
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: use ALTERNATIVE instead of x86_cr3_pcid_noflush" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: use ALTERNATIVE instead of x86_cr3_pcid_noflush
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Tue, 3 Oct 2017 20:49:04 -0700
Subject: kaiser: use ALTERNATIVE instead of x86_cr3_pcid_noflush
From: Hugh Dickins <hughd(a)google.com>
Now that we're playing the ALTERNATIVE game, use that more efficient
method: instead of user-mapping an extra page, and reading an extra
cacheline each time for x86_cr3_pcid_noflush.
Neel has found that __stringify(bts $X86_CR3_PCID_NOFLUSH_BIT, %rax)
is a working substitute for the "bts $63, %rax" in these ALTERNATIVEs;
but the one line with $63 in looks clearer, so let's stick with that.
Worried about what happens with an ALTERNATIVE between the jump and
jump label in another ALTERNATIVE? I was, but have checked the
combinations in SWITCH_KERNEL_CR3_NO_STACK at entry_SYSCALL_64,
and it does a good job.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 7 ++++---
arch/x86/include/asm/kaiser.h | 6 +++---
arch/x86/mm/kaiser.c | 11 +----------
3 files changed, 8 insertions(+), 16 deletions(-)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1056,7 +1056,8 @@ ENTRY(paranoid_entry)
jz 2f
orl $2, %ebx
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
- orq x86_cr3_pcid_noflush, %rax
+ /* If PCID enabled, set X86_CR3_PCID_NOFLUSH_BIT */
+ ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID
movq %rax, %cr3
2:
#endif
@@ -1318,7 +1319,7 @@ ENTRY(nmi)
/* %rax is saved above, so OK to clobber here */
ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER
/* If PCID enabled, NOFLUSH now and NOFLUSH on return */
- orq x86_cr3_pcid_noflush, %rax
+ ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID
pushq %rax
/* mask off "user" bit of pgd address and 12 PCID bits: */
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
@@ -1562,7 +1563,7 @@ end_repeat_nmi:
/* %rax is saved above, so OK to clobber here */
ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER
/* If PCID enabled, NOFLUSH now and NOFLUSH on return */
- orq x86_cr3_pcid_noflush, %rax
+ ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID
pushq %rax
/* mask off "user" bit of pgd address and 12 PCID bits: */
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -25,7 +25,8 @@
.macro _SWITCH_TO_KERNEL_CR3 reg
movq %cr3, \reg
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
-orq x86_cr3_pcid_noflush, \reg
+/* If PCID enabled, set X86_CR3_PCID_NOFLUSH_BIT */
+ALTERNATIVE "", "bts $63, \reg", X86_FEATURE_PCID
movq \reg, %cr3
.endm
@@ -39,7 +40,7 @@ movq \reg, %cr3
movq %cr3, \reg
orq PER_CPU_VAR(x86_cr3_pcid_user), \reg
js 9f
-/* FLUSH this time, reset to NOFLUSH for next time (if PCID enabled) */
+/* If PCID enabled, FLUSH this time, reset to NOFLUSH for next time */
movb \regb, PER_CPU_VAR(x86_cr3_pcid_user+7)
9:
movq \reg, %cr3
@@ -90,7 +91,6 @@ movq PER_CPU_VAR(unsafe_stack_register_b
*/
DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
-extern unsigned long x86_cr3_pcid_noflush;
DECLARE_PER_CPU(unsigned long, x86_cr3_pcid_user);
extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -32,7 +32,6 @@ DEFINE_PER_CPU_USER_MAPPED(unsigned long
* This is also handy because systems that do not support PCIDs
* just end up or'ing a 0 into their CR3, which does no harm.
*/
-unsigned long x86_cr3_pcid_noflush __read_mostly;
DEFINE_PER_CPU(unsigned long, x86_cr3_pcid_user);
/*
@@ -357,10 +356,6 @@ void __init kaiser_init(void)
kaiser_add_user_map_early(&debug_idt_table,
sizeof(gate_desc) * NR_VECTORS,
__PAGE_KERNEL);
-
- kaiser_add_user_map_early(&x86_cr3_pcid_noflush,
- sizeof(x86_cr3_pcid_noflush),
- __PAGE_KERNEL);
}
/* Add a mapping to the shadow mapping, and synchronize the mappings */
@@ -434,18 +429,14 @@ pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp,
void kaiser_setup_pcid(void)
{
- unsigned long kern_cr3 = 0;
unsigned long user_cr3 = KAISER_SHADOW_PGD_OFFSET;
- if (this_cpu_has(X86_FEATURE_PCID)) {
- kern_cr3 |= X86_CR3_PCID_KERN_NOFLUSH;
+ if (this_cpu_has(X86_FEATURE_PCID))
user_cr3 |= X86_CR3_PCID_USER_NOFLUSH;
- }
/*
* These variables are used by the entry/exit
* code to change PCID and pgd and TLB flushing.
*/
- x86_cr3_pcid_noflush = kern_cr3;
this_cpu_write(x86_cr3_pcid_user, user_cr3);
}
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: tidied up kaiser_add/remove_mapping slightly" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: tidied up kaiser_add/remove_mapping slightly
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 3 Sep 2017 19:23:08 -0700
Subject: kaiser: tidied up kaiser_add/remove_mapping slightly
From: Hugh Dickins <hughd(a)google.com>
Yes, unmap_pud_range_nofree()'s declaration ought to be in a
header file really, but I'm not sure we want to use it anyway:
so for now just declare it inside kaiser_remove_mapping().
And there doesn't seem to be such a thing as unmap_p4d_range(),
even in a 5-level paging tree.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/kaiser.c | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -286,8 +286,7 @@ void __init kaiser_init(void)
__PAGE_KERNEL);
}
-extern void unmap_pud_range_nofree(pgd_t *pgd, unsigned long start, unsigned long end);
-// add a mapping to the shadow-mapping, and synchronize the mappings
+/* Add a mapping to the shadow mapping, and synchronize the mappings */
int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags)
{
return kaiser_add_user_map((const void *)addr, size, flags);
@@ -295,15 +294,13 @@ int kaiser_add_mapping(unsigned long add
void kaiser_remove_mapping(unsigned long start, unsigned long size)
{
+ extern void unmap_pud_range_nofree(pgd_t *pgd,
+ unsigned long start, unsigned long end);
unsigned long end = start + size;
unsigned long addr;
for (addr = start; addr < end; addr += PGDIR_SIZE) {
pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(addr));
- /*
- * unmap_p4d_range() handles > P4D_SIZE unmaps,
- * so no need to trim 'end'.
- */
unmap_pud_range_nofree(pgd, addr, end);
}
}
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: tidied up asm/kaiser.h somewhat" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: tidied up asm/kaiser.h somewhat
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-tidied-up-asm-kaiser.h-somewhat.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 3 Sep 2017 19:18:07 -0700
Subject: kaiser: tidied up asm/kaiser.h somewhat
From: Hugh Dickins <hughd(a)google.com>
Mainly deleting a surfeit of blank lines, and reflowing header comment.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/kaiser.h | 32 +++++++++++++-------------------
1 file changed, 13 insertions(+), 19 deletions(-)
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -1,15 +1,17 @@
#ifndef _ASM_X86_KAISER_H
#define _ASM_X86_KAISER_H
-
-/* This file includes the definitions for the KAISER feature.
- * KAISER is a counter measure against x86_64 side channel attacks on the kernel virtual memory.
- * It has a shodow-pgd for every process. the shadow-pgd has a minimalistic kernel-set mapped,
- * but includes the whole user memory. Within a kernel context switch, or when an interrupt is handled,
- * the pgd is switched to the normal one. When the system switches to user mode, the shadow pgd is enabled.
- * By this, the virtual memory chaches are freed, and the user may not attack the whole kernel memory.
+/*
+ * This file includes the definitions for the KAISER feature.
+ * KAISER is a counter measure against x86_64 side channel attacks on
+ * the kernel virtual memory. It has a shadow pgd for every process: the
+ * shadow pgd has a minimalistic kernel-set mapped, but includes the whole
+ * user memory. Within a kernel context switch, or when an interrupt is handled,
+ * the pgd is switched to the normal one. When the system switches to user mode,
+ * the shadow pgd is enabled. By this, the virtual memory caches are freed,
+ * and the user may not attack the whole kernel memory.
*
- * A minimalistic kernel mapping holds the parts needed to be mapped in user mode, as the entry/exit functions
- * of the user space, or the stacks.
+ * A minimalistic kernel mapping holds the parts needed to be mapped in user
+ * mode, such as the entry/exit functions of the user space, or the stacks.
*/
#ifdef __ASSEMBLY__
#ifdef CONFIG_KAISER
@@ -48,13 +50,10 @@ _SWITCH_TO_KERNEL_CR3 %rax
movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
.endm
-
.macro SWITCH_USER_CR3_NO_STACK
-
movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)
_SWITCH_TO_USER_CR3 %rax
movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
-
.endm
#else /* CONFIG_KAISER */
@@ -72,7 +71,6 @@ movq PER_CPU_VAR(unsafe_stack_register_b
#else /* __ASSEMBLY__ */
-
#ifdef CONFIG_KAISER
/*
* Upon kernel/user mode switch, it may happen that the address
@@ -80,7 +78,6 @@ movq PER_CPU_VAR(unsafe_stack_register_b
* stored. To change the address space, another register is
* needed. A register therefore has to be stored/restored.
*/
-
DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
/**
@@ -95,7 +92,6 @@ DECLARE_PER_CPU_USER_MAPPED(unsigned lon
*/
extern int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags);
-
/**
* kaiser_remove_mapping - unmap a virtual memory part of the shadow mapping
* @addr: the start address of the range
@@ -104,12 +100,12 @@ extern int kaiser_add_mapping(unsigned l
extern void kaiser_remove_mapping(unsigned long start, unsigned long size);
/**
- * kaiser_initialize_mapping - Initalize the shadow mapping
+ * kaiser_init - Initialize the shadow mapping
*
* Most parts of the shadow mapping can be mapped upon boot
* time. Only per-process things like the thread stacks
* or a new LDT have to be mapped at runtime. These boot-
- * time mappings are permanent and nevertunmapped.
+ * time mappings are permanent and never unmapped.
*/
extern void kaiser_init(void);
@@ -117,6 +113,4 @@ extern void kaiser_init(void);
#endif /* __ASSEMBLY */
-
-
#endif /* _ASM_X86_KAISER_H */
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-stack-map-page_size-at-thread_size-page_size.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 3 Sep 2017 18:57:03 -0700
Subject: kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE
From: Hugh Dickins <hughd(a)google.com>
Kaiser only needs to map one page of the stack; and
kernel/fork.c did not build on powerpc (no __PAGE_KERNEL).
It's all cleaner if linux/kaiser.h provides kaiser_map_thread_stack()
and kaiser_unmap_thread_stack() wrappers around asm/kaiser.h's
kaiser_add_mapping() and kaiser_remove_mapping(). And use
linux/kaiser.h in init/main.c to avoid the #ifdefs there.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
include/linux/kaiser.h | 40 +++++++++++++++++++++++++++++++++-------
init/main.c | 6 +-----
kernel/fork.c | 7 ++-----
3 files changed, 36 insertions(+), 17 deletions(-)
--- a/include/linux/kaiser.h
+++ b/include/linux/kaiser.h
@@ -1,26 +1,52 @@
-#ifndef _INCLUDE_KAISER_H
-#define _INCLUDE_KAISER_H
+#ifndef _LINUX_KAISER_H
+#define _LINUX_KAISER_H
#ifdef CONFIG_KAISER
#include <asm/kaiser.h>
+
+static inline int kaiser_map_thread_stack(void *stack)
+{
+ /*
+ * Map that page of kernel stack on which we enter from user context.
+ */
+ return kaiser_add_mapping((unsigned long)stack +
+ THREAD_SIZE - PAGE_SIZE, PAGE_SIZE, __PAGE_KERNEL);
+}
+
+static inline void kaiser_unmap_thread_stack(void *stack)
+{
+ /*
+ * Note: may be called even when kaiser_map_thread_stack() failed.
+ */
+ kaiser_remove_mapping((unsigned long)stack +
+ THREAD_SIZE - PAGE_SIZE, PAGE_SIZE);
+}
#else
/*
* These stubs are used whenever CONFIG_KAISER is off, which
- * includes architectures that support KAISER, but have it
- * disabled.
+ * includes architectures that support KAISER, but have it disabled.
*/
static inline void kaiser_init(void)
{
}
-static inline void kaiser_remove_mapping(unsigned long start, unsigned long size)
+static inline int kaiser_add_mapping(unsigned long addr,
+ unsigned long size, unsigned long flags)
+{
+ return 0;
+}
+static inline void kaiser_remove_mapping(unsigned long start,
+ unsigned long size)
{
}
-static inline int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags)
+static inline int kaiser_map_thread_stack(void *stack)
{
return 0;
}
+static inline void kaiser_unmap_thread_stack(void *stack)
+{
+}
#endif /* !CONFIG_KAISER */
-#endif /* _INCLUDE_KAISER_H */
+#endif /* _LINUX_KAISER_H */
--- a/init/main.c
+++ b/init/main.c
@@ -81,15 +81,13 @@
#include <linux/integrity.h>
#include <linux/proc_ns.h>
#include <linux/io.h>
+#include <linux/kaiser.h>
#include <asm/io.h>
#include <asm/bugs.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>
-#ifdef CONFIG_KAISER
-#include <asm/kaiser.h>
-#endif
static int kernel_init(void *);
@@ -495,9 +493,7 @@ static void __init mm_init(void)
pgtable_init();
vmalloc_init();
ioremap_huge_init();
-#ifdef CONFIG_KAISER
kaiser_init();
-#endif
}
asmlinkage __visible void __init start_kernel(void)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -168,12 +168,9 @@ static struct thread_info *alloc_thread_
return page ? page_address(page) : NULL;
}
-extern void kaiser_remove_mapping(unsigned long start_addr, unsigned long size);
static inline void free_thread_info(struct thread_info *ti)
{
-#ifdef CONFIG_KAISER
- kaiser_remove_mapping((unsigned long)ti, THREAD_SIZE);
-#endif
+ kaiser_unmap_thread_stack(ti);
free_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER);
}
# else
@@ -358,7 +355,7 @@ static struct task_struct *dup_task_stru
tsk->stack = ti;
- err= kaiser_add_mapping((unsigned long)tsk->stack, THREAD_SIZE, __PAGE_KERNEL);
+ err = kaiser_map_thread_stack(tsk->stack);
if (err)
goto free_ti;
#ifdef CONFIG_SECCOMP
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: PCID 0 for kernel and 128 for user" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: PCID 0 for kernel and 128 for user
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-pcid-0-for-kernel-and-128-for-user.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Fri, 8 Sep 2017 19:26:30 -0700
Subject: kaiser: PCID 0 for kernel and 128 for user
From: Hugh Dickins <hughd(a)google.com>
Why was 4 chosen for kernel PCID and 6 for user PCID?
No good reason in a backport where PCIDs are only used for Kaiser.
If we continue with those, then we shall need to add Andy Lutomirski's
4.13 commit 6c690ee1039b ("x86/mm: Split read_cr3() into read_cr3_pa()
and __read_cr3()"), which deals with the problem of read_cr3() callers
finding stray bits in the cr3 that they expected to be page-aligned;
and for hibernation, his 4.14 commit f34902c5c6c0 ("x86/hibernate/64:
Mask off CR3's PCID bits in the saved CR3").
But if 0 is used for kernel PCID, then there's no need to add in those
commits - whenever the kernel looks, it sees 0 in the lower bits; and
0 for kernel seems an obvious choice.
And I naughtily propose 128 for user PCID. Because there's a place
in _SWITCH_TO_USER_CR3 where it takes note of the need for TLB FLUSH,
but needs to reset that to NOFLUSH for the next occasion. Currently
it does so with a "movb $(0x80)" into the high byte of the per-cpu
quadword, but that will cause a machine without PCID support to crash.
Now, if %al just happened to have 0x80 in it at that point, on a
machine with PCID support, but 0 on a machine without PCID support...
(That will go badly wrong once the pgd can be at a physical address
above 2^56, but even with 5-level paging, physical goes up to 2^52.)
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/kaiser.h | 19 ++++++++++++-------
arch/x86/include/asm/pgtable_types.h | 7 ++++---
arch/x86/mm/tlb.c | 3 +++
3 files changed, 19 insertions(+), 10 deletions(-)
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -29,14 +29,19 @@ orq X86_CR3_PCID_KERN_VAR, \reg
movq \reg, %cr3
.endm
-.macro _SWITCH_TO_USER_CR3 reg
+.macro _SWITCH_TO_USER_CR3 reg regb
+/*
+ * regb must be the low byte portion of reg: because we have arranged
+ * for the low byte of the user PCID to serve as the high byte of NOFLUSH
+ * (0x80 for each when PCID is enabled, or 0x00 when PCID and NOFLUSH are
+ * not enabled): so that the one register can update both memory and cr3.
+ */
movq %cr3, \reg
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
orq PER_CPU_VAR(X86_CR3_PCID_USER_VAR), \reg
js 9f
-// FLUSH this time, reset to NOFLUSH for next time
-// But if nopcid? Consider using 0x80 for user pcid?
-movb $(0x80), PER_CPU_VAR(X86_CR3_PCID_USER_VAR+7)
+/* FLUSH this time, reset to NOFLUSH for next time (if PCID enabled) */
+movb \regb, PER_CPU_VAR(X86_CR3_PCID_USER_VAR+7)
9:
movq \reg, %cr3
.endm
@@ -49,7 +54,7 @@ popq %rax
.macro SWITCH_USER_CR3
pushq %rax
-_SWITCH_TO_USER_CR3 %rax
+_SWITCH_TO_USER_CR3 %rax %al
popq %rax
.endm
@@ -61,7 +66,7 @@ movq PER_CPU_VAR(unsafe_stack_register_b
.macro SWITCH_USER_CR3_NO_STACK
movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)
-_SWITCH_TO_USER_CR3 %rax
+_SWITCH_TO_USER_CR3 %rax %al
movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
.endm
@@ -69,7 +74,7 @@ movq PER_CPU_VAR(unsafe_stack_register_b
.macro SWITCH_KERNEL_CR3 reg
.endm
-.macro SWITCH_USER_CR3 reg
+.macro SWITCH_USER_CR3 reg regb
.endm
.macro SWITCH_USER_CR3_NO_STACK
.endm
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -111,16 +111,17 @@
/* Mask for all the PCID-related bits in CR3: */
#define X86_CR3_PCID_MASK (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_MASK)
+#define X86_CR3_PCID_ASID_KERN (_AC(0x0,UL))
+
#if defined(CONFIG_KAISER) && defined(CONFIG_X86_64)
-#define X86_CR3_PCID_ASID_KERN (_AC(0x4,UL))
-#define X86_CR3_PCID_ASID_USER (_AC(0x6,UL))
+/* Let X86_CR3_PCID_ASID_USER be usable for the X86_CR3_PCID_NOFLUSH bit */
+#define X86_CR3_PCID_ASID_USER (_AC(0x80,UL))
#define X86_CR3_PCID_KERN_FLUSH (X86_CR3_PCID_ASID_KERN)
#define X86_CR3_PCID_USER_FLUSH (X86_CR3_PCID_ASID_USER)
#define X86_CR3_PCID_KERN_NOFLUSH (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_KERN)
#define X86_CR3_PCID_USER_NOFLUSH (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_USER)
#else
-#define X86_CR3_PCID_ASID_KERN (_AC(0x0,UL))
#define X86_CR3_PCID_ASID_USER (_AC(0x0,UL))
/*
* PCIDs are unsupported on 32-bit and none of these bits can be
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -50,6 +50,9 @@ static void load_new_mm_cr3(pgd_t *pgdir
* invpcid_flush_single_context(X86_CR3_PCID_ASID_USER) could
* do it here, but can only be used if X86_FEATURE_INVPCID is
* available - and many machines support pcid without invpcid.
+ *
+ * The line below is a no-op: X86_CR3_PCID_KERN_FLUSH is now 0;
+ * but keep that line in there in case something changes.
*/
new_mm_cr3 |= X86_CR3_PCID_KERN_FLUSH;
kaiser_flush_tlb_on_return_to_user();
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: paranoid_entry pass cr3 need to paranoid_exit" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: paranoid_entry pass cr3 need to paranoid_exit
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Tue, 26 Sep 2017 18:43:07 -0700
Subject: kaiser: paranoid_entry pass cr3 need to paranoid_exit
From: Hugh Dickins <hughd(a)google.com>
Neel Natu points out that paranoid_entry() was wrong to assume that
an entry that did not need swapgs would not need SWITCH_KERNEL_CR3:
paranoid_entry (used for debug breakpoint, int3, double fault or MCE;
though I think it's only the MCE case that is cause for concern here)
can break in at an awkward time, between cr3 switch and swapgs, but
its handling always needs kernel gs and kernel cr3.
Easy to fix in itself, but paranoid_entry() also needs to convey to
paranoid_exit() (and my reading of macro idtentry says paranoid_entry
and paranoid_exit are always paired) how to restore the prior state.
The swapgs state is already conveyed by %ebx (0 or 1), so extend that
also to convey when SWITCH_USER_CR3 will be needed (2 or 3).
(Yes, I'd much prefer that 0 meant no swapgs, whereas it's the other
way round: and a convention shared with error_entry() and error_exit(),
which I don't want to touch. Perhaps I should have inverted the bit
for switch cr3 too, but did not.)
paranoid_exit() would be straightforward, except for TRACE_IRQS: it
did TRACE_IRQS_IRETQ when doing swapgs, but TRACE_IRQS_IRETQ_DEBUG
when not: which is it supposed to use when SWITCH_USER_CR3 is split
apart from that? As best as I can determine, commit 5963e317b1e9
("ftrace/x86: Do not change stacks in DEBUG when calling lockdep")
missed the swapgs case, and should have used TRACE_IRQS_IRETQ_DEBUG
there too (the discrepancy has nothing to do with the liberal use
of _NO_STACK and _UNSAFE_STACK hereabouts: TRACE_IRQS_OFF_DEBUG has
just been used in all cases); discrepancy lovingly preserved across
several paranoid_exit() cleanups, but I'm now removing it.
Neel further indicates that to use SWITCH_USER_CR3_NO_STACK there in
paranoid_exit() is now not only unnecessary but unsafe: might corrupt
syscall entry's unsafe_stack_register_backup of %rax. Just use
SWITCH_USER_CR3: and delete SWITCH_USER_CR3_NO_STACK altogether,
before we make the mistake of using it again.
hughd adds: this commit fixes an issue in the Kaiser-without-PCIDs
part of the series, and ought to be moved earlier, if you decided
to make a release of Kaiser-without-PCIDs.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 46 ++++++++++++++++++++++++++++++++----------
arch/x86/include/asm/kaiser.h | 8 -------
2 files changed, 36 insertions(+), 18 deletions(-)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1025,7 +1025,11 @@ idtentry machine_check has_error_cod
/*
* Save all registers in pt_regs, and switch gs if needed.
* Use slow, but surefire "are we in kernel?" check.
- * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
+ *
+ * Return: ebx=0: needs swapgs but not SWITCH_USER_CR3 in paranoid_exit
+ * ebx=1: needs neither swapgs nor SWITCH_USER_CR3 in paranoid_exit
+ * ebx=2: needs both swapgs and SWITCH_USER_CR3 in paranoid_exit
+ * ebx=3: needs SWITCH_USER_CR3 but not swapgs in paranoid_exit
*/
ENTRY(paranoid_entry)
cld
@@ -1037,9 +1041,26 @@ ENTRY(paranoid_entry)
testl %edx, %edx
js 1f /* negative -> in kernel */
SWAPGS
- SWITCH_KERNEL_CR3
xorl %ebx, %ebx
-1: ret
+1:
+#ifdef CONFIG_KAISER
+ /*
+ * We might have come in between a swapgs and a SWITCH_KERNEL_CR3
+ * on entry, or between a SWITCH_USER_CR3 and a swapgs on exit.
+ * Do a conditional SWITCH_KERNEL_CR3: this could safely be done
+ * unconditionally, but we need to find out whether the reverse
+ * should be done on return (conveyed to paranoid_exit in %ebx).
+ */
+ movq %cr3, %rax
+ testl $KAISER_SHADOW_PGD_OFFSET, %eax
+ jz 2f
+ orl $2, %ebx
+ andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
+ orq x86_cr3_pcid_noflush, %rax
+ movq %rax, %cr3
+2:
+#endif
+ ret
END(paranoid_entry)
/*
@@ -1052,20 +1073,25 @@ END(paranoid_entry)
* be complicated. Fortunately, we there's no good reason
* to try to handle preemption here.
*
- * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
+ * On entry: ebx=0: needs swapgs but not SWITCH_USER_CR3
+ * ebx=1: needs neither swapgs nor SWITCH_USER_CR3
+ * ebx=2: needs both swapgs and SWITCH_USER_CR3
+ * ebx=3: needs SWITCH_USER_CR3 but not swapgs
*/
ENTRY(paranoid_exit)
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF_DEBUG
- testl %ebx, %ebx /* swapgs needed? */
+ TRACE_IRQS_IRETQ_DEBUG
+#ifdef CONFIG_KAISER
+ testl $2, %ebx /* SWITCH_USER_CR3 needed? */
+ jz paranoid_exit_no_switch
+ SWITCH_USER_CR3
+paranoid_exit_no_switch:
+#endif
+ testl $1, %ebx /* swapgs needed? */
jnz paranoid_exit_no_swapgs
- TRACE_IRQS_IRETQ
- SWITCH_USER_CR3_NO_STACK
SWAPGS_UNSAFE_STACK
- jmp paranoid_exit_restore
paranoid_exit_no_swapgs:
- TRACE_IRQS_IRETQ_DEBUG
-paranoid_exit_restore:
RESTORE_EXTRA_REGS
RESTORE_C_REGS
REMOVE_PT_GPREGS_FROM_STACK 8
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -63,20 +63,12 @@ _SWITCH_TO_KERNEL_CR3 %rax
movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
.endm
-.macro SWITCH_USER_CR3_NO_STACK
-movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)
-_SWITCH_TO_USER_CR3 %rax %al
-movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
-.endm
-
#else /* CONFIG_KAISER */
.macro SWITCH_KERNEL_CR3 reg
.endm
.macro SWITCH_USER_CR3 reg regb
.endm
-.macro SWITCH_USER_CR3_NO_STACK
-.endm
.macro SWITCH_KERNEL_CR3_NO_STACK
.endm
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: name that 0x1000 KAISER_SHADOW_PGD_OFFSET" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: name that 0x1000 KAISER_SHADOW_PGD_OFFSET
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sat, 9 Sep 2017 17:31:18 -0700
Subject: kaiser: name that 0x1000 KAISER_SHADOW_PGD_OFFSET
From: Hugh Dickins <hughd(a)google.com>
There's a 0x1000 in various places, which looks better with a name.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 4 ++--
arch/x86/include/asm/kaiser.h | 7 +++++--
2 files changed, 7 insertions(+), 4 deletions(-)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1292,7 +1292,7 @@ ENTRY(nmi)
movq %cr3, %rax
pushq %rax
#ifdef CONFIG_KAISER_REAL_SWITCH
- andq $(~0x1000), %rax
+ andq $(~KAISER_SHADOW_PGD_OFFSET), %rax
#endif
movq %rax, %cr3
#endif
@@ -1535,7 +1535,7 @@ end_repeat_nmi:
movq %cr3, %rax
pushq %rax
#ifdef CONFIG_KAISER_REAL_SWITCH
- andq $(~0x1000), %rax
+ andq $(~KAISER_SHADOW_PGD_OFFSET), %rax
#endif
movq %rax, %cr3
#endif
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -13,13 +13,16 @@
* A minimalistic kernel mapping holds the parts needed to be mapped in user
* mode, such as the entry/exit functions of the user space, or the stacks.
*/
+
+#define KAISER_SHADOW_PGD_OFFSET 0x1000
+
#ifdef __ASSEMBLY__
#ifdef CONFIG_KAISER
.macro _SWITCH_TO_KERNEL_CR3 reg
movq %cr3, \reg
#ifdef CONFIG_KAISER_REAL_SWITCH
-andq $(~0x1000), \reg
+andq $(~KAISER_SHADOW_PGD_OFFSET), \reg
#endif
movq \reg, %cr3
.endm
@@ -27,7 +30,7 @@ movq \reg, %cr3
.macro _SWITCH_TO_USER_CR3 reg
movq %cr3, \reg
#ifdef CONFIG_KAISER_REAL_SWITCH
-orq $(0x1000), \reg
+orq $(KAISER_SHADOW_PGD_OFFSET), \reg
#endif
movq \reg, %cr3
.endm
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: merged update" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: merged update
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-merged-update.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Dave Hansen <dave.hansen(a)linux.intel.com>
Date: Wed, 30 Aug 2017 16:23:00 -0700
Subject: kaiser: merged update
From: Dave Hansen <dave.hansen(a)linux.intel.com>
Merged fixes and cleanups, rebased to 4.4.89 tree (no 5-level paging).
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 106 ++++++++++-
arch/x86/include/asm/kaiser.h | 43 ++--
arch/x86/include/asm/pgtable.h | 18 +
arch/x86/include/asm/pgtable_64.h | 48 ++++-
arch/x86/include/asm/pgtable_types.h | 6
arch/x86/kernel/espfix_64.c | 13 -
arch/x86/kernel/head_64.S | 19 +-
arch/x86/kernel/ldt.c | 27 ++
arch/x86/kernel/tracepoint.c | 2
arch/x86/mm/kaiser.c | 318 +++++++++++++++++++++++++----------
arch/x86/mm/pageattr.c | 63 +++++-
arch/x86/mm/pgtable.c | 40 +---
include/linux/kaiser.h | 26 ++
kernel/fork.c | 9
security/Kconfig | 5
15 files changed, 553 insertions(+), 190 deletions(-)
create mode 100644 include/linux/kaiser.h
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -212,6 +212,13 @@ entry_SYSCALL_64_fastpath:
movq RIP(%rsp), %rcx
movq EFLAGS(%rsp), %r11
RESTORE_C_REGS_EXCEPT_RCX_R11
+ /*
+ * This opens a window where we have a user CR3, but are
+ * running in the kernel. This makes using the CS
+ * register useless for telling whether or not we need to
+ * switch CR3 in NMIs. Normal interrupts are OK because
+ * they are off here.
+ */
SWITCH_USER_CR3
movq RSP(%rsp), %rsp
/*
@@ -350,11 +357,25 @@ GLOBAL(int_ret_from_sys_call)
syscall_return_via_sysret:
/* rcx and r11 are already restored (see code above) */
RESTORE_C_REGS_EXCEPT_RCX_R11
+ /*
+ * This opens a window where we have a user CR3, but are
+ * running in the kernel. This makes using the CS
+ * register useless for telling whether or not we need to
+ * switch CR3 in NMIs. Normal interrupts are OK because
+ * they are off here.
+ */
SWITCH_USER_CR3
movq RSP(%rsp), %rsp
USERGS_SYSRET64
opportunistic_sysret_failed:
+ /*
+ * This opens a window where we have a user CR3, but are
+ * running in the kernel. This makes using the CS
+ * register useless for telling whether or not we need to
+ * switch CR3 in NMIs. Normal interrupts are OK because
+ * they are off here.
+ */
SWITCH_USER_CR3
SWAPGS
jmp restore_c_regs_and_iret
@@ -1059,6 +1080,13 @@ ENTRY(error_entry)
cld
SAVE_C_REGS 8
SAVE_EXTRA_REGS 8
+ /*
+ * error_entry() always returns with a kernel gsbase and
+ * CR3. We must also have a kernel CR3/gsbase before
+ * calling TRACE_IRQS_*. Just unconditionally switch to
+ * the kernel CR3 here.
+ */
+ SWITCH_KERNEL_CR3
xorl %ebx, %ebx
testb $3, CS+8(%rsp)
jz .Lerror_kernelspace
@@ -1069,7 +1097,6 @@ ENTRY(error_entry)
* from user mode due to an IRET fault.
*/
SWAPGS
- SWITCH_KERNEL_CR3
.Lerror_entry_from_usermode_after_swapgs:
/*
@@ -1122,7 +1149,7 @@ ENTRY(error_entry)
* Switch to kernel gsbase:
*/
SWAPGS
- SWITCH_KERNEL_CR3
+
/*
* Pretend that the exception came from user mode: set up pt_regs
* as if we faulted immediately after IRET and clear EBX so that
@@ -1222,7 +1249,10 @@ ENTRY(nmi)
*/
SWAPGS_UNSAFE_STACK
- SWITCH_KERNEL_CR3_NO_STACK
+ /*
+ * percpu variables are mapped with user CR3, so no need
+ * to switch CR3 here.
+ */
cld
movq %rsp, %rdx
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
@@ -1256,14 +1286,33 @@ ENTRY(nmi)
movq %rsp, %rdi
movq $-1, %rsi
+#ifdef CONFIG_KAISER
+ /* Unconditionally use kernel CR3 for do_nmi() */
+ /* %rax is saved above, so OK to clobber here */
+ movq %cr3, %rax
+ pushq %rax
+#ifdef CONFIG_KAISER_REAL_SWITCH
+ andq $(~0x1000), %rax
+#endif
+ movq %rax, %cr3
+#endif
call do_nmi
+ /*
+ * Unconditionally restore CR3. I know we return to
+ * kernel code that needs user CR3, but do we ever return
+ * to "user mode" where we need the kernel CR3?
+ */
+#ifdef CONFIG_KAISER
+ popq %rax
+ mov %rax, %cr3
+#endif
/*
* Return back to user mode. We must *not* do the normal exit
- * work, because we don't want to enable interrupts. Fortunately,
- * do_nmi doesn't modify pt_regs.
+ * work, because we don't want to enable interrupts. Do not
+ * switch to user CR3: we might be going back to kernel code
+ * that had a user CR3 set.
*/
- SWITCH_USER_CR3
SWAPGS
jmp restore_c_regs_and_iret
@@ -1459,23 +1508,54 @@ end_repeat_nmi:
ALLOC_PT_GPREGS_ON_STACK
/*
- * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
- * as we should not be calling schedule in NMI context.
- * Even with normal interrupts enabled. An NMI should not be
- * setting NEED_RESCHED or anything that normal interrupts and
- * exceptions might do.
+ * Use the same approach as paranoid_entry to handle SWAPGS, but
+ * without CR3 handling since we do that differently in NMIs. No
+ * need to use paranoid_exit as we should not be calling schedule
+ * in NMI context. Even with normal interrupts enabled. An NMI
+ * should not be setting NEED_RESCHED or anything that normal
+ * interrupts and exceptions might do.
*/
- call paranoid_entry
+ cld
+ SAVE_C_REGS
+ SAVE_EXTRA_REGS
+ movl $1, %ebx
+ movl $MSR_GS_BASE, %ecx
+ rdmsr
+ testl %edx, %edx
+ js 1f /* negative -> in kernel */
+ SWAPGS
+ xorl %ebx, %ebx
+1:
+#ifdef CONFIG_KAISER
+ /* Unconditionally use kernel CR3 for do_nmi() */
+ /* %rax is saved above, so OK to clobber here */
+ movq %cr3, %rax
+ pushq %rax
+#ifdef CONFIG_KAISER_REAL_SWITCH
+ andq $(~0x1000), %rax
+#endif
+ movq %rax, %cr3
+#endif
/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
movq %rsp, %rdi
+ addq $8, %rdi /* point %rdi at ptregs, fixed up for CR3 */
movq $-1, %rsi
call do_nmi
+ /*
+ * Unconditionally restore CR3. We might be returning to
+ * kernel code that needs user CR3, like just just before
+ * a sysret.
+ */
+#ifdef CONFIG_KAISER
+ popq %rax
+ mov %rax, %cr3
+#endif
testl %ebx, %ebx /* swapgs needed? */
jnz nmi_restore
nmi_swapgs:
- SWITCH_USER_CR3_NO_STACK
+ /* We fixed up CR3 above, so no need to switch it here */
SWAPGS_UNSAFE_STACK
nmi_restore:
RESTORE_EXTRA_REGS
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -16,13 +16,17 @@
.macro _SWITCH_TO_KERNEL_CR3 reg
movq %cr3, \reg
+#ifdef CONFIG_KAISER_REAL_SWITCH
andq $(~0x1000), \reg
+#endif
movq \reg, %cr3
.endm
.macro _SWITCH_TO_USER_CR3 reg
movq %cr3, \reg
+#ifdef CONFIG_KAISER_REAL_SWITCH
orq $(0x1000), \reg
+#endif
movq \reg, %cr3
.endm
@@ -65,48 +69,53 @@ movq PER_CPU_VAR(unsafe_stack_register_b
.endm
#endif /* CONFIG_KAISER */
+
#else /* __ASSEMBLY__ */
#ifdef CONFIG_KAISER
-// Upon kernel/user mode switch, it may happen that
-// the address space has to be switched before the registers have been stored.
-// To change the address space, another register is needed.
-// A register therefore has to be stored/restored.
-//
-DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
+/*
+ * Upon kernel/user mode switch, it may happen that the address
+ * space has to be switched before the registers have been
+ * stored. To change the address space, another register is
+ * needed. A register therefore has to be stored/restored.
+*/
-#endif /* CONFIG_KAISER */
+DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
/**
- * shadowmem_add_mapping - map a virtual memory part to the shadow mapping
+ * kaiser_add_mapping - map a virtual memory part to the shadow (user) mapping
* @addr: the start address of the range
* @size: the size of the range
* @flags: The mapping flags of the pages
*
- * the mapping is done on a global scope, so no bigger synchronization has to be done.
- * the pages have to be manually unmapped again when they are not needed any longer.
+ * The mapping is done on a global scope, so no bigger
+ * synchronization has to be done. the pages have to be
+ * manually unmapped again when they are not needed any longer.
*/
-extern void kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags);
+extern int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags);
/**
- * shadowmem_remove_mapping - unmap a virtual memory part of the shadow mapping
+ * kaiser_remove_mapping - unmap a virtual memory part of the shadow mapping
* @addr: the start address of the range
* @size: the size of the range
*/
extern void kaiser_remove_mapping(unsigned long start, unsigned long size);
/**
- * shadowmem_initialize_mapping - Initalize the shadow mapping
+ * kaiser_initialize_mapping - Initalize the shadow mapping
*
- * most parts of the shadow mapping can be mapped upon boot time.
- * only the thread stacks have to be mapped on runtime.
- * the mapped regions are not unmapped at all.
+ * Most parts of the shadow mapping can be mapped upon boot
+ * time. Only per-process things like the thread stacks
+ * or a new LDT have to be mapped at runtime. These boot-
+ * time mappings are permanent and nevertunmapped.
*/
extern void kaiser_init(void);
-#endif
+#endif /* CONFIG_KAISER */
+
+#endif /* __ASSEMBLY */
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -653,7 +653,17 @@ static inline pud_t *pud_offset(pgd_t *p
static inline int pgd_bad(pgd_t pgd)
{
- return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+ pgdval_t ignore_flags = _PAGE_USER;
+ /*
+ * We set NX on KAISER pgds that map userspace memory so
+ * that userspace can not meaningfully use the kernel
+ * page table by accident; it will fault on the first
+ * instruction it tries to run. See native_set_pgd().
+ */
+ if (IS_ENABLED(CONFIG_KAISER))
+ ignore_flags |= _PAGE_NX;
+
+ return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
}
static inline int pgd_none(pgd_t pgd)
@@ -857,8 +867,10 @@ static inline void clone_pgd_range(pgd_t
{
memcpy(dst, src, count * sizeof(pgd_t));
#ifdef CONFIG_KAISER
- // clone the shadow pgd part as well
- memcpy(native_get_shadow_pgd(dst), native_get_shadow_pgd(src), count * sizeof(pgd_t));
+ /* Clone the shadow pgd part as well */
+ memcpy(native_get_shadow_pgd(dst),
+ native_get_shadow_pgd(src),
+ count * sizeof(pgd_t));
#endif
}
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -107,26 +107,58 @@ static inline void native_pud_clear(pud_
}
#ifdef CONFIG_KAISER
-static inline pgd_t * native_get_shadow_pgd(pgd_t *pgdp) {
+static inline pgd_t * native_get_shadow_pgd(pgd_t *pgdp)
+{
return (pgd_t *)(void*)((unsigned long)(void*)pgdp | (unsigned long)PAGE_SIZE);
}
-static inline pgd_t * native_get_normal_pgd(pgd_t *pgdp) {
+static inline pgd_t * native_get_normal_pgd(pgd_t *pgdp)
+{
return (pgd_t *)(void*)((unsigned long)(void*)pgdp & ~(unsigned long)PAGE_SIZE);
}
+#else
+static inline pgd_t * native_get_shadow_pgd(pgd_t *pgdp)
+{
+ BUILD_BUG_ON(1);
+ return NULL;
+}
+static inline pgd_t * native_get_normal_pgd(pgd_t *pgdp)
+{
+ return pgdp;
+}
#endif /* CONFIG_KAISER */
+/*
+ * Page table pages are page-aligned. The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ * This returns true for user pages that need to get copied into
+ * both the user and kernel copies of the page tables, and false
+ * for kernel pages that should only be in the kernel copy.
+ */
+static inline bool is_userspace_pgd(void *__ptr)
+{
+ unsigned long ptr = (unsigned long)__ptr;
+
+ return ((ptr % PAGE_SIZE) < (PAGE_SIZE / 2));
+}
+
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
#ifdef CONFIG_KAISER
- // We know that a pgd is page aligned.
- // Therefore the lower indices have to be mapped to user space.
- // These pages are mapped to the shadow mapping.
- if ((((unsigned long)pgdp) % PAGE_SIZE) < (PAGE_SIZE / 2)) {
+ pteval_t extra_kern_pgd_flags = 0;
+ /* Do we need to also populate the shadow pgd? */
+ if (is_userspace_pgd(pgdp)) {
native_get_shadow_pgd(pgdp)->pgd = pgd.pgd;
+ /*
+ * Even if the entry is *mapping* userspace, ensure
+ * that userspace can not use it. This way, if we
+ * get out to userspace running on the kernel CR3,
+ * userspace will crash instead of running.
+ */
+ extra_kern_pgd_flags = _PAGE_NX;
}
-
- pgdp->pgd = pgd.pgd & ~_PAGE_USER;
+ pgdp->pgd = pgd.pgd;
+ pgdp->pgd |= extra_kern_pgd_flags;
#else /* CONFIG_KAISER */
*pgdp = pgd;
#endif
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -42,7 +42,7 @@
#ifdef CONFIG_KAISER
#define _PAGE_GLOBAL (_AT(pteval_t, 0))
#else
-#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
+#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
#endif
#define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1)
#define _PAGE_SOFTW2 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2)
@@ -93,11 +93,7 @@
#define _PAGE_NX (_AT(pteval_t, 0))
#endif
-#ifdef CONFIG_KAISER
-#define _PAGE_PROTNONE (_AT(pteval_t, 0))
-#else
#define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
-#endif
#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \
_PAGE_ACCESSED | _PAGE_DIRTY)
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -127,11 +127,14 @@ void __init init_espfix_bsp(void)
/* Install the espfix pud into the kernel page directory */
pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
-#ifdef CONFIG_KAISER
- // add the esp stack pud to the shadow mapping here.
- // This can be done directly, because the fixup stack has its own pud
- set_pgd(native_get_shadow_pgd(pgd_p), __pgd(_PAGE_TABLE | __pa((pud_t *)espfix_pud_page)));
-#endif
+ /*
+ * Just copy the top-level PGD that is mapping the espfix
+ * area to ensure it is mapped into the shadow user page
+ * tables.
+ */
+ if (IS_ENABLED(CONFIG_KAISER))
+ set_pgd(native_get_shadow_pgd(pgd_p),
+ __pgd(_KERNPG_TABLE | __pa((pud_t *)espfix_pud_page)));
/* Randomize the locations */
init_espfix_random();
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -442,11 +442,24 @@ early_idt_ripmsg:
GLOBAL(name)
#ifdef CONFIG_KAISER
+/*
+ * Each PGD needs to be 8k long and 8k aligned. We do not
+ * ever go out to userspace with these, so we do not
+ * strictly *need* the second page, but this allows us to
+ * have a single set_pgd() implementation that does not
+ * need to worry about whether it has 4k or 8k to work
+ * with.
+ *
+ * This ensures PGDs are 8k long:
+ */
+#define KAISER_USER_PGD_FILL 512
+/* This ensures they are 8k-aligned: */
#define NEXT_PGD_PAGE(name) \
.balign 2 * PAGE_SIZE; \
GLOBAL(name)
#else
#define NEXT_PGD_PAGE(name) NEXT_PAGE(name)
+#define KAISER_USER_PGD_FILL 0
#endif
/* Automate the creation of 1 to 1 mapping pmd entries */
@@ -461,6 +474,7 @@ GLOBAL(name)
NEXT_PGD_PAGE(early_level4_pgt)
.fill 511,8,0
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+ .fill KAISER_USER_PGD_FILL,8,0
NEXT_PAGE(early_dynamic_pgts)
.fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0
@@ -469,7 +483,8 @@ NEXT_PAGE(early_dynamic_pgts)
#ifndef CONFIG_XEN
NEXT_PGD_PAGE(init_level4_pgt)
- .fill 2*512,8,0
+ .fill 512,8,0
+ .fill KAISER_USER_PGD_FILL,8,0
#else
NEXT_PGD_PAGE(init_level4_pgt)
.quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
@@ -478,6 +493,7 @@ NEXT_PGD_PAGE(init_level4_pgt)
.org init_level4_pgt + L4_START_KERNEL*8, 0
/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+ .fill KAISER_USER_PGD_FILL,8,0
NEXT_PAGE(level3_ident_pgt)
.quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
@@ -488,6 +504,7 @@ NEXT_PAGE(level2_ident_pgt)
*/
PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
#endif
+ .fill KAISER_USER_PGD_FILL,8,0
NEXT_PAGE(level3_kernel_pgt)
.fill L3_START_KERNEL,8,0
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -18,6 +18,7 @@
#include <linux/uaccess.h>
#include <asm/ldt.h>
+#include <asm/kaiser.h>
#include <asm/desc.h>
#include <asm/mmu_context.h>
#include <asm/syscalls.h>
@@ -34,11 +35,21 @@ static void flush_ldt(void *current_mm)
set_ldt(pc->ldt->entries, pc->ldt->size);
}
+static void __free_ldt_struct(struct ldt_struct *ldt)
+{
+ if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
+ vfree(ldt->entries);
+ else
+ free_page((unsigned long)ldt->entries);
+ kfree(ldt);
+}
+
/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
static struct ldt_struct *alloc_ldt_struct(int size)
{
struct ldt_struct *new_ldt;
int alloc_size;
+ int ret = 0;
if (size > LDT_ENTRIES)
return NULL;
@@ -66,6 +77,14 @@ static struct ldt_struct *alloc_ldt_stru
return NULL;
}
+ // FIXME: make kaiser_add_mapping() return an error code
+ // when it fails
+ kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size,
+ __PAGE_KERNEL);
+ if (ret) {
+ __free_ldt_struct(new_ldt);
+ return NULL;
+ }
new_ldt->size = size;
return new_ldt;
}
@@ -92,12 +111,10 @@ static void free_ldt_struct(struct ldt_s
if (likely(!ldt))
return;
+ kaiser_remove_mapping((unsigned long)ldt->entries,
+ ldt->size * LDT_ENTRY_SIZE);
paravirt_free_ldt(ldt->entries, ldt->size);
- if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
- vfree(ldt->entries);
- else
- free_page((unsigned long)ldt->entries);
- kfree(ldt);
+ __free_ldt_struct(ldt);
}
/*
--- a/arch/x86/kernel/tracepoint.c
+++ b/arch/x86/kernel/tracepoint.c
@@ -9,10 +9,12 @@
#include <linux/atomic.h>
atomic_t trace_idt_ctr = ATOMIC_INIT(0);
+__aligned(PAGE_SIZE)
struct desc_ptr trace_idt_descr = { NR_VECTORS * 16 - 1,
(unsigned long) trace_idt_table };
/* No need to be aligned, but done to keep all IDTs defined the same way. */
+__aligned(PAGE_SIZE)
gate_desc trace_idt_table[NR_VECTORS] __page_aligned_bss;
static int trace_irq_vector_refcount;
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -1,160 +1,306 @@
-
-
+#include <linux/bug.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/bug.h>
#include <linux/init.h>
+#include <linux/interrupt.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
-
#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+
+#include <asm/kaiser.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/desc.h>
#ifdef CONFIG_KAISER
__visible DEFINE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
+/*
+ * At runtime, the only things we map are some things for CPU
+ * hotplug, and stacks for new processes. No two CPUs will ever
+ * be populating the same addresses, so we only need to ensure
+ * that we protect between two CPUs trying to allocate and
+ * populate the same page table page.
+ *
+ * Only take this lock when doing a set_p[4um]d(), but it is not
+ * needed for doing a set_pte(). We assume that only the *owner*
+ * of a given allocation will be doing this for _their_
+ * allocation.
+ *
+ * This ensures that once a system has been running for a while
+ * and there have been stacks all over and these page tables
+ * are fully populated, there will be no further acquisitions of
+ * this lock.
+ */
+static DEFINE_SPINLOCK(shadow_table_allocation_lock);
-/**
- * Get the real ppn from a address in kernel mapping.
- * @param address The virtual adrress
- * @return the physical address
+/*
+ * Returns -1 on error.
*/
-static inline unsigned long get_pa_from_mapping (unsigned long address)
+static inline unsigned long get_pa_from_mapping(unsigned long vaddr)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
- pgd = pgd_offset_k(address);
- BUG_ON(pgd_none(*pgd) || pgd_large(*pgd));
+ pgd = pgd_offset_k(vaddr);
+ /*
+ * We made all the kernel PGDs present in kaiser_init().
+ * We expect them to stay that way.
+ */
+ BUG_ON(pgd_none(*pgd));
+ /*
+ * PGDs are either 512GB or 128TB on all x86_64
+ * configurations. We don't handle these.
+ */
+ BUG_ON(pgd_large(*pgd));
+
+ pud = pud_offset(pgd, vaddr);
+ if (pud_none(*pud)) {
+ WARN_ON_ONCE(1);
+ return -1;
+ }
- pud = pud_offset(pgd, address);
- BUG_ON(pud_none(*pud));
+ if (pud_large(*pud))
+ return (pud_pfn(*pud) << PAGE_SHIFT) | (vaddr & ~PUD_PAGE_MASK);
- if (pud_large(*pud)) {
- return (pud_pfn(*pud) << PAGE_SHIFT) | (address & ~PUD_PAGE_MASK);
+ pmd = pmd_offset(pud, vaddr);
+ if (pmd_none(*pmd)) {
+ WARN_ON_ONCE(1);
+ return -1;
}
- pmd = pmd_offset(pud, address);
- BUG_ON(pmd_none(*pmd));
+ if (pmd_large(*pmd))
+ return (pmd_pfn(*pmd) << PAGE_SHIFT) | (vaddr & ~PMD_PAGE_MASK);
- if (pmd_large(*pmd)) {
- return (pmd_pfn(*pmd) << PAGE_SHIFT) | (address & ~PMD_PAGE_MASK);
+ pte = pte_offset_kernel(pmd, vaddr);
+ if (pte_none(*pte)) {
+ WARN_ON_ONCE(1);
+ return -1;
}
- pte = pte_offset_kernel(pmd, address);
- BUG_ON(pte_none(*pte));
-
- return (pte_pfn(*pte) << PAGE_SHIFT) | (address & ~PAGE_MASK);
+ return (pte_pfn(*pte) << PAGE_SHIFT) | (vaddr & ~PAGE_MASK);
}
-void _kaiser_copy (unsigned long start_addr, unsigned long size,
- unsigned long flags)
+/*
+ * This is a relatively normal page table walk, except that it
+ * also tries to allocate page tables pages along the way.
+ *
+ * Returns a pointer to a PTE on success, or NULL on failure.
+ */
+static pte_t *kaiser_pagetable_walk(unsigned long address, bool is_atomic)
{
- pgd_t *pgd;
- pud_t *pud;
pmd_t *pmd;
- pte_t *pte;
- unsigned long address;
- unsigned long end_addr = start_addr + size;
- unsigned long target_address;
+ pud_t *pud;
+ pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(address));
+ gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
- for (address = PAGE_ALIGN(start_addr - (PAGE_SIZE - 1));
- address < PAGE_ALIGN(end_addr); address += PAGE_SIZE) {
- target_address = get_pa_from_mapping(address);
+ might_sleep();
+ if (is_atomic) {
+ gfp &= ~GFP_KERNEL;
+ gfp |= __GFP_HIGH | __GFP_ATOMIC;
+ }
- pgd = native_get_shadow_pgd(pgd_offset_k(address));
+ if (pgd_none(*pgd)) {
+ WARN_ONCE(1, "All shadow pgds should have been populated");
+ return NULL;
+ }
+ BUILD_BUG_ON(pgd_large(*pgd) != 0);
- BUG_ON(pgd_none(*pgd) && "All shadow pgds should be mapped at this time\n");
- BUG_ON(pgd_large(*pgd));
+ pud = pud_offset(pgd, address);
+ /* The shadow page tables do not use large mappings: */
+ if (pud_large(*pud)) {
+ WARN_ON(1);
+ return NULL;
+ }
+ if (pud_none(*pud)) {
+ unsigned long new_pmd_page = __get_free_page(gfp);
+ if (!new_pmd_page)
+ return NULL;
+ spin_lock(&shadow_table_allocation_lock);
+ if (pud_none(*pud))
+ set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
+ else
+ free_page(new_pmd_page);
+ spin_unlock(&shadow_table_allocation_lock);
+ }
- pud = pud_offset(pgd, address);
- if (pud_none(*pud)) {
- set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd_alloc_one(0, address))));
- }
- BUG_ON(pud_large(*pud));
+ pmd = pmd_offset(pud, address);
+ /* The shadow page tables do not use large mappings: */
+ if (pmd_large(*pmd)) {
+ WARN_ON(1);
+ return NULL;
+ }
+ if (pmd_none(*pmd)) {
+ unsigned long new_pte_page = __get_free_page(gfp);
+ if (!new_pte_page)
+ return NULL;
+ spin_lock(&shadow_table_allocation_lock);
+ if (pmd_none(*pmd))
+ set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page)));
+ else
+ free_page(new_pte_page);
+ spin_unlock(&shadow_table_allocation_lock);
+ }
- pmd = pmd_offset(pud, address);
- if (pmd_none(*pmd)) {
- set_pmd(pmd, __pmd(_PAGE_TABLE | __pa(pte_alloc_one_kernel(0, address))));
- }
- BUG_ON(pmd_large(*pmd));
+ return pte_offset_kernel(pmd, address);
+}
- pte = pte_offset_kernel(pmd, address);
+int kaiser_add_user_map(const void *__start_addr, unsigned long size,
+ unsigned long flags)
+{
+ int ret = 0;
+ pte_t *pte;
+ unsigned long start_addr = (unsigned long )__start_addr;
+ unsigned long address = start_addr & PAGE_MASK;
+ unsigned long end_addr = PAGE_ALIGN(start_addr + size);
+ unsigned long target_address;
+
+ for (;address < end_addr; address += PAGE_SIZE) {
+ target_address = get_pa_from_mapping(address);
+ if (target_address == -1) {
+ ret = -EIO;
+ break;
+ }
+ pte = kaiser_pagetable_walk(address, false);
if (pte_none(*pte)) {
set_pte(pte, __pte(flags | target_address));
} else {
- BUG_ON(__pa(pte_page(*pte)) != target_address);
+ pte_t tmp;
+ set_pte(&tmp, __pte(flags | target_address));
+ WARN_ON_ONCE(!pte_same(*pte, tmp));
}
}
+ return ret;
}
-// at first, add a pmd for every pgd entry in the shadowmem-kernel-part of the kernel mapping
-static inline void __init _kaiser_init(void)
+static int kaiser_add_user_map_ptrs(const void *start, const void *end, unsigned long flags)
+{
+ unsigned long size = end - start;
+
+ return kaiser_add_user_map(start, size, flags);
+}
+
+/*
+ * Ensure that the top level of the (shadow) page tables are
+ * entirely populated. This ensures that all processes that get
+ * forked have the same entries. This way, we do not have to
+ * ever go set up new entries in older processes.
+ *
+ * Note: we never free these, so there are no updates to them
+ * after this.
+ */
+static void __init kaiser_init_all_pgds(void)
{
pgd_t *pgd;
int i = 0;
pgd = native_get_shadow_pgd(pgd_offset_k((unsigned long )0));
for (i = PTRS_PER_PGD / 2; i < PTRS_PER_PGD; i++) {
- set_pgd(pgd + i, __pgd(_PAGE_TABLE |__pa(pud_alloc_one(0, 0))));
+ pgd_t new_pgd;
+ pud_t *pud = pud_alloc_one(&init_mm, PAGE_OFFSET + i * PGDIR_SIZE);
+ if (!pud) {
+ WARN_ON(1);
+ break;
+ }
+ new_pgd = __pgd(_KERNPG_TABLE |__pa(pud));
+ /*
+ * Make sure not to stomp on some other pgd entry.
+ */
+ if (!pgd_none(pgd[i])) {
+ WARN_ON(1);
+ continue;
+ }
+ set_pgd(pgd + i, new_pgd);
}
}
+#define kaiser_add_user_map_early(start, size, flags) do { \
+ int __ret = kaiser_add_user_map(start, size, flags); \
+ WARN_ON(__ret); \
+} while (0)
+
+#define kaiser_add_user_map_ptrs_early(start, end, flags) do { \
+ int __ret = kaiser_add_user_map_ptrs(start, end, flags); \
+ WARN_ON(__ret); \
+} while (0)
+
extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
-spinlock_t shadow_table_lock;
+/*
+ * If anything in here fails, we will likely die on one of the
+ * first kernel->user transitions and init will die. But, we
+ * will have most of the kernel up by then and should be able to
+ * get a clean warning out of it. If we BUG_ON() here, we run
+ * the risk of being before we have good console output.
+ */
void __init kaiser_init(void)
{
int cpu;
- spin_lock_init(&shadow_table_lock);
-
- spin_lock(&shadow_table_lock);
- _kaiser_init();
+ kaiser_init_all_pgds();
for_each_possible_cpu(cpu) {
- // map the per cpu user variables
- _kaiser_copy(
- (unsigned long) (__per_cpu_user_mapped_start + per_cpu_offset(cpu)),
- (unsigned long) __per_cpu_user_mapped_end - (unsigned long) __per_cpu_user_mapped_start,
- __PAGE_KERNEL);
- }
-
- // map the entry/exit text section, which is responsible to switch between user- and kernel mode
- _kaiser_copy(
- (unsigned long) __entry_text_start,
- (unsigned long) __entry_text_end - (unsigned long) __entry_text_start,
- __PAGE_KERNEL_RX);
-
- // the fixed map address of the idt_table
- _kaiser_copy(
- (unsigned long) idt_descr.address,
- sizeof(gate_desc) * NR_VECTORS,
- __PAGE_KERNEL_RO);
+ void *percpu_vaddr = __per_cpu_user_mapped_start +
+ per_cpu_offset(cpu);
+ unsigned long percpu_sz = __per_cpu_user_mapped_end -
+ __per_cpu_user_mapped_start;
+ kaiser_add_user_map_early(percpu_vaddr, percpu_sz,
+ __PAGE_KERNEL);
+ }
- spin_unlock(&shadow_table_lock);
+ /*
+ * Map the entry/exit text section, which is needed at
+ * switches from user to and from kernel.
+ */
+ kaiser_add_user_map_ptrs_early(__entry_text_start, __entry_text_end,
+ __PAGE_KERNEL_RX);
+
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
+ kaiser_add_user_map_ptrs_early(__irqentry_text_start,
+ __irqentry_text_end,
+ __PAGE_KERNEL_RX);
+#endif
+ kaiser_add_user_map_early((void *)idt_descr.address,
+ sizeof(gate_desc) * NR_VECTORS,
+ __PAGE_KERNEL_RO);
+#ifdef CONFIG_TRACING
+ kaiser_add_user_map_early(&trace_idt_descr,
+ sizeof(trace_idt_descr),
+ __PAGE_KERNEL);
+ kaiser_add_user_map_early(&trace_idt_table,
+ sizeof(gate_desc) * NR_VECTORS,
+ __PAGE_KERNEL);
+#endif
+ kaiser_add_user_map_early(&debug_idt_descr, sizeof(debug_idt_descr),
+ __PAGE_KERNEL);
+ kaiser_add_user_map_early(&debug_idt_table,
+ sizeof(gate_desc) * NR_VECTORS,
+ __PAGE_KERNEL);
}
+extern void unmap_pud_range_nofree(pgd_t *pgd, unsigned long start, unsigned long end);
// add a mapping to the shadow-mapping, and synchronize the mappings
-void kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags)
+int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags)
{
- spin_lock(&shadow_table_lock);
- _kaiser_copy(addr, size, flags);
- spin_unlock(&shadow_table_lock);
+ return kaiser_add_user_map((const void *)addr, size, flags);
}
-extern void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end);
void kaiser_remove_mapping(unsigned long start, unsigned long size)
{
- pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(start));
- spin_lock(&shadow_table_lock);
- do {
- unmap_pud_range(pgd, start, start + size);
- } while (pgd++ != native_get_shadow_pgd(pgd_offset_k(start + size)));
- spin_unlock(&shadow_table_lock);
+ unsigned long end = start + size;
+ unsigned long addr;
+
+ for (addr = start; addr < end; addr += PGDIR_SIZE) {
+ pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(addr));
+ /*
+ * unmap_p4d_range() handles > P4D_SIZE unmaps,
+ * so no need to trim 'end'.
+ */
+ unmap_pud_range_nofree(pgd, addr, end);
+ }
}
#endif /* CONFIG_KAISER */
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -52,6 +52,7 @@ static DEFINE_SPINLOCK(cpa_lock);
#define CPA_FLUSHTLB 1
#define CPA_ARRAY 2
#define CPA_PAGES_ARRAY 4
+#define CPA_FREE_PAGETABLES 8
#ifdef CONFIG_PROC_FS
static unsigned long direct_pages_count[PG_LEVEL_NUM];
@@ -723,10 +724,13 @@ static int split_large_page(struct cpa_d
return 0;
}
-static bool try_to_free_pte_page(pte_t *pte)
+static bool try_to_free_pte_page(struct cpa_data *cpa, pte_t *pte)
{
int i;
+ if (!(cpa->flags & CPA_FREE_PAGETABLES))
+ return false;
+
for (i = 0; i < PTRS_PER_PTE; i++)
if (!pte_none(pte[i]))
return false;
@@ -735,10 +739,13 @@ static bool try_to_free_pte_page(pte_t *
return true;
}
-static bool try_to_free_pmd_page(pmd_t *pmd)
+static bool try_to_free_pmd_page(struct cpa_data *cpa, pmd_t *pmd)
{
int i;
+ if (!(cpa->flags & CPA_FREE_PAGETABLES))
+ return false;
+
for (i = 0; i < PTRS_PER_PMD; i++)
if (!pmd_none(pmd[i]))
return false;
@@ -759,7 +766,9 @@ static bool try_to_free_pud_page(pud_t *
return true;
}
-static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
+static bool unmap_pte_range(struct cpa_data *cpa, pmd_t *pmd,
+ unsigned long start,
+ unsigned long end)
{
pte_t *pte = pte_offset_kernel(pmd, start);
@@ -770,22 +779,23 @@ static bool unmap_pte_range(pmd_t *pmd,
pte++;
}
- if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) {
+ if (try_to_free_pte_page(cpa, (pte_t *)pmd_page_vaddr(*pmd))) {
pmd_clear(pmd);
return true;
}
return false;
}
-static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd,
+static void __unmap_pmd_range(struct cpa_data *cpa, pud_t *pud, pmd_t *pmd,
unsigned long start, unsigned long end)
{
- if (unmap_pte_range(pmd, start, end))
- if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+ if (unmap_pte_range(cpa, pmd, start, end))
+ if (try_to_free_pmd_page(cpa, (pmd_t *)pud_page_vaddr(*pud)))
pud_clear(pud);
}
-static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
+static void unmap_pmd_range(struct cpa_data *cpa, pud_t *pud,
+ unsigned long start, unsigned long end)
{
pmd_t *pmd = pmd_offset(pud, start);
@@ -796,7 +806,7 @@ static void unmap_pmd_range(pud_t *pud,
unsigned long next_page = (start + PMD_SIZE) & PMD_MASK;
unsigned long pre_end = min_t(unsigned long, end, next_page);
- __unmap_pmd_range(pud, pmd, start, pre_end);
+ __unmap_pmd_range(cpa, pud, pmd, start, pre_end);
start = pre_end;
pmd++;
@@ -809,7 +819,8 @@ static void unmap_pmd_range(pud_t *pud,
if (pmd_large(*pmd))
pmd_clear(pmd);
else
- __unmap_pmd_range(pud, pmd, start, start + PMD_SIZE);
+ __unmap_pmd_range(cpa, pud, pmd,
+ start, start + PMD_SIZE);
start += PMD_SIZE;
pmd++;
@@ -819,17 +830,19 @@ static void unmap_pmd_range(pud_t *pud,
* 4K leftovers?
*/
if (start < end)
- return __unmap_pmd_range(pud, pmd, start, end);
+ return __unmap_pmd_range(cpa, pud, pmd, start, end);
/*
* Try again to free the PMD page if haven't succeeded above.
*/
if (!pud_none(*pud))
- if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+ if (try_to_free_pmd_page(cpa, (pmd_t *)pud_page_vaddr(*pud)))
pud_clear(pud);
}
-void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
+static void __unmap_pud_range(struct cpa_data *cpa, pgd_t *pgd,
+ unsigned long start,
+ unsigned long end)
{
pud_t *pud = pud_offset(pgd, start);
@@ -840,7 +853,7 @@ void unmap_pud_range(pgd_t *pgd, unsigne
unsigned long next_page = (start + PUD_SIZE) & PUD_MASK;
unsigned long pre_end = min_t(unsigned long, end, next_page);
- unmap_pmd_range(pud, start, pre_end);
+ unmap_pmd_range(cpa, pud, start, pre_end);
start = pre_end;
pud++;
@@ -854,7 +867,7 @@ void unmap_pud_range(pgd_t *pgd, unsigne
if (pud_large(*pud))
pud_clear(pud);
else
- unmap_pmd_range(pud, start, start + PUD_SIZE);
+ unmap_pmd_range(cpa, pud, start, start + PUD_SIZE);
start += PUD_SIZE;
pud++;
@@ -864,7 +877,7 @@ void unmap_pud_range(pgd_t *pgd, unsigne
* 2M leftovers?
*/
if (start < end)
- unmap_pmd_range(pud, start, end);
+ unmap_pmd_range(cpa, pud, start, end);
/*
* No need to try to free the PUD page because we'll free it in
@@ -872,6 +885,24 @@ void unmap_pud_range(pgd_t *pgd, unsigne
*/
}
+static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
+{
+ struct cpa_data cpa = {
+ .flags = CPA_FREE_PAGETABLES,
+ };
+
+ __unmap_pud_range(&cpa, pgd, start, end);
+}
+
+void unmap_pud_range_nofree(pgd_t *pgd, unsigned long start, unsigned long end)
+{
+ struct cpa_data cpa = {
+ .flags = 0,
+ };
+
+ __unmap_pud_range(&cpa, pgd, start, end);
+}
+
static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end)
{
pgd_t *pgd_entry = root + pgd_index(addr);
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -340,40 +340,26 @@ static inline void _pgd_free(pgd_t *pgd)
kmem_cache_free(pgd_cache, pgd);
}
#else
-static inline pgd_t *_pgd_alloc(void)
-{
-#ifdef CONFIG_KAISER
- // Instead of one PML4, we aquire two PML4s and, thus, an 8kb-aligned memory
- // block. Therefore, we have to allocate at least 3 pages. However, the
- // __get_free_pages returns us 4 pages. Hence, we store the base pointer at
- // the beginning of the page of our 8kb-aligned memory block in order to
- // correctly free it afterwars.
- unsigned long pages = __get_free_pages(PGALLOC_GFP, get_order(4*PAGE_SIZE));
-
- if(native_get_normal_pgd((pgd_t*) pages) == (pgd_t*) pages)
- {
- *((unsigned long*)(pages + 2 * PAGE_SIZE)) = pages;
- return (pgd_t *) pages;
- }
- else
- {
- *((unsigned long*)(pages + 3 * PAGE_SIZE)) = pages;
- return (pgd_t *) (pages + PAGE_SIZE);
- }
+#ifdef CONFIG_KAISER
+/*
+ * Instead of one pmd, we aquire two pmds. Being order-1, it is
+ * both 8k in size and 8k-aligned. That lets us just flip bit 12
+ * in a pointer to swap between the two 4k halves.
+ */
+#define PGD_ALLOCATION_ORDER 1
#else
- return (pgd_t *)__get_free_page(PGALLOC_GFP);
+#define PGD_ALLOCATION_ORDER 0
#endif
+
+static inline pgd_t *_pgd_alloc(void)
+{
+ return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER);
}
static inline void _pgd_free(pgd_t *pgd)
{
-#ifdef CONFIG_KAISER
- unsigned long pages = *((unsigned long*) ((char*) pgd + 2 * PAGE_SIZE));
- free_pages(pages, get_order(4*PAGE_SIZE));
-#else
- free_page((unsigned long)pgd);
-#endif
+ free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
}
#endif /* CONFIG_X86_PAE */
--- /dev/null
+++ b/include/linux/kaiser.h
@@ -0,0 +1,26 @@
+#ifndef _INCLUDE_KAISER_H
+#define _INCLUDE_KAISER_H
+
+#ifdef CONFIG_KAISER
+#include <asm/kaiser.h>
+#else
+
+/*
+ * These stubs are used whenever CONFIG_KAISER is off, which
+ * includes architectures that support KAISER, but have it
+ * disabled.
+ */
+
+static inline void kaiser_init(void)
+{
+}
+static inline void kaiser_remove_mapping(unsigned long start, unsigned long size)
+{
+}
+static inline int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags)
+{
+ return 0;
+}
+
+#endif /* !CONFIG_KAISER */
+#endif /* _INCLUDE_KAISER_H */
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -58,6 +58,7 @@
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/freezer.h>
+#include <linux/kaiser.h>
#include <linux/delayacct.h>
#include <linux/taskstats_kern.h>
#include <linux/random.h>
@@ -335,7 +336,6 @@ void set_task_stack_end_magic(struct tas
*stackend = STACK_END_MAGIC; /* for overflow detection */
}
-extern void kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags);
static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
{
struct task_struct *tsk;
@@ -357,9 +357,10 @@ static struct task_struct *dup_task_stru
goto free_ti;
tsk->stack = ti;
-#ifdef CONFIG_KAISER
- kaiser_add_mapping((unsigned long)tsk->stack, THREAD_SIZE, __PAGE_KERNEL);
-#endif
+
+ err= kaiser_add_mapping((unsigned long)tsk->stack, THREAD_SIZE, __PAGE_KERNEL);
+ if (err)
+ goto free_ti;
#ifdef CONFIG_SECCOMP
/*
* We must handle setting up seccomp filters once we're under
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -32,12 +32,17 @@ config SECURITY
If you are unsure how to answer this question, answer N.
config KAISER
bool "Remove the kernel mapping in user mode"
+ default y
depends on X86_64
depends on !PARAVIRT
help
This enforces a strict kernel and user space isolation in order to close
hardware side channels on kernel address information.
+config KAISER_REAL_SWITCH
+ bool "KAISER: actually switch page tables"
+ default y
+
config SECURITYFS
bool "Enable the securityfs filesystem"
help
Patches currently in stable-queue which might be from dave.hansen(a)linux.intel.com are
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: load_new_mm_cr3() let SWITCH_USER_CR3 flush user" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: load_new_mm_cr3() let SWITCH_USER_CR3 flush user
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Thu, 17 Aug 2017 15:00:37 -0700
Subject: kaiser: load_new_mm_cr3() let SWITCH_USER_CR3 flush user
From: Hugh Dickins <hughd(a)google.com>
We have many machines (Westmere, Sandybridge, Ivybridge) supporting
PCID but not INVPCID: on these load_new_mm_cr3() simply crashed.
Flushing user context inside load_new_mm_cr3() without the use of
invpcid is difficult: momentarily switch from kernel to user context
and back to do so? I'm not sure whether that can be safely done at
all, and would risk polluting user context with kernel internals,
and kernel context with stale user externals.
Instead, follow the hint in the comment that was there: change
X86_CR3_PCID_USER_VAR to be a per-cpu variable, then load_new_mm_cr3()
can leave a note in it, for SWITCH_USER_CR3 on return to userspace to
flush user context TLB, instead of default X86_CR3_PCID_USER_NOFLUSH.
Which works well enough that there's no need to do it this way only
when invpcid is unsupported: it's a good alternative to invpcid here.
But there's a couple of inlines in asm/tlbflush.h that need to do the
same trick, so it's best to localize all this per-cpu business in
mm/kaiser.c: moving that part of the initialization from setup_pcid()
to kaiser_setup_pcid(); with kaiser_flush_tlb_on_return_to_user() the
function for noting an X86_CR3_PCID_USER_FLUSH. And let's keep a
KAISER_SHADOW_PGD_OFFSET in there, to avoid the extra OR on exit.
I did try to make the feature tests in asm/tlbflush.h more consistent
with each other: there seem to be far too many ways of performing such
tests, and I don't have a good grasp of their differences. At first
I converted them all to be static_cpu_has(): but that proved to be a
mistake, as the comment in __native_flush_tlb_single() hints; so then
I reversed and made them all this_cpu_has(). Probably all gratuitous
change, but that's the way it's working at present.
I am slightly bothered by the way non-per-cpu X86_CR3_PCID_KERN_VAR
gets re-initialized by each cpu (before and after these changes):
no problem when (as usual) all cpus on a machine have the same
features, but in principle incorrect. However, my experiment
to per-cpu-ify that one did not end well...
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/kaiser.h | 18 +++++++-----
arch/x86/include/asm/tlbflush.h | 58 +++++++++++++++++++++++++++-------------
arch/x86/kernel/cpu/common.c | 22 ---------------
arch/x86/mm/kaiser.c | 50 ++++++++++++++++++++++++++++++----
arch/x86/mm/tlb.c | 46 ++++++++++++-------------------
5 files changed, 114 insertions(+), 80 deletions(-)
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -32,13 +32,12 @@ movq \reg, %cr3
.macro _SWITCH_TO_USER_CR3 reg
movq %cr3, \reg
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
-/*
- * This can obviously be one instruction by putting the
- * KAISER_SHADOW_PGD_OFFSET bit in the X86_CR3_PCID_USER_VAR.
- * But, just leave it now for simplicity.
- */
-orq X86_CR3_PCID_USER_VAR, \reg
-orq $(KAISER_SHADOW_PGD_OFFSET), \reg
+orq PER_CPU_VAR(X86_CR3_PCID_USER_VAR), \reg
+js 9f
+// FLUSH this time, reset to NOFLUSH for next time
+// But if nopcid? Consider using 0x80 for user pcid?
+movb $(0x80), PER_CPU_VAR(X86_CR3_PCID_USER_VAR+7)
+9:
movq \reg, %cr3
.endm
@@ -90,6 +89,11 @@ movq PER_CPU_VAR(unsafe_stack_register_b
*/
DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
+extern unsigned long X86_CR3_PCID_KERN_VAR;
+DECLARE_PER_CPU(unsigned long, X86_CR3_PCID_USER_VAR);
+
+extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
+
/**
* kaiser_add_mapping - map a virtual memory part to the shadow (user) mapping
* @addr: the start address of the range
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -12,6 +12,7 @@ static inline void __invpcid(unsigned lo
unsigned long type)
{
struct { u64 d[2]; } desc = { { pcid, addr } };
+
/*
* The memory clobber is because the whole point is to invalidate
* stale TLB entries and, especially if we're flushing global
@@ -130,27 +131,42 @@ static inline void cr4_set_bits_and_upda
cr4_set_bits(mask);
}
+/*
+ * Declare a couple of kaiser interfaces here for convenience,
+ * to avoid the need for asm/kaiser.h in unexpected places.
+ */
+#ifdef CONFIG_KAISER
+extern void kaiser_setup_pcid(void);
+extern void kaiser_flush_tlb_on_return_to_user(void);
+#else
+static inline void kaiser_setup_pcid(void)
+{
+}
+static inline void kaiser_flush_tlb_on_return_to_user(void)
+{
+}
+#endif
+
static inline void __native_flush_tlb(void)
{
- if (!cpu_feature_enabled(X86_FEATURE_INVPCID)) {
- /*
- * If current->mm == NULL then we borrow a mm which may change during a
- * task switch and therefore we must not be preempted while we write CR3
- * back:
+ if (this_cpu_has(X86_FEATURE_INVPCID)) {
+ /*
+ * Note, this works with CR4.PCIDE=0 or 1.
*/
- preempt_disable();
- native_write_cr3(native_read_cr3());
- preempt_enable();
+ invpcid_flush_all_nonglobals();
return;
}
+
/*
- * We are no longer using globals with KAISER, so a
- * "nonglobals" flush would work too. But, this is more
- * conservative.
- *
- * Note, this works with CR4.PCIDE=0 or 1.
+ * If current->mm == NULL then we borrow a mm which may change during a
+ * task switch and therefore we must not be preempted while we write CR3
+ * back:
*/
- invpcid_flush_all();
+ preempt_disable();
+ if (this_cpu_has(X86_FEATURE_PCID))
+ kaiser_flush_tlb_on_return_to_user();
+ native_write_cr3(native_read_cr3());
+ preempt_enable();
}
static inline void __native_flush_tlb_global_irq_disabled(void)
@@ -166,9 +182,13 @@ static inline void __native_flush_tlb_gl
static inline void __native_flush_tlb_global(void)
{
+#ifdef CONFIG_KAISER
+ /* Globals are not used at all */
+ __native_flush_tlb();
+#else
unsigned long flags;
- if (static_cpu_has(X86_FEATURE_INVPCID)) {
+ if (this_cpu_has(X86_FEATURE_INVPCID)) {
/*
* Using INVPCID is considerably faster than a pair of writes
* to CR4 sandwiched inside an IRQ flag save/restore.
@@ -185,10 +205,9 @@ static inline void __native_flush_tlb_gl
* be called from deep inside debugging code.)
*/
raw_local_irq_save(flags);
-
__native_flush_tlb_global_irq_disabled();
-
raw_local_irq_restore(flags);
+#endif
}
static inline void __native_flush_tlb_single(unsigned long addr)
@@ -199,9 +218,12 @@ static inline void __native_flush_tlb_si
*
* The ASIDs used below are hard-coded. But, we must not
* call invpcid(type=1/2) before CR4.PCIDE=1. Just call
- * invpcid in the case we are called early.
+ * invlpg in the case we are called early.
*/
+
if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) {
+ if (this_cpu_has(X86_FEATURE_PCID))
+ kaiser_flush_tlb_on_return_to_user();
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
return;
}
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -321,33 +321,12 @@ static __always_inline void setup_smap(s
}
}
-/*
- * These can have bit 63 set, so we can not just use a plain "or"
- * instruction to get their value or'd into CR3. It would take
- * another register. So, we use a memory reference to these
- * instead.
- *
- * This is also handy because systems that do not support
- * PCIDs just end up or'ing a 0 into their CR3, which does
- * no harm.
- */
-__aligned(PAGE_SIZE) unsigned long X86_CR3_PCID_KERN_VAR = 0;
-__aligned(PAGE_SIZE) unsigned long X86_CR3_PCID_USER_VAR = 0;
-
static void setup_pcid(struct cpuinfo_x86 *c)
{
if (cpu_has(c, X86_FEATURE_PCID)) {
if (cpu_has(c, X86_FEATURE_PGE)) {
cr4_set_bits(X86_CR4_PCIDE);
/*
- * These variables are used by the entry/exit
- * code to change PCIDs.
- */
-#ifdef CONFIG_KAISER
- X86_CR3_PCID_KERN_VAR = X86_CR3_PCID_KERN_NOFLUSH;
- X86_CR3_PCID_USER_VAR = X86_CR3_PCID_USER_NOFLUSH;
-#endif
- /*
* INVPCID has two "groups" of types:
* 1/2: Invalidate an individual address
* 3/4: Invalidate all contexts
@@ -372,6 +351,7 @@ static void setup_pcid(struct cpuinfo_x8
clear_cpu_cap(c, X86_FEATURE_PCID);
}
}
+ kaiser_setup_pcid();
}
/*
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -12,12 +12,26 @@
#include <linux/ftrace.h>
#include <asm/kaiser.h>
+#include <asm/tlbflush.h> /* to verify its kaiser declarations */
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/desc.h>
+
#ifdef CONFIG_KAISER
+__visible
+DEFINE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
+
+/*
+ * These can have bit 63 set, so we can not just use a plain "or"
+ * instruction to get their value or'd into CR3. It would take
+ * another register. So, we use a memory reference to these instead.
+ *
+ * This is also handy because systems that do not support PCIDs
+ * just end up or'ing a 0 into their CR3, which does no harm.
+ */
+__aligned(PAGE_SIZE) unsigned long X86_CR3_PCID_KERN_VAR;
+DEFINE_PER_CPU(unsigned long, X86_CR3_PCID_USER_VAR);
-__visible DEFINE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
/*
* At runtime, the only things we map are some things for CPU
* hotplug, and stacks for new processes. No two CPUs will ever
@@ -239,9 +253,6 @@ static void __init kaiser_init_all_pgds(
WARN_ON(__ret); \
} while (0)
-extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
-extern unsigned long X86_CR3_PCID_KERN_VAR;
-extern unsigned long X86_CR3_PCID_USER_VAR;
/*
* If anything in here fails, we will likely die on one of the
* first kernel->user transitions and init will die. But, we
@@ -295,8 +306,6 @@ void __init kaiser_init(void)
kaiser_add_user_map_early(&X86_CR3_PCID_KERN_VAR, PAGE_SIZE,
__PAGE_KERNEL);
- kaiser_add_user_map_early(&X86_CR3_PCID_USER_VAR, PAGE_SIZE,
- __PAGE_KERNEL);
}
/* Add a mapping to the shadow mapping, and synchronize the mappings */
@@ -361,4 +370,33 @@ pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp,
}
return pgd;
}
+
+void kaiser_setup_pcid(void)
+{
+ unsigned long kern_cr3 = 0;
+ unsigned long user_cr3 = KAISER_SHADOW_PGD_OFFSET;
+
+ if (this_cpu_has(X86_FEATURE_PCID)) {
+ kern_cr3 |= X86_CR3_PCID_KERN_NOFLUSH;
+ user_cr3 |= X86_CR3_PCID_USER_NOFLUSH;
+ }
+ /*
+ * These variables are used by the entry/exit
+ * code to change PCID and pgd and TLB flushing.
+ */
+ X86_CR3_PCID_KERN_VAR = kern_cr3;
+ this_cpu_write(X86_CR3_PCID_USER_VAR, user_cr3);
+}
+
+/*
+ * Make a note that this cpu will need to flush USER tlb on return to user.
+ * Caller checks whether this_cpu_has(X86_FEATURE_PCID) before calling:
+ * if cpu does not, then the NOFLUSH bit will never have been set.
+ */
+void kaiser_flush_tlb_on_return_to_user(void)
+{
+ this_cpu_write(X86_CR3_PCID_USER_VAR,
+ X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET);
+}
+EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user);
#endif /* CONFIG_KAISER */
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -6,13 +6,14 @@
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/cpu.h>
+#include <linux/debugfs.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/cache.h>
#include <asm/apic.h>
#include <asm/uv/uv.h>
-#include <linux/debugfs.h>
+#include <asm/kaiser.h>
/*
* TLB flushing, formerly SMP-only
@@ -38,34 +39,23 @@ static void load_new_mm_cr3(pgd_t *pgdir
{
unsigned long new_mm_cr3 = __pa(pgdir);
- /*
- * KAISER, plus PCIDs needs some extra work here. But,
- * if either of features is not present, we need no
- * PCIDs here and just do a normal, full TLB flush with
- * the write_cr3()
- */
- if (!IS_ENABLED(CONFIG_KAISER) ||
- !cpu_feature_enabled(X86_FEATURE_PCID))
- goto out_set_cr3;
- /*
- * We reuse the same PCID for different tasks, so we must
- * flush all the entires for the PCID out when we change
- * tasks.
- */
- new_mm_cr3 = X86_CR3_PCID_KERN_FLUSH | __pa(pgdir);
-
- /*
- * The flush from load_cr3() may leave old TLB entries
- * for userspace in place. We must flush that context
- * separately. We can theoretically delay doing this
- * until we actually load up the userspace CR3, but
- * that's a bit tricky. We have to have the "need to
- * flush userspace PCID" bit per-cpu and check it in the
- * exit-to-userspace paths.
- */
- invpcid_flush_single_context(X86_CR3_PCID_ASID_USER);
+#ifdef CONFIG_KAISER
+ if (this_cpu_has(X86_FEATURE_PCID)) {
+ /*
+ * We reuse the same PCID for different tasks, so we must
+ * flush all the entries for the PCID out when we change tasks.
+ * Flush KERN below, flush USER when returning to userspace in
+ * kaiser's SWITCH_USER_CR3 (_SWITCH_TO_USER_CR3) macro.
+ *
+ * invpcid_flush_single_context(X86_CR3_PCID_ASID_USER) could
+ * do it here, but can only be used if X86_FEATURE_INVPCID is
+ * available - and many machines support pcid without invpcid.
+ */
+ new_mm_cr3 |= X86_CR3_PCID_KERN_FLUSH;
+ kaiser_flush_tlb_on_return_to_user();
+ }
+#endif /* CONFIG_KAISER */
-out_set_cr3:
/*
* Caution: many callers of this function expect
* that load_cr3() is serializing and orders TLB
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: kaiser_remove_mapping() move along the pgd" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: kaiser_remove_mapping() move along the pgd
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Mon, 2 Oct 2017 10:57:24 -0700
Subject: kaiser: kaiser_remove_mapping() move along the pgd
From: Hugh Dickins <hughd(a)google.com>
When removing the bogus comment from kaiser_remove_mapping(),
I really ought to have checked the extent of its bogosity: as
Neel points out, there is nothing to stop unmap_pud_range_nofree()
from continuing beyond the end of a pud (and starting in the wrong
position on the next).
Fix kaiser_remove_mapping() to constrain the extent and advance pgd
pointer correctly: use pgd_addr_end() macro as used throughout base
mm (but don't assume page-rounded start and size in this case).
But this bug was very unlikely to trigger in this backport: since
any buddy allocation is contained within a single pud extent, and
we are not using vmapped stacks (and are only mapping one page of
stack anyway): the only way to hit this bug here would be when
freeing a large modified ldt.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/kaiser.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -297,11 +297,13 @@ void kaiser_remove_mapping(unsigned long
extern void unmap_pud_range_nofree(pgd_t *pgd,
unsigned long start, unsigned long end);
unsigned long end = start + size;
- unsigned long addr;
+ unsigned long addr, next;
+ pgd_t *pgd;
- for (addr = start; addr < end; addr += PGDIR_SIZE) {
- pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(addr));
- unmap_pud_range_nofree(pgd, addr, end);
+ pgd = native_get_shadow_pgd(pgd_offset_k(start));
+ for (addr = start; addr < end; pgd++, addr = next) {
+ next = pgd_addr_end(addr, end);
+ unmap_pud_range_nofree(pgd, addr, next);
}
}
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: kaiser_flush_tlb_on_return_to_user() check PCID" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: kaiser_flush_tlb_on_return_to_user() check PCID
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sat, 4 Nov 2017 18:43:06 -0700
Subject: kaiser: kaiser_flush_tlb_on_return_to_user() check PCID
From: Hugh Dickins <hughd(a)google.com>
Let kaiser_flush_tlb_on_return_to_user() do the X86_FEATURE_PCID
check, instead of each caller doing it inline first: nobody needs
to optimize for the noPCID case, it's clearer this way, and better
suits later changes. Replace those no-op X86_CR3_PCID_KERN_FLUSH lines
by a BUILD_BUG_ON() in load_new_mm_cr3(), in case something changes.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/tlbflush.h | 4 ++--
arch/x86/mm/kaiser.c | 6 +++---
arch/x86/mm/tlb.c | 8 ++++----
3 files changed, 9 insertions(+), 9 deletions(-)
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -157,7 +157,7 @@ static inline void __native_flush_tlb(vo
* back:
*/
preempt_disable();
- if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID))
+ if (kaiser_enabled)
kaiser_flush_tlb_on_return_to_user();
native_write_cr3(native_read_cr3());
preempt_enable();
@@ -216,7 +216,7 @@ static inline void __native_flush_tlb_si
*/
if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) {
- if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID))
+ if (kaiser_enabled)
kaiser_flush_tlb_on_return_to_user();
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
return;
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -436,12 +436,12 @@ void kaiser_setup_pcid(void)
/*
* Make a note that this cpu will need to flush USER tlb on return to user.
- * Caller checks whether this_cpu_has(X86_FEATURE_PCID) before calling:
- * if cpu does not, then the NOFLUSH bit will never have been set.
+ * If cpu does not have PCID, then the NOFLUSH bit will never have been set.
*/
void kaiser_flush_tlb_on_return_to_user(void)
{
- this_cpu_write(x86_cr3_pcid_user,
+ if (this_cpu_has(X86_FEATURE_PCID))
+ this_cpu_write(x86_cr3_pcid_user,
X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET);
}
EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user);
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -39,7 +39,7 @@ static void load_new_mm_cr3(pgd_t *pgdir
{
unsigned long new_mm_cr3 = __pa(pgdir);
- if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID)) {
+ if (kaiser_enabled) {
/*
* We reuse the same PCID for different tasks, so we must
* flush all the entries for the PCID out when we change tasks.
@@ -50,10 +50,10 @@ static void load_new_mm_cr3(pgd_t *pgdir
* do it here, but can only be used if X86_FEATURE_INVPCID is
* available - and many machines support pcid without invpcid.
*
- * The line below is a no-op: X86_CR3_PCID_KERN_FLUSH is now 0;
- * but keep that line in there in case something changes.
+ * If X86_CR3_PCID_KERN_FLUSH actually added something, then it
+ * would be needed in the write_cr3() below - if PCIDs enabled.
*/
- new_mm_cr3 |= X86_CR3_PCID_KERN_FLUSH;
+ BUILD_BUG_ON(X86_CR3_PCID_KERN_FLUSH);
kaiser_flush_tlb_on_return_to_user();
}
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: KAISER depends on SMP" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: KAISER depends on SMP
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-kaiser-depends-on-smp.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Wed, 13 Sep 2017 14:03:10 -0700
Subject: kaiser: KAISER depends on SMP
From: Hugh Dickins <hughd(a)google.com>
It is absurd that KAISER should depend on SMP, but apparently nobody
has tried a UP build before: which breaks on implicit declaration of
function 'per_cpu_offset' in arch/x86/mm/kaiser.c.
Now, you would expect that to be trivially fixed up; but looking at
the System.map when that block is #ifdef'ed out of kaiser_init(),
I see that in a UP build __per_cpu_user_mapped_end is precisely at
__per_cpu_user_mapped_start, and the items carefully gathered into
that section for user-mapping on SMP, dispersed elsewhere on UP.
So, some other kind of section assignment will be needed on UP,
but implementing that is not a priority: just make KAISER depend
on SMP for now.
Also inserted a blank line before the option, tidied up the
brief Kconfig help message, and added an "If unsure, Y".
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
security/Kconfig | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -30,14 +30,16 @@ config SECURITY
model will be used.
If you are unsure how to answer this question, answer N.
+
config KAISER
bool "Remove the kernel mapping in user mode"
default y
- depends on X86_64
- depends on !PARAVIRT
+ depends on X86_64 && SMP && !PARAVIRT
help
- This enforces a strict kernel and user space isolation in order to close
- hardware side channels on kernel address information.
+ This enforces a strict kernel and user space isolation, in order
+ to close hardware side channels on kernel address information.
+
+ If you are unsure how to answer this question, answer Y.
config KAISER_REAL_SWITCH
bool "KAISER: actually switch page tables"
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: fix unlikely error in alloc_ldt_struct()" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: fix unlikely error in alloc_ldt_struct()
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Mon, 4 Dec 2017 20:13:35 -0800
Subject: kaiser: fix unlikely error in alloc_ldt_struct()
From: Hugh Dickins <hughd(a)google.com>
An error from kaiser_add_mapping() here is not at all likely, but
Eric Biggers rightly points out that __free_ldt_struct() relies on
new_ldt->size being initialized: move that up.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/kernel/ldt.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -79,11 +79,11 @@ static struct ldt_struct *alloc_ldt_stru
ret = kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size,
__PAGE_KERNEL);
+ new_ldt->size = size;
if (ret) {
__free_ldt_struct(new_ldt);
return NULL;
}
- new_ldt->size = size;
return new_ldt;
}
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: fix regs to do_nmi() ifndef CONFIG_KAISER" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: fix regs to do_nmi() ifndef CONFIG_KAISER
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Thu, 21 Sep 2017 20:39:56 -0700
Subject: kaiser: fix regs to do_nmi() ifndef CONFIG_KAISER
From: Hugh Dickins <hughd(a)google.com>
pjt has observed that nmi's second (nmi_from_kernel) call to do_nmi()
adjusted the %rdi regs arg, rightly when CONFIG_KAISER, but wrongly
when not CONFIG_KAISER.
Although the minimal change is to add an #ifdef CONFIG_KAISER around
the addq line, that looks cluttered, and I prefer how the first call
to do_nmi() handled it: prepare args in %rdi and %rsi before getting
into the CONFIG_KAISER block, since it does not touch them at all.
And while we're here, place the "#ifdef CONFIG_KAISER" that follows
each, to enclose the "Unconditionally restore CR3" comment: matching
how the "Unconditionally use kernel CR3" comment above is enclosed.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1297,12 +1297,13 @@ ENTRY(nmi)
movq %rax, %cr3
#endif
call do_nmi
+
+#ifdef CONFIG_KAISER
/*
* Unconditionally restore CR3. I know we return to
* kernel code that needs user CR3, but do we ever return
* to "user mode" where we need the kernel CR3?
*/
-#ifdef CONFIG_KAISER
popq %rax
mov %rax, %cr3
#endif
@@ -1526,6 +1527,8 @@ end_repeat_nmi:
SWAPGS
xorl %ebx, %ebx
1:
+ movq %rsp, %rdi
+ movq $-1, %rsi
#ifdef CONFIG_KAISER
/* Unconditionally use kernel CR3 for do_nmi() */
/* %rax is saved above, so OK to clobber here */
@@ -1538,16 +1541,14 @@ end_repeat_nmi:
#endif
/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
- movq %rsp, %rdi
- addq $8, %rdi /* point %rdi at ptregs, fixed up for CR3 */
- movq $-1, %rsi
call do_nmi
+
+#ifdef CONFIG_KAISER
/*
* Unconditionally restore CR3. We might be returning to
* kernel code that needs user CR3, like just just before
* a sysret.
*/
-#ifdef CONFIG_KAISER
popq %rax
mov %rax, %cr3
#endif
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: fix perf crashes" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: fix perf crashes
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-fix-perf-crashes.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Wed, 23 Aug 2017 14:21:14 -0700
Subject: kaiser: fix perf crashes
From: Hugh Dickins <hughd(a)google.com>
Avoid perf crashes: place debug_store in the user-mapped per-cpu area
instead of allocating, and use page allocator plus kaiser_add_mapping()
to keep the BTS and PEBS buffers user-mapped (that is, present in the
user mapping, though visible only to kernel and hardware). The PEBS
fixup buffer does not need this treatment.
The need for a user-mapped struct debug_store showed up before doing
any conscious perf testing: in a couple of kernel paging oopses on
Westmere, implicating the debug_store offset of the per-cpu area.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/kernel/cpu/perf_event_intel_ds.c | 57 +++++++++++++++++++++++-------
1 file changed, 45 insertions(+), 12 deletions(-)
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -2,11 +2,15 @@
#include <linux/types.h>
#include <linux/slab.h>
+#include <asm/kaiser.h>
#include <asm/perf_event.h>
#include <asm/insn.h>
#include "perf_event.h"
+static
+DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct debug_store, cpu_debug_store);
+
/* The size of a BTS record in bytes: */
#define BTS_RECORD_SIZE 24
@@ -268,6 +272,39 @@ void fini_debug_store_on_cpu(int cpu)
static DEFINE_PER_CPU(void *, insn_buffer);
+static void *dsalloc(size_t size, gfp_t flags, int node)
+{
+#ifdef CONFIG_KAISER
+ unsigned int order = get_order(size);
+ struct page *page;
+ unsigned long addr;
+
+ page = __alloc_pages_node(node, flags | __GFP_ZERO, order);
+ if (!page)
+ return NULL;
+ addr = (unsigned long)page_address(page);
+ if (kaiser_add_mapping(addr, size, __PAGE_KERNEL) < 0) {
+ __free_pages(page, order);
+ addr = 0;
+ }
+ return (void *)addr;
+#else
+ return kmalloc_node(size, flags | __GFP_ZERO, node);
+#endif
+}
+
+static void dsfree(const void *buffer, size_t size)
+{
+#ifdef CONFIG_KAISER
+ if (!buffer)
+ return;
+ kaiser_remove_mapping((unsigned long)buffer, size);
+ free_pages((unsigned long)buffer, get_order(size));
+#else
+ kfree(buffer);
+#endif
+}
+
static int alloc_pebs_buffer(int cpu)
{
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -278,7 +315,7 @@ static int alloc_pebs_buffer(int cpu)
if (!x86_pmu.pebs)
return 0;
- buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
+ buffer = dsalloc(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
if (unlikely(!buffer))
return -ENOMEM;
@@ -289,7 +326,7 @@ static int alloc_pebs_buffer(int cpu)
if (x86_pmu.intel_cap.pebs_format < 2) {
ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
if (!ibuffer) {
- kfree(buffer);
+ dsfree(buffer, x86_pmu.pebs_buffer_size);
return -ENOMEM;
}
per_cpu(insn_buffer, cpu) = ibuffer;
@@ -315,7 +352,8 @@ static void release_pebs_buffer(int cpu)
kfree(per_cpu(insn_buffer, cpu));
per_cpu(insn_buffer, cpu) = NULL;
- kfree((void *)(unsigned long)ds->pebs_buffer_base);
+ dsfree((void *)(unsigned long)ds->pebs_buffer_base,
+ x86_pmu.pebs_buffer_size);
ds->pebs_buffer_base = 0;
}
@@ -329,7 +367,7 @@ static int alloc_bts_buffer(int cpu)
if (!x86_pmu.bts)
return 0;
- buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+ buffer = dsalloc(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
if (unlikely(!buffer)) {
WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
return -ENOMEM;
@@ -355,19 +393,15 @@ static void release_bts_buffer(int cpu)
if (!ds || !x86_pmu.bts)
return;
- kfree((void *)(unsigned long)ds->bts_buffer_base);
+ dsfree((void *)(unsigned long)ds->bts_buffer_base, BTS_BUFFER_SIZE);
ds->bts_buffer_base = 0;
}
static int alloc_ds_buffer(int cpu)
{
- int node = cpu_to_node(cpu);
- struct debug_store *ds;
-
- ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
- if (unlikely(!ds))
- return -ENOMEM;
+ struct debug_store *ds = per_cpu_ptr(&cpu_debug_store, cpu);
+ memset(ds, 0, sizeof(*ds));
per_cpu(cpu_hw_events, cpu).ds = ds;
return 0;
@@ -381,7 +415,6 @@ static void release_ds_buffer(int cpu)
return;
per_cpu(cpu_hw_events, cpu).ds = NULL;
- kfree(ds);
}
void release_ds_buffers(void)
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: fix build and FIXME in alloc_ldt_struct()" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: fix build and FIXME in alloc_ldt_struct()
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 3 Sep 2017 17:09:44 -0700
Subject: kaiser: fix build and FIXME in alloc_ldt_struct()
From: Hugh Dickins <hughd(a)google.com>
Include linux/kaiser.h instead of asm/kaiser.h to build ldt.c without
CONFIG_KAISER. kaiser_add_mapping() does already return an error code,
so fix the FIXME.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/kernel/ldt.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -16,9 +16,9 @@
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
+#include <linux/kaiser.h>
#include <asm/ldt.h>
-#include <asm/kaiser.h>
#include <asm/desc.h>
#include <asm/mmu_context.h>
#include <asm/syscalls.h>
@@ -49,7 +49,7 @@ static struct ldt_struct *alloc_ldt_stru
{
struct ldt_struct *new_ldt;
int alloc_size;
- int ret = 0;
+ int ret;
if (size > LDT_ENTRIES)
return NULL;
@@ -77,10 +77,8 @@ static struct ldt_struct *alloc_ldt_stru
return NULL;
}
- // FIXME: make kaiser_add_mapping() return an error code
- // when it fails
- kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size,
- __PAGE_KERNEL);
+ ret = kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size,
+ __PAGE_KERNEL);
if (ret) {
__free_ldt_struct(new_ldt);
return NULL;
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: ENOMEM if kaiser_pagetable_walk() NULL" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: ENOMEM if kaiser_pagetable_walk() NULL
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-enomem-if-kaiser_pagetable_walk-null.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 3 Sep 2017 18:48:02 -0700
Subject: kaiser: ENOMEM if kaiser_pagetable_walk() NULL
From: Hugh Dickins <hughd(a)google.com>
kaiser_add_user_map() took no notice when kaiser_pagetable_walk() failed.
And avoid its might_sleep() when atomic (though atomic at present unused).
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/kaiser.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -99,11 +99,11 @@ static pte_t *kaiser_pagetable_walk(unsi
pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(address));
gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
- might_sleep();
if (is_atomic) {
gfp &= ~GFP_KERNEL;
gfp |= __GFP_HIGH | __GFP_ATOMIC;
- }
+ } else
+ might_sleep();
if (pgd_none(*pgd)) {
WARN_ONCE(1, "All shadow pgds should have been populated");
@@ -160,13 +160,17 @@ int kaiser_add_user_map(const void *__st
unsigned long end_addr = PAGE_ALIGN(start_addr + size);
unsigned long target_address;
- for (;address < end_addr; address += PAGE_SIZE) {
+ for (; address < end_addr; address += PAGE_SIZE) {
target_address = get_pa_from_mapping(address);
if (target_address == -1) {
ret = -EIO;
break;
}
pte = kaiser_pagetable_walk(address, false);
+ if (!pte) {
+ ret = -ENOMEM;
+ break;
+ }
if (pte_none(*pte)) {
set_pte(pte, __pte(flags | target_address));
} else {
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: drop is_atomic arg to kaiser_pagetable_walk()" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: drop is_atomic arg to kaiser_pagetable_walk()
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 29 Oct 2017 11:36:19 -0700
Subject: kaiser: drop is_atomic arg to kaiser_pagetable_walk()
From: Hugh Dickins <hughd(a)google.com>
I have not observed a might_sleep() warning from setup_fixmap_gdt()'s
use of kaiser_add_mapping() in our tree (why not?), but like upstream
we have not provided a way for that to pass is_atomic true down to
kaiser_pagetable_walk(), and at startup it's far from a likely source
of trouble: so just delete the walk's is_atomic arg and might_sleep().
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/kaiser.c | 10 ++--------
1 file changed, 2 insertions(+), 8 deletions(-)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -108,19 +108,13 @@ static inline unsigned long get_pa_from_
*
* Returns a pointer to a PTE on success, or NULL on failure.
*/
-static pte_t *kaiser_pagetable_walk(unsigned long address, bool is_atomic)
+static pte_t *kaiser_pagetable_walk(unsigned long address)
{
pmd_t *pmd;
pud_t *pud;
pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(address));
gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
- if (is_atomic) {
- gfp &= ~GFP_KERNEL;
- gfp |= __GFP_HIGH | __GFP_ATOMIC;
- } else
- might_sleep();
-
if (pgd_none(*pgd)) {
WARN_ONCE(1, "All shadow pgds should have been populated");
return NULL;
@@ -195,7 +189,7 @@ static int kaiser_add_user_map(const voi
ret = -EIO;
break;
}
- pte = kaiser_pagetable_walk(address, false);
+ pte = kaiser_pagetable_walk(address);
if (!pte) {
ret = -ENOMEM;
break;
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: do not set _PAGE_NX on pgd_none" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: do not set _PAGE_NX on pgd_none
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-do-not-set-_page_nx-on-pgd_none.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Tue, 5 Sep 2017 12:05:01 -0700
Subject: kaiser: do not set _PAGE_NX on pgd_none
From: Hugh Dickins <hughd(a)google.com>
native_pgd_clear() uses native_set_pgd(), so native_set_pgd() must
avoid setting the _PAGE_NX bit on an otherwise pgd_none() entry:
usually that just generated a warning on exit, but sometimes
more mysterious and damaging failures (our production machines
could not complete booting).
The original fix to this just avoided adding _PAGE_NX to
an empty entry; but eventually more problems surfaced with kexec,
and EFI mapping expected to be a problem too. So now instead
change native_set_pgd() to update shadow only if _PAGE_USER:
A few places (kernel/machine_kexec_64.c, platform/efi/efi_64.c for sure)
use set_pgd() to set up a temporary internal virtual address space, with
physical pages remapped at what Kaiser regards as userspace addresses:
Kaiser then assumes a shadow pgd follows, which it will try to corrupt.
This appears to be responsible for the recent kexec and kdump failures;
though it's unclear how those did not manifest as a problem before.
Ah, the shadow pgd will only be assumed to "follow" if the requested
pgd is on an even-numbered page: so I suppose it was going wrong 50%
of the time all along.
What we need is a flag to set_pgd(), to tell it we're dealing with
userspace. Er, isn't that what the pgd's _PAGE_USER bit is saying?
Add a test for that. But we cannot do the same for pgd_clear()
(which may be called to clear corrupted entries - set aside the
question of "corrupt in which pgd?" until later), so there just
rely on pgd_clear() not being called in the problematic cases -
with a WARN_ON_ONCE() which should fire half the time if it is.
But this is getting too big for an inline function: move it into
arch/x86/mm/kaiser.c (which then demands a boot/compressed mod);
and de-void and de-space native_get_shadow/normal_pgd() while here.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/boot/compressed/misc.h | 1
arch/x86/include/asm/pgtable_64.h | 51 +++++++++-----------------------------
arch/x86/mm/kaiser.c | 42 +++++++++++++++++++++++++++++++
3 files changed, 56 insertions(+), 38 deletions(-)
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -9,6 +9,7 @@
*/
#undef CONFIG_PARAVIRT
#undef CONFIG_PARAVIRT_SPINLOCKS
+#undef CONFIG_KAISER
#undef CONFIG_KASAN
#include <linux/linkage.h>
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -107,61 +107,36 @@ static inline void native_pud_clear(pud_
}
#ifdef CONFIG_KAISER
-static inline pgd_t * native_get_shadow_pgd(pgd_t *pgdp)
+extern pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd);
+
+static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp)
{
- return (pgd_t *)(void*)((unsigned long)(void*)pgdp | (unsigned long)PAGE_SIZE);
+ return (pgd_t *)((unsigned long)pgdp | (unsigned long)PAGE_SIZE);
}
-static inline pgd_t * native_get_normal_pgd(pgd_t *pgdp)
+static inline pgd_t *native_get_normal_pgd(pgd_t *pgdp)
{
- return (pgd_t *)(void*)((unsigned long)(void*)pgdp & ~(unsigned long)PAGE_SIZE);
+ return (pgd_t *)((unsigned long)pgdp & ~(unsigned long)PAGE_SIZE);
}
#else
-static inline pgd_t * native_get_shadow_pgd(pgd_t *pgdp)
+static inline pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ return pgd;
+}
+static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp)
{
BUILD_BUG_ON(1);
return NULL;
}
-static inline pgd_t * native_get_normal_pgd(pgd_t *pgdp)
+static inline pgd_t *native_get_normal_pgd(pgd_t *pgdp)
{
return pgdp;
}
#endif /* CONFIG_KAISER */
-/*
- * Page table pages are page-aligned. The lower half of the top
- * level is used for userspace and the top half for the kernel.
- * This returns true for user pages that need to get copied into
- * both the user and kernel copies of the page tables, and false
- * for kernel pages that should only be in the kernel copy.
- */
-static inline bool is_userspace_pgd(void *__ptr)
-{
- unsigned long ptr = (unsigned long)__ptr;
-
- return ((ptr % PAGE_SIZE) < (PAGE_SIZE / 2));
-}
-
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
-#ifdef CONFIG_KAISER
- pteval_t extra_kern_pgd_flags = 0;
- /* Do we need to also populate the shadow pgd? */
- if (is_userspace_pgd(pgdp)) {
- native_get_shadow_pgd(pgdp)->pgd = pgd.pgd;
- /*
- * Even if the entry is *mapping* userspace, ensure
- * that userspace can not use it. This way, if we
- * get out to userspace running on the kernel CR3,
- * userspace will crash instead of running.
- */
- extra_kern_pgd_flags = _PAGE_NX;
- }
- pgdp->pgd = pgd.pgd;
- pgdp->pgd |= extra_kern_pgd_flags;
-#else /* CONFIG_KAISER */
- *pgdp = pgd;
-#endif
+ *pgdp = kaiser_set_shadow_pgd(pgdp, pgd);
}
static inline void native_pgd_clear(pgd_t *pgd)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -303,4 +303,46 @@ void kaiser_remove_mapping(unsigned long
unmap_pud_range_nofree(pgd, addr, end);
}
}
+
+/*
+ * Page table pages are page-aligned. The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ * This returns true for user pages that need to get copied into
+ * both the user and kernel copies of the page tables, and false
+ * for kernel pages that should only be in the kernel copy.
+ */
+static inline bool is_userspace_pgd(pgd_t *pgdp)
+{
+ return ((unsigned long)pgdp % PAGE_SIZE) < (PAGE_SIZE / 2);
+}
+
+pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ /*
+ * Do we need to also populate the shadow pgd? Check _PAGE_USER to
+ * skip cases like kexec and EFI which make temporary low mappings.
+ */
+ if (pgd.pgd & _PAGE_USER) {
+ if (is_userspace_pgd(pgdp)) {
+ native_get_shadow_pgd(pgdp)->pgd = pgd.pgd;
+ /*
+ * Even if the entry is *mapping* userspace, ensure
+ * that userspace can not use it. This way, if we
+ * get out to userspace running on the kernel CR3,
+ * userspace will crash instead of running.
+ */
+ pgd.pgd |= _PAGE_NX;
+ }
+ } else if (!pgd.pgd) {
+ /*
+ * pgd_clear() cannot check _PAGE_USER, and is even used to
+ * clear corrupted pgd entries: so just rely on cases like
+ * kexec and EFI never to be using pgd_clear().
+ */
+ if (!WARN_ON_ONCE((unsigned long)pgdp & PAGE_SIZE) &&
+ is_userspace_pgd(pgdp))
+ native_get_shadow_pgd(pgdp)->pgd = pgd.pgd;
+ }
+ return pgd;
+}
#endif /* CONFIG_KAISER */
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: delete KAISER_REAL_SWITCH option" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: delete KAISER_REAL_SWITCH option
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-delete-kaiser_real_switch-option.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 3 Sep 2017 18:30:43 -0700
Subject: kaiser: delete KAISER_REAL_SWITCH option
From: Hugh Dickins <hughd(a)google.com>
We fail to see what CONFIG_KAISER_REAL_SWITCH is for: it seems to be
left over from early development, and now just obscures tricky parts
of the code. Delete it before adding PCIDs, or nokaiser boot option.
(Or if there is some good reason to keep the option, then it needs
a help text - and a "depends on KAISER", so that all those without
KAISER are not asked the question.)
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/entry/entry_64.S | 4 ----
arch/x86/include/asm/kaiser.h | 4 ----
security/Kconfig | 4 ----
3 files changed, 12 deletions(-)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1291,9 +1291,7 @@ ENTRY(nmi)
/* %rax is saved above, so OK to clobber here */
movq %cr3, %rax
pushq %rax
-#ifdef CONFIG_KAISER_REAL_SWITCH
andq $(~KAISER_SHADOW_PGD_OFFSET), %rax
-#endif
movq %rax, %cr3
#endif
call do_nmi
@@ -1534,9 +1532,7 @@ end_repeat_nmi:
/* %rax is saved above, so OK to clobber here */
movq %cr3, %rax
pushq %rax
-#ifdef CONFIG_KAISER_REAL_SWITCH
andq $(~KAISER_SHADOW_PGD_OFFSET), %rax
-#endif
movq %rax, %cr3
#endif
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -21,17 +21,13 @@
.macro _SWITCH_TO_KERNEL_CR3 reg
movq %cr3, \reg
-#ifdef CONFIG_KAISER_REAL_SWITCH
andq $(~KAISER_SHADOW_PGD_OFFSET), \reg
-#endif
movq \reg, %cr3
.endm
.macro _SWITCH_TO_USER_CR3 reg
movq %cr3, \reg
-#ifdef CONFIG_KAISER_REAL_SWITCH
orq $(KAISER_SHADOW_PGD_OFFSET), \reg
-#endif
movq \reg, %cr3
.endm
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -41,10 +41,6 @@ config KAISER
If you are unsure how to answer this question, answer Y.
-config KAISER_REAL_SWITCH
- bool "KAISER: actually switch page tables"
- default y
-
config SECURITYFS
bool "Enable the securityfs filesystem"
help
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: disabled on Xen PV" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: disabled on Xen PV
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-disabled-on-xen-pv.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Jiri Kosina <jkosina(a)suse.cz>
Date: Tue, 2 Jan 2018 14:19:49 +0100
Subject: kaiser: disabled on Xen PV
From: Jiri Kosina <jkosina(a)suse.cz>
Kaiser cannot be used on paravirtualized MMUs (namely reading and writing CR3).
This does not work with KAISER as the CR3 switch from and to user space PGD
would require to map the whole XEN_PV machinery into both.
More importantly, enabling KAISER on Xen PV doesn't make too much sense, as PV
guests use distinct %cr3 values for kernel and user already.
Signed-off-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/kaiser.c | 5 +++++
1 file changed, 5 insertions(+)
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -264,6 +264,9 @@ void __init kaiser_check_boottime_disabl
char arg[5];
int ret;
+ if (boot_cpu_has(X86_FEATURE_XENPV))
+ goto silent_disable;
+
ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
if (ret > 0) {
if (!strncmp(arg, "on", 2))
@@ -291,6 +294,8 @@ enable:
disable:
pr_info("Kernel/User page tables isolation: disabled\n");
+
+silent_disable:
kaiser_enabled = 0;
setup_clear_cpu_cap(X86_FEATURE_KAISER);
}
Patches currently in stable-queue which might be from jkosina(a)suse.cz are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-disabled-on-xen-pv.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: cleanups while trying for gold link" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: cleanups while trying for gold link
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-cleanups-while-trying-for-gold-link.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Mon, 21 Aug 2017 20:11:43 -0700
Subject: kaiser: cleanups while trying for gold link
From: Hugh Dickins <hughd(a)google.com>
While trying to get our gold link to work, four cleanups:
matched the gdt_page declaration to its definition;
in fiddling unsuccessfully with PERCPU_INPUT(), lined up backslashes;
lined up the backslashes according to convention in percpu-defs.h;
deleted the unused irq_stack_pointer addition to irq_stack_union.
Sad to report that aligning backslashes does not appear to help gold
align to 8192: but while these did not help, they are worth keeping.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/desc.h | 2 +-
arch/x86/include/asm/processor.h | 5 -----
include/asm-generic/vmlinux.lds.h | 18 ++++++++----------
include/linux/percpu-defs.h | 24 ++++++++++++------------
4 files changed, 21 insertions(+), 28 deletions(-)
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -43,7 +43,7 @@ struct gdt_page {
struct desc_struct gdt[GDT_ENTRIES];
} __attribute__((aligned(PAGE_SIZE)));
-DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
+DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page);
static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
{
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -332,11 +332,6 @@ union irq_stack_union {
char gs_base[40];
unsigned long stack_canary;
};
-
- struct {
- char irq_stack_pointer[64];
- char unused[IRQ_STACK_SIZE - 64];
- };
};
DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible;
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -725,16 +725,14 @@
*/
#define PERCPU_INPUT(cacheline) \
VMLINUX_SYMBOL(__per_cpu_start) = .; \
- \
- VMLINUX_SYMBOL(__per_cpu_user_mapped_start) = .; \
- *(.data..percpu..first) \
- . = ALIGN(cacheline); \
- *(.data..percpu..user_mapped) \
- *(.data..percpu..user_mapped..shared_aligned) \
- . = ALIGN(PAGE_SIZE); \
- *(.data..percpu..user_mapped..page_aligned) \
- VMLINUX_SYMBOL(__per_cpu_user_mapped_end) = .; \
- \
+ VMLINUX_SYMBOL(__per_cpu_user_mapped_start) = .; \
+ *(.data..percpu..first) \
+ . = ALIGN(cacheline); \
+ *(.data..percpu..user_mapped) \
+ *(.data..percpu..user_mapped..shared_aligned) \
+ . = ALIGN(PAGE_SIZE); \
+ *(.data..percpu..user_mapped..page_aligned) \
+ VMLINUX_SYMBOL(__per_cpu_user_mapped_end) = .; \
. = ALIGN(PAGE_SIZE); \
*(.data..percpu..page_aligned) \
. = ALIGN(cacheline); \
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -121,10 +121,10 @@
#define DEFINE_PER_CPU(type, name) \
DEFINE_PER_CPU_SECTION(type, name, "")
-#define DECLARE_PER_CPU_USER_MAPPED(type, name) \
+#define DECLARE_PER_CPU_USER_MAPPED(type, name) \
DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION)
-#define DEFINE_PER_CPU_USER_MAPPED(type, name) \
+#define DEFINE_PER_CPU_USER_MAPPED(type, name) \
DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION)
/*
@@ -156,11 +156,11 @@
DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
____cacheline_aligned_in_smp
-#define DECLARE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \
+#define DECLARE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \
DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION PER_CPU_SHARED_ALIGNED_SECTION) \
____cacheline_aligned_in_smp
-#define DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \
+#define DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \
DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION PER_CPU_SHARED_ALIGNED_SECTION) \
____cacheline_aligned_in_smp
@@ -185,18 +185,18 @@
/*
* Declaration/definition used for per-CPU variables that must be page aligned and need to be mapped in user mode.
*/
-#define DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \
- DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \
- __aligned(PAGE_SIZE)
-
-#define DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \
- DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \
- __aligned(PAGE_SIZE)
+#define DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \
+ DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \
+ __aligned(PAGE_SIZE)
+
+#define DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \
+ DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \
+ __aligned(PAGE_SIZE)
/*
* Declaration/definition used for per-CPU variables that must be read mostly.
*/
-#define DECLARE_PER_CPU_READ_MOSTLY(type, name) \
+#define DECLARE_PER_CPU_READ_MOSTLY(type, name) \
DECLARE_PER_CPU_SECTION(type, name, "..read_mostly")
#define DEFINE_PER_CPU_READ_MOSTLY(type, name) \
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: asm/tlbflush.h handle noPGE at lower level" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: asm/tlbflush.h handle noPGE at lower level
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sat, 4 Nov 2017 18:23:24 -0700
Subject: kaiser: asm/tlbflush.h handle noPGE at lower level
From: Hugh Dickins <hughd(a)google.com>
I found asm/tlbflush.h too twisty, and think it safer not to avoid
__native_flush_tlb_global_irq_disabled() in the kaiser_enabled case,
but instead let it handle kaiser_enabled along with cr3: it can just
use __native_flush_tlb() for that, no harm in re-disabling preemption.
(This is not the same change as Kirill and Dave have suggested for
upstream, flipping PGE in cr4: that's neat, but needs a cpu_has_pge
check; cr3 is enough for kaiser, and thought to be cheaper than cr4.)
Also delete the X86_FEATURE_INVPCID invpcid_flush_all_nonglobals()
preference from __native_flush_tlb(): unlike the invpcid_flush_all()
preference in __native_flush_tlb_global(), it's not seen in upstream
4.14, and was recently reported to be surprisingly slow.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/tlbflush.h | 27 +++------------------------
1 file changed, 3 insertions(+), 24 deletions(-)
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -151,14 +151,6 @@ static inline void kaiser_flush_tlb_on_r
static inline void __native_flush_tlb(void)
{
- if (this_cpu_has(X86_FEATURE_INVPCID)) {
- /*
- * Note, this works with CR4.PCIDE=0 or 1.
- */
- invpcid_flush_all_nonglobals();
- return;
- }
-
/*
* If current->mm == NULL then we borrow a mm which may change during a
* task switch and therefore we must not be preempted while we write CR3
@@ -182,11 +174,8 @@ static inline void __native_flush_tlb_gl
/* restore PGE as it was before */
native_write_cr4(cr4);
} else {
- /*
- * x86_64 microcode update comes this way when CR4.PGE is not
- * enabled, and it's safer for all callers to allow this case.
- */
- native_write_cr3(native_read_cr3());
+ /* do it with cr3, letting kaiser flush user PCID */
+ __native_flush_tlb();
}
}
@@ -194,12 +183,6 @@ static inline void __native_flush_tlb_gl
{
unsigned long flags;
- if (kaiser_enabled) {
- /* Globals are not used at all */
- __native_flush_tlb();
- return;
- }
-
if (this_cpu_has(X86_FEATURE_INVPCID)) {
/*
* Using INVPCID is considerably faster than a pair of writes
@@ -255,11 +238,7 @@ static inline void __native_flush_tlb_si
static inline void __flush_tlb_all(void)
{
- if (cpu_has_pge)
- __flush_tlb_global();
- else
- __flush_tlb();
-
+ __flush_tlb_global();
/*
* Note: if we somehow had PCID but not PGE, then this wouldn't work --
* we'd end up flushing kernel translations for the current ASID but
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: add "nokaiser" boot option, using ALTERNATIVE" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: add "nokaiser" boot option, using ALTERNATIVE
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-add-nokaiser-boot-option-using-alternative.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Sun, 24 Sep 2017 16:59:49 -0700
Subject: kaiser: add "nokaiser" boot option, using ALTERNATIVE
From: Hugh Dickins <hughd(a)google.com>
Added "nokaiser" boot option: an early param like "noinvpcid".
Most places now check int kaiser_enabled (#defined 0 when not
CONFIG_KAISER) instead of #ifdef CONFIG_KAISER; but entry_64.S
and entry_64_compat.S are using the ALTERNATIVE technique, which
patches in the preferred instructions at runtime. That technique
is tied to x86 cpu features, so X86_FEATURE_KAISER is fabricated.
Prior to "nokaiser", Kaiser #defined _PAGE_GLOBAL 0: revert that,
but be careful with both _PAGE_GLOBAL and CR4.PGE: setting them when
nokaiser like when !CONFIG_KAISER, but not setting either when kaiser -
neither matters on its own, but it's hard to be sure that _PAGE_GLOBAL
won't get set in some obscure corner, or something add PGE into CR4.
By omitting _PAGE_GLOBAL from __supported_pte_mask when kaiser_enabled,
all page table setup which uses pte_pfn() masks it out of the ptes.
It's slightly shameful that the same declaration versus definition of
kaiser_enabled appears in not one, not two, but in three header files
(asm/kaiser.h, asm/pgtable.h, asm/tlbflush.h). I felt safer that way,
than with #including any of those in any of the others; and did not
feel it worth an asm/kaiser_enabled.h - kernel/cpu/common.c includes
them all, so we shall hear about it if they get out of synch.
Cleanups while in the area: removed the silly #ifdef CONFIG_KAISER
from kaiser.c; removed the unused native_get_normal_pgd(); removed
the spurious reg clutter from SWITCH_*_CR3 macro stubs; corrected some
comments. But more interestingly, set CR4.PSE in secondary_startup_64:
the manual is clear that it does not matter whether it's 0 or 1 when
4-level-pts are enabled, but I was distracted to find cr4 different on
BSP and auxiliaries - BSP alone was adding PSE, in probe_page_size_mask().
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
Documentation/kernel-parameters.txt | 2 +
arch/x86/entry/entry_64.S | 15 +++++++------
arch/x86/include/asm/cpufeature.h | 3 ++
arch/x86/include/asm/kaiser.h | 27 +++++++++++++++++-------
arch/x86/include/asm/pgtable.h | 20 ++++++++++++-----
arch/x86/include/asm/pgtable_64.h | 13 +++--------
arch/x86/include/asm/pgtable_types.h | 4 ---
arch/x86/include/asm/tlbflush.h | 39 ++++++++++++++++++++++-------------
arch/x86/kernel/cpu/common.c | 28 ++++++++++++++++++++++++-
arch/x86/kernel/espfix_64.c | 3 +-
arch/x86/kernel/head_64.S | 4 +--
arch/x86/mm/init.c | 2 -
arch/x86/mm/init_64.c | 10 ++++++++
arch/x86/mm/kaiser.c | 26 +++++++++++++++++++----
arch/x86/mm/pgtable.c | 8 +------
arch/x86/mm/tlb.c | 4 ---
16 files changed, 143 insertions(+), 65 deletions(-)
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2523,6 +2523,8 @@ bytes respectively. Such letter suffixes
nojitter [IA-64] Disables jitter checking for ITC timers.
+ nokaiser [X86-64] Disable KAISER isolation of kernel from user.
+
no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver
no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1051,7 +1051,7 @@ ENTRY(paranoid_entry)
* unconditionally, but we need to find out whether the reverse
* should be done on return (conveyed to paranoid_exit in %ebx).
*/
- movq %cr3, %rax
+ ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER
testl $KAISER_SHADOW_PGD_OFFSET, %eax
jz 2f
orl $2, %ebx
@@ -1083,6 +1083,7 @@ ENTRY(paranoid_exit)
TRACE_IRQS_OFF_DEBUG
TRACE_IRQS_IRETQ_DEBUG
#ifdef CONFIG_KAISER
+ /* No ALTERNATIVE for X86_FEATURE_KAISER: paranoid_entry sets %ebx */
testl $2, %ebx /* SWITCH_USER_CR3 needed? */
jz paranoid_exit_no_switch
SWITCH_USER_CR3
@@ -1315,13 +1316,14 @@ ENTRY(nmi)
#ifdef CONFIG_KAISER
/* Unconditionally use kernel CR3 for do_nmi() */
/* %rax is saved above, so OK to clobber here */
- movq %cr3, %rax
+ ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER
/* If PCID enabled, NOFLUSH now and NOFLUSH on return */
orq x86_cr3_pcid_noflush, %rax
pushq %rax
/* mask off "user" bit of pgd address and 12 PCID bits: */
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
movq %rax, %cr3
+2:
#endif
call do_nmi
@@ -1331,8 +1333,7 @@ ENTRY(nmi)
* kernel code that needs user CR3, but do we ever return
* to "user mode" where we need the kernel CR3?
*/
- popq %rax
- mov %rax, %cr3
+ ALTERNATIVE "", "popq %rax; movq %rax, %cr3", X86_FEATURE_KAISER
#endif
/*
@@ -1559,13 +1560,14 @@ end_repeat_nmi:
#ifdef CONFIG_KAISER
/* Unconditionally use kernel CR3 for do_nmi() */
/* %rax is saved above, so OK to clobber here */
- movq %cr3, %rax
+ ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER
/* If PCID enabled, NOFLUSH now and NOFLUSH on return */
orq x86_cr3_pcid_noflush, %rax
pushq %rax
/* mask off "user" bit of pgd address and 12 PCID bits: */
andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
movq %rax, %cr3
+2:
#endif
/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
@@ -1577,8 +1579,7 @@ end_repeat_nmi:
* kernel code that needs user CR3, like just just before
* a sysret.
*/
- popq %rax
- mov %rax, %cr3
+ ALTERNATIVE "", "popq %rax; movq %rax, %cr3", X86_FEATURE_KAISER
#endif
testl %ebx, %ebx /* swapgs needed? */
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -200,6 +200,9 @@
#define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
+/* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
+#define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_KAISER w/o nokaiser */
+
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -46,28 +46,33 @@ movq \reg, %cr3
.endm
.macro SWITCH_KERNEL_CR3
-pushq %rax
+ALTERNATIVE "jmp 8f", "pushq %rax", X86_FEATURE_KAISER
_SWITCH_TO_KERNEL_CR3 %rax
popq %rax
+8:
.endm
.macro SWITCH_USER_CR3
-pushq %rax
+ALTERNATIVE "jmp 8f", "pushq %rax", X86_FEATURE_KAISER
_SWITCH_TO_USER_CR3 %rax %al
popq %rax
+8:
.endm
.macro SWITCH_KERNEL_CR3_NO_STACK
-movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)
+ALTERNATIVE "jmp 8f", \
+ __stringify(movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)), \
+ X86_FEATURE_KAISER
_SWITCH_TO_KERNEL_CR3 %rax
movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
+8:
.endm
#else /* CONFIG_KAISER */
-.macro SWITCH_KERNEL_CR3 reg
+.macro SWITCH_KERNEL_CR3
.endm
-.macro SWITCH_USER_CR3 reg regb
+.macro SWITCH_USER_CR3
.endm
.macro SWITCH_KERNEL_CR3_NO_STACK
.endm
@@ -90,6 +95,16 @@ DECLARE_PER_CPU(unsigned long, x86_cr3_p
extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
+extern int kaiser_enabled;
+#else
+#define kaiser_enabled 0
+#endif /* CONFIG_KAISER */
+
+/*
+ * Kaiser function prototypes are needed even when CONFIG_KAISER is not set,
+ * so as to build with tests on kaiser_enabled instead of #ifdefs.
+ */
+
/**
* kaiser_add_mapping - map a virtual memory part to the shadow (user) mapping
* @addr: the start address of the range
@@ -119,8 +134,6 @@ extern void kaiser_remove_mapping(unsign
*/
extern void kaiser_init(void);
-#endif /* CONFIG_KAISER */
-
#endif /* __ASSEMBLY */
#endif /* _ASM_X86_KAISER_H */
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -18,6 +18,12 @@
#ifndef __ASSEMBLY__
#include <asm/x86_init.h>
+#ifdef CONFIG_KAISER
+extern int kaiser_enabled;
+#else
+#define kaiser_enabled 0
+#endif
+
void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
void ptdump_walk_pgd_level_checkwx(void);
@@ -660,7 +666,7 @@ static inline int pgd_bad(pgd_t pgd)
* page table by accident; it will fault on the first
* instruction it tries to run. See native_set_pgd().
*/
- if (IS_ENABLED(CONFIG_KAISER))
+ if (kaiser_enabled)
ignore_flags |= _PAGE_NX;
return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
@@ -865,12 +871,14 @@ static inline void pmdp_set_wrprotect(st
*/
static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
{
- memcpy(dst, src, count * sizeof(pgd_t));
+ memcpy(dst, src, count * sizeof(pgd_t));
#ifdef CONFIG_KAISER
- /* Clone the shadow pgd part as well */
- memcpy(native_get_shadow_pgd(dst),
- native_get_shadow_pgd(src),
- count * sizeof(pgd_t));
+ if (kaiser_enabled) {
+ /* Clone the shadow pgd part as well */
+ memcpy(native_get_shadow_pgd(dst),
+ native_get_shadow_pgd(src),
+ count * sizeof(pgd_t));
+ }
#endif
}
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -111,13 +111,12 @@ extern pgd_t kaiser_set_shadow_pgd(pgd_t
static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp)
{
+#ifdef CONFIG_DEBUG_VM
+ /* linux/mmdebug.h may not have been included at this point */
+ BUG_ON(!kaiser_enabled);
+#endif
return (pgd_t *)((unsigned long)pgdp | (unsigned long)PAGE_SIZE);
}
-
-static inline pgd_t *native_get_normal_pgd(pgd_t *pgdp)
-{
- return (pgd_t *)((unsigned long)pgdp & ~(unsigned long)PAGE_SIZE);
-}
#else
static inline pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
{
@@ -128,10 +127,6 @@ static inline pgd_t *native_get_shadow_p
BUILD_BUG_ON(1);
return NULL;
}
-static inline pgd_t *native_get_normal_pgd(pgd_t *pgdp)
-{
- return pgdp;
-}
#endif /* CONFIG_KAISER */
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -39,11 +39,7 @@
#define _PAGE_ACCESSED (_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
#define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
#define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE)
-#ifdef CONFIG_KAISER
-#define _PAGE_GLOBAL (_AT(pteval_t, 0))
-#else
#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
-#endif
#define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1)
#define _PAGE_SOFTW2 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2)
#define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT)
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -136,9 +136,11 @@ static inline void cr4_set_bits_and_upda
* to avoid the need for asm/kaiser.h in unexpected places.
*/
#ifdef CONFIG_KAISER
+extern int kaiser_enabled;
extern void kaiser_setup_pcid(void);
extern void kaiser_flush_tlb_on_return_to_user(void);
#else
+#define kaiser_enabled 0
static inline void kaiser_setup_pcid(void)
{
}
@@ -163,7 +165,7 @@ static inline void __native_flush_tlb(vo
* back:
*/
preempt_disable();
- if (this_cpu_has(X86_FEATURE_PCID))
+ if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID))
kaiser_flush_tlb_on_return_to_user();
native_write_cr3(native_read_cr3());
preempt_enable();
@@ -174,20 +176,30 @@ static inline void __native_flush_tlb_gl
unsigned long cr4;
cr4 = this_cpu_read(cpu_tlbstate.cr4);
- /* clear PGE */
- native_write_cr4(cr4 & ~X86_CR4_PGE);
- /* write old PGE again and flush TLBs */
- native_write_cr4(cr4);
+ if (cr4 & X86_CR4_PGE) {
+ /* clear PGE and flush TLB of all entries */
+ native_write_cr4(cr4 & ~X86_CR4_PGE);
+ /* restore PGE as it was before */
+ native_write_cr4(cr4);
+ } else {
+ /*
+ * x86_64 microcode update comes this way when CR4.PGE is not
+ * enabled, and it's safer for all callers to allow this case.
+ */
+ native_write_cr3(native_read_cr3());
+ }
}
static inline void __native_flush_tlb_global(void)
{
-#ifdef CONFIG_KAISER
- /* Globals are not used at all */
- __native_flush_tlb();
-#else
unsigned long flags;
+ if (kaiser_enabled) {
+ /* Globals are not used at all */
+ __native_flush_tlb();
+ return;
+ }
+
if (this_cpu_has(X86_FEATURE_INVPCID)) {
/*
* Using INVPCID is considerably faster than a pair of writes
@@ -207,7 +219,6 @@ static inline void __native_flush_tlb_gl
raw_local_irq_save(flags);
__native_flush_tlb_global_irq_disabled();
raw_local_irq_restore(flags);
-#endif
}
static inline void __native_flush_tlb_single(unsigned long addr)
@@ -222,7 +233,7 @@ static inline void __native_flush_tlb_si
*/
if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) {
- if (this_cpu_has(X86_FEATURE_PCID))
+ if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID))
kaiser_flush_tlb_on_return_to_user();
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
return;
@@ -237,9 +248,9 @@ static inline void __native_flush_tlb_si
* Make sure to do only a single invpcid when KAISER is
* disabled and we have only a single ASID.
*/
- if (X86_CR3_PCID_ASID_KERN != X86_CR3_PCID_ASID_USER)
- invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr);
- invpcid_flush_one(X86_CR3_PCID_ASID_USER, addr);
+ if (kaiser_enabled)
+ invpcid_flush_one(X86_CR3_PCID_ASID_USER, addr);
+ invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr);
}
static inline void __flush_tlb_all(void)
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -178,6 +178,20 @@ static int __init x86_pcid_setup(char *s
return 1;
}
__setup("nopcid", x86_pcid_setup);
+
+static int __init x86_nokaiser_setup(char *s)
+{
+ /* nokaiser doesn't accept parameters */
+ if (s)
+ return -EINVAL;
+#ifdef CONFIG_KAISER
+ kaiser_enabled = 0;
+ setup_clear_cpu_cap(X86_FEATURE_KAISER);
+ pr_info("nokaiser: KAISER feature disabled\n");
+#endif
+ return 0;
+}
+early_param("nokaiser", x86_nokaiser_setup);
#endif
static int __init x86_noinvpcid_setup(char *s)
@@ -324,7 +338,7 @@ static __always_inline void setup_smap(s
static void setup_pcid(struct cpuinfo_x86 *c)
{
if (cpu_has(c, X86_FEATURE_PCID)) {
- if (cpu_has(c, X86_FEATURE_PGE)) {
+ if (cpu_has(c, X86_FEATURE_PGE) || kaiser_enabled) {
cr4_set_bits(X86_CR4_PCIDE);
/*
* INVPCID has two "groups" of types:
@@ -747,6 +761,10 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_power = cpuid_edx(0x80000007);
init_scattered_cpuid_features(c);
+#ifdef CONFIG_KAISER
+ if (kaiser_enabled)
+ set_cpu_cap(c, X86_FEATURE_KAISER);
+#endif
}
static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
@@ -1406,6 +1424,14 @@ void cpu_init(void)
* try to read it.
*/
cr4_init_shadow();
+ if (!kaiser_enabled) {
+ /*
+ * secondary_startup_64() deferred setting PGE in cr4:
+ * probe_page_size_mask() sets it on the boot cpu,
+ * but it needs to be set on each secondary cpu.
+ */
+ cr4_set_bits(X86_CR4_PGE);
+ }
/*
* Load microcode on this cpu if a valid microcode is available.
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -132,9 +132,10 @@ void __init init_espfix_bsp(void)
* area to ensure it is mapped into the shadow user page
* tables.
*/
- if (IS_ENABLED(CONFIG_KAISER))
+ if (kaiser_enabled) {
set_pgd(native_get_shadow_pgd(pgd_p),
__pgd(_KERNPG_TABLE | __pa((pud_t *)espfix_pud_page)));
+ }
/* Randomize the locations */
init_espfix_random();
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -183,8 +183,8 @@ ENTRY(secondary_startup_64)
movq $(init_level4_pgt - __START_KERNEL_map), %rax
1:
- /* Enable PAE mode and PGE */
- movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx
+ /* Enable PAE and PSE, but defer PGE until kaiser_enabled is decided */
+ movl $(X86_CR4_PAE | X86_CR4_PSE), %ecx
movq %rcx, %cr4
/* Setup early boot stage 4 level pagetables. */
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -165,7 +165,7 @@ static void __init probe_page_size_mask(
cr4_set_bits_and_update_boot(X86_CR4_PSE);
/* Enable PGE if available */
- if (cpu_has_pge) {
+ if (cpu_has_pge && !kaiser_enabled) {
cr4_set_bits_and_update_boot(X86_CR4_PGE);
__supported_pte_mask |= _PAGE_GLOBAL;
} else
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -395,6 +395,16 @@ void __init cleanup_highmap(void)
continue;
if (vaddr < (unsigned long) _text || vaddr > end)
set_pmd(pmd, __pmd(0));
+ else if (kaiser_enabled) {
+ /*
+ * level2_kernel_pgt is initialized with _PAGE_GLOBAL:
+ * clear that now. This is not important, so long as
+ * CR4.PGE remains clear, but it removes an anomaly.
+ * Physical mapping setup below avoids _PAGE_GLOBAL
+ * by use of massage_pgprot() inside pfn_pte() etc.
+ */
+ set_pmd(pmd, pmd_clear_flags(*pmd, _PAGE_GLOBAL));
+ }
}
}
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -17,7 +17,9 @@
#include <asm/pgalloc.h>
#include <asm/desc.h>
-#ifdef CONFIG_KAISER
+int kaiser_enabled __read_mostly = 1;
+EXPORT_SYMBOL(kaiser_enabled); /* for inlined TLB flush functions */
+
__visible
DEFINE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
@@ -168,8 +170,8 @@ static pte_t *kaiser_pagetable_walk(unsi
return pte_offset_kernel(pmd, address);
}
-int kaiser_add_user_map(const void *__start_addr, unsigned long size,
- unsigned long flags)
+static int kaiser_add_user_map(const void *__start_addr, unsigned long size,
+ unsigned long flags)
{
int ret = 0;
pte_t *pte;
@@ -178,6 +180,15 @@ int kaiser_add_user_map(const void *__st
unsigned long end_addr = PAGE_ALIGN(start_addr + size);
unsigned long target_address;
+ /*
+ * It is convenient for callers to pass in __PAGE_KERNEL etc,
+ * and there is no actual harm from setting _PAGE_GLOBAL, so
+ * long as CR4.PGE is not set. But it is nonetheless troubling
+ * to see Kaiser itself setting _PAGE_GLOBAL (now that "nokaiser"
+ * requires that not to be #defined to 0): so mask it off here.
+ */
+ flags &= ~_PAGE_GLOBAL;
+
for (; address < end_addr; address += PAGE_SIZE) {
target_address = get_pa_from_mapping(address);
if (target_address == -1) {
@@ -264,6 +275,8 @@ void __init kaiser_init(void)
{
int cpu;
+ if (!kaiser_enabled)
+ return;
kaiser_init_all_pgds();
for_each_possible_cpu(cpu) {
@@ -312,6 +325,8 @@ void __init kaiser_init(void)
/* Add a mapping to the shadow mapping, and synchronize the mappings */
int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags)
{
+ if (!kaiser_enabled)
+ return 0;
return kaiser_add_user_map((const void *)addr, size, flags);
}
@@ -323,6 +338,8 @@ void kaiser_remove_mapping(unsigned long
unsigned long addr, next;
pgd_t *pgd;
+ if (!kaiser_enabled)
+ return;
pgd = native_get_shadow_pgd(pgd_offset_k(start));
for (addr = start; addr < end; pgd++, addr = next) {
next = pgd_addr_end(addr, end);
@@ -344,6 +361,8 @@ static inline bool is_userspace_pgd(pgd_
pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
{
+ if (!kaiser_enabled)
+ return pgd;
/*
* Do we need to also populate the shadow pgd? Check _PAGE_USER to
* skip cases like kexec and EFI which make temporary low mappings.
@@ -400,4 +419,3 @@ void kaiser_flush_tlb_on_return_to_user(
X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET);
}
EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user);
-#endif /* CONFIG_KAISER */
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -341,16 +341,12 @@ static inline void _pgd_free(pgd_t *pgd)
}
#else
-#ifdef CONFIG_KAISER
/*
- * Instead of one pmd, we aquire two pmds. Being order-1, it is
+ * Instead of one pgd, Kaiser acquires two pgds. Being order-1, it is
* both 8k in size and 8k-aligned. That lets us just flip bit 12
* in a pointer to swap between the two 4k halves.
*/
-#define PGD_ALLOCATION_ORDER 1
-#else
-#define PGD_ALLOCATION_ORDER 0
-#endif
+#define PGD_ALLOCATION_ORDER kaiser_enabled
static inline pgd_t *_pgd_alloc(void)
{
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -39,8 +39,7 @@ static void load_new_mm_cr3(pgd_t *pgdir
{
unsigned long new_mm_cr3 = __pa(pgdir);
-#ifdef CONFIG_KAISER
- if (this_cpu_has(X86_FEATURE_PCID)) {
+ if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID)) {
/*
* We reuse the same PCID for different tasks, so we must
* flush all the entries for the PCID out when we change tasks.
@@ -57,7 +56,6 @@ static void load_new_mm_cr3(pgd_t *pgdir
new_mm_cr3 |= X86_CR3_PCID_KERN_FLUSH;
kaiser_flush_tlb_on_return_to_user();
}
-#endif /* CONFIG_KAISER */
/*
* Caution: many callers of this function expect
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "kaiser: _pgd_alloc() without __GFP_REPEAT to avoid stalls" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
kaiser: _pgd_alloc() without __GFP_REPEAT to avoid stalls
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Wed Jan 3 18:58:12 CET 2018
From: Hugh Dickins <hughd(a)google.com>
Date: Fri, 13 Oct 2017 12:10:00 -0700
Subject: kaiser: _pgd_alloc() without __GFP_REPEAT to avoid stalls
From: Hugh Dickins <hughd(a)google.com>
Synthetic filesystem mempressure testing has shown softlockups, with
hour-long page allocation stalls, and pgd_alloc() trying for order:1
with __GFP_REPEAT in one of the backtraces each time.
That's _pgd_alloc() going for a Kaiser double-pgd, using the __GFP_REPEAT
common to all page table allocations, but actually having no effect on
order:0 (see should_alloc_oom() and should_continue_reclaim() in this
tree, but beware that ports to another tree might behave differently).
Order:1 stack allocation has been working satisfactorily without
__GFP_REPEAT forever, and page table allocation only asks __GFP_REPEAT
for awkward occasions in a long-running process: it's not appropriate
at fork or exec time, and seems to be doing much more harm than good:
getting those contiguous pages under very heavy mempressure can be
hard (though even without it, Kaiser does generate more mempressure).
Mask out that __GFP_REPEAT inside _pgd_alloc(). Why not take it out
of the PGALLOG_GFP altogether, as v4.7 commit a3a9a59d2067 ("x86: get
rid of superfluous __GFP_REPEAT") did? Because I think that might
make a difference to our page table memcg charging, which I'd prefer
not to interfere with at this time.
hughd adds: __alloc_pages_slowpath() in the 4.4.89-stable tree handles
__GFP_REPEAT a little differently than in prod kernel or 3.18.72-stable,
so it may not always be exactly a no-op on order:0 pages, as said above;
but I think still appropriate to omit it from Kaiser or non-Kaiser pgd.
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Jiri Kosina <jkosina(a)suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/mm/pgtable.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -6,7 +6,7 @@
#include <asm/fixmap.h>
#include <asm/mtrr.h>
-#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
#ifdef CONFIG_HIGHPTE
#define PGALLOC_USER_GFP __GFP_HIGHMEM
@@ -354,7 +354,9 @@ static inline void _pgd_free(pgd_t *pgd)
static inline pgd_t *_pgd_alloc(void)
{
- return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER);
+ /* No __GFP_REPEAT: to avoid page allocation stalls in order-1 case */
+ return (pgd_t *)__get_free_pages(PGALLOC_GFP & ~__GFP_REPEAT,
+ PGD_ALLOCATION_ORDER);
}
static inline void _pgd_free(pgd_t *pgd)
Patches currently in stable-queue which might be from hughd(a)google.com are
queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch
queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.4/kaiser-merged-update.patch
queue-4.4/kaiser-delete-kaiser_real_switch-option.patch
queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.4/kaiser-fix-perf-crashes.patch
queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.4/kaiser-kernel-address-isolation.patch
queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.4/kaiser-kaiser-depends-on-smp.patch
queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch
7 years, 8 months
- 1
- 0
Re: [Linux-stable-mirror] v3.18.86 build: 0 failures 1 warnings (v3.18.86)
by Greg KH
On Wed, Jan 03, 2018 at 03:41:21PM +0000, Mark Brown wrote:
> On Wed, Jan 03, 2018 at 04:32:35PM +0100, Arnd Bergmann wrote:
>
> > It might be a problem with different 'make' versions, or something else
> > in the environment that leads to "-Wno-frame-address" not being set
> > on the command line instead.
>
> I'm using "GNU Make 4.1" - this is all just the default Debian stuff,
> I've not customized my x86 host environment.
Make 4.2.1 here with gcc 7.2.1 and I get tons of build warnings on my
3.18.y tree on my laptop, but my build machine running Fedora (make
4.2.1 and gcc 7.2.1) I get no build warnings at all.
I've given up trying to track it down for my laptop, something is
preventing the compiler flag from being added to the gcc command line,
and I don't care anymore...
thanks,
greg k-h
7 years, 8 months
- 1
- 0
Re: [Linux-stable-mirror] [PATCH] IB/core: Fix two kernel warnings triggered by rxe registration
by Jason Gunthorpe
On Mon, Dec 25, 2017 at 12:28:39PM +0200, Leon Romanovsky wrote:
> On Fri, Dec 22, 2017 at 01:38:52PM -0800, Bart Van Assche wrote:
> > Avoid that the following two warnings are reported when registering an
> > rxe device:
> >
> > WARNING: CPU: 2 PID: 1005 at drivers/infiniband/core/device.c:449 ib_register_device+0x591/0x640 [ib_core]
> > CPU: 2 PID: 1005 Comm: run_tests Not tainted 4.15.0-rc4-dbg+ #2
> > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014
> > RIP: 0010:ib_register_device+0x591/0x640 [ib_core]
> > Call Trace:
> > rxe_register_device+0x3c6/0x470 [rdma_rxe]
> > rxe_add+0x543/0x5e0 [rdma_rxe]
> > rxe_net_add+0x37/0xb0 [rdma_rxe]
> > rxe_param_set_add+0x5a/0x120 [rdma_rxe]
> > param_attr_store+0x5e/0xc0
> > module_attr_store+0x19/0x30
> > sysfs_kf_write+0x3d/0x50
> > kernfs_fop_write+0x116/0x1a0
> > __vfs_write+0x23/0x120
> > vfs_write+0xbe/0x1b0
> > SyS_write+0x44/0xa0
> > entry_SYSCALL_64_fastpath+0x23/0x9a
> >
> > WARNING: CPU: 2 PID: 1005 at drivers/infiniband/core/sysfs.c:1279 ib_device_register_sysfs+0x11d/0x160 [ib_core]
> > CPU: 2 PID: 1005 Comm: run_tests Tainted: G W 4.15.0-rc4-dbg+ #2
> > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014
> > RIP: 0010:ib_device_register_sysfs+0x11d/0x160 [ib_core]
> > Call Trace:
> > ib_register_device+0x3f7/0x640 [ib_core]
> > rxe_register_device+0x3c6/0x470 [rdma_rxe]
> > rxe_add+0x543/0x5e0 [rdma_rxe]
> > rxe_net_add+0x37/0xb0 [rdma_rxe]
> > rxe_param_set_add+0x5a/0x120 [rdma_rxe]
> > param_attr_store+0x5e/0xc0
> > module_attr_store+0x19/0x30
> > sysfs_kf_write+0x3d/0x50
> > kernfs_fop_write+0x116/0x1a0
> > __vfs_write+0x23/0x120
> > vfs_write+0xbe/0x1b0
> > SyS_write+0x44/0xa0
> > entry_SYSCALL_64_fastpath+0x23/0x9a
> >
> > Fixes: commit 99db9494035f ("IB/core: Remove ib_device.dma_device")
>
> ^^^^^^ redundant
>
> > Signed-off-by: Bart Van Assche <bart.vanassche(a)wdc.com>
> > Cc: Leon Romanovsky <leon(a)kernel.org>
> > Cc: stable(a)vger.kernel.org # v4.11
> > drivers/infiniband/core/device.c | 2 +-
> > drivers/infiniband/core/sysfs.c | 1 -
> > 2 files changed, 1 insertion(+), 2 deletions(-)
> >
> > diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
> > index 30914f3baa5f..b9d7570e9989 100644
> > +++ b/drivers/infiniband/core/device.c
> > @@ -446,7 +446,6 @@ int ib_register_device(struct ib_device *device,
> > struct ib_udata uhw = {.outlen = 0, .inlen = 0};
> > struct device *parent = device->dev.parent;
> >
> > - WARN_ON_ONCE(!parent);
> > WARN_ON_ONCE(device->dma_device);
> > if (device->dev.dma_ops) {
>
> I understand that it fixed warning for you, but why is it correct?
> You are using "parent" in this "if (device->dev.dma_ops)" too.
If no parent is specified then the caller must provide a full set of
DMA data and none should be copied from the parent.
Presumably rxe does this, and has no parent because it is a virtual
device.
I'm a little more worried about the ib_device_register_sysfs - why was
the WARN_ON ever there?
What do you think about this as a clarification Bart?
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index bb2686d56d3c65..c535c7803d80a7 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -446,7 +446,6 @@ int ib_register_device(struct ib_device *device,
struct ib_udata uhw = {.outlen = 0, .inlen = 0};
struct device *parent = device->dev.parent;
- WARN_ON_ONCE(!parent);
WARN_ON_ONCE(device->dma_device);
if (device->dev.dma_ops) {
/*
@@ -455,16 +454,20 @@ int ib_register_device(struct ib_device *device,
* into device->dev.
*/
device->dma_device = &device->dev;
- if (!device->dev.dma_mask)
- device->dev.dma_mask = parent->dma_mask;
- if (!device->dev.coherent_dma_mask)
- device->dev.coherent_dma_mask =
- parent->coherent_dma_mask;
+
+ if (parent) {
+ if (!device->dev.dma_mask)
+ device->dev.dma_mask = parent->dma_mask;
+ if (!device->dev.coherent_dma_mask)
+ device->dev.coherent_dma_mask =
+ parent->coherent_dma_mask;
+ }
} else {
/*
* The caller did not provide custom DMA operations. Use the
* DMA mapping operations of the parent device.
*/
+ WARN_ON_ONCE(!parent);
device->dma_device = parent;
}
7 years, 8 months
- 2
- 1
[Linux-stable-mirror] [tip:efi/core] efi/capsule-loader: Reinstate virtual capsule mapping
by tip-bot for Ard Biesheuvel
Commit-ID: f24c4d478013d82bd1b943df566fff3561d52864
Gitweb: https://git.kernel.org/tip/f24c4d478013d82bd1b943df566fff3561d52864
Author: Ard Biesheuvel <ard.biesheuvel(a)linaro.org>
AuthorDate: Tue, 2 Jan 2018 17:21:10 +0000
Committer: Ingo Molnar <mingo(a)kernel.org>
CommitDate: Wed, 3 Jan 2018 13:54:31 +0100
efi/capsule-loader: Reinstate virtual capsule mapping
Commit:
82c3768b8d68 ("efi/capsule-loader: Use a cached copy of the capsule header")
... refactored the capsule loading code that maps the capsule header,
to avoid having to map it several times.
However, as it turns out, the vmap() call we ended up removing did not
just map the header, but the entire capsule image, and dropping this
virtual mapping breaks capsules that are processed by the firmware
immediately (i.e., without a reboot).
Unfortunately, that change was part of a larger refactor that allowed
a quirk to be implemented for Quark, which has a non-standard memory
layout for capsules, and we have slightly painted ourselves into a
corner by allowing quirk code to mangle the capsule header and memory
layout.
So we need to fix this without breaking Quark. Fortunately, Quark does
not appear to care about the virtual mapping, and so we can simply
do a partial revert of commit:
2a457fb31df6 ("efi/capsule-loader: Use page addresses rather than struct page pointers")
... and create a vmap() mapping of the entire capsule (including header)
based on the reinstated struct page array, unless running on Quark, in
which case we pass the capsule header copy as before.
Reported-by: Ge Song <ge.song(a)hxt-semitech.com>
Tested-by: Bryan O'Donoghue <pure.logic(a)nexus-software.ie>
Tested-by: Ge Song <ge.song(a)hxt-semitech.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel(a)linaro.org>
Cc: <stable(a)vger.kernel.org>
Cc: Dave Young <dyoung(a)redhat.com>
Cc: Linus Torvalds <torvalds(a)linux-foundation.org>
Cc: Matt Fleming <matt(a)codeblueprint.co.uk>
Cc: Peter Zijlstra <peterz(a)infradead.org>
Cc: Thomas Gleixner <tglx(a)linutronix.de>
Cc: linux-efi(a)vger.kernel.org
Fixes: 82c3768b8d68 ("efi/capsule-loader: Use a cached copy of the capsule header")
Link: http://lkml.kernel.org/r/20180102172110.17018-3-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo(a)kernel.org>
---
arch/x86/platform/efi/quirks.c | 13 +++++++++-
drivers/firmware/efi/capsule-loader.c | 45 ++++++++++++++++++++++++++++-------
include/linux/efi.h | 4 +++-
3 files changed, 52 insertions(+), 10 deletions(-)
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 8a99a2e..5b513cc 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -592,7 +592,18 @@ static int qrk_capsule_setup_info(struct capsule_info *cap_info, void **pkbuff,
/*
* Update the first page pointer to skip over the CSH header.
*/
- cap_info->pages[0] += csh->headersize;
+ cap_info->phys[0] += csh->headersize;
+
+ /*
+ * cap_info->capsule should point at a virtual mapping of the entire
+ * capsule, starting at the capsule header. Our image has the Quark
+ * security header prepended, so we cannot rely on the default vmap()
+ * mapping created by the generic capsule code.
+ * Given that the Quark firmware does not appear to care about the
+ * virtual mapping, let's just point cap_info->capsule at our copy
+ * of the capsule header.
+ */
+ cap_info->capsule = &cap_info->header;
return 1;
}
diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c
index ec8ac5c..055e2e8 100644
--- a/drivers/firmware/efi/capsule-loader.c
+++ b/drivers/firmware/efi/capsule-loader.c
@@ -20,10 +20,6 @@
#define NO_FURTHER_WRITE_ACTION -1
-#ifndef phys_to_page
-#define phys_to_page(x) pfn_to_page((x) >> PAGE_SHIFT)
-#endif
-
/**
* efi_free_all_buff_pages - free all previous allocated buffer pages
* @cap_info: pointer to current instance of capsule_info structure
@@ -35,7 +31,7 @@
static void efi_free_all_buff_pages(struct capsule_info *cap_info)
{
while (cap_info->index > 0)
- __free_page(phys_to_page(cap_info->pages[--cap_info->index]));
+ __free_page(cap_info->pages[--cap_info->index]);
cap_info->index = NO_FURTHER_WRITE_ACTION;
}
@@ -71,6 +67,14 @@ int __efi_capsule_setup_info(struct capsule_info *cap_info)
cap_info->pages = temp_page;
+ temp_page = krealloc(cap_info->phys,
+ pages_needed * sizeof(phys_addr_t *),
+ GFP_KERNEL | __GFP_ZERO);
+ if (!temp_page)
+ return -ENOMEM;
+
+ cap_info->phys = temp_page;
+
return 0;
}
@@ -105,9 +109,24 @@ int __weak efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff,
**/
static ssize_t efi_capsule_submit_update(struct capsule_info *cap_info)
{
+ bool do_vunmap = false;
int ret;
- ret = efi_capsule_update(&cap_info->header, cap_info->pages);
+ /*
+ * cap_info->capsule may have been assigned already by a quirk
+ * handler, so only overwrite it if it is NULL
+ */
+ if (!cap_info->capsule) {
+ cap_info->capsule = vmap(cap_info->pages, cap_info->index,
+ VM_MAP, PAGE_KERNEL);
+ if (!cap_info->capsule)
+ return -ENOMEM;
+ do_vunmap = true;
+ }
+
+ ret = efi_capsule_update(cap_info->capsule, cap_info->phys);
+ if (do_vunmap)
+ vunmap(cap_info->capsule);
if (ret) {
pr_err("capsule update failed\n");
return ret;
@@ -165,10 +184,12 @@ static ssize_t efi_capsule_write(struct file *file, const char __user *buff,
goto failed;
}
- cap_info->pages[cap_info->index++] = page_to_phys(page);
+ cap_info->pages[cap_info->index] = page;
+ cap_info->phys[cap_info->index] = page_to_phys(page);
cap_info->page_bytes_remain = PAGE_SIZE;
+ cap_info->index++;
} else {
- page = phys_to_page(cap_info->pages[cap_info->index - 1]);
+ page = cap_info->pages[cap_info->index - 1];
}
kbuff = kmap(page);
@@ -252,6 +273,7 @@ static int efi_capsule_release(struct inode *inode, struct file *file)
struct capsule_info *cap_info = file->private_data;
kfree(cap_info->pages);
+ kfree(cap_info->phys);
kfree(file->private_data);
file->private_data = NULL;
return 0;
@@ -281,6 +303,13 @@ static int efi_capsule_open(struct inode *inode, struct file *file)
return -ENOMEM;
}
+ cap_info->phys = kzalloc(sizeof(void *), GFP_KERNEL);
+ if (!cap_info->phys) {
+ kfree(cap_info->pages);
+ kfree(cap_info);
+ return -ENOMEM;
+ }
+
file->private_data = cap_info;
return 0;
diff --git a/include/linux/efi.h b/include/linux/efi.h
index d813f7b..29fdf80 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -140,11 +140,13 @@ struct efi_boot_memmap {
struct capsule_info {
efi_capsule_header_t header;
+ efi_capsule_header_t *capsule;
int reset_type;
long index;
size_t count;
size_t total_size;
- phys_addr_t *pages;
+ struct page **pages;
+ phys_addr_t *phys;
size_t page_bytes_remain;
};
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Applied "ASoC: skl: Fix kernel warning due to zero NHTL entry" to the asoc tree
by Mark Brown
The patch
ASoC: skl: Fix kernel warning due to zero NHTL entry
has been applied to the asoc tree at
https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git
All being well this means that it will be integrated into the linux-next
tree (usually sometime in the next 24 hours) and sent to Linus during
the next merge window (or sooner if it is a bug fix), however if
problems are discovered then the patch may be dropped or reverted.
You may get further e-mails resulting from automated or manual testing
and review of the tree, please engage with people reporting problems and
send followup patches addressing any issues that are reported if needed.
If any updates are required or you are submitting further changes they
should be sent as incremental updates against current git, existing
patches will not be replaced.
Please add any relevant lists and maintainers to the CCs when replying
to this mail.
Thanks,
Mark
>From 20a1ea2222e7cbf96e9bf8579362e971491e6aea Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai(a)suse.de>
Date: Wed, 3 Jan 2018 16:38:46 +0100
Subject: [PATCH] ASoC: skl: Fix kernel warning due to zero NHTL entry
I got the following kernel warning when loading snd-soc-skl module on
Dell Latitude 7270 laptop:
memremap attempted on mixed range 0x0000000000000000 size: 0x0
WARNING: CPU: 0 PID: 484 at kernel/memremap.c:98 memremap+0x8a/0x180
Call Trace:
skl_nhlt_init+0x82/0xf0 [snd_soc_skl]
skl_probe+0x2ee/0x7c0 [snd_soc_skl]
....
It seems that the machine doesn't support the SKL DSP gives the empty
NHLT entry, and it triggers the warning. For avoiding it, let do the
zero check before calling memremap().
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai(a)suse.de>
Signed-off-by: Mark Brown <broonie(a)kernel.org>
---
sound/soc/intel/skylake/skl-nhlt.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/sound/soc/intel/skylake/skl-nhlt.c b/sound/soc/intel/skylake/skl-nhlt.c
index d14c50a60289..1ce414d86d8a 100644
--- a/sound/soc/intel/skylake/skl-nhlt.c
+++ b/sound/soc/intel/skylake/skl-nhlt.c
@@ -43,7 +43,8 @@ struct nhlt_acpi_table *skl_nhlt_init(struct device *dev)
obj = acpi_evaluate_dsm(handle, &osc_guid, 1, 1, NULL);
if (obj && obj->type == ACPI_TYPE_BUFFER) {
nhlt_ptr = (struct nhlt_resource_desc *)obj->buffer.pointer;
- nhlt_table = (struct nhlt_acpi_table *)
+ if (nhlt_ptr->length)
+ nhlt_table = (struct nhlt_acpi_table *)
memremap(nhlt_ptr->min_addr, nhlt_ptr->length,
MEMREMAP_WB);
ACPI_FREE(obj);
--
2.15.1
7 years, 8 months
- 1
- 0
Re: [Linux-stable-mirror] v3.18.86 build: 0 failures 1 warnings (v3.18.86)
by Arnd Bergmann
On Wed, Jan 3, 2018 at 3:59 PM, Mark Brown <broonie(a)kernel.org> wrote:
> On Wed, Jan 03, 2018 at 03:52:12PM +0100, Arnd Bergmann wrote:
>
>> Greg and Mark, which x86-64 compiler versions do you use?
>
> gcc (Debian 6.3.0-18) 6.3.0 20170516
I installed that version here, same as my other gcc-6 versions, the
"-Wno-frame-address" option gets set and interpreted correctly:
$ git checkout v3.18.91 ; touch kernel/sched/core.c ; make V=1
defconfig kernel/sched/core.o CC=gcc-6 2>&1 | tail
...
gcc-6 -Wp,-MD,kernel/sched/.core.o.d -nostdinc -isystem
/usr/lib/gcc/x86_64-linux-gnu/6/include -I./arch/x86/include
-Iarch/x86/include/generated -Iinclude -I./arch/x86/include/uapi
-Iarch/x86/include/generated/uapi -I./include/uapi
-Iinclude/generated/uapi -include ./include/linux/kconfig.h
-D__KERNEL__ -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs
-fno-strict-aliasing -fno-common -Werror-implicit-function-declaration
-Wno-format-security -std=gnu89 -m64 -mno-80387 -mno-fp-ret-in-387
-mtune=generic -mno-red-zone -mcmodel=kernel -funit-at-a-time
-maccumulate-outgoing-args -DCONFIG_AS_CFI=1
-DCONFIG_AS_CFI_SIGNAL_FRAME=1 -DCONFIG_AS_CFI_SECTIONS=1
-DCONFIG_AS_FXSAVEQ=1 -DCONFIG_AS_CRC32=1 -DCONFIG_AS_AVX=1
-DCONFIG_AS_AVX2=1 -pipe -Wno-sign-compare
-fno-asynchronous-unwind-tables -mno-sse -mno-mmx -mno-sse2 -mno-3dnow
-mno-avx -fno-delete-null-pointer-checks -Wno-frame-address -fno-PIE
-O2 --param=allow-store-data-races=0 -Wframe-larger-than=2048
-fno-stack-protector -Wno-unused-but-set-variable
-Wno-unused-const-variable -fno-omit-frame-pointer
-fno-optimize-sibling-calls -fno-var-tracking-assignments
-Wdeclaration-after-statement -Wno-pointer-sign -fno-strict-overflow
-fno-stack-check -fconserve-stack -Werror=implicit-int
-Werror=strict-prototypes -Werror=date-time -DCC_HAVE_ASM_GOTO
-D"KBUILD_STR(s)=#s" -D"KBUILD_BASENAME=KBUILD_STR(core)"
-D"KBUILD_MODNAME=KBUILD_STR(core)" -c -o kernel/sched/core.o
kernel/sched/core.c
It might be a problem with different 'make' versions, or something else
in the environment that leads to "-Wno-frame-address" not being set
on the command line instead.
Arnd
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "x86/boot: Add early cmdline parsing for options with arguments" has been added to the 4.4-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
x86/boot: Add early cmdline parsing for options with arguments
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
x86-boot-add-early-cmdline-parsing-for-options-with-arguments.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From e505371dd83963caae1a37ead9524e8d997341be Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky(a)amd.com>
Date: Mon, 17 Jul 2017 16:10:33 -0500
Subject: x86/boot: Add early cmdline parsing for options with arguments
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
From: Tom Lendacky <thomas.lendacky(a)amd.com>
commit e505371dd83963caae1a37ead9524e8d997341be upstream.
Add a cmdline_find_option() function to look for cmdline options that
take arguments. The argument is returned in a supplied buffer and the
argument length (regardless of whether it fits in the supplied buffer)
is returned, with -1 indicating not found.
Signed-off-by: Tom Lendacky <thomas.lendacky(a)amd.com>
Reviewed-by: Thomas Gleixner <tglx(a)linutronix.de>
Cc: Alexander Potapenko <glider(a)google.com>
Cc: Andrey Ryabinin <aryabinin(a)virtuozzo.com>
Cc: Andy Lutomirski <luto(a)kernel.org>
Cc: Arnd Bergmann <arnd(a)arndb.de>
Cc: Borislav Petkov <bp(a)alien8.de>
Cc: Brijesh Singh <brijesh.singh(a)amd.com>
Cc: Dave Young <dyoung(a)redhat.com>
Cc: Dmitry Vyukov <dvyukov(a)google.com>
Cc: Jonathan Corbet <corbet(a)lwn.net>
Cc: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com>
Cc: Larry Woodman <lwoodman(a)redhat.com>
Cc: Linus Torvalds <torvalds(a)linux-foundation.org>
Cc: Matt Fleming <matt(a)codeblueprint.co.uk>
Cc: Michael S. Tsirkin <mst(a)redhat.com>
Cc: Paolo Bonzini <pbonzini(a)redhat.com>
Cc: Peter Zijlstra <peterz(a)infradead.org>
Cc: Radim Krčmář <rkrcmar(a)redhat.com>
Cc: Rik van Riel <riel(a)redhat.com>
Cc: Toshimitsu Kani <toshi.kani(a)hpe.com>
Cc: kasan-dev(a)googlegroups.com
Cc: kvm(a)vger.kernel.org
Cc: linux-arch(a)vger.kernel.org
Cc: linux-doc(a)vger.kernel.org
Cc: linux-efi(a)vger.kernel.org
Cc: linux-mm(a)kvack.org
Link: http://lkml.kernel.org/r/36b5f97492a9745dce27682305f990fc20e5cf8a.150031921…
Signed-off-by: Ingo Molnar <mingo(a)kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/cmdline.h | 2
arch/x86/lib/cmdline.c | 105 +++++++++++++++++++++++++++++++++++++++++
2 files changed, 107 insertions(+)
--- a/arch/x86/include/asm/cmdline.h
+++ b/arch/x86/include/asm/cmdline.h
@@ -2,5 +2,7 @@
#define _ASM_X86_CMDLINE_H
int cmdline_find_option_bool(const char *cmdline_ptr, const char *option);
+int cmdline_find_option(const char *cmdline_ptr, const char *option,
+ char *buffer, int bufsize);
#endif /* _ASM_X86_CMDLINE_H */
--- a/arch/x86/lib/cmdline.c
+++ b/arch/x86/lib/cmdline.c
@@ -82,3 +82,108 @@ int cmdline_find_option_bool(const char
return 0; /* Buffer overrun */
}
+
+/*
+ * Find a non-boolean option (i.e. option=argument). In accordance with
+ * standard Linux practice, if this option is repeated, this returns the
+ * last instance on the command line.
+ *
+ * @cmdline: the cmdline string
+ * @max_cmdline_size: the maximum size of cmdline
+ * @option: option string to look for
+ * @buffer: memory buffer to return the option argument
+ * @bufsize: size of the supplied memory buffer
+ *
+ * Returns the length of the argument (regardless of if it was
+ * truncated to fit in the buffer), or -1 on not found.
+ */
+static int
+__cmdline_find_option(const char *cmdline, int max_cmdline_size,
+ const char *option, char *buffer, int bufsize)
+{
+ char c;
+ int pos = 0, len = -1;
+ const char *opptr = NULL;
+ char *bufptr = buffer;
+ enum {
+ st_wordstart = 0, /* Start of word/after whitespace */
+ st_wordcmp, /* Comparing this word */
+ st_wordskip, /* Miscompare, skip */
+ st_bufcpy, /* Copying this to buffer */
+ } state = st_wordstart;
+
+ if (!cmdline)
+ return -1; /* No command line */
+
+ /*
+ * This 'pos' check ensures we do not overrun
+ * a non-NULL-terminated 'cmdline'
+ */
+ while (pos++ < max_cmdline_size) {
+ c = *(char *)cmdline++;
+ if (!c)
+ break;
+
+ switch (state) {
+ case st_wordstart:
+ if (myisspace(c))
+ break;
+
+ state = st_wordcmp;
+ opptr = option;
+ /* fall through */
+
+ case st_wordcmp:
+ if ((c == '=') && !*opptr) {
+ /*
+ * We matched all the way to the end of the
+ * option we were looking for, prepare to
+ * copy the argument.
+ */
+ len = 0;
+ bufptr = buffer;
+ state = st_bufcpy;
+ break;
+ } else if (c == *opptr++) {
+ /*
+ * We are currently matching, so continue
+ * to the next character on the cmdline.
+ */
+ break;
+ }
+ state = st_wordskip;
+ /* fall through */
+
+ case st_wordskip:
+ if (myisspace(c))
+ state = st_wordstart;
+ break;
+
+ case st_bufcpy:
+ if (myisspace(c)) {
+ state = st_wordstart;
+ } else {
+ /*
+ * Increment len, but don't overrun the
+ * supplied buffer and leave room for the
+ * NULL terminator.
+ */
+ if (++len < bufsize)
+ *bufptr++ = c;
+ }
+ break;
+ }
+ }
+
+ if (bufsize)
+ *bufptr = '\0';
+
+ return len;
+}
+
+int cmdline_find_option(const char *cmdline, const char *option, char *buffer,
+ int bufsize)
+{
+ return __cmdline_find_option(cmdline, COMMAND_LINE_SIZE, option,
+ buffer, bufsize);
+}
Patches currently in stable-queue which might be from thomas.lendacky(a)amd.com are
queue-4.4/x86-boot-add-early-cmdline-parsing-for-options-with-arguments.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "x86/boot: Add early cmdline parsing for options with arguments" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
x86/boot: Add early cmdline parsing for options with arguments
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
x86-boot-add-early-cmdline-parsing-for-options-with-arguments.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From e505371dd83963caae1a37ead9524e8d997341be Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky(a)amd.com>
Date: Mon, 17 Jul 2017 16:10:33 -0500
Subject: x86/boot: Add early cmdline parsing for options with arguments
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
From: Tom Lendacky <thomas.lendacky(a)amd.com>
commit e505371dd83963caae1a37ead9524e8d997341be upstream.
Add a cmdline_find_option() function to look for cmdline options that
take arguments. The argument is returned in a supplied buffer and the
argument length (regardless of whether it fits in the supplied buffer)
is returned, with -1 indicating not found.
Signed-off-by: Tom Lendacky <thomas.lendacky(a)amd.com>
Reviewed-by: Thomas Gleixner <tglx(a)linutronix.de>
Cc: Alexander Potapenko <glider(a)google.com>
Cc: Andrey Ryabinin <aryabinin(a)virtuozzo.com>
Cc: Andy Lutomirski <luto(a)kernel.org>
Cc: Arnd Bergmann <arnd(a)arndb.de>
Cc: Borislav Petkov <bp(a)alien8.de>
Cc: Brijesh Singh <brijesh.singh(a)amd.com>
Cc: Dave Young <dyoung(a)redhat.com>
Cc: Dmitry Vyukov <dvyukov(a)google.com>
Cc: Jonathan Corbet <corbet(a)lwn.net>
Cc: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com>
Cc: Larry Woodman <lwoodman(a)redhat.com>
Cc: Linus Torvalds <torvalds(a)linux-foundation.org>
Cc: Matt Fleming <matt(a)codeblueprint.co.uk>
Cc: Michael S. Tsirkin <mst(a)redhat.com>
Cc: Paolo Bonzini <pbonzini(a)redhat.com>
Cc: Peter Zijlstra <peterz(a)infradead.org>
Cc: Radim Krčmář <rkrcmar(a)redhat.com>
Cc: Rik van Riel <riel(a)redhat.com>
Cc: Toshimitsu Kani <toshi.kani(a)hpe.com>
Cc: kasan-dev(a)googlegroups.com
Cc: kvm(a)vger.kernel.org
Cc: linux-arch(a)vger.kernel.org
Cc: linux-doc(a)vger.kernel.org
Cc: linux-efi(a)vger.kernel.org
Cc: linux-mm(a)kvack.org
Link: http://lkml.kernel.org/r/36b5f97492a9745dce27682305f990fc20e5cf8a.150031921…
Signed-off-by: Ingo Molnar <mingo(a)kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/x86/include/asm/cmdline.h | 2
arch/x86/lib/cmdline.c | 105 +++++++++++++++++++++++++++++++++++++++++
2 files changed, 107 insertions(+)
--- a/arch/x86/include/asm/cmdline.h
+++ b/arch/x86/include/asm/cmdline.h
@@ -2,5 +2,7 @@
#define _ASM_X86_CMDLINE_H
int cmdline_find_option_bool(const char *cmdline_ptr, const char *option);
+int cmdline_find_option(const char *cmdline_ptr, const char *option,
+ char *buffer, int bufsize);
#endif /* _ASM_X86_CMDLINE_H */
--- a/arch/x86/lib/cmdline.c
+++ b/arch/x86/lib/cmdline.c
@@ -104,7 +104,112 @@ __cmdline_find_option_bool(const char *c
return 0; /* Buffer overrun */
}
+/*
+ * Find a non-boolean option (i.e. option=argument). In accordance with
+ * standard Linux practice, if this option is repeated, this returns the
+ * last instance on the command line.
+ *
+ * @cmdline: the cmdline string
+ * @max_cmdline_size: the maximum size of cmdline
+ * @option: option string to look for
+ * @buffer: memory buffer to return the option argument
+ * @bufsize: size of the supplied memory buffer
+ *
+ * Returns the length of the argument (regardless of if it was
+ * truncated to fit in the buffer), or -1 on not found.
+ */
+static int
+__cmdline_find_option(const char *cmdline, int max_cmdline_size,
+ const char *option, char *buffer, int bufsize)
+{
+ char c;
+ int pos = 0, len = -1;
+ const char *opptr = NULL;
+ char *bufptr = buffer;
+ enum {
+ st_wordstart = 0, /* Start of word/after whitespace */
+ st_wordcmp, /* Comparing this word */
+ st_wordskip, /* Miscompare, skip */
+ st_bufcpy, /* Copying this to buffer */
+ } state = st_wordstart;
+
+ if (!cmdline)
+ return -1; /* No command line */
+
+ /*
+ * This 'pos' check ensures we do not overrun
+ * a non-NULL-terminated 'cmdline'
+ */
+ while (pos++ < max_cmdline_size) {
+ c = *(char *)cmdline++;
+ if (!c)
+ break;
+
+ switch (state) {
+ case st_wordstart:
+ if (myisspace(c))
+ break;
+
+ state = st_wordcmp;
+ opptr = option;
+ /* fall through */
+
+ case st_wordcmp:
+ if ((c == '=') && !*opptr) {
+ /*
+ * We matched all the way to the end of the
+ * option we were looking for, prepare to
+ * copy the argument.
+ */
+ len = 0;
+ bufptr = buffer;
+ state = st_bufcpy;
+ break;
+ } else if (c == *opptr++) {
+ /*
+ * We are currently matching, so continue
+ * to the next character on the cmdline.
+ */
+ break;
+ }
+ state = st_wordskip;
+ /* fall through */
+
+ case st_wordskip:
+ if (myisspace(c))
+ state = st_wordstart;
+ break;
+
+ case st_bufcpy:
+ if (myisspace(c)) {
+ state = st_wordstart;
+ } else {
+ /*
+ * Increment len, but don't overrun the
+ * supplied buffer and leave room for the
+ * NULL terminator.
+ */
+ if (++len < bufsize)
+ *bufptr++ = c;
+ }
+ break;
+ }
+ }
+
+ if (bufsize)
+ *bufptr = '\0';
+
+ return len;
+}
+
int cmdline_find_option_bool(const char *cmdline, const char *option)
{
return __cmdline_find_option_bool(cmdline, COMMAND_LINE_SIZE, option);
}
+
+int cmdline_find_option(const char *cmdline, const char *option, char *buffer,
+ int bufsize)
+{
+ return __cmdline_find_option(cmdline, COMMAND_LINE_SIZE, option,
+ buffer, bufsize);
+}
Patches currently in stable-queue which might be from thomas.lendacky(a)amd.com are
queue-4.9/x86-boot-add-early-cmdline-parsing-for-options-with-arguments.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] v3.18.86 build: 0 failures 1 warnings (v3.18.86)
by Build bot for Mark Brown
Tree/Branch: v3.18.86
Git describe: v3.18.86
Commit: 1d2acf22c2 Linux 3.18.86
Build Time: 67 min 20 sec
Passed: 9 / 9 (100.00 %)
Failed: 0 / 9 ( 0.00 %)
Errors: 0
Warnings: 1
Section Mismatches: 0
-------------------------------------------------------------------------------
defconfigs with issues (other than build errors):
2 warnings 0 mismatches : x86_64-defconfig
-------------------------------------------------------------------------------
Warnings Summary: 1
2 ../include/linux/ftrace.h:632:36: warning: calling '__builtin_return_address' with a nonzero argument is unsafe [-Wframe-address]
===============================================================================
Detailed per-defconfig build reports below:
-------------------------------------------------------------------------------
x86_64-defconfig : PASS, 0 errors, 2 warnings, 0 section mismatches
Warnings:
../include/linux/ftrace.h:632:36: warning: calling '__builtin_return_address' with a nonzero argument is unsafe [-Wframe-address]
../include/linux/ftrace.h:632:36: warning: calling '__builtin_return_address' with a nonzero argument is unsafe [-Wframe-address]
-------------------------------------------------------------------------------
Passed with no errors, warnings or mismatches:
arm64-allnoconfig
arm64-allmodconfig
arm-multi_v5_defconfig
arm-multi_v7_defconfig
arm-allmodconfig
arm-allnoconfig
x86_64-allnoconfig
arm64-defconfig
close failed in file object destructor:
sys.excepthook is missing
lost sys.stderr
7 years, 8 months
- 3
- 4
Re: [Linux-stable-mirror] Linux 4.14.11
by Greg KH
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 05496622b4ef..520fdec15bbb 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2685,6 +2685,8 @@
steal time is computed, but won't influence scheduler
behaviour
+ nopti [X86-64] Disable kernel page table isolation
+
nolapic [X86-32,APIC] Do not enable or use the local APIC.
nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
@@ -3253,6 +3255,12 @@
pt. [PARIDE]
See Documentation/blockdev/paride.txt.
+ pti= [X86_64]
+ Control user/kernel address space isolation:
+ on - enable
+ off - disable
+ auto - default setting
+
pty.legacy_count=
[KNL] Number of legacy pty's. Overwrites compiled-in
default number.
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 51101708a03a..ad41b3813f0a 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -12,6 +12,7 @@ ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
... unused hole ...
ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB)
... unused hole ...
+fffffe0000000000 - fffffe7fffffffff (=39 bits) LDT remap for PTI
fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
... unused hole ...
@@ -29,8 +30,8 @@ Virtual memory map with 5 level page tables:
hole caused by [56:63] sign extension
ff00000000000000 - ff0fffffffffffff (=52 bits) guard hole, reserved for hypervisor
ff10000000000000 - ff8fffffffffffff (=55 bits) direct mapping of all phys. memory
-ff90000000000000 - ff91ffffffffffff (=49 bits) hole
-ff92000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space
+ff90000000000000 - ff9fffffffffffff (=52 bits) LDT remap for PTI
+ffa0000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space (12800 TB)
ffd2000000000000 - ffd3ffffffffffff (=49 bits) hole
ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
... unused hole ...
diff --git a/Makefile b/Makefile
index 9edfb78836a9..655887067dc7 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 4
PATCHLEVEL = 14
-SUBLEVEL = 10
+SUBLEVEL = 11
EXTRAVERSION =
NAME = Petit Gorille
@@ -802,6 +802,9 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign)
# disable invalid "can't wrap" optimizations for signed / pointers
KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow)
+# Make sure -fstack-check isn't enabled (like gentoo apparently did)
+KBUILD_CFLAGS += $(call cc-option,-fno-stack-check,)
+
# conserve stack if available
KBUILD_CFLAGS += $(call cc-option,-fconserve-stack)
diff --git a/arch/sparc/lib/hweight.S b/arch/sparc/lib/hweight.S
index e5547b22cd18..0ddbbb031822 100644
--- a/arch/sparc/lib/hweight.S
+++ b/arch/sparc/lib/hweight.S
@@ -44,8 +44,8 @@ EXPORT_SYMBOL(__arch_hweight32)
.previous
ENTRY(__arch_hweight64)
- sethi %hi(__sw_hweight16), %g1
- jmpl %g1 + %lo(__sw_hweight16), %g0
+ sethi %hi(__sw_hweight64), %g1
+ jmpl %g1 + %lo(__sw_hweight64), %g0
nop
ENDPROC(__arch_hweight64)
EXPORT_SYMBOL(__arch_hweight64)
diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c
index 972319ff5b01..e691ff734cb5 100644
--- a/arch/x86/boot/compressed/pagetable.c
+++ b/arch/x86/boot/compressed/pagetable.c
@@ -23,6 +23,9 @@
*/
#undef CONFIG_AMD_MEM_ENCRYPT
+/* No PAGE_TABLE_ISOLATION support needed either: */
+#undef CONFIG_PAGE_TABLE_ISOLATION
+
#include "misc.h"
/* These actually do the work of building the kernel identity maps. */
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 3fd8bc560fae..45a63e00a6af 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -1,6 +1,11 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/jump_label.h>
#include <asm/unwind_hints.h>
+#include <asm/cpufeatures.h>
+#include <asm/page_types.h>
+#include <asm/percpu.h>
+#include <asm/asm-offsets.h>
+#include <asm/processor-flags.h>
/*
@@ -187,6 +192,146 @@ For 32-bit we have the following conventions - kernel is built with
#endif
.endm
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+/*
+ * PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two
+ * halves:
+ */
+#define PTI_SWITCH_PGTABLES_MASK (1<<PAGE_SHIFT)
+#define PTI_SWITCH_MASK (PTI_SWITCH_PGTABLES_MASK|(1<<X86_CR3_PTI_SWITCH_BIT))
+
+.macro SET_NOFLUSH_BIT reg:req
+ bts $X86_CR3_PCID_NOFLUSH_BIT, \reg
+.endm
+
+.macro ADJUST_KERNEL_CR3 reg:req
+ ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID
+ /* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
+ andq $(~PTI_SWITCH_MASK), \reg
+.endm
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ mov %cr3, \scratch_reg
+ ADJUST_KERNEL_CR3 \scratch_reg
+ mov \scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+#define THIS_CPU_user_pcid_flush_mask \
+ PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
+
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ mov %cr3, \scratch_reg
+
+ ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+ /*
+ * Test if the ASID needs a flush.
+ */
+ movq \scratch_reg, \scratch_reg2
+ andq $(0x7FF), \scratch_reg /* mask ASID */
+ bt \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ jnc .Lnoflush_\@
+
+ /* Flush needed, clear the bit */
+ btr \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ movq \scratch_reg2, \scratch_reg
+ jmp .Lwrcr3_\@
+
+.Lnoflush_\@:
+ movq \scratch_reg2, \scratch_reg
+ SET_NOFLUSH_BIT \scratch_reg
+
+.Lwrcr3_\@:
+ /* Flip the PGD and ASID to the user version */
+ orq $(PTI_SWITCH_MASK), \scratch_reg
+ mov \scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
+ pushq %rax
+ SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax
+ popq %rax
+.endm
+
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+ ALTERNATIVE "jmp .Ldone_\@", "", X86_FEATURE_PTI
+ movq %cr3, \scratch_reg
+ movq \scratch_reg, \save_reg
+ /*
+ * Is the "switch mask" all zero? That means that both of
+ * these are zero:
+ *
+ * 1. The user/kernel PCID bit, and
+ * 2. The user/kernel "bit" that points CR3 to the
+ * bottom half of the 8k PGD
+ *
+ * That indicates a kernel CR3 value, not a user CR3.
+ */
+ testq $(PTI_SWITCH_MASK), \scratch_reg
+ jz .Ldone_\@
+
+ ADJUST_KERNEL_CR3 \scratch_reg
+ movq \scratch_reg, %cr3
+
+.Ldone_\@:
+.endm
+
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+
+ ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+ /*
+ * KERNEL pages can always resume with NOFLUSH as we do
+ * explicit flushes.
+ */
+ bt $X86_CR3_PTI_SWITCH_BIT, \save_reg
+ jnc .Lnoflush_\@
+
+ /*
+ * Check if there's a pending flush for the user ASID we're
+ * about to set.
+ */
+ movq \save_reg, \scratch_reg
+ andq $(0x7FF), \scratch_reg
+ bt \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ jnc .Lnoflush_\@
+
+ btr \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ jmp .Lwrcr3_\@
+
+.Lnoflush_\@:
+ SET_NOFLUSH_BIT \save_reg
+
+.Lwrcr3_\@:
+ /*
+ * The CR3 write could be avoided when not changing its value,
+ * but would require a CR3 read *and* a scratch register.
+ */
+ movq \save_reg, %cr3
+.Lend_\@:
+.endm
+
+#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+.endm
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+.endm
+.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
+.endm
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+.endm
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+.endm
+
+#endif
+
#endif /* CONFIG_X86_64 */
/*
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 22c891c3b78d..dd696b966e58 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -23,7 +23,6 @@
#include <asm/segment.h>
#include <asm/cache.h>
#include <asm/errno.h>
-#include "calling.h"
#include <asm/asm-offsets.h>
#include <asm/msr.h>
#include <asm/unistd.h>
@@ -40,6 +39,8 @@
#include <asm/frame.h>
#include <linux/err.h>
+#include "calling.h"
+
.code64
.section .entry.text, "ax"
@@ -164,6 +165,9 @@ ENTRY(entry_SYSCALL_64_trampoline)
/* Stash the user RSP. */
movq %rsp, RSP_SCRATCH
+ /* Note: using %rsp as a scratch reg. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
/* Load the top of the task stack into RSP */
movq CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp
@@ -203,6 +207,10 @@ ENTRY(entry_SYSCALL_64)
*/
swapgs
+ /*
+ * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it
+ * is not required to switch CR3.
+ */
movq %rsp, PER_CPU_VAR(rsp_scratch)
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
@@ -399,6 +407,7 @@ syscall_return_via_sysret:
* We are on the trampoline stack. All regs except RDI are live.
* We can do future final exit work right here.
*/
+ SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
popq %rdi
popq %rsp
@@ -736,6 +745,8 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode)
* We can do future final exit work right here.
*/
+ SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+
/* Restore RDI. */
popq %rdi
SWAPGS
@@ -818,7 +829,9 @@ native_irq_return_ldt:
*/
pushq %rdi /* Stash user RDI */
- SWAPGS
+ SWAPGS /* to kernel GS */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi /* to kernel CR3 */
+
movq PER_CPU_VAR(espfix_waddr), %rdi
movq %rax, (0*8)(%rdi) /* user RAX */
movq (1*8)(%rsp), %rax /* user RIP */
@@ -834,7 +847,6 @@ native_irq_return_ldt:
/* Now RAX == RSP. */
andl $0xffff0000, %eax /* RAX = (RSP & 0xffff0000) */
- popq %rdi /* Restore user RDI */
/*
* espfix_stack[31:16] == 0. The page tables are set up such that
@@ -845,7 +857,11 @@ native_irq_return_ldt:
* still points to an RO alias of the ESPFIX stack.
*/
orq PER_CPU_VAR(espfix_stack), %rax
- SWAPGS
+
+ SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+ SWAPGS /* to user GS */
+ popq %rdi /* Restore user RDI */
+
movq %rax, %rsp
UNWIND_HINT_IRET_REGS offset=8
@@ -945,6 +961,8 @@ ENTRY(switch_to_thread_stack)
UNWIND_HINT_FUNC
pushq %rdi
+ /* Need to switch before accessing the thread stack. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
movq %rsp, %rdi
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
@@ -1244,7 +1262,11 @@ ENTRY(paranoid_entry)
js 1f /* negative -> in kernel */
SWAPGS
xorl %ebx, %ebx
-1: ret
+
+1:
+ SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
+
+ ret
END(paranoid_entry)
/*
@@ -1266,6 +1288,7 @@ ENTRY(paranoid_exit)
testl %ebx, %ebx /* swapgs needed? */
jnz .Lparanoid_exit_no_swapgs
TRACE_IRQS_IRETQ
+ RESTORE_CR3 scratch_reg=%rbx save_reg=%r14
SWAPGS_UNSAFE_STACK
jmp .Lparanoid_exit_restore
.Lparanoid_exit_no_swapgs:
@@ -1293,6 +1316,8 @@ ENTRY(error_entry)
* from user mode due to an IRET fault.
*/
SWAPGS
+ /* We have user CR3. Change to kernel CR3. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
.Lerror_entry_from_usermode_after_swapgs:
/* Put us onto the real thread stack. */
@@ -1339,6 +1364,7 @@ ENTRY(error_entry)
* .Lgs_change's error handler with kernel gsbase.
*/
SWAPGS
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
jmp .Lerror_entry_done
.Lbstep_iret:
@@ -1348,10 +1374,11 @@ ENTRY(error_entry)
.Lerror_bad_iret:
/*
- * We came from an IRET to user mode, so we have user gsbase.
- * Switch to kernel gsbase:
+ * We came from an IRET to user mode, so we have user
+ * gsbase and CR3. Switch to kernel gsbase and CR3:
*/
SWAPGS
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
/*
* Pretend that the exception came from user mode: set up pt_regs
@@ -1383,6 +1410,10 @@ END(error_exit)
/*
* Runs on exception stack. Xen PV does not go through this path at all,
* so we can use real assembly here.
+ *
+ * Registers:
+ * %r14: Used to save/restore the CR3 of the interrupted context
+ * when PAGE_TABLE_ISOLATION is in use. Do not clobber.
*/
ENTRY(nmi)
UNWIND_HINT_IRET_REGS
@@ -1446,6 +1477,7 @@ ENTRY(nmi)
swapgs
cld
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
movq %rsp, %rdx
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
UNWIND_HINT_IRET_REGS base=%rdx offset=8
@@ -1698,6 +1730,8 @@ end_repeat_nmi:
movq $-1, %rsi
call do_nmi
+ RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
+
testl %ebx, %ebx /* swapgs needed? */
jnz nmi_restore
nmi_swapgs:
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 95ad40eb7eff..40f17009ec20 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -49,6 +49,10 @@
ENTRY(entry_SYSENTER_compat)
/* Interrupts are off on entry. */
SWAPGS
+
+ /* We are about to clobber %rsp anyway, clobbering here is OK */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
/*
@@ -215,6 +219,12 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe)
pushq $0 /* pt_regs->r14 = 0 */
pushq $0 /* pt_regs->r15 = 0 */
+ /*
+ * We just saved %rdi so it is safe to clobber. It is not
+ * preserved during the C calls inside TRACE_IRQS_OFF anyway.
+ */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+
/*
* User mode is traced as though IRQs are on, and SYSENTER
* turned them off.
@@ -256,10 +266,22 @@ sysret32_from_system_call:
* when the system call started, which is already known to user
* code. We zero R8-R10 to avoid info leaks.
*/
+ movq RSP-ORIG_RAX(%rsp), %rsp
+
+ /*
+ * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored
+ * on the process stack which is not mapped to userspace and
+ * not readable after we SWITCH_TO_USER_CR3. Delay the CR3
+ * switch until after after the last reference to the process
+ * stack.
+ *
+ * %r8/%r9 are zeroed before the sysret, thus safe to clobber.
+ */
+ SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9
+
xorq %r8, %r8
xorq %r9, %r9
xorq %r10, %r10
- movq RSP-ORIG_RAX(%rsp), %rsp
swapgs
sysretl
END(entry_SYSCALL_compat)
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 1faf40f2dda9..577fa8adb785 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -344,14 +344,14 @@ int in_gate_area_no_mm(unsigned long addr)
* vsyscalls but leave the page not present. If so, we skip calling
* this.
*/
-static void __init set_vsyscall_pgtable_user_bits(void)
+void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
- pgd = pgd_offset_k(VSYSCALL_ADDR);
+ pgd = pgd_offset_pgd(root, VSYSCALL_ADDR);
set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
p4d = p4d_offset(pgd, VSYSCALL_ADDR);
#if CONFIG_PGTABLE_LEVELS >= 5
@@ -373,7 +373,7 @@ void __init map_vsyscall(void)
vsyscall_mode == NATIVE
? PAGE_KERNEL_VSYSCALL
: PAGE_KERNEL_VVAR);
- set_vsyscall_pgtable_user_bits();
+ set_vsyscall_pgtable_user_bits(swapper_pg_dir);
}
BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 3674a4b6f8bd..8f0aace08b87 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -3,16 +3,18 @@
#include <linux/types.h>
#include <linux/slab.h>
+#include <asm/cpu_entry_area.h>
#include <asm/perf_event.h>
#include <asm/insn.h>
#include "../perf_event.h"
+/* Waste a full page so it can be mapped into the cpu_entry_area */
+DEFINE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
/* The size of a BTS record in bytes: */
#define BTS_RECORD_SIZE 24
-#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4)
#define PEBS_FIXUP_SIZE PAGE_SIZE
/*
@@ -279,17 +281,52 @@ void fini_debug_store_on_cpu(int cpu)
static DEFINE_PER_CPU(void *, insn_buffer);
-static int alloc_pebs_buffer(int cpu)
+static void ds_update_cea(void *cea, void *addr, size_t size, pgprot_t prot)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+ phys_addr_t pa;
+ size_t msz = 0;
+
+ pa = virt_to_phys(addr);
+ for (; msz < size; msz += PAGE_SIZE, pa += PAGE_SIZE, cea += PAGE_SIZE)
+ cea_set_pte(cea, pa, prot);
+}
+
+static void ds_clear_cea(void *cea, size_t size)
+{
+ size_t msz = 0;
+
+ for (; msz < size; msz += PAGE_SIZE, cea += PAGE_SIZE)
+ cea_set_pte(cea, 0, PAGE_NONE);
+}
+
+static void *dsalloc_pages(size_t size, gfp_t flags, int cpu)
+{
+ unsigned int order = get_order(size);
int node = cpu_to_node(cpu);
- int max;
- void *buffer, *ibuffer;
+ struct page *page;
+
+ page = __alloc_pages_node(node, flags | __GFP_ZERO, order);
+ return page ? page_address(page) : NULL;
+}
+
+static void dsfree_pages(const void *buffer, size_t size)
+{
+ if (buffer)
+ free_pages((unsigned long)buffer, get_order(size));
+}
+
+static int alloc_pebs_buffer(int cpu)
+{
+ struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+ struct debug_store *ds = hwev->ds;
+ size_t bsiz = x86_pmu.pebs_buffer_size;
+ int max, node = cpu_to_node(cpu);
+ void *buffer, *ibuffer, *cea;
if (!x86_pmu.pebs)
return 0;
- buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
+ buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu);
if (unlikely(!buffer))
return -ENOMEM;
@@ -300,25 +337,27 @@ static int alloc_pebs_buffer(int cpu)
if (x86_pmu.intel_cap.pebs_format < 2) {
ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
if (!ibuffer) {
- kfree(buffer);
+ dsfree_pages(buffer, bsiz);
return -ENOMEM;
}
per_cpu(insn_buffer, cpu) = ibuffer;
}
-
- max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size;
-
- ds->pebs_buffer_base = (u64)(unsigned long)buffer;
+ hwev->ds_pebs_vaddr = buffer;
+ /* Update the cpu entry area mapping */
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+ ds->pebs_buffer_base = (unsigned long) cea;
+ ds_update_cea(cea, buffer, bsiz, PAGE_KERNEL);
ds->pebs_index = ds->pebs_buffer_base;
- ds->pebs_absolute_maximum = ds->pebs_buffer_base +
- max * x86_pmu.pebs_record_size;
-
+ max = x86_pmu.pebs_record_size * (bsiz / x86_pmu.pebs_record_size);
+ ds->pebs_absolute_maximum = ds->pebs_buffer_base + max;
return 0;
}
static void release_pebs_buffer(int cpu)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+ struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+ struct debug_store *ds = hwev->ds;
+ void *cea;
if (!ds || !x86_pmu.pebs)
return;
@@ -326,73 +365,70 @@ static void release_pebs_buffer(int cpu)
kfree(per_cpu(insn_buffer, cpu));
per_cpu(insn_buffer, cpu) = NULL;
- kfree((void *)(unsigned long)ds->pebs_buffer_base);
+ /* Clear the fixmap */
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+ ds_clear_cea(cea, x86_pmu.pebs_buffer_size);
ds->pebs_buffer_base = 0;
+ dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size);
+ hwev->ds_pebs_vaddr = NULL;
}
static int alloc_bts_buffer(int cpu)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
- int node = cpu_to_node(cpu);
- int max, thresh;
- void *buffer;
+ struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+ struct debug_store *ds = hwev->ds;
+ void *buffer, *cea;
+ int max;
if (!x86_pmu.bts)
return 0;
- buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+ buffer = dsalloc_pages(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, cpu);
if (unlikely(!buffer)) {
WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
return -ENOMEM;
}
-
- max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
- thresh = max / 16;
-
- ds->bts_buffer_base = (u64)(unsigned long)buffer;
+ hwev->ds_bts_vaddr = buffer;
+ /* Update the fixmap */
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
+ ds->bts_buffer_base = (unsigned long) cea;
+ ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL);
ds->bts_index = ds->bts_buffer_base;
- ds->bts_absolute_maximum = ds->bts_buffer_base +
- max * BTS_RECORD_SIZE;
- ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
- thresh * BTS_RECORD_SIZE;
-
+ max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE);
+ ds->bts_absolute_maximum = ds->bts_buffer_base + max;
+ ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16);
return 0;
}
static void release_bts_buffer(int cpu)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+ struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+ struct debug_store *ds = hwev->ds;
+ void *cea;
if (!ds || !x86_pmu.bts)
return;
- kfree((void *)(unsigned long)ds->bts_buffer_base);
+ /* Clear the fixmap */
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
+ ds_clear_cea(cea, BTS_BUFFER_SIZE);
ds->bts_buffer_base = 0;
+ dsfree_pages(hwev->ds_bts_vaddr, BTS_BUFFER_SIZE);
+ hwev->ds_bts_vaddr = NULL;
}
static int alloc_ds_buffer(int cpu)
{
- int node = cpu_to_node(cpu);
- struct debug_store *ds;
-
- ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
- if (unlikely(!ds))
- return -ENOMEM;
+ struct debug_store *ds = &get_cpu_entry_area(cpu)->cpu_debug_store;
+ memset(ds, 0, sizeof(*ds));
per_cpu(cpu_hw_events, cpu).ds = ds;
-
return 0;
}
static void release_ds_buffer(int cpu)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
- if (!ds)
- return;
-
per_cpu(cpu_hw_events, cpu).ds = NULL;
- kfree(ds);
}
void release_ds_buffers(void)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index f7aaadf9331f..8e4ea143ed96 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -14,6 +14,8 @@
#include <linux/perf_event.h>
+#include <asm/intel_ds.h>
+
/* To enable MSR tracing please use the generic trace points. */
/*
@@ -77,8 +79,6 @@ struct amd_nb {
struct event_constraint event_constraints[X86_PMC_IDX_MAX];
};
-/* The maximal number of PEBS events: */
-#define MAX_PEBS_EVENTS 8
#define PEBS_COUNTER_MASK ((1ULL << MAX_PEBS_EVENTS) - 1)
/*
@@ -95,23 +95,6 @@ struct amd_nb {
PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)
-/*
- * A debug store configuration.
- *
- * We only support architectures that use 64bit fields.
- */
-struct debug_store {
- u64 bts_buffer_base;
- u64 bts_index;
- u64 bts_absolute_maximum;
- u64 bts_interrupt_threshold;
- u64 pebs_buffer_base;
- u64 pebs_index;
- u64 pebs_absolute_maximum;
- u64 pebs_interrupt_threshold;
- u64 pebs_event_reset[MAX_PEBS_EVENTS];
-};
-
#define PEBS_REGS \
(PERF_REG_X86_AX | \
PERF_REG_X86_BX | \
@@ -216,6 +199,8 @@ struct cpu_hw_events {
* Intel DebugStore bits
*/
struct debug_store *ds;
+ void *ds_pebs_vaddr;
+ void *ds_bts_vaddr;
u64 pebs_enabled;
int n_pebs;
int n_large_pebs;
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index 2fbc69a0916e..4a7884b8dca5 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -5,6 +5,7 @@
#include <linux/percpu-defs.h>
#include <asm/processor.h>
+#include <asm/intel_ds.h>
/*
* cpu_entry_area is a percpu region that contains things needed by the CPU
@@ -40,6 +41,18 @@ struct cpu_entry_area {
*/
char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
#endif
+#ifdef CONFIG_CPU_SUP_INTEL
+ /*
+ * Per CPU debug store for Intel performance monitoring. Wastes a
+ * full page at the moment.
+ */
+ struct debug_store cpu_debug_store;
+ /*
+ * The actual PEBS/BTS buffers must be mapped to user space
+ * Reserve enough fixmap PTEs.
+ */
+ struct debug_store_buffers cpu_debug_buffers;
+#endif
};
#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area))
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 800104c8a3ed..07cdd1715705 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -197,11 +197,12 @@
#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */
-
+#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
#define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */
@@ -340,5 +341,6 @@
#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#define X86_BUG_CPU_INSECURE X86_BUG(14) /* CPU is insecure and needs kernel page table isolation */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index bc359dd2f7f6..85e23bb7b34e 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -21,6 +21,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
desc->type = (info->read_exec_only ^ 1) << 1;
desc->type |= info->contents << 2;
+ /* Set the ACCESS bit so it can be mapped RO */
+ desc->type |= 1;
desc->s = 1;
desc->dpl = 0x3;
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index c10c9128f54e..e428e16dd822 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -44,6 +44,12 @@
# define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31))
#endif
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define DISABLE_PTI 0
+#else
+# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -54,7 +60,7 @@
#define DISABLED_MASK4 (DISABLE_PCID)
#define DISABLED_MASK5 0
#define DISABLED_MASK6 0
-#define DISABLED_MASK7 0
+#define DISABLED_MASK7 (DISABLE_PTI)
#define DISABLED_MASK8 0
#define DISABLED_MASK9 (DISABLE_MPX)
#define DISABLED_MASK10 0
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
new file mode 100644
index 000000000000..62a9f4966b42
--- /dev/null
+++ b/arch/x86/include/asm/intel_ds.h
@@ -0,0 +1,36 @@
+#ifndef _ASM_INTEL_DS_H
+#define _ASM_INTEL_DS_H
+
+#include <linux/percpu-defs.h>
+
+#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
+#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4)
+
+/* The maximal number of PEBS events: */
+#define MAX_PEBS_EVENTS 8
+
+/*
+ * A debug store configuration.
+ *
+ * We only support architectures that use 64bit fields.
+ */
+struct debug_store {
+ u64 bts_buffer_base;
+ u64 bts_index;
+ u64 bts_absolute_maximum;
+ u64 bts_interrupt_threshold;
+ u64 pebs_buffer_base;
+ u64 pebs_index;
+ u64 pebs_absolute_maximum;
+ u64 pebs_interrupt_threshold;
+ u64 pebs_event_reset[MAX_PEBS_EVENTS];
+} __aligned(PAGE_SIZE);
+
+DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
+struct debug_store_buffers {
+ char bts_buffer[BTS_BUFFER_SIZE];
+ char pebs_buffer[PEBS_BUFFER_SIZE];
+};
+
+#endif
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 5ede7cae1d67..c931b88982a0 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -50,10 +50,33 @@ struct ldt_struct {
* call gates. On native, we could merge the ldt_struct and LDT
* allocations, but it's not worth trying to optimize.
*/
- struct desc_struct *entries;
- unsigned int nr_entries;
+ struct desc_struct *entries;
+ unsigned int nr_entries;
+
+ /*
+ * If PTI is in use, then the entries array is not mapped while we're
+ * in user mode. The whole array will be aliased at the addressed
+ * given by ldt_slot_va(slot). We use two slots so that we can allocate
+ * and map, and enable a new LDT without invalidating the mapping
+ * of an older, still-in-use LDT.
+ *
+ * slot will be -1 if this LDT doesn't have an alias mapping.
+ */
+ int slot;
};
+/* This is a multiple of PAGE_SIZE. */
+#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE)
+
+static inline void *ldt_slot_va(int slot)
+{
+#ifdef CONFIG_X86_64
+ return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
+#else
+ BUG();
+#endif
+}
+
/*
* Used for LDT copy/destruction.
*/
@@ -64,6 +87,7 @@ static inline void init_new_context_ldt(struct mm_struct *mm)
}
int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm);
void destroy_context_ldt(struct mm_struct *mm);
+void ldt_arch_exit_mmap(struct mm_struct *mm);
#else /* CONFIG_MODIFY_LDT_SYSCALL */
static inline void init_new_context_ldt(struct mm_struct *mm) { }
static inline int ldt_dup_context(struct mm_struct *oldmm,
@@ -71,7 +95,8 @@ static inline int ldt_dup_context(struct mm_struct *oldmm,
{
return 0;
}
-static inline void destroy_context_ldt(struct mm_struct *mm) {}
+static inline void destroy_context_ldt(struct mm_struct *mm) { }
+static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { }
#endif
static inline void load_mm_ldt(struct mm_struct *mm)
@@ -96,10 +121,31 @@ static inline void load_mm_ldt(struct mm_struct *mm)
* that we can see.
*/
- if (unlikely(ldt))
- set_ldt(ldt->entries, ldt->nr_entries);
- else
+ if (unlikely(ldt)) {
+ if (static_cpu_has(X86_FEATURE_PTI)) {
+ if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) {
+ /*
+ * Whoops -- either the new LDT isn't mapped
+ * (if slot == -1) or is mapped into a bogus
+ * slot (if slot > 1).
+ */
+ clear_LDT();
+ return;
+ }
+
+ /*
+ * If page table isolation is enabled, ldt->entries
+ * will not be mapped in the userspace pagetables.
+ * Tell the CPU to access the LDT through the alias
+ * at ldt_slot_va(ldt->slot).
+ */
+ set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries);
+ } else {
+ set_ldt(ldt->entries, ldt->nr_entries);
+ }
+ } else {
clear_LDT();
+ }
#else
clear_LDT();
#endif
@@ -194,6 +240,7 @@ static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
static inline void arch_exit_mmap(struct mm_struct *mm)
{
paravirt_arch_exit_mmap(mm);
+ ldt_arch_exit_mmap(mm);
}
#ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 4b5e1eafada7..aff42e1da6ee 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -30,6 +30,17 @@ static inline void paravirt_release_p4d(unsigned long pfn) {}
*/
extern gfp_t __userpte_alloc_gfp;
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Instead of one PGD, we acquire two PGDs. Being order-1, it is
+ * both 8k in size and 8k-aligned. That lets us just flip bit 12
+ * in a pointer to swap between the two 4k halves.
+ */
+#define PGD_ALLOCATION_ORDER 1
+#else
+#define PGD_ALLOCATION_ORDER 0
+#endif
+
/*
* Allocate and free page tables.
*/
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index f02de8bc1f72..211368922cad 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -28,6 +28,7 @@ extern pgd_t early_top_pgt[PTRS_PER_PGD];
int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
void ptdump_walk_pgd_level_checkwx(void);
#ifdef CONFIG_DEBUG_WX
@@ -846,7 +847,12 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
static inline int p4d_bad(p4d_t p4d)
{
- return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
+ unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER;
+
+ if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ ignore_flags |= _PAGE_NX;
+
+ return (p4d_flags(p4d) & ~ignore_flags) != 0;
}
#endif /* CONFIG_PGTABLE_LEVELS > 3 */
@@ -880,7 +886,12 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
static inline int pgd_bad(pgd_t pgd)
{
- return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+ unsigned long ignore_flags = _PAGE_USER;
+
+ if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ ignore_flags |= _PAGE_NX;
+
+ return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
}
static inline int pgd_none(pgd_t pgd)
@@ -909,7 +920,11 @@ static inline int pgd_none(pgd_t pgd)
* pgd_offset() returns a (pgd_t *)
* pgd_index() is used get the offset into the pgd page's array of pgd_t's;
*/
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
+#define pgd_offset_pgd(pgd, address) (pgd + pgd_index((address)))
+/*
+ * a shortcut to get a pgd_t in a given mm
+ */
+#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address))
/*
* a shortcut which implies the use of the kernel's pgd, instead
* of a process's
@@ -1111,7 +1126,14 @@ static inline int pud_write(pud_t pud)
*/
static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
{
- memcpy(dst, src, count * sizeof(pgd_t));
+ memcpy(dst, src, count * sizeof(pgd_t));
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+ /* Clone the user space pgd as well */
+ memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src),
+ count * sizeof(pgd_t));
+#endif
}
#define PTE_SHIFT ilog2(PTRS_PER_PTE)
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index e9f05331e732..81462e9a34f6 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -131,9 +131,97 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
#endif
}
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and
+ * the user one is in the last 4k. To switch between them, you
+ * just need to flip the 12th bit in their addresses.
+ */
+#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT
+
+/*
+ * This generates better code than the inline assembly in
+ * __set_bit().
+ */
+static inline void *ptr_set_bit(void *ptr, int bit)
+{
+ unsigned long __ptr = (unsigned long)ptr;
+
+ __ptr |= BIT(bit);
+ return (void *)__ptr;
+}
+static inline void *ptr_clear_bit(void *ptr, int bit)
+{
+ unsigned long __ptr = (unsigned long)ptr;
+
+ __ptr &= ~BIT(bit);
+ return (void *)__ptr;
+}
+
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+ return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
+{
+ return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
+{
+ return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
+{
+ return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
+/*
+ * Page table pages are page-aligned. The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ *
+ * Returns true for parts of the PGD that map userspace and
+ * false for the parts that map the kernel.
+ */
+static inline bool pgdp_maps_userspace(void *__ptr)
+{
+ unsigned long ptr = (unsigned long)__ptr;
+
+ return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2);
+}
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd);
+
+/*
+ * Take a PGD location (pgdp) and a pgd value that needs to be set there.
+ * Populates the user and returns the resulting PGD that must be set in
+ * the kernel copy of the page tables.
+ */
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return pgd;
+ return __pti_set_user_pgd(pgdp, pgd);
+}
+#else
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ return pgd;
+}
+#endif
+
static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
{
+#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL)
+ p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd);
+#else
*p4dp = p4d;
+#endif
}
static inline void native_p4d_clear(p4d_t *p4d)
@@ -147,7 +235,11 @@ static inline void native_p4d_clear(p4d_t *p4d)
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ *pgdp = pti_set_user_pgd(pgdp, pgd);
+#else
*pgdp = pgd;
+#endif
}
static inline void native_pgd_clear(pgd_t *pgd)
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 3d27831bc58d..b97a539bcdee 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -79,13 +79,17 @@ typedef struct { pteval_t pte; } pte_t;
#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
#ifdef CONFIG_X86_5LEVEL
-# define VMALLOC_SIZE_TB _AC(16384, UL)
-# define __VMALLOC_BASE _AC(0xff92000000000000, UL)
+# define VMALLOC_SIZE_TB _AC(12800, UL)
+# define __VMALLOC_BASE _AC(0xffa0000000000000, UL)
# define __VMEMMAP_BASE _AC(0xffd4000000000000, UL)
+# define LDT_PGD_ENTRY _AC(-112, UL)
+# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
#else
# define VMALLOC_SIZE_TB _AC(32, UL)
# define __VMALLOC_BASE _AC(0xffffc90000000000, UL)
# define __VMEMMAP_BASE _AC(0xffffea0000000000, UL)
+# define LDT_PGD_ENTRY _AC(-4, UL)
+# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
#endif
#ifdef CONFIG_RANDOMIZE_MEMORY
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 43212a43ee69..6a60fea90b9d 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -38,6 +38,11 @@
#define CR3_ADDR_MASK __sme_clr(0x7FFFFFFFFFFFF000ull)
#define CR3_PCID_MASK 0xFFFull
#define CR3_NOFLUSH BIT_ULL(63)
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define X86_CR3_PTI_SWITCH_BIT 11
+#endif
+
#else
/*
* CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 9e482d8b0b97..9c18da64daa9 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -851,13 +851,22 @@ static inline void spin_lock_prefetch(const void *x)
#else
/*
- * User space process size. 47bits minus one guard page. The guard
- * page is necessary on Intel CPUs: if a SYSCALL instruction is at
- * the highest possible canonical userspace address, then that
- * syscall will enter the kernel with a non-canonical return
- * address, and SYSRET will explode dangerously. We avoid this
- * particular problem by preventing anything from being mapped
- * at the maximum canonical address.
+ * User space process size. This is the first address outside the user range.
+ * There are a few constraints that determine this:
+ *
+ * On Intel CPUs, if a SYSCALL instruction is at the highest canonical
+ * address, then that syscall will enter the kernel with a
+ * non-canonical return address, and SYSRET will explode dangerously.
+ * We avoid this particular problem by preventing anything executable
+ * from being mapped at the maximum canonical address.
+ *
+ * On AMD CPUs in the Ryzen family, there's a nasty bug in which the
+ * CPUs malfunction if they execute code from the highest canonical page.
+ * They'll speculate right off the end of the canonical space, and
+ * bad things happen. This is worked around in the same way as the
+ * Intel problem.
+ *
+ * With page table isolation enabled, we map the LDT in ... [stay tuned]
*/
#define TASK_SIZE_MAX ((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
new file mode 100644
index 000000000000..0b5ef05b2d2d
--- /dev/null
+++ b/arch/x86/include/asm/pti.h
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _ASM_X86_PTI_H
+#define _ASM_X86_PTI_H
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+extern void pti_init(void);
+extern void pti_check_boottime_disable(void);
+#else
+static inline void pti_check_boottime_disable(void) { }
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_PTI_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 171b429f43a2..f9b48ce152eb 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -10,38 +10,90 @@
#include <asm/special_insns.h>
#include <asm/smp.h>
#include <asm/invpcid.h>
+#include <asm/pti.h>
+#include <asm/processor-flags.h>
-static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
-{
- /*
- * Bump the generation count. This also serves as a full barrier
- * that synchronizes with switch_mm(): callers are required to order
- * their read of mm_cpumask after their writes to the paging
- * structures.
- */
- return atomic64_inc_return(&mm->context.tlb_gen);
-}
+/*
+ * The x86 feature is called PCID (Process Context IDentifier). It is similar
+ * to what is traditionally called ASID on the RISC processors.
+ *
+ * We don't use the traditional ASID implementation, where each process/mm gets
+ * its own ASID and flush/restart when we run out of ASID space.
+ *
+ * Instead we have a small per-cpu array of ASIDs and cache the last few mm's
+ * that came by on this CPU, allowing cheaper switch_mm between processes on
+ * this CPU.
+ *
+ * We end up with different spaces for different things. To avoid confusion we
+ * use different names for each of them:
+ *
+ * ASID - [0, TLB_NR_DYN_ASIDS-1]
+ * the canonical identifier for an mm
+ *
+ * kPCID - [1, TLB_NR_DYN_ASIDS]
+ * the value we write into the PCID part of CR3; corresponds to the
+ * ASID+1, because PCID 0 is special.
+ *
+ * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
+ * for KPTI each mm has two address spaces and thus needs two
+ * PCID values, but we can still do with a single ASID denomination
+ * for each mm. Corresponds to kPCID + 2048.
+ *
+ */
/* There are 12 bits of space for ASIDS in CR3 */
#define CR3_HW_ASID_BITS 12
+
/*
* When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
* user/kernel switches
*/
-#define PTI_CONSUMED_ASID_BITS 0
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define PTI_CONSUMED_PCID_BITS 1
+#else
+# define PTI_CONSUMED_PCID_BITS 0
+#endif
+
+#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS)
-#define CR3_AVAIL_ASID_BITS (CR3_HW_ASID_BITS - PTI_CONSUMED_ASID_BITS)
/*
* ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid. -1 below to account
- * for them being zero-based. Another -1 is because ASID 0 is reserved for
+ * for them being zero-based. Another -1 is because PCID 0 is reserved for
* use by non-PCID-aware users.
*/
-#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_ASID_BITS) - 2)
+#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2)
+
+/*
+ * 6 because 6 should be plenty and struct tlb_state will fit in two cache
+ * lines.
+ */
+#define TLB_NR_DYN_ASIDS 6
+/*
+ * Given @asid, compute kPCID
+ */
static inline u16 kern_pcid(u16 asid)
{
VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ /*
+ * Make sure that the dynamic ASID space does not confict with the
+ * bit we are using to switch between user and kernel ASIDs.
+ */
+ BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_SWITCH_BIT));
+
/*
+ * The ASID being passed in here should have respected the
+ * MAX_ASID_AVAILABLE and thus never have the switch bit set.
+ */
+ VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_SWITCH_BIT));
+#endif
+ /*
+ * The dynamically-assigned ASIDs that get passed in are small
+ * (<TLB_NR_DYN_ASIDS). They never have the high switch bit set,
+ * so do not bother to clear it.
+ *
* If PCID is on, ASID-aware code paths put the ASID+1 into the
* PCID bits. This serves two purposes. It prevents a nasty
* situation in which PCID-unaware code saves CR3, loads some other
@@ -53,6 +105,18 @@ static inline u16 kern_pcid(u16 asid)
return asid + 1;
}
+/*
+ * Given @asid, compute uPCID
+ */
+static inline u16 user_pcid(u16 asid)
+{
+ u16 ret = kern_pcid(asid);
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ ret |= 1 << X86_CR3_PTI_SWITCH_BIT;
+#endif
+ return ret;
+}
+
struct pgd_t;
static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
{
@@ -95,12 +159,6 @@ static inline bool tlb_defer_switch_to_init_mm(void)
return !static_cpu_has(X86_FEATURE_PCID);
}
-/*
- * 6 because 6 should be plenty and struct tlb_state will fit in
- * two cache lines.
- */
-#define TLB_NR_DYN_ASIDS 6
-
struct tlb_context {
u64 ctx_id;
u64 tlb_gen;
@@ -134,6 +192,24 @@ struct tlb_state {
*/
bool is_lazy;
+ /*
+ * If set we changed the page tables in such a way that we
+ * needed an invalidation of all contexts (aka. PCIDs / ASIDs).
+ * This tells us to go invalidate all the non-loaded ctxs[]
+ * on the next context switch.
+ *
+ * The current ctx was kept up-to-date as it ran and does not
+ * need to be invalidated.
+ */
+ bool invalidate_other;
+
+ /*
+ * Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate
+ * the corresponding user PCID needs a flush next time we
+ * switch to it; see SWITCH_TO_USER_CR3.
+ */
+ unsigned short user_pcid_flush_mask;
+
/*
* Access to this CR4 shadow and to H/W CR4 is protected by
* disabling interrupts when modifying either one.
@@ -211,6 +287,14 @@ static inline unsigned long cr4_read_shadow(void)
return this_cpu_read(cpu_tlbstate.cr4);
}
+/*
+ * Mark all other ASIDs as invalid, preserves the current.
+ */
+static inline void invalidate_other_asid(void)
+{
+ this_cpu_write(cpu_tlbstate.invalidate_other, true);
+}
+
/*
* Save some of cr4 feature set we're using (e.g. Pentium 4MB
* enable and PPro Global page enable), so that any CPU's that boot
@@ -230,19 +314,48 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
extern void initialize_tlbstate_and_flush(void);
+/*
+ * Given an ASID, flush the corresponding user ASID. We can delay this
+ * until the next time we switch to it.
+ *
+ * See SWITCH_TO_USER_CR3.
+ */
+static inline void invalidate_user_asid(u16 asid)
+{
+ /* There is no user ASID if address space separation is off */
+ if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ return;
+
+ /*
+ * We only have a single ASID if PCID is off and the CR3
+ * write will have flushed it.
+ */
+ if (!cpu_feature_enabled(X86_FEATURE_PCID))
+ return;
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ __set_bit(kern_pcid(asid),
+ (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask));
+}
+
/*
* flush the entire current user mapping
*/
static inline void __native_flush_tlb(void)
{
/*
- * If current->mm == NULL then we borrow a mm which may change during a
- * task switch and therefore we must not be preempted while we write CR3
- * back:
+ * Preemption or interrupts must be disabled to protect the access
+ * to the per CPU variable and to prevent being preempted between
+ * read_cr3() and write_cr3().
*/
- preempt_disable();
+ WARN_ON_ONCE(preemptible());
+
+ invalidate_user_asid(this_cpu_read(cpu_tlbstate.loaded_mm_asid));
+
+ /* If current->mm == NULL then the read_cr3() "borrows" an mm */
native_write_cr3(__native_read_cr3());
- preempt_enable();
}
/*
@@ -256,6 +369,8 @@ static inline void __native_flush_tlb_global(void)
/*
* Using INVPCID is considerably faster than a pair of writes
* to CR4 sandwiched inside an IRQ flag save/restore.
+ *
+ * Note, this works with CR4.PCIDE=0 or 1.
*/
invpcid_flush_all();
return;
@@ -282,7 +397,21 @@ static inline void __native_flush_tlb_global(void)
*/
static inline void __native_flush_tlb_single(unsigned long addr)
{
+ u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ /*
+ * Some platforms #GP if we call invpcid(type=1/2) before CR4.PCIDE=1.
+ * Just use invalidate_user_asid() in case we are called early.
+ */
+ if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE))
+ invalidate_user_asid(loaded_mm_asid);
+ else
+ invpcid_flush_one(user_pcid(loaded_mm_asid), addr);
}
/*
@@ -298,14 +427,6 @@ static inline void __flush_tlb_all(void)
*/
__flush_tlb();
}
-
- /*
- * Note: if we somehow had PCID but not PGE, then this wouldn't work --
- * we'd end up flushing kernel translations for the current ASID but
- * we might fail to flush kernel translations for other cached ASIDs.
- *
- * To avoid this issue, we force PCID off if PGE is off.
- */
}
/*
@@ -315,6 +436,16 @@ static inline void __flush_tlb_one(unsigned long addr)
{
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
__flush_tlb_single(addr);
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ /*
+ * __flush_tlb_single() will have cleared the TLB entry for this ASID,
+ * but since kernel space is replicated across all, we must also
+ * invalidate all others.
+ */
+ invalidate_other_asid();
}
#define TLB_FLUSH_ALL -1UL
@@ -375,6 +506,17 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
void native_flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info);
+static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
+{
+ /*
+ * Bump the generation count. This also serves as a full barrier
+ * that synchronizes with switch_mm(): callers are required to order
+ * their read of mm_cpumask after their writes to the paging
+ * structures.
+ */
+ return atomic64_inc_return(&mm->context.tlb_gen);
+}
+
static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
struct mm_struct *mm)
{
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index d9a7c659009c..b986b2ca688a 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -7,6 +7,7 @@
#ifdef CONFIG_X86_VSYSCALL_EMULATION
extern void map_vsyscall(void);
+extern void set_vsyscall_pgtable_user_bits(pgd_t *root);
/*
* Called on instruction fetch fault in vsyscall page.
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index 53b4ca55ebb6..97abdaab9535 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -78,7 +78,12 @@
#define X86_CR3_PWT _BITUL(X86_CR3_PWT_BIT)
#define X86_CR3_PCD_BIT 4 /* Page Cache Disable */
#define X86_CR3_PCD _BITUL(X86_CR3_PCD_BIT)
-#define X86_CR3_PCID_MASK _AC(0x00000fff,UL) /* PCID Mask */
+
+#define X86_CR3_PCID_BITS 12
+#define X86_CR3_PCID_MASK (_AC((1UL << X86_CR3_PCID_BITS) - 1, UL))
+
+#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */
+#define X86_CR3_PCID_NOFLUSH _BITULL(X86_CR3_PCID_NOFLUSH_BIT)
/*
* Intel CPU features in CR4
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 676b7cf4b62b..76417a9aab73 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -17,6 +17,7 @@
#include <asm/sigframe.h>
#include <asm/bootparam.h>
#include <asm/suspend.h>
+#include <asm/tlbflush.h>
#ifdef CONFIG_XEN
#include <xen/interface/xen.h>
@@ -94,6 +95,9 @@ void common(void) {
BLANK();
DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
+ /* TLB state for the entry code */
+ OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask);
+
/* Layout info for cpu_entry_area */
OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss);
OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8ddcfa4d4165..f2a94dfb434e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -898,6 +898,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
}
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
+
+ /* Assume for now that ALL x86 CPUs are insecure */
+ setup_force_cpu_bug(X86_BUG_CPU_INSECURE);
+
fpu__init_system(c);
#ifdef CONFIG_X86_32
@@ -1335,7 +1339,10 @@ void syscall_init(void)
(entry_SYSCALL_64_trampoline - _entry_trampoline);
wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
- wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline);
+ if (static_cpu_has(X86_FEATURE_PTI))
+ wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline);
+ else
+ wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
#ifdef CONFIG_IA32_EMULATION
wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat);
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 36b17e0febe8..5fa110699ed2 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -297,11 +297,13 @@ int __die(const char *str, struct pt_regs *regs, long err)
unsigned long sp;
#endif
printk(KERN_DEFAULT
- "%s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff, ++die_counter,
+ "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter,
IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
- IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "");
+ IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "",
+ IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ?
+ (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : "");
if (notify_die(DIE_OOPS, str, regs, err,
current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7dca675fe78d..04a625f0fcda 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -341,6 +341,27 @@ GLOBAL(early_recursion_flag)
.balign PAGE_SIZE; \
GLOBAL(name)
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Each PGD needs to be 8k long and 8k aligned. We do not
+ * ever go out to userspace with these, so we do not
+ * strictly *need* the second page, but this allows us to
+ * have a single set_pgd() implementation that does not
+ * need to worry about whether it has 4k or 8k to work
+ * with.
+ *
+ * This ensures PGDs are 8k long:
+ */
+#define PTI_USER_PGD_FILL 512
+/* This ensures they are 8k-aligned: */
+#define NEXT_PGD_PAGE(name) \
+ .balign 2 * PAGE_SIZE; \
+GLOBAL(name)
+#else
+#define NEXT_PGD_PAGE(name) NEXT_PAGE(name)
+#define PTI_USER_PGD_FILL 0
+#endif
+
/* Automate the creation of 1 to 1 mapping pmd entries */
#define PMDS(START, PERM, COUNT) \
i = 0 ; \
@@ -350,13 +371,14 @@ GLOBAL(name)
.endr
__INITDATA
-NEXT_PAGE(early_top_pgt)
+NEXT_PGD_PAGE(early_top_pgt)
.fill 511,8,0
#ifdef CONFIG_X86_5LEVEL
.quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
#else
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
#endif
+ .fill PTI_USER_PGD_FILL,8,0
NEXT_PAGE(early_dynamic_pgts)
.fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0
@@ -364,13 +386,14 @@ NEXT_PAGE(early_dynamic_pgts)
.data
#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH)
-NEXT_PAGE(init_top_pgt)
+NEXT_PGD_PAGE(init_top_pgt)
.quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
.org init_top_pgt + PGD_PAGE_OFFSET*8, 0
.quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
.org init_top_pgt + PGD_START_KERNEL*8, 0
/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
+ .fill PTI_USER_PGD_FILL,8,0
NEXT_PAGE(level3_ident_pgt)
.quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
@@ -381,8 +404,9 @@ NEXT_PAGE(level2_ident_pgt)
*/
PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
#else
-NEXT_PAGE(init_top_pgt)
+NEXT_PGD_PAGE(init_top_pgt)
.fill 512,8,0
+ .fill PTI_USER_PGD_FILL,8,0
#endif
#ifdef CONFIG_X86_5LEVEL
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index a6b5d62f45a7..26d713ecad34 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -24,6 +24,7 @@
#include <linux/uaccess.h>
#include <asm/ldt.h>
+#include <asm/tlb.h>
#include <asm/desc.h>
#include <asm/mmu_context.h>
#include <asm/syscalls.h>
@@ -51,13 +52,11 @@ static void refresh_ldt_segments(void)
static void flush_ldt(void *__mm)
{
struct mm_struct *mm = __mm;
- mm_context_t *pc;
if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm)
return;
- pc = &mm->context;
- set_ldt(pc->ldt->entries, pc->ldt->nr_entries);
+ load_mm_ldt(mm);
refresh_ldt_segments();
}
@@ -94,10 +93,126 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
return NULL;
}
+ /* The new LDT isn't aliased for PTI yet. */
+ new_ldt->slot = -1;
+
new_ldt->nr_entries = num_entries;
return new_ldt;
}
+/*
+ * If PTI is enabled, this maps the LDT into the kernelmode and
+ * usermode tables for the given mm.
+ *
+ * There is no corresponding unmap function. Even if the LDT is freed, we
+ * leave the PTEs around until the slot is reused or the mm is destroyed.
+ * This is harmless: the LDT is always in ordinary memory, and no one will
+ * access the freed slot.
+ *
+ * If we wanted to unmap freed LDTs, we'd also need to do a flush to make
+ * it useful, and the flush would slow down modify_ldt().
+ */
+static int
+map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ bool is_vmalloc, had_top_level_entry;
+ unsigned long va;
+ spinlock_t *ptl;
+ pgd_t *pgd;
+ int i;
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return 0;
+
+ /*
+ * Any given ldt_struct should have map_ldt_struct() called at most
+ * once.
+ */
+ WARN_ON(ldt->slot != -1);
+
+ /*
+ * Did we already have the top level entry allocated? We can't
+ * use pgd_none() for this because it doens't do anything on
+ * 4-level page table kernels.
+ */
+ pgd = pgd_offset(mm, LDT_BASE_ADDR);
+ had_top_level_entry = (pgd->pgd != 0);
+
+ is_vmalloc = is_vmalloc_addr(ldt->entries);
+
+ for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) {
+ unsigned long offset = i << PAGE_SHIFT;
+ const void *src = (char *)ldt->entries + offset;
+ unsigned long pfn;
+ pte_t pte, *ptep;
+
+ va = (unsigned long)ldt_slot_va(slot) + offset;
+ pfn = is_vmalloc ? vmalloc_to_pfn(src) :
+ page_to_pfn(virt_to_page(src));
+ /*
+ * Treat the PTI LDT range as a *userspace* range.
+ * get_locked_pte() will allocate all needed pagetables
+ * and account for them in this mm.
+ */
+ ptep = get_locked_pte(mm, va, &ptl);
+ if (!ptep)
+ return -ENOMEM;
+ /*
+ * Map it RO so the easy to find address is not a primary
+ * target via some kernel interface which misses a
+ * permission check.
+ */
+ pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL));
+ set_pte_at(mm, va, ptep, pte);
+ pte_unmap_unlock(ptep, ptl);
+ }
+
+ if (mm->context.ldt) {
+ /*
+ * We already had an LDT. The top-level entry should already
+ * have been allocated and synchronized with the usermode
+ * tables.
+ */
+ WARN_ON(!had_top_level_entry);
+ if (static_cpu_has(X86_FEATURE_PTI))
+ WARN_ON(!kernel_to_user_pgdp(pgd)->pgd);
+ } else {
+ /*
+ * This is the first time we're mapping an LDT for this process.
+ * Sync the pgd to the usermode tables.
+ */
+ WARN_ON(had_top_level_entry);
+ if (static_cpu_has(X86_FEATURE_PTI)) {
+ WARN_ON(kernel_to_user_pgdp(pgd)->pgd);
+ set_pgd(kernel_to_user_pgdp(pgd), *pgd);
+ }
+ }
+
+ va = (unsigned long)ldt_slot_va(slot);
+ flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0);
+
+ ldt->slot = slot;
+#endif
+ return 0;
+}
+
+static void free_ldt_pgtables(struct mm_struct *mm)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ struct mmu_gather tlb;
+ unsigned long start = LDT_BASE_ADDR;
+ unsigned long end = start + (1UL << PGDIR_SHIFT);
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ tlb_gather_mmu(&tlb, mm, start, end);
+ free_pgd_range(&tlb, start, end, start, end);
+ tlb_finish_mmu(&tlb, start, end);
+#endif
+}
+
/* After calling this, the LDT is immutable. */
static void finalize_ldt_struct(struct ldt_struct *ldt)
{
@@ -156,6 +271,12 @@ int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm)
new_ldt->nr_entries * LDT_ENTRY_SIZE);
finalize_ldt_struct(new_ldt);
+ retval = map_ldt_struct(mm, new_ldt, 0);
+ if (retval) {
+ free_ldt_pgtables(mm);
+ free_ldt_struct(new_ldt);
+ goto out_unlock;
+ }
mm->context.ldt = new_ldt;
out_unlock:
@@ -174,6 +295,11 @@ void destroy_context_ldt(struct mm_struct *mm)
mm->context.ldt = NULL;
}
+void ldt_arch_exit_mmap(struct mm_struct *mm)
+{
+ free_ldt_pgtables(mm);
+}
+
static int read_ldt(void __user *ptr, unsigned long bytecount)
{
struct mm_struct *mm = current->mm;
@@ -287,6 +413,25 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
new_ldt->entries[ldt_info.entry_number] = ldt;
finalize_ldt_struct(new_ldt);
+ /*
+ * If we are using PTI, map the new LDT into the userspace pagetables.
+ * If there is already an LDT, use the other slot so that other CPUs
+ * will continue to use the old LDT until install_ldt() switches
+ * them over to the new LDT.
+ */
+ error = map_ldt_struct(mm, new_ldt, old_ldt ? !old_ldt->slot : 0);
+ if (error) {
+ /*
+ * This only can fail for the first LDT setup. If an LDT is
+ * already installed then the PTE page is already
+ * populated. Mop up a half populated page table.
+ */
+ if (!WARN_ON_ONCE(old_ldt))
+ free_ldt_pgtables(mm);
+ free_ldt_struct(new_ldt);
+ goto out_unlock;
+ }
+
install_ldt(mm, new_ldt);
free_ldt_struct(old_ldt);
error = 0;
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 00bc751c861c..edfede768688 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -48,8 +48,6 @@ static void load_segments(void)
"\tmovl $"STR(__KERNEL_DS)",%%eax\n"
"\tmovl %%eax,%%ds\n"
"\tmovl %%eax,%%es\n"
- "\tmovl %%eax,%%fs\n"
- "\tmovl %%eax,%%gs\n"
"\tmovl %%eax,%%ss\n"
: : : "eax", "memory");
#undef STR
@@ -232,8 +230,8 @@ void machine_kexec(struct kimage *image)
* The gdt & idt are now invalid.
* If you want to load them you must set up your own idt & gdt.
*/
- set_gdt(phys_to_virt(0), 0);
idt_invalidate(phys_to_virt(0));
+ set_gdt(phys_to_virt(0), 0);
/* now call it */
image->start = relocate_kernel_ptr((unsigned long)image->head,
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 12bf07d44dfe..2651ca2112c4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -128,25 +128,16 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
spin_lock_irqsave(&rtc_lock, flags);
CMOS_WRITE(0xa, 0xf);
spin_unlock_irqrestore(&rtc_lock, flags);
- local_flush_tlb();
- pr_debug("1.\n");
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
start_eip >> 4;
- pr_debug("2.\n");
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
start_eip & 0xf;
- pr_debug("3.\n");
}
static inline void smpboot_restore_warm_reset_vector(void)
{
unsigned long flags;
- /*
- * Install writable page 0 entry to set BIOS data area.
- */
- local_flush_tlb();
-
/*
* Paranoid: Set warm reset code and vector here back
* to default values.
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 9a9c9b076955..a5b802a12212 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -93,17 +93,10 @@ static void set_tls_desc(struct task_struct *p, int idx,
cpu = get_cpu();
while (n-- > 0) {
- if (LDT_empty(info) || LDT_zero(info)) {
+ if (LDT_empty(info) || LDT_zero(info))
memset(desc, 0, sizeof(*desc));
- } else {
+ else
fill_ldt(desc, info);
-
- /*
- * Always set the accessed bit so that the CPU
- * doesn't try to write to the (read-only) GDT.
- */
- desc->type |= 1;
- }
++info;
++desc;
}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 7c16fe0b60c2..b33e860d32fe 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -361,7 +361,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
*
* No need for ist_enter here because we don't use RCU.
*/
- if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
+ if (((long)regs->sp >> P4D_SHIFT) == ESPFIX_PGD_ENTRY &&
regs->cs == __KERNEL_CS &&
regs->ip == (unsigned long)native_irq_return_iret)
{
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index d2a8b5a24a44..1e413a9326aa 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -61,11 +61,17 @@ jiffies_64 = jiffies;
. = ALIGN(HPAGE_SIZE); \
__end_rodata_hpage_align = .;
+#define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE);
+#define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE);
+
#else
#define X64_ALIGN_RODATA_BEGIN
#define X64_ALIGN_RODATA_END
+#define ALIGN_ENTRY_TEXT_BEGIN
+#define ALIGN_ENTRY_TEXT_END
+
#endif
PHDRS {
@@ -102,8 +108,10 @@ SECTIONS
CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
+ ALIGN_ENTRY_TEXT_BEGIN
ENTRY_TEXT
IRQENTRY_TEXT
+ ALIGN_ENTRY_TEXT_END
SOFTIRQENTRY_TEXT
*(.fixup)
*(.gnu.warning)
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 2e0017af8f9b..52906808e277 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -43,9 +43,10 @@ obj-$(CONFIG_AMD_NUMA) += amdtopology.o
obj-$(CONFIG_ACPI_NUMA) += srat.o
obj-$(CONFIG_NUMA_EMU) += numa_emulation.o
-obj-$(CONFIG_X86_INTEL_MPX) += mpx.o
-obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o
-obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o
+obj-$(CONFIG_X86_INTEL_MPX) += mpx.o
+obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o
+obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o
+obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_boot.o
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index fe814fd5e014..b9283cc27622 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -38,6 +38,32 @@ cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot)
cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot);
}
+static void percpu_setup_debug_store(int cpu)
+{
+#ifdef CONFIG_CPU_SUP_INTEL
+ int npages;
+ void *cea;
+
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return;
+
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_store;
+ npages = sizeof(struct debug_store) / PAGE_SIZE;
+ BUILD_BUG_ON(sizeof(struct debug_store) % PAGE_SIZE != 0);
+ cea_map_percpu_pages(cea, &per_cpu(cpu_debug_store, cpu), npages,
+ PAGE_KERNEL);
+
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers;
+ /*
+ * Force the population of PMDs for not yet allocated per cpu
+ * memory like debug store buffers.
+ */
+ npages = sizeof(struct debug_store_buffers) / PAGE_SIZE;
+ for (; npages; npages--, cea += PAGE_SIZE)
+ cea_set_pte(cea, 0, PAGE_NONE);
+#endif
+}
+
/* Setup the fixmap mappings only once per-processor */
static void __init setup_cpu_entry_area(int cpu)
{
@@ -109,6 +135,7 @@ static void __init setup_cpu_entry_area(int cpu)
cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline,
__pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
#endif
+ percpu_setup_debug_store(cpu);
}
static __init void setup_cpu_entry_area_ptes(void)
diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c
index bfcffdf6c577..421f2664ffa0 100644
--- a/arch/x86/mm/debug_pagetables.c
+++ b/arch/x86/mm/debug_pagetables.c
@@ -5,7 +5,7 @@
static int ptdump_show(struct seq_file *m, void *v)
{
- ptdump_walk_pgd_level(m, NULL);
+ ptdump_walk_pgd_level_debugfs(m, NULL, false);
return 0;
}
@@ -22,21 +22,89 @@ static const struct file_operations ptdump_fops = {
.release = single_release,
};
-static struct dentry *pe;
+static int ptdump_show_curknl(struct seq_file *m, void *v)
+{
+ if (current->mm->pgd) {
+ down_read(¤t->mm->mmap_sem);
+ ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, false);
+ up_read(¤t->mm->mmap_sem);
+ }
+ return 0;
+}
+
+static int ptdump_open_curknl(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, ptdump_show_curknl, NULL);
+}
+
+static const struct file_operations ptdump_curknl_fops = {
+ .owner = THIS_MODULE,
+ .open = ptdump_open_curknl,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+static struct dentry *pe_curusr;
+
+static int ptdump_show_curusr(struct seq_file *m, void *v)
+{
+ if (current->mm->pgd) {
+ down_read(¤t->mm->mmap_sem);
+ ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, true);
+ up_read(¤t->mm->mmap_sem);
+ }
+ return 0;
+}
+
+static int ptdump_open_curusr(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, ptdump_show_curusr, NULL);
+}
+
+static const struct file_operations ptdump_curusr_fops = {
+ .owner = THIS_MODULE,
+ .open = ptdump_open_curusr,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+#endif
+
+static struct dentry *dir, *pe_knl, *pe_curknl;
static int __init pt_dump_debug_init(void)
{
- pe = debugfs_create_file("kernel_page_tables", S_IRUSR, NULL, NULL,
- &ptdump_fops);
- if (!pe)
+ dir = debugfs_create_dir("page_tables", NULL);
+ if (!dir)
return -ENOMEM;
+ pe_knl = debugfs_create_file("kernel", 0400, dir, NULL,
+ &ptdump_fops);
+ if (!pe_knl)
+ goto err;
+
+ pe_curknl = debugfs_create_file("current_kernel", 0400,
+ dir, NULL, &ptdump_curknl_fops);
+ if (!pe_curknl)
+ goto err;
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ pe_curusr = debugfs_create_file("current_user", 0400,
+ dir, NULL, &ptdump_curusr_fops);
+ if (!pe_curusr)
+ goto err;
+#endif
return 0;
+err:
+ debugfs_remove_recursive(dir);
+ return -ENOMEM;
}
static void __exit pt_dump_debug_exit(void)
{
- debugfs_remove_recursive(pe);
+ debugfs_remove_recursive(dir);
}
module_init(pt_dump_debug_init);
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 43dedbfb7257..f56902c1f04b 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -52,11 +52,17 @@ enum address_markers_idx {
USER_SPACE_NR = 0,
KERNEL_SPACE_NR,
LOW_KERNEL_NR,
+#if defined(CONFIG_MODIFY_LDT_SYSCALL) && defined(CONFIG_X86_5LEVEL)
+ LDT_NR,
+#endif
VMALLOC_START_NR,
VMEMMAP_START_NR,
#ifdef CONFIG_KASAN
KASAN_SHADOW_START_NR,
KASAN_SHADOW_END_NR,
+#endif
+#if defined(CONFIG_MODIFY_LDT_SYSCALL) && !defined(CONFIG_X86_5LEVEL)
+ LDT_NR,
#endif
CPU_ENTRY_AREA_NR,
#ifdef CONFIG_X86_ESPFIX64
@@ -81,6 +87,9 @@ static struct addr_marker address_markers[] = {
#ifdef CONFIG_KASAN
[KASAN_SHADOW_START_NR] = { KASAN_SHADOW_START, "KASAN shadow" },
[KASAN_SHADOW_END_NR] = { KASAN_SHADOW_END, "KASAN shadow end" },
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ [LDT_NR] = { LDT_BASE_ADDR, "LDT remap" },
#endif
[CPU_ENTRY_AREA_NR] = { CPU_ENTRY_AREA_BASE,"CPU entry Area" },
#ifdef CONFIG_X86_ESPFIX64
@@ -467,7 +476,7 @@ static inline bool is_hypervisor_range(int idx)
}
static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
- bool checkwx)
+ bool checkwx, bool dmesg)
{
#ifdef CONFIG_X86_64
pgd_t *start = (pgd_t *) &init_top_pgt;
@@ -480,7 +489,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
if (pgd) {
start = pgd;
- st.to_dmesg = true;
+ st.to_dmesg = dmesg;
}
st.check_wx = checkwx;
@@ -518,13 +527,37 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
{
- ptdump_walk_pgd_level_core(m, pgd, false);
+ ptdump_walk_pgd_level_core(m, pgd, false, true);
+}
+
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ if (user && static_cpu_has(X86_FEATURE_PTI))
+ pgd = kernel_to_user_pgdp(pgd);
+#endif
+ ptdump_walk_pgd_level_core(m, pgd, false, false);
+}
+EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
+
+static void ptdump_walk_user_pgd_level_checkwx(void)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ pgd_t *pgd = (pgd_t *) &init_top_pgt;
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ pr_info("x86/mm: Checking user space page tables\n");
+ pgd = kernel_to_user_pgdp(pgd);
+ ptdump_walk_pgd_level_core(NULL, pgd, true, false);
+#endif
}
-EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level);
void ptdump_walk_pgd_level_checkwx(void)
{
- ptdump_walk_pgd_level_core(NULL, NULL, true);
+ ptdump_walk_pgd_level_core(NULL, NULL, true, false);
+ ptdump_walk_user_pgd_level_checkwx();
}
static int __init pt_dump_init(void)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index a22c2b95e513..80259ad8c386 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -20,6 +20,7 @@
#include <asm/kaslr.h>
#include <asm/hypervisor.h>
#include <asm/cpufeature.h>
+#include <asm/pti.h>
/*
* We need to define the tracepoints somewhere, and tlb.c
@@ -161,6 +162,12 @@ struct map_range {
static int page_size_mask;
+static void enable_global_pages(void)
+{
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ __supported_pte_mask |= _PAGE_GLOBAL;
+}
+
static void __init probe_page_size_mask(void)
{
/*
@@ -179,11 +186,11 @@ static void __init probe_page_size_mask(void)
cr4_set_bits_and_update_boot(X86_CR4_PSE);
/* Enable PGE if available */
+ __supported_pte_mask &= ~_PAGE_GLOBAL;
if (boot_cpu_has(X86_FEATURE_PGE)) {
cr4_set_bits_and_update_boot(X86_CR4_PGE);
- __supported_pte_mask |= _PAGE_GLOBAL;
- } else
- __supported_pte_mask &= ~_PAGE_GLOBAL;
+ enable_global_pages();
+ }
/* Enable 1 GB linear kernel mappings if available: */
if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) {
@@ -196,34 +203,44 @@ static void __init probe_page_size_mask(void)
static void setup_pcid(void)
{
-#ifdef CONFIG_X86_64
- if (boot_cpu_has(X86_FEATURE_PCID)) {
- if (boot_cpu_has(X86_FEATURE_PGE)) {
- /*
- * This can't be cr4_set_bits_and_update_boot() --
- * the trampoline code can't handle CR4.PCIDE and
- * it wouldn't do any good anyway. Despite the name,
- * cr4_set_bits_and_update_boot() doesn't actually
- * cause the bits in question to remain set all the
- * way through the secondary boot asm.
- *
- * Instead, we brute-force it and set CR4.PCIDE
- * manually in start_secondary().
- */
- cr4_set_bits(X86_CR4_PCIDE);
- } else {
- /*
- * flush_tlb_all(), as currently implemented, won't
- * work if PCID is on but PGE is not. Since that
- * combination doesn't exist on real hardware, there's
- * no reason to try to fully support it, but it's
- * polite to avoid corrupting data if we're on
- * an improperly configured VM.
- */
- setup_clear_cpu_cap(X86_FEATURE_PCID);
- }
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return;
+
+ if (!boot_cpu_has(X86_FEATURE_PCID))
+ return;
+
+ if (boot_cpu_has(X86_FEATURE_PGE)) {
+ /*
+ * This can't be cr4_set_bits_and_update_boot() -- the
+ * trampoline code can't handle CR4.PCIDE and it wouldn't
+ * do any good anyway. Despite the name,
+ * cr4_set_bits_and_update_boot() doesn't actually cause
+ * the bits in question to remain set all the way through
+ * the secondary boot asm.
+ *
+ * Instead, we brute-force it and set CR4.PCIDE manually in
+ * start_secondary().
+ */
+ cr4_set_bits(X86_CR4_PCIDE);
+
+ /*
+ * INVPCID's single-context modes (2/3) only work if we set
+ * X86_CR4_PCIDE, *and* we INVPCID support. It's unusable
+ * on systems that have X86_CR4_PCIDE clear, or that have
+ * no INVPCID support at all.
+ */
+ if (boot_cpu_has(X86_FEATURE_INVPCID))
+ setup_force_cpu_cap(X86_FEATURE_INVPCID_SINGLE);
+ } else {
+ /*
+ * flush_tlb_all(), as currently implemented, won't work if
+ * PCID is on but PGE is not. Since that combination
+ * doesn't exist on real hardware, there's no reason to try
+ * to fully support it, but it's polite to avoid corrupting
+ * data if we're on an improperly configured VM.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_PCID);
}
-#endif
}
#ifdef CONFIG_X86_32
@@ -624,6 +641,7 @@ void __init init_mem_mapping(void)
{
unsigned long end;
+ pti_check_boottime_disable();
probe_page_size_mask();
setup_pcid();
@@ -847,7 +865,7 @@ void __init zone_sizes_init(void)
free_area_init_nodes(max_zone_pfns);
}
-DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
+__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
.loaded_mm = &init_mm,
.next_asid = 1,
.cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 17ebc5a978cc..9b7bcbd33cc2 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -355,14 +355,15 @@ static inline void _pgd_free(pgd_t *pgd)
kmem_cache_free(pgd_cache, pgd);
}
#else
+
static inline pgd_t *_pgd_alloc(void)
{
- return (pgd_t *)__get_free_page(PGALLOC_GFP);
+ return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER);
}
static inline void _pgd_free(pgd_t *pgd)
{
- free_page((unsigned long)pgd);
+ free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
}
#endif /* CONFIG_X86_PAE */
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
new file mode 100644
index 000000000000..bce8aea65606
--- /dev/null
+++ b/arch/x86/mm/pti.c
@@ -0,0 +1,387 @@
+/*
+ * Copyright(c) 2017 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * This code is based in part on work published here:
+ *
+ * https://github.com/IAIK/KAISER
+ *
+ * The original work was written by and and signed off by for the Linux
+ * kernel by:
+ *
+ * Signed-off-by: Richard Fellner <richard.fellner(a)student.tugraz.at>
+ * Signed-off-by: Moritz Lipp <moritz.lipp(a)iaik.tugraz.at>
+ * Signed-off-by: Daniel Gruss <daniel.gruss(a)iaik.tugraz.at>
+ * Signed-off-by: Michael Schwarz <michael.schwarz(a)iaik.tugraz.at>
+ *
+ * Major changes to the original code by: Dave Hansen <dave.hansen(a)intel.com>
+ * Mostly rewritten by Thomas Gleixner <tglx(a)linutronix.de> and
+ * Andy Lutomirsky <luto(a)amacapital.net>
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/bug.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+
+#include <asm/cpufeature.h>
+#include <asm/hypervisor.h>
+#include <asm/vsyscall.h>
+#include <asm/cmdline.h>
+#include <asm/pti.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/desc.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt
+
+/* Backporting helper */
+#ifndef __GFP_NOTRACK
+#define __GFP_NOTRACK 0
+#endif
+
+static void __init pti_print_if_insecure(const char *reason)
+{
+ if (boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
+ pr_info("%s\n", reason);
+}
+
+static void __init pti_print_if_secure(const char *reason)
+{
+ if (!boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
+ pr_info("%s\n", reason);
+}
+
+void __init pti_check_boottime_disable(void)
+{
+ char arg[5];
+ int ret;
+
+ if (hypervisor_is_type(X86_HYPER_XEN_PV)) {
+ pti_print_if_insecure("disabled on XEN PV.");
+ return;
+ }
+
+ ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
+ if (ret > 0) {
+ if (ret == 3 && !strncmp(arg, "off", 3)) {
+ pti_print_if_insecure("disabled on command line.");
+ return;
+ }
+ if (ret == 2 && !strncmp(arg, "on", 2)) {
+ pti_print_if_secure("force enabled on command line.");
+ goto enable;
+ }
+ if (ret == 4 && !strncmp(arg, "auto", 4))
+ goto autosel;
+ }
+
+ if (cmdline_find_option_bool(boot_command_line, "nopti")) {
+ pti_print_if_insecure("disabled on command line.");
+ return;
+ }
+
+autosel:
+ if (!boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
+ return;
+enable:
+ setup_force_cpu_cap(X86_FEATURE_PTI);
+}
+
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ /*
+ * Changes to the high (kernel) portion of the kernelmode page
+ * tables are not automatically propagated to the usermode tables.
+ *
+ * Users should keep in mind that, unlike the kernelmode tables,
+ * there is no vmalloc_fault equivalent for the usermode tables.
+ * Top-level entries added to init_mm's usermode pgd after boot
+ * will not be automatically propagated to other mms.
+ */
+ if (!pgdp_maps_userspace(pgdp))
+ return pgd;
+
+ /*
+ * The user page tables get the full PGD, accessible from
+ * userspace:
+ */
+ kernel_to_user_pgdp(pgdp)->pgd = pgd.pgd;
+
+ /*
+ * If this is normal user memory, make it NX in the kernel
+ * pagetables so that, if we somehow screw up and return to
+ * usermode with the kernel CR3 loaded, we'll get a page fault
+ * instead of allowing user code to execute with the wrong CR3.
+ *
+ * As exceptions, we don't set NX if:
+ * - _PAGE_USER is not set. This could be an executable
+ * EFI runtime mapping or something similar, and the kernel
+ * may execute from it
+ * - we don't have NX support
+ * - we're clearing the PGD (i.e. the new pgd is not present).
+ */
+ if ((pgd.pgd & (_PAGE_USER|_PAGE_PRESENT)) == (_PAGE_USER|_PAGE_PRESENT) &&
+ (__supported_pte_mask & _PAGE_NX))
+ pgd.pgd |= _PAGE_NX;
+
+ /* return the copy of the PGD we want the kernel to use: */
+ return pgd;
+}
+
+/*
+ * Walk the user copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.
+ *
+ * Returns a pointer to a P4D on success, or NULL on failure.
+ */
+static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
+{
+ pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address));
+ gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+
+ if (address < PAGE_OFFSET) {
+ WARN_ONCE(1, "attempt to walk user address\n");
+ return NULL;
+ }
+
+ if (pgd_none(*pgd)) {
+ unsigned long new_p4d_page = __get_free_page(gfp);
+ if (!new_p4d_page)
+ return NULL;
+
+ if (pgd_none(*pgd)) {
+ set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
+ new_p4d_page = 0;
+ }
+ if (new_p4d_page)
+ free_page(new_p4d_page);
+ }
+ BUILD_BUG_ON(pgd_large(*pgd) != 0);
+
+ return p4d_offset(pgd, address);
+}
+
+/*
+ * Walk the user copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.
+ *
+ * Returns a pointer to a PMD on success, or NULL on failure.
+ */
+static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
+{
+ gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+ p4d_t *p4d = pti_user_pagetable_walk_p4d(address);
+ pud_t *pud;
+
+ BUILD_BUG_ON(p4d_large(*p4d) != 0);
+ if (p4d_none(*p4d)) {
+ unsigned long new_pud_page = __get_free_page(gfp);
+ if (!new_pud_page)
+ return NULL;
+
+ if (p4d_none(*p4d)) {
+ set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page)));
+ new_pud_page = 0;
+ }
+ if (new_pud_page)
+ free_page(new_pud_page);
+ }
+
+ pud = pud_offset(p4d, address);
+ /* The user page tables do not use large mappings: */
+ if (pud_large(*pud)) {
+ WARN_ON(1);
+ return NULL;
+ }
+ if (pud_none(*pud)) {
+ unsigned long new_pmd_page = __get_free_page(gfp);
+ if (!new_pmd_page)
+ return NULL;
+
+ if (pud_none(*pud)) {
+ set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
+ new_pmd_page = 0;
+ }
+ if (new_pmd_page)
+ free_page(new_pmd_page);
+ }
+
+ return pmd_offset(pud, address);
+}
+
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
+/*
+ * Walk the shadow copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down. Does not support large pages.
+ *
+ * Note: this is only used when mapping *new* kernel data into the
+ * user/shadow page tables. It is never used for userspace data.
+ *
+ * Returns a pointer to a PTE on success, or NULL on failure.
+ */
+static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
+{
+ gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+ pmd_t *pmd = pti_user_pagetable_walk_pmd(address);
+ pte_t *pte;
+
+ /* We can't do anything sensible if we hit a large mapping. */
+ if (pmd_large(*pmd)) {
+ WARN_ON(1);
+ return NULL;
+ }
+
+ if (pmd_none(*pmd)) {
+ unsigned long new_pte_page = __get_free_page(gfp);
+ if (!new_pte_page)
+ return NULL;
+
+ if (pmd_none(*pmd)) {
+ set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page)));
+ new_pte_page = 0;
+ }
+ if (new_pte_page)
+ free_page(new_pte_page);
+ }
+
+ pte = pte_offset_kernel(pmd, address);
+ if (pte_flags(*pte) & _PAGE_USER) {
+ WARN_ONCE(1, "attempt to walk to user pte\n");
+ return NULL;
+ }
+ return pte;
+}
+
+static void __init pti_setup_vsyscall(void)
+{
+ pte_t *pte, *target_pte;
+ unsigned int level;
+
+ pte = lookup_address(VSYSCALL_ADDR, &level);
+ if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte))
+ return;
+
+ target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR);
+ if (WARN_ON(!target_pte))
+ return;
+
+ *target_pte = *pte;
+ set_vsyscall_pgtable_user_bits(kernel_to_user_pgdp(swapper_pg_dir));
+}
+#else
+static void __init pti_setup_vsyscall(void) { }
+#endif
+
+static void __init
+pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
+{
+ unsigned long addr;
+
+ /*
+ * Clone the populated PMDs which cover start to end. These PMD areas
+ * can have holes.
+ */
+ for (addr = start; addr < end; addr += PMD_SIZE) {
+ pmd_t *pmd, *target_pmd;
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+
+ pgd = pgd_offset_k(addr);
+ if (WARN_ON(pgd_none(*pgd)))
+ return;
+ p4d = p4d_offset(pgd, addr);
+ if (WARN_ON(p4d_none(*p4d)))
+ return;
+ pud = pud_offset(p4d, addr);
+ if (pud_none(*pud))
+ continue;
+ pmd = pmd_offset(pud, addr);
+ if (pmd_none(*pmd))
+ continue;
+
+ target_pmd = pti_user_pagetable_walk_pmd(addr);
+ if (WARN_ON(!target_pmd))
+ return;
+
+ /*
+ * Copy the PMD. That is, the kernelmode and usermode
+ * tables will share the last-level page tables of this
+ * address range
+ */
+ *target_pmd = pmd_clear_flags(*pmd, clear);
+ }
+}
+
+/*
+ * Clone a single p4d (i.e. a top-level entry on 4-level systems and a
+ * next-level entry on 5-level systems.
+ */
+static void __init pti_clone_p4d(unsigned long addr)
+{
+ p4d_t *kernel_p4d, *user_p4d;
+ pgd_t *kernel_pgd;
+
+ user_p4d = pti_user_pagetable_walk_p4d(addr);
+ kernel_pgd = pgd_offset_k(addr);
+ kernel_p4d = p4d_offset(kernel_pgd, addr);
+ *user_p4d = *kernel_p4d;
+}
+
+/*
+ * Clone the CPU_ENTRY_AREA into the user space visible page table.
+ */
+static void __init pti_clone_user_shared(void)
+{
+ pti_clone_p4d(CPU_ENTRY_AREA_BASE);
+}
+
+/*
+ * Clone the ESPFIX P4D into the user space visinble page table
+ */
+static void __init pti_setup_espfix64(void)
+{
+#ifdef CONFIG_X86_ESPFIX64
+ pti_clone_p4d(ESPFIX_BASE_ADDR);
+#endif
+}
+
+/*
+ * Clone the populated PMDs of the entry and irqentry text and force it RO.
+ */
+static void __init pti_clone_entry_text(void)
+{
+ pti_clone_pmds((unsigned long) __entry_text_start,
+ (unsigned long) __irqentry_text_end, _PAGE_RW);
+}
+
+/*
+ * Initialize kernel page table isolation
+ */
+void __init pti_init(void)
+{
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ pr_info("enabled\n");
+
+ pti_clone_user_shared();
+ pti_clone_entry_text();
+ pti_setup_espfix64();
+ pti_setup_vsyscall();
+}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 0a1be3adc97e..a1561957dccb 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -28,6 +28,38 @@
* Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
*/
+/*
+ * We get here when we do something requiring a TLB invalidation
+ * but could not go invalidate all of the contexts. We do the
+ * necessary invalidation by clearing out the 'ctx_id' which
+ * forces a TLB flush when the context is loaded.
+ */
+void clear_asid_other(void)
+{
+ u16 asid;
+
+ /*
+ * This is only expected to be set if we have disabled
+ * kernel _PAGE_GLOBAL pages.
+ */
+ if (!static_cpu_has(X86_FEATURE_PTI)) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+
+ for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
+ /* Do not need to flush the current asid */
+ if (asid == this_cpu_read(cpu_tlbstate.loaded_mm_asid))
+ continue;
+ /*
+ * Make sure the next time we go to switch to
+ * this asid, we do a flush:
+ */
+ this_cpu_write(cpu_tlbstate.ctxs[asid].ctx_id, 0);
+ }
+ this_cpu_write(cpu_tlbstate.invalidate_other, false);
+}
+
atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
@@ -42,6 +74,9 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
return;
}
+ if (this_cpu_read(cpu_tlbstate.invalidate_other))
+ clear_asid_other();
+
for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
if (this_cpu_read(cpu_tlbstate.ctxs[asid].ctx_id) !=
next->context.ctx_id)
@@ -65,6 +100,25 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
*need_flush = true;
}
+static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, bool need_flush)
+{
+ unsigned long new_mm_cr3;
+
+ if (need_flush) {
+ invalidate_user_asid(new_asid);
+ new_mm_cr3 = build_cr3(pgdir, new_asid);
+ } else {
+ new_mm_cr3 = build_cr3_noflush(pgdir, new_asid);
+ }
+
+ /*
+ * Caution: many callers of this function expect
+ * that load_cr3() is serializing and orders TLB
+ * fills with respect to the mm_cpumask writes.
+ */
+ write_cr3(new_mm_cr3);
+}
+
void leave_mm(int cpu)
{
struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
@@ -195,7 +249,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
if (need_flush) {
this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
- write_cr3(build_cr3(next->pgd, new_asid));
+ load_new_mm_cr3(next->pgd, new_asid, true);
/*
* NB: This gets called via leave_mm() in the idle path
@@ -208,7 +262,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
} else {
/* The new ASID is already up to date. */
- write_cr3(build_cr3_noflush(next->pgd, new_asid));
+ load_new_mm_cr3(next->pgd, new_asid, false);
/* See above wrt _rcuidle. */
trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 20fb31579b69..39c4b35ac7a4 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -195,6 +195,9 @@ static pgd_t *efi_pgd;
* because we want to avoid inserting EFI region mappings (EFI_VA_END
* to EFI_VA_START) into the standard kernel page tables. Everything
* else can be shared, see efi_sync_low_kernel_mappings().
+ *
+ * We don't want the pgd on the pgd_list and cannot use pgd_alloc() for the
+ * allocation.
*/
int __init efi_alloc_page_tables(void)
{
@@ -207,7 +210,7 @@ int __init efi_alloc_page_tables(void)
return 0;
gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO;
- efi_pgd = (pgd_t *)__get_free_page(gfp_mask);
+ efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
if (!efi_pgd)
return -ENOMEM;
diff --git a/block/blk-map.c b/block/blk-map.c
index d5251edcc0dd..368daa02714e 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -12,22 +12,29 @@
#include "blk.h"
/*
- * Append a bio to a passthrough request. Only works can be merged into
- * the request based on the driver constraints.
+ * Append a bio to a passthrough request. Only works if the bio can be merged
+ * into the request based on the driver constraints.
*/
-int blk_rq_append_bio(struct request *rq, struct bio *bio)
+int blk_rq_append_bio(struct request *rq, struct bio **bio)
{
- blk_queue_bounce(rq->q, &bio);
+ struct bio *orig_bio = *bio;
+
+ blk_queue_bounce(rq->q, bio);
if (!rq->bio) {
- blk_rq_bio_prep(rq->q, rq, bio);
+ blk_rq_bio_prep(rq->q, rq, *bio);
} else {
- if (!ll_back_merge_fn(rq->q, rq, bio))
+ if (!ll_back_merge_fn(rq->q, rq, *bio)) {
+ if (orig_bio != *bio) {
+ bio_put(*bio);
+ *bio = orig_bio;
+ }
return -EINVAL;
+ }
- rq->biotail->bi_next = bio;
- rq->biotail = bio;
- rq->__data_len += bio->bi_iter.bi_size;
+ rq->biotail->bi_next = *bio;
+ rq->biotail = *bio;
+ rq->__data_len += (*bio)->bi_iter.bi_size;
}
return 0;
@@ -80,14 +87,12 @@ static int __blk_rq_map_user_iov(struct request *rq,
* We link the bounce buffer in and could have to traverse it
* later so we have to get a ref to prevent it from being freed
*/
- ret = blk_rq_append_bio(rq, bio);
- bio_get(bio);
+ ret = blk_rq_append_bio(rq, &bio);
if (ret) {
- bio_endio(bio);
__blk_rq_unmap_user(orig_bio);
- bio_put(bio);
return ret;
}
+ bio_get(bio);
return 0;
}
@@ -220,7 +225,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
int reading = rq_data_dir(rq) == READ;
unsigned long addr = (unsigned long) kbuf;
int do_copy = 0;
- struct bio *bio;
+ struct bio *bio, *orig_bio;
int ret;
if (len > (queue_max_hw_sectors(q) << 9))
@@ -243,10 +248,11 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
if (do_copy)
rq->rq_flags |= RQF_COPY_USER;
- ret = blk_rq_append_bio(rq, bio);
+ orig_bio = bio;
+ ret = blk_rq_append_bio(rq, &bio);
if (unlikely(ret)) {
/* request is too big */
- bio_put(bio);
+ bio_put(orig_bio);
return ret;
}
diff --git a/block/bounce.c b/block/bounce.c
index fceb1a96480b..1d05c422c932 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -200,6 +200,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
unsigned i = 0;
bool bounce = false;
int sectors = 0;
+ bool passthrough = bio_is_passthrough(*bio_orig);
bio_for_each_segment(from, *bio_orig, iter) {
if (i++ < BIO_MAX_PAGES)
@@ -210,13 +211,14 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
if (!bounce)
return;
- if (sectors < bio_sectors(*bio_orig)) {
+ if (!passthrough && sectors < bio_sectors(*bio_orig)) {
bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split);
bio_chain(bio, *bio_orig);
generic_make_request(*bio_orig);
*bio_orig = bio;
}
- bio = bio_clone_bioset(*bio_orig, GFP_NOIO, bounce_bio_set);
+ bio = bio_clone_bioset(*bio_orig, GFP_NOIO, passthrough ? NULL :
+ bounce_bio_set);
bio_for_each_segment_all(to, bio, i) {
struct page *page = to->bv_page;
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 88b4bbe58100..a340766b51fe 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -482,7 +482,8 @@ enum binder_deferred_state {
* @tsk task_struct for group_leader of process
* (invariant after initialized)
* @files files_struct for process
- * (invariant after initialized)
+ * (protected by @files_lock)
+ * @files_lock mutex to protect @files
* @deferred_work_node: element for binder_deferred_list
* (protected by binder_deferred_lock)
* @deferred_work: bitmap of deferred work to perform
@@ -530,6 +531,7 @@ struct binder_proc {
int pid;
struct task_struct *tsk;
struct files_struct *files;
+ struct mutex files_lock;
struct hlist_node deferred_work_node;
int deferred_work;
bool is_dead;
@@ -877,20 +879,26 @@ static void binder_inc_node_tmpref_ilocked(struct binder_node *node);
static int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
{
- struct files_struct *files = proc->files;
unsigned long rlim_cur;
unsigned long irqs;
+ int ret;
- if (files == NULL)
- return -ESRCH;
-
- if (!lock_task_sighand(proc->tsk, &irqs))
- return -EMFILE;
-
+ mutex_lock(&proc->files_lock);
+ if (proc->files == NULL) {
+ ret = -ESRCH;
+ goto err;
+ }
+ if (!lock_task_sighand(proc->tsk, &irqs)) {
+ ret = -EMFILE;
+ goto err;
+ }
rlim_cur = task_rlimit(proc->tsk, RLIMIT_NOFILE);
unlock_task_sighand(proc->tsk, &irqs);
- return __alloc_fd(files, 0, rlim_cur, flags);
+ ret = __alloc_fd(proc->files, 0, rlim_cur, flags);
+err:
+ mutex_unlock(&proc->files_lock);
+ return ret;
}
/*
@@ -899,8 +907,10 @@ static int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
static void task_fd_install(
struct binder_proc *proc, unsigned int fd, struct file *file)
{
+ mutex_lock(&proc->files_lock);
if (proc->files)
__fd_install(proc->files, fd, file);
+ mutex_unlock(&proc->files_lock);
}
/*
@@ -910,9 +920,11 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd)
{
int retval;
- if (proc->files == NULL)
- return -ESRCH;
-
+ mutex_lock(&proc->files_lock);
+ if (proc->files == NULL) {
+ retval = -ESRCH;
+ goto err;
+ }
retval = __close_fd(proc->files, fd);
/* can't restart close syscall because file table entry was cleared */
if (unlikely(retval == -ERESTARTSYS ||
@@ -920,7 +932,8 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd)
retval == -ERESTARTNOHAND ||
retval == -ERESTART_RESTARTBLOCK))
retval = -EINTR;
-
+err:
+ mutex_unlock(&proc->files_lock);
return retval;
}
@@ -4627,7 +4640,9 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
ret = binder_alloc_mmap_handler(&proc->alloc, vma);
if (ret)
return ret;
+ mutex_lock(&proc->files_lock);
proc->files = get_files_struct(current);
+ mutex_unlock(&proc->files_lock);
return 0;
err_bad_arg:
@@ -4651,6 +4666,7 @@ static int binder_open(struct inode *nodp, struct file *filp)
spin_lock_init(&proc->outer_lock);
get_task_struct(current->group_leader);
proc->tsk = current->group_leader;
+ mutex_init(&proc->files_lock);
INIT_LIST_HEAD(&proc->todo);
proc->default_priority = task_nice(current);
binder_dev = container_of(filp->private_data, struct binder_device,
@@ -4903,9 +4919,11 @@ static void binder_deferred_func(struct work_struct *work)
files = NULL;
if (defer & BINDER_DEFERRED_PUT_FILES) {
+ mutex_lock(&proc->files_lock);
files = proc->files;
if (files)
proc->files = NULL;
+ mutex_unlock(&proc->files_lock);
}
if (defer & BINDER_DEFERRED_FLUSH)
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index eb3af2739537..07532d83be0b 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -186,6 +186,11 @@ static void cache_associativity(struct cacheinfo *this_leaf)
this_leaf->ways_of_associativity = (size / nr_sets) / line_size;
}
+static bool cache_node_is_unified(struct cacheinfo *this_leaf)
+{
+ return of_property_read_bool(this_leaf->of_node, "cache-unified");
+}
+
static void cache_of_override_properties(unsigned int cpu)
{
int index;
@@ -194,6 +199,14 @@ static void cache_of_override_properties(unsigned int cpu)
for (index = 0; index < cache_leaves(cpu); index++) {
this_leaf = this_cpu_ci->info_list + index;
+ /*
+ * init_cache_level must setup the cache level correctly
+ * overriding the architecturally specified levels, so
+ * if type is NONE at this stage, it should be unified
+ */
+ if (this_leaf->type == CACHE_TYPE_NOCACHE &&
+ cache_node_is_unified(this_leaf))
+ this_leaf->type = CACHE_TYPE_UNIFIED;
cache_size(this_leaf);
cache_get_line_size(this_leaf);
cache_nr_sets(this_leaf);
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index eb4528c87c0b..d6f3d9ee1350 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1074,7 +1074,7 @@ void acpi_gpiochip_add(struct gpio_chip *chip)
}
if (!chip->names)
- devprop_gpiochip_set_names(chip);
+ devprop_gpiochip_set_names(chip, dev_fwnode(chip->parent));
acpi_gpiochip_request_regions(acpi_gpio);
acpi_gpiochip_scan_gpios(acpi_gpio);
diff --git a/drivers/gpio/gpiolib-devprop.c b/drivers/gpio/gpiolib-devprop.c
index 27f383bda7d9..f748aa3e77f7 100644
--- a/drivers/gpio/gpiolib-devprop.c
+++ b/drivers/gpio/gpiolib-devprop.c
@@ -19,30 +19,27 @@
/**
* devprop_gpiochip_set_names - Set GPIO line names using device properties
* @chip: GPIO chip whose lines should be named, if possible
+ * @fwnode: Property Node containing the gpio-line-names property
*
* Looks for device property "gpio-line-names" and if it exists assigns
* GPIO line names for the chip. The memory allocated for the assigned
* names belong to the underlying firmware node and should not be released
* by the caller.
*/
-void devprop_gpiochip_set_names(struct gpio_chip *chip)
+void devprop_gpiochip_set_names(struct gpio_chip *chip,
+ const struct fwnode_handle *fwnode)
{
struct gpio_device *gdev = chip->gpiodev;
const char **names;
int ret, i;
- if (!chip->parent) {
- dev_warn(&gdev->dev, "GPIO chip parent is NULL\n");
- return;
- }
-
- ret = device_property_read_string_array(chip->parent, "gpio-line-names",
+ ret = fwnode_property_read_string_array(fwnode, "gpio-line-names",
NULL, 0);
if (ret < 0)
return;
if (ret != gdev->ngpio) {
- dev_warn(chip->parent,
+ dev_warn(&gdev->dev,
"names %d do not match number of GPIOs %d\n", ret,
gdev->ngpio);
return;
@@ -52,10 +49,10 @@ void devprop_gpiochip_set_names(struct gpio_chip *chip)
if (!names)
return;
- ret = device_property_read_string_array(chip->parent, "gpio-line-names",
+ ret = fwnode_property_read_string_array(fwnode, "gpio-line-names",
names, gdev->ngpio);
if (ret < 0) {
- dev_warn(chip->parent, "failed to read GPIO line names\n");
+ dev_warn(&gdev->dev, "failed to read GPIO line names\n");
kfree(names);
return;
}
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index bfcd20699ec8..ba38f530e403 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -493,7 +493,8 @@ int of_gpiochip_add(struct gpio_chip *chip)
/* If the chip defines names itself, these take precedence */
if (!chip->names)
- devprop_gpiochip_set_names(chip);
+ devprop_gpiochip_set_names(chip,
+ of_fwnode_handle(chip->of_node));
of_node_get(chip->of_node);
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index d003ccb12781..3d4d0634c9dd 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -224,7 +224,8 @@ static inline int gpio_chip_hwgpio(const struct gpio_desc *desc)
return desc - &desc->gdev->descs[0];
}
-void devprop_gpiochip_set_names(struct gpio_chip *chip);
+void devprop_gpiochip_set_names(struct gpio_chip *chip,
+ const struct fwnode_handle *fwnode);
/* With descriptor prefix */
diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c
index feafdb961c48..59b2f96d986a 100644
--- a/drivers/infiniband/core/security.c
+++ b/drivers/infiniband/core/security.c
@@ -386,6 +386,9 @@ int ib_open_shared_qp_security(struct ib_qp *qp, struct ib_device *dev)
if (ret)
return ret;
+ if (!qp->qp_sec)
+ return 0;
+
mutex_lock(&real_qp->qp_sec->mutex);
ret = check_qp_port_pkey_settings(real_qp->qp_sec->ports_pkeys,
qp->qp_sec);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index d8f540054392..93c1a57dbff1 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2085,8 +2085,8 @@ int ib_uverbs_ex_modify_qp(struct ib_uverbs_file *file,
return -EOPNOTSUPP;
if (ucore->inlen > sizeof(cmd)) {
- if (ib_is_udata_cleared(ucore, sizeof(cmd),
- ucore->inlen - sizeof(cmd)))
+ if (!ib_is_udata_cleared(ucore, sizeof(cmd),
+ ucore->inlen - sizeof(cmd)))
return -EOPNOTSUPP;
}
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index de57d6c11a25..9032f77cc38d 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1400,7 +1400,8 @@ int ib_close_qp(struct ib_qp *qp)
spin_unlock_irqrestore(&real_qp->device->event_handler_lock, flags);
atomic_dec(&real_qp->usecnt);
- ib_close_shared_qp_security(qp->qp_sec);
+ if (qp->qp_sec)
+ ib_close_shared_qp_security(qp->qp_sec);
kfree(qp);
return 0;
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index eae8ea81c6e2..514c1000ded1 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -586,10 +586,10 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
ret = -EAGAIN;
goto skip_cqe;
}
- if (unlikely((CQE_WRID_MSN(hw_cqe) != (wq->rq.msn)))) {
+ if (unlikely(!CQE_STATUS(hw_cqe) &&
+ CQE_WRID_MSN(hw_cqe) != wq->rq.msn)) {
t4_set_wq_in_error(wq);
- hw_cqe->header |= htonl(CQE_STATUS_V(T4_ERR_MSN));
- goto proc_cqe;
+ hw_cqe->header |= cpu_to_be32(CQE_STATUS_V(T4_ERR_MSN));
}
goto proc_cqe;
}
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 6ff44dc606eb..3409eee16092 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1129,7 +1129,6 @@ struct hfi1_devdata {
u16 pcie_lnkctl;
u16 pcie_devctl2;
u32 pci_msix0;
- u32 pci_lnkctl3;
u32 pci_tph2;
/*
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 09e50fd2a08f..8c7e7a60b715 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -411,15 +411,12 @@ int restore_pci_variables(struct hfi1_devdata *dd)
if (ret)
goto error;
- ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_SPCIE1,
- dd->pci_lnkctl3);
- if (ret)
- goto error;
-
- ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2, dd->pci_tph2);
- if (ret)
- goto error;
-
+ if (pci_find_ext_capability(dd->pcidev, PCI_EXT_CAP_ID_TPH)) {
+ ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2,
+ dd->pci_tph2);
+ if (ret)
+ goto error;
+ }
return 0;
error:
@@ -469,15 +466,12 @@ int save_pci_variables(struct hfi1_devdata *dd)
if (ret)
goto error;
- ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_SPCIE1,
- &dd->pci_lnkctl3);
- if (ret)
- goto error;
-
- ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2, &dd->pci_tph2);
- if (ret)
- goto error;
-
+ if (pci_find_ext_capability(dd->pcidev, PCI_EXT_CAP_ID_TPH)) {
+ ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2,
+ &dd->pci_tph2);
+ if (ret)
+ goto error;
+ }
return 0;
error:
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 5aff1e33d984..30d479f87cb8 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1415,6 +1415,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
}
INIT_LIST_HEAD(&context->vma_private_list);
+ mutex_init(&context->vma_private_list_mutex);
INIT_LIST_HEAD(&context->db_page_list);
mutex_init(&context->db_page_mutex);
@@ -1576,7 +1577,9 @@ static void mlx5_ib_vma_close(struct vm_area_struct *area)
* mlx5_ib_disassociate_ucontext().
*/
mlx5_ib_vma_priv_data->vma = NULL;
+ mutex_lock(mlx5_ib_vma_priv_data->vma_private_list_mutex);
list_del(&mlx5_ib_vma_priv_data->list);
+ mutex_unlock(mlx5_ib_vma_priv_data->vma_private_list_mutex);
kfree(mlx5_ib_vma_priv_data);
}
@@ -1596,10 +1599,13 @@ static int mlx5_ib_set_vma_data(struct vm_area_struct *vma,
return -ENOMEM;
vma_prv->vma = vma;
+ vma_prv->vma_private_list_mutex = &ctx->vma_private_list_mutex;
vma->vm_private_data = vma_prv;
vma->vm_ops = &mlx5_ib_vm_ops;
+ mutex_lock(&ctx->vma_private_list_mutex);
list_add(&vma_prv->list, vma_head);
+ mutex_unlock(&ctx->vma_private_list_mutex);
return 0;
}
@@ -1642,6 +1648,7 @@ static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
* mlx5_ib_vma_close.
*/
down_write(&owning_mm->mmap_sem);
+ mutex_lock(&context->vma_private_list_mutex);
list_for_each_entry_safe(vma_private, n, &context->vma_private_list,
list) {
vma = vma_private->vma;
@@ -1656,6 +1663,7 @@ static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
list_del(&vma_private->list);
kfree(vma_private);
}
+ mutex_unlock(&context->vma_private_list_mutex);
up_write(&owning_mm->mmap_sem);
mmput(owning_mm);
put_task_struct(owning_process);
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 189e80cd6b2f..754103372faa 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -115,6 +115,8 @@ enum {
struct mlx5_ib_vma_private_data {
struct list_head list;
struct vm_area_struct *vma;
+ /* protect vma_private_list add/del */
+ struct mutex *vma_private_list_mutex;
};
struct mlx5_ib_ucontext {
@@ -129,6 +131,8 @@ struct mlx5_ib_ucontext {
/* Transport Domain number */
u32 tdn;
struct list_head vma_private_list;
+ /* protect vma_private_list add/del */
+ struct mutex vma_private_list_mutex;
unsigned long upd_xlt_page;
/* protect ODP/KSM */
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index d7b53d53c116..72d6ffbfd638 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -167,7 +167,7 @@ static void bcm_sf2_gphy_enable_set(struct dsa_switch *ds, bool enable)
reg = reg_readl(priv, REG_SPHY_CNTRL);
if (enable) {
reg |= PHY_RESET;
- reg &= ~(EXT_PWR_DOWN | IDDQ_BIAS | CK25_DIS);
+ reg &= ~(EXT_PWR_DOWN | IDDQ_BIAS | IDDQ_GLOBAL_PWR | CK25_DIS);
reg_writel(priv, reg, REG_SPHY_CNTRL);
udelay(21);
reg = reg_readl(priv, REG_SPHY_CNTRL);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index dc5de275352a..aa764c5e3c6b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1875,7 +1875,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
* here forever if we consistently cannot allocate
* buffers.
*/
- else if (rc == -ENOMEM)
+ else if (rc == -ENOMEM && budget)
rx_pkts++;
else if (rc == -EBUSY) /* partial completion */
break;
@@ -1961,7 +1961,7 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget)
cpu_to_le32(RX_CMPL_ERRORS_CRC_ERROR);
rc = bnxt_rx_pkt(bp, bnapi, &raw_cons, &event);
- if (likely(rc == -EIO))
+ if (likely(rc == -EIO) && budget)
rx_pkts++;
else if (rc == -EBUSY) /* partial completion */
break;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 656e6af70f0a..aef3fcf2f5b9 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -14227,7 +14227,9 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
/* Reset PHY, otherwise the read DMA engine will be in a mode that
* breaks all requests to 256 bytes.
*/
- if (tg3_asic_rev(tp) == ASIC_REV_57766)
+ if (tg3_asic_rev(tp) == ASIC_REV_57766 ||
+ tg3_asic_rev(tp) == ASIC_REV_5717 ||
+ tg3_asic_rev(tp) == ASIC_REV_5719)
reset_phy = true;
err = tg3_restart_hw(tp, reset_phy);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 3dc2d771a222..faf7cdc97ebf 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -818,6 +818,12 @@ static void fec_enet_bd_init(struct net_device *dev)
for (i = 0; i < txq->bd.ring_size; i++) {
/* Initialize the BD for every fragment in the page. */
bdp->cbd_sc = cpu_to_fec16(0);
+ if (bdp->cbd_bufaddr &&
+ !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
+ dma_unmap_single(&fep->pdev->dev,
+ fec32_to_cpu(bdp->cbd_bufaddr),
+ fec16_to_cpu(bdp->cbd_datlen),
+ DMA_TO_DEVICE);
if (txq->tx_skbuff[i]) {
dev_kfree_skb_any(txq->tx_skbuff[i]);
txq->tx_skbuff[i] = NULL;
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index c9798210fa0f..0495487f7b42 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -344,7 +344,8 @@ static int orion_mdio_probe(struct platform_device *pdev)
dev->regs + MVMDIO_ERR_INT_MASK);
} else if (dev->err_interrupt == -EPROBE_DEFER) {
- return -EPROBE_DEFER;
+ ret = -EPROBE_DEFER;
+ goto out_mdio;
}
if (pdev->dev.of_node)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 1fffdebbc9e8..e9a1fbcc4adf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -362,7 +362,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
case MLX5_CMD_OP_ALLOC_Q_COUNTER:
case MLX5_CMD_OP_QUERY_Q_COUNTER:
- case MLX5_CMD_OP_SET_RATE_LIMIT:
+ case MLX5_CMD_OP_SET_PP_RATE_LIMIT:
case MLX5_CMD_OP_QUERY_RATE_LIMIT:
case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT:
@@ -505,7 +505,7 @@ const char *mlx5_command_str(int command)
MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
- MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT);
+ MLX5_COMMAND_STR_CASE(SET_PP_RATE_LIMIT);
MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 13b5ef9d8703..5fa071620104 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -590,6 +590,7 @@ struct mlx5e_channel {
struct mlx5_core_dev *mdev;
struct mlx5e_tstamp *tstamp;
int ix;
+ int cpu;
};
struct mlx5e_channels {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cc11bbbd0309..3cdb932cae76 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -71,11 +71,6 @@ struct mlx5e_channel_param {
struct mlx5e_cq_param icosq_cq;
};
-static int mlx5e_get_node(struct mlx5e_priv *priv, int ix)
-{
- return pci_irq_get_node(priv->mdev->pdev, MLX5_EQ_VEC_COMP_BASE + ix);
-}
-
static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
{
return MLX5_CAP_GEN(mdev, striding_rq) &&
@@ -452,17 +447,16 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
int mtt_sz = mlx5e_get_wqe_mtt_sz();
int mtt_alloc = mtt_sz + MLX5_UMR_ALIGN - 1;
- int node = mlx5e_get_node(c->priv, c->ix);
int i;
rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
- GFP_KERNEL, node);
+ GFP_KERNEL, cpu_to_node(c->cpu));
if (!rq->mpwqe.info)
goto err_out;
/* We allocate more than mtt_sz as we will align the pointer */
- rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz,
- GFP_KERNEL, node);
+ rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, GFP_KERNEL,
+ cpu_to_node(c->cpu));
if (unlikely(!rq->mpwqe.mtt_no_align))
goto err_free_wqe_info;
@@ -570,7 +564,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
int err;
int i;
- rqp->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+ rqp->wq.db_numa_node = cpu_to_node(c->cpu);
err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq,
&rq->wq_ctrl);
@@ -636,8 +630,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
default: /* MLX5_WQ_TYPE_LINKED_LIST */
rq->wqe.frag_info =
kzalloc_node(wq_sz * sizeof(*rq->wqe.frag_info),
- GFP_KERNEL,
- mlx5e_get_node(c->priv, c->ix));
+ GFP_KERNEL, cpu_to_node(c->cpu));
if (!rq->wqe.frag_info) {
err = -ENOMEM;
goto err_rq_wq_destroy;
@@ -1007,13 +1000,13 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
sq->uar_map = mdev->mlx5e_res.bfreg.map;
sq->min_inline_mode = params->tx_min_inline_mode;
- param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+ param->wq.db_numa_node = cpu_to_node(c->cpu);
err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
if (err)
return err;
sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
- err = mlx5e_alloc_xdpsq_db(sq, mlx5e_get_node(c->priv, c->ix));
+ err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu));
if (err)
goto err_sq_wq_destroy;
@@ -1060,13 +1053,13 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
sq->channel = c;
sq->uar_map = mdev->mlx5e_res.bfreg.map;
- param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+ param->wq.db_numa_node = cpu_to_node(c->cpu);
err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
if (err)
return err;
sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
- err = mlx5e_alloc_icosq_db(sq, mlx5e_get_node(c->priv, c->ix));
+ err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu));
if (err)
goto err_sq_wq_destroy;
@@ -1132,13 +1125,13 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
if (MLX5_IPSEC_DEV(c->priv->mdev))
set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
- param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+ param->wq.db_numa_node = cpu_to_node(c->cpu);
err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
if (err)
return err;
sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
- err = mlx5e_alloc_txqsq_db(sq, mlx5e_get_node(c->priv, c->ix));
+ err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu));
if (err)
goto err_sq_wq_destroy;
@@ -1510,8 +1503,8 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c,
struct mlx5_core_dev *mdev = c->priv->mdev;
int err;
- param->wq.buf_numa_node = mlx5e_get_node(c->priv, c->ix);
- param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+ param->wq.buf_numa_node = cpu_to_node(c->cpu);
+ param->wq.db_numa_node = cpu_to_node(c->cpu);
param->eq_ix = c->ix;
err = mlx5e_alloc_cq_common(mdev, param, cq);
@@ -1610,6 +1603,11 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq)
mlx5e_free_cq(cq);
}
+static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
+{
+ return cpumask_first(priv->mdev->priv.irq_info[ix].mask);
+}
+
static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
struct mlx5e_params *params,
struct mlx5e_channel_param *cparam)
@@ -1758,12 +1756,13 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
{
struct mlx5e_cq_moder icocq_moder = {0, 0};
struct net_device *netdev = priv->netdev;
+ int cpu = mlx5e_get_cpu(priv, ix);
struct mlx5e_channel *c;
unsigned int irq;
int err;
int eqn;
- c = kzalloc_node(sizeof(*c), GFP_KERNEL, mlx5e_get_node(priv, ix));
+ c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
if (!c)
return -ENOMEM;
@@ -1771,6 +1770,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
c->mdev = priv->mdev;
c->tstamp = &priv->tstamp;
c->ix = ix;
+ c->cpu = cpu;
c->pdev = &priv->mdev->pdev->dev;
c->netdev = priv->netdev;
c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
@@ -1859,8 +1859,7 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
for (tc = 0; tc < c->num_tc; tc++)
mlx5e_activate_txqsq(&c->sq[tc]);
mlx5e_activate_rq(&c->rq);
- netif_set_xps_queue(c->netdev,
- mlx5_get_vector_affinity(c->priv->mdev, c->ix), c->ix);
+ netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix);
}
static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
@@ -3554,6 +3553,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
struct sk_buff *skb,
netdev_features_t features)
{
+ unsigned int offset = 0;
struct udphdr *udph;
u8 proto;
u16 port;
@@ -3563,7 +3563,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
proto = ip_hdr(skb)->protocol;
break;
case htons(ETH_P_IPV6):
- proto = ipv6_hdr(skb)->nexthdr;
+ proto = ipv6_find_hdr(skb, &offset, -1, NULL, NULL);
break;
default:
goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c
index 3c11d6e2160a..14962969c5ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c
@@ -66,6 +66,9 @@ static int mlx5_fpga_mem_read_i2c(struct mlx5_fpga_device *fdev, size_t size,
u8 actual_size;
int err;
+ if (!size)
+ return -EINVAL;
+
if (!fdev->mdev)
return -ENOTCONN;
@@ -95,6 +98,9 @@ static int mlx5_fpga_mem_write_i2c(struct mlx5_fpga_device *fdev, size_t size,
u8 actual_size;
int err;
+ if (!size)
+ return -EINVAL;
+
if (!fdev->mdev)
return -ENOTCONN;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 06562c9a6b9c..8bfc37e4ec87 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -316,9 +316,6 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
{
struct mlx5_priv *priv = &dev->priv;
struct mlx5_eq_table *table = &priv->eq_table;
- struct irq_affinity irqdesc = {
- .pre_vectors = MLX5_EQ_VEC_COMP_BASE,
- };
int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq);
int nvec;
@@ -332,10 +329,9 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
if (!priv->irq_info)
goto err_free_msix;
- nvec = pci_alloc_irq_vectors_affinity(dev->pdev,
+ nvec = pci_alloc_irq_vectors(dev->pdev,
MLX5_EQ_VEC_COMP_BASE + 1, nvec,
- PCI_IRQ_MSIX | PCI_IRQ_AFFINITY,
- &irqdesc);
+ PCI_IRQ_MSIX);
if (nvec < 0)
return nvec;
@@ -621,6 +617,63 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev)
return (u64)timer_l | (u64)timer_h1 << 32;
}
+static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+ struct mlx5_priv *priv = &mdev->priv;
+ int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
+
+ if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
+ mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
+ return -ENOMEM;
+ }
+
+ cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
+ priv->irq_info[i].mask);
+
+ if (IS_ENABLED(CONFIG_SMP) &&
+ irq_set_affinity_hint(irq, priv->irq_info[i].mask))
+ mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
+
+ return 0;
+}
+
+static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+ struct mlx5_priv *priv = &mdev->priv;
+ int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
+
+ irq_set_affinity_hint(irq, NULL);
+ free_cpumask_var(priv->irq_info[i].mask);
+}
+
+static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
+{
+ int err;
+ int i;
+
+ for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) {
+ err = mlx5_irq_set_affinity_hint(mdev, i);
+ if (err)
+ goto err_out;
+ }
+
+ return 0;
+
+err_out:
+ for (i--; i >= 0; i--)
+ mlx5_irq_clear_affinity_hint(mdev, i);
+
+ return err;
+}
+
+static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
+{
+ int i;
+
+ for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++)
+ mlx5_irq_clear_affinity_hint(mdev, i);
+}
+
int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
unsigned int *irqn)
{
@@ -1093,6 +1146,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
goto err_stop_eqs;
}
+ err = mlx5_irq_set_affinity_hints(dev);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n");
+ goto err_affinity_hints;
+ }
+
err = mlx5_init_fs(dev);
if (err) {
dev_err(&pdev->dev, "Failed to init flow steering\n");
@@ -1150,6 +1209,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
mlx5_cleanup_fs(dev);
err_fs:
+ mlx5_irq_clear_affinity_hints(dev);
+
+err_affinity_hints:
free_comp_eqs(dev);
err_stop_eqs:
@@ -1218,6 +1280,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
mlx5_sriov_detach(dev);
mlx5_cleanup_fs(dev);
+ mlx5_irq_clear_affinity_hints(dev);
free_comp_eqs(dev);
mlx5_stop_eqs(dev);
mlx5_put_uars_page(dev, priv->uar);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index db9e665ab104..889130edb715 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -213,8 +213,8 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
err_cmd:
memset(din, 0, sizeof(din));
memset(dout, 0, sizeof(dout));
- MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
- MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
+ MLX5_SET(destroy_qp_in, din, opcode, MLX5_CMD_OP_DESTROY_QP);
+ MLX5_SET(destroy_qp_in, din, qpn, qp->qpn);
mlx5_cmd_exec(dev, din, sizeof(din), dout, sizeof(dout));
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
index e651e4c02867..d3c33e9eea72 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
@@ -125,16 +125,16 @@ static struct mlx5_rl_entry *find_rl_entry(struct mlx5_rl_table *table,
return ret_entry;
}
-static int mlx5_set_rate_limit_cmd(struct mlx5_core_dev *dev,
+static int mlx5_set_pp_rate_limit_cmd(struct mlx5_core_dev *dev,
u32 rate, u16 index)
{
- u32 in[MLX5_ST_SZ_DW(set_rate_limit_in)] = {0};
- u32 out[MLX5_ST_SZ_DW(set_rate_limit_out)] = {0};
+ u32 in[MLX5_ST_SZ_DW(set_pp_rate_limit_in)] = {0};
+ u32 out[MLX5_ST_SZ_DW(set_pp_rate_limit_out)] = {0};
- MLX5_SET(set_rate_limit_in, in, opcode,
- MLX5_CMD_OP_SET_RATE_LIMIT);
- MLX5_SET(set_rate_limit_in, in, rate_limit_index, index);
- MLX5_SET(set_rate_limit_in, in, rate_limit, rate);
+ MLX5_SET(set_pp_rate_limit_in, in, opcode,
+ MLX5_CMD_OP_SET_PP_RATE_LIMIT);
+ MLX5_SET(set_pp_rate_limit_in, in, rate_limit_index, index);
+ MLX5_SET(set_pp_rate_limit_in, in, rate_limit, rate);
return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
}
@@ -173,7 +173,7 @@ int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index)
entry->refcount++;
} else {
/* new rate limit */
- err = mlx5_set_rate_limit_cmd(dev, rate, entry->index);
+ err = mlx5_set_pp_rate_limit_cmd(dev, rate, entry->index);
if (err) {
mlx5_core_err(dev, "Failed configuring rate: %u (%d)\n",
rate, err);
@@ -209,7 +209,7 @@ void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate)
entry->refcount--;
if (!entry->refcount) {
/* need to remove rate */
- mlx5_set_rate_limit_cmd(dev, 0, entry->index);
+ mlx5_set_pp_rate_limit_cmd(dev, 0, entry->index);
entry->rate = 0;
}
@@ -262,8 +262,8 @@ void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev)
/* Clear all configured rates */
for (i = 0; i < table->max_size; i++)
if (table->rl_entry[i].rate)
- mlx5_set_rate_limit_cmd(dev, 0,
- table->rl_entry[i].index);
+ mlx5_set_pp_rate_limit_cmd(dev, 0,
+ table->rl_entry[i].index);
kfree(dev->priv.rl_table.rl_entry);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index 07a9ba6cfc70..2f74953e4561 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -71,9 +71,9 @@ struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
struct mlx5e_vxlan *vxlan;
- spin_lock(&vxlan_db->lock);
+ spin_lock_bh(&vxlan_db->lock);
vxlan = radix_tree_lookup(&vxlan_db->tree, port);
- spin_unlock(&vxlan_db->lock);
+ spin_unlock_bh(&vxlan_db->lock);
return vxlan;
}
@@ -88,8 +88,12 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
struct mlx5e_vxlan *vxlan;
int err;
- if (mlx5e_vxlan_lookup_port(priv, port))
+ mutex_lock(&priv->state_lock);
+ vxlan = mlx5e_vxlan_lookup_port(priv, port);
+ if (vxlan) {
+ atomic_inc(&vxlan->refcount);
goto free_work;
+ }
if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
goto free_work;
@@ -99,10 +103,11 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
goto err_delete_port;
vxlan->udp_port = port;
+ atomic_set(&vxlan->refcount, 1);
- spin_lock_irq(&vxlan_db->lock);
+ spin_lock_bh(&vxlan_db->lock);
err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan);
- spin_unlock_irq(&vxlan_db->lock);
+ spin_unlock_bh(&vxlan_db->lock);
if (err)
goto err_free;
@@ -113,35 +118,39 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
err_delete_port:
mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
free_work:
+ mutex_unlock(&priv->state_lock);
kfree(vxlan_work);
}
-static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port)
+static void mlx5e_vxlan_del_port(struct work_struct *work)
{
+ struct mlx5e_vxlan_work *vxlan_work =
+ container_of(work, struct mlx5e_vxlan_work, work);
+ struct mlx5e_priv *priv = vxlan_work->priv;
struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
+ u16 port = vxlan_work->port;
struct mlx5e_vxlan *vxlan;
+ bool remove = false;
- spin_lock_irq(&vxlan_db->lock);
- vxlan = radix_tree_delete(&vxlan_db->tree, port);
- spin_unlock_irq(&vxlan_db->lock);
-
+ mutex_lock(&priv->state_lock);
+ spin_lock_bh(&vxlan_db->lock);
+ vxlan = radix_tree_lookup(&vxlan_db->tree, port);
if (!vxlan)
- return;
-
- mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlan->udp_port);
-
- kfree(vxlan);
-}
+ goto out_unlock;
-static void mlx5e_vxlan_del_port(struct work_struct *work)
-{
- struct mlx5e_vxlan_work *vxlan_work =
- container_of(work, struct mlx5e_vxlan_work, work);
- struct mlx5e_priv *priv = vxlan_work->priv;
- u16 port = vxlan_work->port;
+ if (atomic_dec_and_test(&vxlan->refcount)) {
+ radix_tree_delete(&vxlan_db->tree, port);
+ remove = true;
+ }
- __mlx5e_vxlan_core_del_port(priv, port);
+out_unlock:
+ spin_unlock_bh(&vxlan_db->lock);
+ if (remove) {
+ mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+ kfree(vxlan);
+ }
+ mutex_unlock(&priv->state_lock);
kfree(vxlan_work);
}
@@ -171,12 +180,11 @@ void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
struct mlx5e_vxlan *vxlan;
unsigned int port = 0;
- spin_lock_irq(&vxlan_db->lock);
+ /* Lockless since we are the only radix-tree consumers, wq is disabled */
while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) {
port = vxlan->udp_port;
- spin_unlock_irq(&vxlan_db->lock);
- __mlx5e_vxlan_core_del_port(priv, (u16)port);
- spin_lock_irq(&vxlan_db->lock);
+ radix_tree_delete(&vxlan_db->tree, port);
+ mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+ kfree(vxlan);
}
- spin_unlock_irq(&vxlan_db->lock);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
index 5def12c048e3..5ef6ae7d568a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
@@ -36,6 +36,7 @@
#include "en.h"
struct mlx5e_vxlan {
+ atomic_t refcount;
u16 udp_port;
};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index db38880f54b4..3ead7439821c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4164,6 +4164,7 @@ static int mlxsw_sp_port_stp_set(struct mlxsw_sp_port *mlxsw_sp_port,
static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port)
{
+ u16 vid = 1;
int err;
err = mlxsw_sp_port_vp_mode_set(mlxsw_sp_port, true);
@@ -4176,8 +4177,19 @@ static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port)
true, false);
if (err)
goto err_port_vlan_set;
+
+ for (; vid <= VLAN_N_VID - 1; vid++) {
+ err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_port,
+ vid, false);
+ if (err)
+ goto err_vid_learning_set;
+ }
+
return 0;
+err_vid_learning_set:
+ for (vid--; vid >= 1; vid--)
+ mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, true);
err_port_vlan_set:
mlxsw_sp_port_stp_set(mlxsw_sp_port, false);
err_port_stp_set:
@@ -4187,6 +4199,12 @@ static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port)
static void mlxsw_sp_port_ovs_leave(struct mlxsw_sp_port *mlxsw_sp_port)
{
+ u16 vid;
+
+ for (vid = VLAN_N_VID - 1; vid >= 1; vid--)
+ mlxsw_sp_port_vid_learning_set(mlxsw_sp_port,
+ vid, true);
+
mlxsw_sp_port_vlan_set(mlxsw_sp_port, 2, VLAN_N_VID - 1,
false, false);
mlxsw_sp_port_stp_set(mlxsw_sp_port, false);
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 32bf1fecf864..9b85cbd5a231 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -77,6 +77,7 @@ static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
}
if (buffer->flags & EFX_TX_BUF_SKB) {
+ EFX_WARN_ON_PARANOID(!pkts_compl || !bytes_compl);
(*pkts_compl)++;
(*bytes_compl) += buffer->skb->len;
dev_consume_skb_any((struct sk_buff *)buffer->skb);
@@ -426,12 +427,14 @@ static int efx_tx_map_data(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue)
{
struct efx_tx_buffer *buffer;
+ unsigned int bytes_compl = 0;
+ unsigned int pkts_compl = 0;
/* Work backwards until we hit the original insert pointer value */
while (tx_queue->insert_count != tx_queue->write_count) {
--tx_queue->insert_count;
buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
- efx_dequeue_buffer(tx_queue, buffer, NULL, NULL);
+ efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
}
}
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 4d02b27df044..a3f456b91c99 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -2069,7 +2069,7 @@ static struct phy_driver marvell_drivers[] = {
.flags = PHY_HAS_INTERRUPT,
.probe = marvell_probe,
.config_init = &m88e1145_config_init,
- .config_aneg = &marvell_config_aneg,
+ .config_aneg = &m88e1101_config_aneg,
.read_status = &genphy_read_status,
.ack_interrupt = &marvell_ack_interrupt,
.config_intr = &marvell_config_intr,
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index fdb43dd9b5cd..6c45ff650ec7 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -622,6 +622,7 @@ static int ksz9031_read_status(struct phy_device *phydev)
phydev->link = 0;
if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev))
phydev->drv->config_intr(phydev);
+ return genphy_config_aneg(phydev);
}
return 0;
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index bcb4755bcd95..4b377b978a0b 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -525,6 +525,7 @@ struct phylink *phylink_create(struct net_device *ndev, struct device_node *np,
pl->link_config.pause = MLO_PAUSE_AN;
pl->link_config.speed = SPEED_UNKNOWN;
pl->link_config.duplex = DUPLEX_UNKNOWN;
+ pl->link_config.an_enabled = true;
pl->ops = ops;
__set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state);
@@ -948,6 +949,7 @@ int phylink_ethtool_ksettings_set(struct phylink *pl,
mutex_lock(&pl->state_mutex);
/* Configure the MAC to match the new settings */
linkmode_copy(pl->link_config.advertising, our_kset.link_modes.advertising);
+ pl->link_config.interface = config.interface;
pl->link_config.speed = our_kset.base.speed;
pl->link_config.duplex = our_kset.base.duplex;
pl->link_config.an_enabled = our_kset.base.autoneg != AUTONEG_DISABLE;
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 81394a4b2803..2092febfcb42 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1204,6 +1204,7 @@ static const struct usb_device_id products[] = {
{QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */
{QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */
{QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */
+ {QMI_FIXED_INTF(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */
{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */
{QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a2f4e52fadb5..9e9202b50e73 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3105,6 +3105,11 @@ static void vxlan_config_apply(struct net_device *dev,
max_mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM :
VXLAN_HEADROOM);
+ if (max_mtu < ETH_MIN_MTU)
+ max_mtu = ETH_MIN_MTU;
+
+ if (!changelink && !conf->mtu)
+ dev->mtu = max_mtu;
}
if (dev->mtu > max_mtu)
diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c
index 4307bf0013e1..63e916d4d069 100644
--- a/drivers/phy/tegra/xusb.c
+++ b/drivers/phy/tegra/xusb.c
@@ -75,14 +75,14 @@ MODULE_DEVICE_TABLE(of, tegra_xusb_padctl_of_match);
static struct device_node *
tegra_xusb_find_pad_node(struct tegra_xusb_padctl *padctl, const char *name)
{
- /*
- * of_find_node_by_name() drops a reference, so make sure to grab one.
- */
- struct device_node *np = of_node_get(padctl->dev->of_node);
+ struct device_node *pads, *np;
+
+ pads = of_get_child_by_name(padctl->dev->of_node, "pads");
+ if (!pads)
+ return NULL;
- np = of_find_node_by_name(np, "pads");
- if (np)
- np = of_find_node_by_name(np, name);
+ np = of_get_child_by_name(pads, name);
+ of_node_put(pads);
return np;
}
@@ -90,16 +90,16 @@ tegra_xusb_find_pad_node(struct tegra_xusb_padctl *padctl, const char *name)
static struct device_node *
tegra_xusb_pad_find_phy_node(struct tegra_xusb_pad *pad, unsigned int index)
{
- /*
- * of_find_node_by_name() drops a reference, so make sure to grab one.
- */
- struct device_node *np = of_node_get(pad->dev.of_node);
+ struct device_node *np, *lanes;
- np = of_find_node_by_name(np, "lanes");
- if (!np)
+ lanes = of_get_child_by_name(pad->dev.of_node, "lanes");
+ if (!lanes)
return NULL;
- return of_find_node_by_name(np, pad->soc->lanes[index].name);
+ np = of_get_child_by_name(lanes, pad->soc->lanes[index].name);
+ of_node_put(lanes);
+
+ return np;
}
static int
@@ -195,7 +195,7 @@ int tegra_xusb_pad_register(struct tegra_xusb_pad *pad,
unsigned int i;
int err;
- children = of_find_node_by_name(pad->dev.of_node, "lanes");
+ children = of_get_child_by_name(pad->dev.of_node, "lanes");
if (!children)
return -ENODEV;
@@ -444,21 +444,21 @@ static struct device_node *
tegra_xusb_find_port_node(struct tegra_xusb_padctl *padctl, const char *type,
unsigned int index)
{
- /*
- * of_find_node_by_name() drops a reference, so make sure to grab one.
- */
- struct device_node *np = of_node_get(padctl->dev->of_node);
+ struct device_node *ports, *np;
+ char *name;
- np = of_find_node_by_name(np, "ports");
- if (np) {
- char *name;
+ ports = of_get_child_by_name(padctl->dev->of_node, "ports");
+ if (!ports)
+ return NULL;
- name = kasprintf(GFP_KERNEL, "%s-%u", type, index);
- if (!name)
- return ERR_PTR(-ENOMEM);
- np = of_find_node_by_name(np, name);
- kfree(name);
+ name = kasprintf(GFP_KERNEL, "%s-%u", type, index);
+ if (!name) {
+ of_node_put(ports);
+ return ERR_PTR(-ENOMEM);
}
+ np = of_get_child_by_name(ports, name);
+ kfree(name);
+ of_node_put(ports);
return np;
}
@@ -847,7 +847,7 @@ static void tegra_xusb_remove_ports(struct tegra_xusb_padctl *padctl)
static int tegra_xusb_padctl_probe(struct platform_device *pdev)
{
- struct device_node *np = of_node_get(pdev->dev.of_node);
+ struct device_node *np = pdev->dev.of_node;
const struct tegra_xusb_padctl_soc *soc;
struct tegra_xusb_padctl *padctl;
const struct of_device_id *match;
@@ -855,7 +855,7 @@ static int tegra_xusb_padctl_probe(struct platform_device *pdev)
int err;
/* for backwards compatibility with old device trees */
- np = of_find_node_by_name(np, "pads");
+ np = of_get_child_by_name(np, "pads");
if (!np) {
dev_warn(&pdev->dev, "deprecated DT, using legacy driver\n");
return tegra_xusb_padctl_legacy_probe(pdev);
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 5340efc673a9..92dd4aef21a3 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -564,9 +564,9 @@ enum qeth_cq {
};
struct qeth_ipato {
- int enabled;
- int invert4;
- int invert6;
+ bool enabled;
+ bool invert4;
+ bool invert6;
struct list_head entries;
};
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 330e5d3dadf3..7c7a244b6684 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1479,9 +1479,9 @@ static int qeth_setup_card(struct qeth_card *card)
qeth_set_intial_options(card);
/* IP address takeover */
INIT_LIST_HEAD(&card->ipato.entries);
- card->ipato.enabled = 0;
- card->ipato.invert4 = 0;
- card->ipato.invert6 = 0;
+ card->ipato.enabled = false;
+ card->ipato.invert4 = false;
+ card->ipato.invert6 = false;
/* init QDIO stuff */
qeth_init_qdio_info(card);
INIT_DELAYED_WORK(&card->buffer_reclaim_work, qeth_buffer_reclaim_work);
@@ -5445,6 +5445,13 @@ int qeth_poll(struct napi_struct *napi, int budget)
}
EXPORT_SYMBOL_GPL(qeth_poll);
+static int qeth_setassparms_inspect_rc(struct qeth_ipa_cmd *cmd)
+{
+ if (!cmd->hdr.return_code)
+ cmd->hdr.return_code = cmd->data.setassparms.hdr.return_code;
+ return cmd->hdr.return_code;
+}
+
int qeth_setassparms_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
@@ -6304,7 +6311,7 @@ static int qeth_ipa_checksum_run_cmd_cb(struct qeth_card *card,
(struct qeth_checksum_cmd *)reply->param;
QETH_CARD_TEXT(card, 4, "chkdoccb");
- if (cmd->hdr.return_code)
+ if (qeth_setassparms_inspect_rc(cmd))
return 0;
memset(chksum_cb, 0, sizeof(*chksum_cb));
diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h
index 194ae9b577cc..e5833837b799 100644
--- a/drivers/s390/net/qeth_l3.h
+++ b/drivers/s390/net/qeth_l3.h
@@ -82,7 +82,7 @@ void qeth_l3_del_vipa(struct qeth_card *, enum qeth_prot_versions, const u8 *);
int qeth_l3_add_rxip(struct qeth_card *, enum qeth_prot_versions, const u8 *);
void qeth_l3_del_rxip(struct qeth_card *card, enum qeth_prot_versions,
const u8 *);
-int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *, struct qeth_ipaddr *);
+void qeth_l3_update_ipato(struct qeth_card *card);
struct qeth_ipaddr *qeth_l3_get_addr_buffer(enum qeth_prot_versions);
int qeth_l3_add_ip(struct qeth_card *, struct qeth_ipaddr *);
int qeth_l3_delete_ip(struct qeth_card *, struct qeth_ipaddr *);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 27185ab38136..36dee176f8e2 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -163,8 +163,8 @@ static void qeth_l3_convert_addr_to_bits(u8 *addr, u8 *bits, int len)
}
}
-int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
- struct qeth_ipaddr *addr)
+static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
+ struct qeth_ipaddr *addr)
{
struct qeth_ipato_entry *ipatoe;
u8 addr_bits[128] = {0, };
@@ -173,6 +173,8 @@ int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
if (!card->ipato.enabled)
return 0;
+ if (addr->type != QETH_IP_TYPE_NORMAL)
+ return 0;
qeth_l3_convert_addr_to_bits((u8 *) &addr->u, addr_bits,
(addr->proto == QETH_PROT_IPV4)? 4:16);
@@ -289,8 +291,7 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
memcpy(addr, tmp_addr, sizeof(struct qeth_ipaddr));
addr->ref_counter = 1;
- if (addr->type == QETH_IP_TYPE_NORMAL &&
- qeth_l3_is_addr_covered_by_ipato(card, addr)) {
+ if (qeth_l3_is_addr_covered_by_ipato(card, addr)) {
QETH_CARD_TEXT(card, 2, "tkovaddr");
addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
}
@@ -604,6 +605,27 @@ int qeth_l3_setrouting_v6(struct qeth_card *card)
/*
* IP address takeover related functions
*/
+
+/**
+ * qeth_l3_update_ipato() - Update 'takeover' property, for all NORMAL IPs.
+ *
+ * Caller must hold ip_lock.
+ */
+void qeth_l3_update_ipato(struct qeth_card *card)
+{
+ struct qeth_ipaddr *addr;
+ unsigned int i;
+
+ hash_for_each(card->ip_htable, i, addr, hnode) {
+ if (addr->type != QETH_IP_TYPE_NORMAL)
+ continue;
+ if (qeth_l3_is_addr_covered_by_ipato(card, addr))
+ addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
+ else
+ addr->set_flags &= ~QETH_IPA_SETIP_TAKEOVER_FLAG;
+ }
+}
+
static void qeth_l3_clear_ipato_list(struct qeth_card *card)
{
struct qeth_ipato_entry *ipatoe, *tmp;
@@ -615,6 +637,7 @@ static void qeth_l3_clear_ipato_list(struct qeth_card *card)
kfree(ipatoe);
}
+ qeth_l3_update_ipato(card);
spin_unlock_bh(&card->ip_lock);
}
@@ -639,8 +662,10 @@ int qeth_l3_add_ipato_entry(struct qeth_card *card,
}
}
- if (!rc)
+ if (!rc) {
list_add_tail(&new->entry, &card->ipato.entries);
+ qeth_l3_update_ipato(card);
+ }
spin_unlock_bh(&card->ip_lock);
@@ -663,6 +688,7 @@ void qeth_l3_del_ipato_entry(struct qeth_card *card,
(proto == QETH_PROT_IPV4)? 4:16) &&
(ipatoe->mask_bits == mask_bits)) {
list_del(&ipatoe->entry);
+ qeth_l3_update_ipato(card);
kfree(ipatoe);
}
}
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index 7a829ad77783..1295dd8ec849 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -370,8 +370,8 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct qeth_card *card = dev_get_drvdata(dev);
- struct qeth_ipaddr *addr;
- int i, rc = 0;
+ bool enable;
+ int rc = 0;
if (!card)
return -EINVAL;
@@ -384,25 +384,18 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
}
if (sysfs_streq(buf, "toggle")) {
- card->ipato.enabled = (card->ipato.enabled)? 0 : 1;
- } else if (sysfs_streq(buf, "1")) {
- card->ipato.enabled = 1;
- hash_for_each(card->ip_htable, i, addr, hnode) {
- if ((addr->type == QETH_IP_TYPE_NORMAL) &&
- qeth_l3_is_addr_covered_by_ipato(card, addr))
- addr->set_flags |=
- QETH_IPA_SETIP_TAKEOVER_FLAG;
- }
- } else if (sysfs_streq(buf, "0")) {
- card->ipato.enabled = 0;
- hash_for_each(card->ip_htable, i, addr, hnode) {
- if (addr->set_flags &
- QETH_IPA_SETIP_TAKEOVER_FLAG)
- addr->set_flags &=
- ~QETH_IPA_SETIP_TAKEOVER_FLAG;
- }
- } else
+ enable = !card->ipato.enabled;
+ } else if (kstrtobool(buf, &enable)) {
rc = -EINVAL;
+ goto out;
+ }
+
+ if (card->ipato.enabled != enable) {
+ card->ipato.enabled = enable;
+ spin_lock_bh(&card->ip_lock);
+ qeth_l3_update_ipato(card);
+ spin_unlock_bh(&card->ip_lock);
+ }
out:
mutex_unlock(&card->conf_mutex);
return rc ? rc : count;
@@ -428,20 +421,27 @@ static ssize_t qeth_l3_dev_ipato_invert4_store(struct device *dev,
const char *buf, size_t count)
{
struct qeth_card *card = dev_get_drvdata(dev);
+ bool invert;
int rc = 0;
if (!card)
return -EINVAL;
mutex_lock(&card->conf_mutex);
- if (sysfs_streq(buf, "toggle"))
- card->ipato.invert4 = (card->ipato.invert4)? 0 : 1;
- else if (sysfs_streq(buf, "1"))
- card->ipato.invert4 = 1;
- else if (sysfs_streq(buf, "0"))
- card->ipato.invert4 = 0;
- else
+ if (sysfs_streq(buf, "toggle")) {
+ invert = !card->ipato.invert4;
+ } else if (kstrtobool(buf, &invert)) {
rc = -EINVAL;
+ goto out;
+ }
+
+ if (card->ipato.invert4 != invert) {
+ card->ipato.invert4 = invert;
+ spin_lock_bh(&card->ip_lock);
+ qeth_l3_update_ipato(card);
+ spin_unlock_bh(&card->ip_lock);
+ }
+out:
mutex_unlock(&card->conf_mutex);
return rc ? rc : count;
}
@@ -607,20 +607,27 @@ static ssize_t qeth_l3_dev_ipato_invert6_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct qeth_card *card = dev_get_drvdata(dev);
+ bool invert;
int rc = 0;
if (!card)
return -EINVAL;
mutex_lock(&card->conf_mutex);
- if (sysfs_streq(buf, "toggle"))
- card->ipato.invert6 = (card->ipato.invert6)? 0 : 1;
- else if (sysfs_streq(buf, "1"))
- card->ipato.invert6 = 1;
- else if (sysfs_streq(buf, "0"))
- card->ipato.invert6 = 0;
- else
+ if (sysfs_streq(buf, "toggle")) {
+ invert = !card->ipato.invert6;
+ } else if (kstrtobool(buf, &invert)) {
rc = -EINVAL;
+ goto out;
+ }
+
+ if (card->ipato.invert6 != invert) {
+ card->ipato.invert6 = invert;
+ spin_lock_bh(&card->ip_lock);
+ qeth_l3_update_ipato(card);
+ spin_unlock_bh(&card->ip_lock);
+ }
+out:
mutex_unlock(&card->conf_mutex);
return rc ? rc : count;
}
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index a4f28b7e4c65..e18877177f1b 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -1576,7 +1576,9 @@ static struct request *_make_request(struct request_queue *q, bool has_write,
return req;
for_each_bio(bio) {
- ret = blk_rq_append_bio(req, bio);
+ struct bio *bounce_bio = bio;
+
+ ret = blk_rq_append_bio(req, &bounce_bio);
if (ret)
return ERR_PTR(ret);
}
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index 93e2c90fa77d..83dc3292e9ab 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -348,7 +348,7 @@ static int ion_dma_buf_begin_cpu_access(struct dma_buf *dmabuf,
mutex_lock(&buffer->lock);
list_for_each_entry(a, &buffer->attachments, list) {
dma_sync_sg_for_cpu(a->dev, a->table->sgl, a->table->nents,
- DMA_BIDIRECTIONAL);
+ direction);
}
mutex_unlock(&buffer->lock);
@@ -370,7 +370,7 @@ static int ion_dma_buf_end_cpu_access(struct dma_buf *dmabuf,
mutex_lock(&buffer->lock);
list_for_each_entry(a, &buffer->attachments, list) {
dma_sync_sg_for_device(a->dev, a->table->sgl, a->table->nents,
- DMA_BIDIRECTIONAL);
+ direction);
}
mutex_unlock(&buffer->lock);
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 7c69b4a9694d..0d99b242e82e 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -920,7 +920,7 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
" %d i: %d bio: %p, allocating another"
" bio\n", bio->bi_vcnt, i, bio);
- rc = blk_rq_append_bio(req, bio);
+ rc = blk_rq_append_bio(req, &bio);
if (rc) {
pr_err("pSCSI: failed to append bio\n");
goto fail;
@@ -938,7 +938,7 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
}
if (bio) {
- rc = blk_rq_append_bio(req, bio);
+ rc = blk_rq_append_bio(req, &bio);
if (rc) {
pr_err("pSCSI: failed to append bio\n");
goto fail;
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index bdf0e6e89991..faf50df81622 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -1764,7 +1764,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
{
struct n_tty_data *ldata = tty->disc_data;
- if (!old || (old->c_lflag ^ tty->termios.c_lflag) & ICANON) {
+ if (!old || (old->c_lflag ^ tty->termios.c_lflag) & (ICANON | EXTPROC)) {
bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE);
ldata->line_start = ldata->read_tail;
if (!L_ICANON(tty) || !read_cnt(ldata)) {
@@ -2427,7 +2427,7 @@ static int n_tty_ioctl(struct tty_struct *tty, struct file *file,
return put_user(tty_chars_in_buffer(tty), (int __user *) arg);
case TIOCINQ:
down_write(&tty->termios_rwsem);
- if (L_ICANON(tty))
+ if (L_ICANON(tty) && !L_EXTPROC(tty))
retval = inq_canon(ldata);
else
retval = read_cnt(ldata);
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index f8eba1c5412f..677fa99b7747 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -446,7 +446,7 @@ EXPORT_SYMBOL_GPL(tty_prepare_flip_string);
* Callers other than flush_to_ldisc() need to exclude the kworker
* from concurrent use of the line discipline, see paste_selection().
*
- * Returns the number of bytes not processed
+ * Returns the number of bytes processed
*/
int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p,
char *f, int count)
diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c
index bb626120296f..53f3bf459dd1 100644
--- a/drivers/usb/chipidea/ci_hdrc_msm.c
+++ b/drivers/usb/chipidea/ci_hdrc_msm.c
@@ -251,7 +251,7 @@ static int ci_hdrc_msm_probe(struct platform_device *pdev)
if (ret)
goto err_mux;
- ulpi_node = of_find_node_by_name(of_node_get(pdev->dev.of_node), "ulpi");
+ ulpi_node = of_get_child_by_name(pdev->dev.of_node, "ulpi");
if (ulpi_node) {
phy_node = of_get_next_available_child(ulpi_node, NULL);
ci->hsic = of_device_is_compatible(phy_node, "qcom,usb-hsic-phy");
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 843ef46d2537..9e3355b97396 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -1007,7 +1007,7 @@ int usb_get_bos_descriptor(struct usb_device *dev)
case USB_SSP_CAP_TYPE:
ssp_cap = (struct usb_ssp_cap_descriptor *)buffer;
ssac = (le32_to_cpu(ssp_cap->bmAttributes) &
- USB_SSP_SUBLINK_SPEED_ATTRIBS) + 1;
+ USB_SSP_SUBLINK_SPEED_ATTRIBS);
if (length >= USB_DT_USB_SSP_CAP_SIZE(ssac))
dev->bos->ssp_cap = ssp_cap;
break;
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 50010282c010..c05c4f877750 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -57,10 +57,11 @@ static const struct usb_device_id usb_quirk_list[] = {
/* Microsoft LifeCam-VX700 v2.0 */
{ USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },
- /* Logitech HD Pro Webcams C920, C920-C and C930e */
+ /* Logitech HD Pro Webcams C920, C920-C, C925e and C930e */
{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
{ USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT },
{ USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
+ { USB_DEVICE(0x046d, 0x085b), .driver_info = USB_QUIRK_DELAY_INIT },
/* Logitech ConferenceCam CC3000e */
{ USB_DEVICE(0x046d, 0x0847), .driver_info = USB_QUIRK_DELAY_INIT },
@@ -154,6 +155,9 @@ static const struct usb_device_id usb_quirk_list[] = {
/* Genesys Logic hub, internally used by KY-688 USB 3.1 Type-C Hub */
{ USB_DEVICE(0x05e3, 0x0612), .driver_info = USB_QUIRK_NO_LPM },
+ /* ELSA MicroLink 56K */
+ { USB_DEVICE(0x05cc, 0x2267), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Genesys Logic hub, internally used by Moshi USB to Ethernet Adapter */
{ USB_DEVICE(0x05e3, 0x0616), .driver_info = USB_QUIRK_NO_LPM },
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 76f392954733..abb8f19ae40f 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -189,6 +189,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
xhci->quirks |= XHCI_TRUST_TX_LENGTH;
xhci->quirks |= XHCI_BROKEN_STREAMS;
}
+ if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
+ pdev->device == 0x0014)
+ xhci->quirks |= XHCI_TRUST_TX_LENGTH;
if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
pdev->device == 0x0015)
xhci->quirks |= XHCI_RESET_ON_RESUME;
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 49d1b2d4606d..d038e543c246 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1017,6 +1017,7 @@ static const struct usb_device_id id_table_combined[] = {
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
{ USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_BT_USB_PID) },
{ USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_WL_USB_PID) },
+ { USB_DEVICE(AIRBUS_DS_VID, AIRBUS_DS_P8GR) },
{ } /* Terminating entry */
};
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 4faa09fe308c..8b4ecd2bd297 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -914,6 +914,12 @@
#define ICPDAS_I7561U_PID 0x0104
#define ICPDAS_I7563U_PID 0x0105
+/*
+ * Airbus Defence and Space
+ */
+#define AIRBUS_DS_VID 0x1e8e /* Vendor ID */
+#define AIRBUS_DS_P8GR 0x6001 /* Tetra P8GR */
+
/*
* RT Systems programming cables for various ham radios
*/
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 54e316b1892d..a9400458ccea 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -236,6 +236,8 @@ static void option_instat_callback(struct urb *urb);
/* These Quectel products use Qualcomm's vendor ID */
#define QUECTEL_PRODUCT_UC20 0x9003
#define QUECTEL_PRODUCT_UC15 0x9090
+/* These Yuga products use Qualcomm's vendor ID */
+#define YUGA_PRODUCT_CLM920_NC5 0x9625
#define QUECTEL_VENDOR_ID 0x2c7c
/* These Quectel products use Quectel's vendor ID */
@@ -283,6 +285,7 @@ static void option_instat_callback(struct urb *urb);
#define TELIT_PRODUCT_LE922_USBCFG3 0x1043
#define TELIT_PRODUCT_LE922_USBCFG5 0x1045
#define TELIT_PRODUCT_ME910 0x1100
+#define TELIT_PRODUCT_ME910_DUAL_MODEM 0x1101
#define TELIT_PRODUCT_LE920 0x1200
#define TELIT_PRODUCT_LE910 0x1201
#define TELIT_PRODUCT_LE910_USBCFG4 0x1206
@@ -648,6 +651,11 @@ static const struct option_blacklist_info telit_me910_blacklist = {
.reserved = BIT(1) | BIT(3),
};
+static const struct option_blacklist_info telit_me910_dual_modem_blacklist = {
+ .sendsetup = BIT(0),
+ .reserved = BIT(3),
+};
+
static const struct option_blacklist_info telit_le910_blacklist = {
.sendsetup = BIT(0),
.reserved = BIT(1) | BIT(2),
@@ -677,6 +685,10 @@ static const struct option_blacklist_info cinterion_rmnet2_blacklist = {
.reserved = BIT(4) | BIT(5),
};
+static const struct option_blacklist_info yuga_clm920_nc5_blacklist = {
+ .reserved = BIT(1) | BIT(4),
+};
+
static const struct usb_device_id option_ids[] = {
{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) },
{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) },
@@ -1181,6 +1193,9 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)},
{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+ /* Yuga products use Qualcomm vendor ID */
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, YUGA_PRODUCT_CLM920_NC5),
+ .driver_info = (kernel_ulong_t)&yuga_clm920_nc5_blacklist },
/* Quectel products using Quectel vendor ID */
{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
@@ -1247,6 +1262,8 @@ static const struct usb_device_id option_ids[] = {
.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
.driver_info = (kernel_ulong_t)&telit_me910_blacklist },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
+ .driver_info = (kernel_ulong_t)&telit_me910_dual_modem_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
.driver_info = (kernel_ulong_t)&telit_le910_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4),
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 9f9d3a904464..55a8fb25ce2b 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -166,6 +166,8 @@ static const struct usb_device_id id_table[] = {
{DEVICE_SWI(0x1199, 0x9079)}, /* Sierra Wireless EM74xx */
{DEVICE_SWI(0x1199, 0x907a)}, /* Sierra Wireless EM74xx QDL */
{DEVICE_SWI(0x1199, 0x907b)}, /* Sierra Wireless EM74xx */
+ {DEVICE_SWI(0x1199, 0x9090)}, /* Sierra Wireless EM7565 QDL */
+ {DEVICE_SWI(0x1199, 0x9091)}, /* Sierra Wireless EM7565 */
{DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
{DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
{DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
@@ -346,6 +348,7 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id)
break;
case 2:
dev_dbg(dev, "NMEA GPS interface found\n");
+ sendsetup = true;
break;
case 3:
dev_dbg(dev, "Modem port found\n");
diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c
index c653ce533430..720408d39f11 100644
--- a/drivers/usb/usbip/stub_dev.c
+++ b/drivers/usb/usbip/stub_dev.c
@@ -163,8 +163,7 @@ static void stub_shutdown_connection(struct usbip_device *ud)
* step 1?
*/
if (ud->tcp_socket) {
- dev_dbg(&sdev->udev->dev, "shutdown tcp_socket %p\n",
- ud->tcp_socket);
+ dev_dbg(&sdev->udev->dev, "shutdown sockfd %d\n", ud->sockfd);
kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
}
diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c
index 7170404e8979..6968c906fa29 100644
--- a/drivers/usb/usbip/stub_main.c
+++ b/drivers/usb/usbip/stub_main.c
@@ -251,11 +251,12 @@ void stub_device_cleanup_urbs(struct stub_device *sdev)
struct stub_priv *priv;
struct urb *urb;
- dev_dbg(&sdev->udev->dev, "free sdev %p\n", sdev);
+ dev_dbg(&sdev->udev->dev, "Stub device cleaning up urbs\n");
while ((priv = stub_priv_pop(sdev))) {
urb = priv->urb;
- dev_dbg(&sdev->udev->dev, "free urb %p\n", urb);
+ dev_dbg(&sdev->udev->dev, "free urb seqnum %lu\n",
+ priv->seqnum);
usb_kill_urb(urb);
kmem_cache_free(stub_priv_cache, priv);
diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c
index 283a9be77a22..5b807185f79e 100644
--- a/drivers/usb/usbip/stub_rx.c
+++ b/drivers/usb/usbip/stub_rx.c
@@ -225,9 +225,6 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev,
if (priv->seqnum != pdu->u.cmd_unlink.seqnum)
continue;
- dev_info(&priv->urb->dev->dev, "unlink urb %p\n",
- priv->urb);
-
/*
* This matched urb is not completed yet (i.e., be in
* flight in usb hcd hardware/driver). Now we are
@@ -266,8 +263,8 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev,
ret = usb_unlink_urb(priv->urb);
if (ret != -EINPROGRESS)
dev_err(&priv->urb->dev->dev,
- "failed to unlink a urb %p, ret %d\n",
- priv->urb, ret);
+ "failed to unlink a urb # %lu, ret %d\n",
+ priv->seqnum, ret);
return 0;
}
diff --git a/drivers/usb/usbip/stub_tx.c b/drivers/usb/usbip/stub_tx.c
index 87ff94be4235..96aa375b80d9 100644
--- a/drivers/usb/usbip/stub_tx.c
+++ b/drivers/usb/usbip/stub_tx.c
@@ -102,7 +102,7 @@ void stub_complete(struct urb *urb)
/* link a urb to the queue of tx. */
spin_lock_irqsave(&sdev->priv_lock, flags);
if (sdev->ud.tcp_socket == NULL) {
- usbip_dbg_stub_tx("ignore urb for closed connection %p", urb);
+ usbip_dbg_stub_tx("ignore urb for closed connection\n");
/* It will be freed in stub_device_cleanup_urbs(). */
} else if (priv->unlinking) {
stub_enqueue_ret_unlink(sdev, priv->seqnum, urb->status);
@@ -204,8 +204,8 @@ static int stub_send_ret_submit(struct stub_device *sdev)
/* 1. setup usbip_header */
setup_ret_submit_pdu(&pdu_header, urb);
- usbip_dbg_stub_tx("setup txdata seqnum: %d urb: %p\n",
- pdu_header.base.seqnum, urb);
+ usbip_dbg_stub_tx("setup txdata seqnum: %d\n",
+ pdu_header.base.seqnum);
usbip_header_correct_endian(&pdu_header, 1);
iov[iovnum].iov_base = &pdu_header;
diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c
index 2281f3562870..17b599b923f3 100644
--- a/drivers/usb/usbip/usbip_common.c
+++ b/drivers/usb/usbip/usbip_common.c
@@ -331,26 +331,20 @@ int usbip_recv(struct socket *sock, void *buf, int size)
struct msghdr msg = {.msg_flags = MSG_NOSIGNAL};
int total = 0;
+ if (!sock || !buf || !size)
+ return -EINVAL;
+
iov_iter_kvec(&msg.msg_iter, READ|ITER_KVEC, &iov, 1, size);
usbip_dbg_xmit("enter\n");
- if (!sock || !buf || !size) {
- pr_err("invalid arg, sock %p buff %p size %d\n", sock, buf,
- size);
- return -EINVAL;
- }
-
do {
- int sz = msg_data_left(&msg);
+ msg_data_left(&msg);
sock->sk->sk_allocation = GFP_NOIO;
result = sock_recvmsg(sock, &msg, MSG_WAITALL);
- if (result <= 0) {
- pr_debug("receive sock %p buf %p size %u ret %d total %d\n",
- sock, buf + total, sz, result, total);
+ if (result <= 0)
goto err;
- }
total += result;
} while (msg_data_left(&msg));
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index 1f0cf81cc145..692cfdef667e 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -670,9 +670,6 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
struct vhci_device *vdev;
unsigned long flags;
- usbip_dbg_vhci_hc("enter, usb_hcd %p urb %p mem_flags %d\n",
- hcd, urb, mem_flags);
-
if (portnum > VHCI_HC_PORTS) {
pr_err("invalid port number %d\n", portnum);
return -ENODEV;
@@ -836,8 +833,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
struct vhci_device *vdev;
unsigned long flags;
- pr_info("dequeue a urb %p\n", urb);
-
spin_lock_irqsave(&vhci->lock, flags);
priv = urb->hcpriv;
@@ -865,7 +860,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
/* tcp connection is closed */
spin_lock(&vdev->priv_lock);
- pr_info("device %p seems to be disconnected\n", vdev);
list_del(&priv->list);
kfree(priv);
urb->hcpriv = NULL;
@@ -877,8 +871,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
* vhci_rx will receive RET_UNLINK and give back the URB.
* Otherwise, we give back it here.
*/
- pr_info("gives back urb %p\n", urb);
-
usb_hcd_unlink_urb_from_ep(hcd, urb);
spin_unlock_irqrestore(&vhci->lock, flags);
@@ -906,8 +898,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
unlink->unlink_seqnum = priv->seqnum;
- pr_info("device %p seems to be still connected\n", vdev);
-
/* send cmd_unlink and try to cancel the pending URB in the
* peer */
list_add_tail(&unlink->list, &vdev->unlink_tx);
@@ -989,7 +979,7 @@ static void vhci_shutdown_connection(struct usbip_device *ud)
/* need this? see stub_dev.c */
if (ud->tcp_socket) {
- pr_debug("shutdown tcp_socket %p\n", ud->tcp_socket);
+ pr_debug("shutdown tcp_socket %d\n", ud->sockfd);
kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
}
diff --git a/drivers/usb/usbip/vhci_rx.c b/drivers/usb/usbip/vhci_rx.c
index ef2f2d5ca6b2..1343037d00f9 100644
--- a/drivers/usb/usbip/vhci_rx.c
+++ b/drivers/usb/usbip/vhci_rx.c
@@ -37,24 +37,23 @@ struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, __u32 seqnum)
urb = priv->urb;
status = urb->status;
- usbip_dbg_vhci_rx("find urb %p vurb %p seqnum %u\n",
- urb, priv, seqnum);
+ usbip_dbg_vhci_rx("find urb seqnum %u\n", seqnum);
switch (status) {
case -ENOENT:
/* fall through */
case -ECONNRESET:
- dev_info(&urb->dev->dev,
- "urb %p was unlinked %ssynchronuously.\n", urb,
- status == -ENOENT ? "" : "a");
+ dev_dbg(&urb->dev->dev,
+ "urb seq# %u was unlinked %ssynchronuously\n",
+ seqnum, status == -ENOENT ? "" : "a");
break;
case -EINPROGRESS:
/* no info output */
break;
default:
- dev_info(&urb->dev->dev,
- "urb %p may be in a error, status %d\n", urb,
- status);
+ dev_dbg(&urb->dev->dev,
+ "urb seq# %u may be in a error, status %d\n",
+ seqnum, status);
}
list_del(&priv->list);
@@ -81,8 +80,8 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
spin_unlock_irqrestore(&vdev->priv_lock, flags);
if (!urb) {
- pr_err("cannot find a urb of seqnum %u\n", pdu->base.seqnum);
- pr_info("max seqnum %d\n",
+ pr_err("cannot find a urb of seqnum %u max seqnum %d\n",
+ pdu->base.seqnum,
atomic_read(&vhci_hcd->seqnum));
usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
return;
@@ -105,7 +104,7 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
if (usbip_dbg_flag_vhci_rx)
usbip_dump_urb(urb);
- usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
+ usbip_dbg_vhci_rx("now giveback urb %u\n", pdu->base.seqnum);
spin_lock_irqsave(&vhci->lock, flags);
usb_hcd_unlink_urb_from_ep(vhci_hcd_to_hcd(vhci_hcd), urb);
@@ -172,7 +171,7 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev,
pr_info("the urb (seqnum %d) was already given back\n",
pdu->base.seqnum);
} else {
- usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
+ usbip_dbg_vhci_rx("now giveback urb %d\n", pdu->base.seqnum);
/* If unlink is successful, status is -ECONNRESET */
urb->status = pdu->u.ret_unlink.status;
diff --git a/drivers/usb/usbip/vhci_tx.c b/drivers/usb/usbip/vhci_tx.c
index 3e7878fe2fd4..a9a663a578b6 100644
--- a/drivers/usb/usbip/vhci_tx.c
+++ b/drivers/usb/usbip/vhci_tx.c
@@ -83,7 +83,8 @@ static int vhci_send_cmd_submit(struct vhci_device *vdev)
memset(&msg, 0, sizeof(msg));
memset(&iov, 0, sizeof(iov));
- usbip_dbg_vhci_tx("setup txdata urb %p\n", urb);
+ usbip_dbg_vhci_tx("setup txdata urb seqnum %lu\n",
+ priv->seqnum);
/* 1. setup usbip_header */
setup_cmd_submit_pdu(&pdu_header, urb);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index fd47bd96b5d3..6362e3606aa5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -241,14 +241,24 @@ struct request {
struct request *next_rq;
};
+static inline bool blk_op_is_scsi(unsigned int op)
+{
+ return op == REQ_OP_SCSI_IN || op == REQ_OP_SCSI_OUT;
+}
+
+static inline bool blk_op_is_private(unsigned int op)
+{
+ return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
+}
+
static inline bool blk_rq_is_scsi(struct request *rq)
{
- return req_op(rq) == REQ_OP_SCSI_IN || req_op(rq) == REQ_OP_SCSI_OUT;
+ return blk_op_is_scsi(req_op(rq));
}
static inline bool blk_rq_is_private(struct request *rq)
{
- return req_op(rq) == REQ_OP_DRV_IN || req_op(rq) == REQ_OP_DRV_OUT;
+ return blk_op_is_private(req_op(rq));
}
static inline bool blk_rq_is_passthrough(struct request *rq)
@@ -256,6 +266,13 @@ static inline bool blk_rq_is_passthrough(struct request *rq)
return blk_rq_is_scsi(rq) || blk_rq_is_private(rq);
}
+static inline bool bio_is_passthrough(struct bio *bio)
+{
+ unsigned op = bio_op(bio);
+
+ return blk_op_is_scsi(op) || blk_op_is_private(op);
+}
+
static inline unsigned short req_get_ioprio(struct request *req)
{
return req->ioprio;
@@ -952,7 +969,7 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
extern void blk_rq_unprep_clone(struct request *rq);
extern blk_status_t blk_insert_cloned_request(struct request_queue *q,
struct request *rq);
-extern int blk_rq_append_bio(struct request *rq, struct bio *bio);
+extern int blk_rq_append_bio(struct request *rq, struct bio **bio);
extern void blk_delay_queue(struct request_queue *, unsigned long);
extern void blk_queue_split(struct request_queue *, struct bio **);
extern void blk_recount_segments(struct request_queue *, struct bio *);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 2477a5cb5bd5..fb83dee528a1 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -86,7 +86,7 @@ enum cpuhp_state {
CPUHP_MM_ZSWP_POOL_PREPARE,
CPUHP_KVM_PPC_BOOK3S_PREPARE,
CPUHP_ZCOMP_PREPARE,
- CPUHP_TIMERS_DEAD,
+ CPUHP_TIMERS_PREPARE,
CPUHP_MIPS_SOC_PREPARE,
CPUHP_BP_PREPARE_DYN,
CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20,
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index ea04ca024f0d..067a6fa675ed 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -272,7 +272,8 @@ struct ipv6_pinfo {
* 100: prefer care-of address
*/
dontfrag:1,
- autoflowlabel:1;
+ autoflowlabel:1,
+ autoflowlabel_set:1;
__u8 min_hopcount;
__u8 tclass;
__be32 rcv_flowinfo;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 401c8972cc3a..8b3d0103c03a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -546,6 +546,7 @@ struct mlx5_core_sriov {
};
struct mlx5_irq_info {
+ cpumask_var_t mask;
char name[MLX5_MAX_IRQ_NAME];
};
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 69772347f866..c8091f06eaa4 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -147,7 +147,7 @@ enum {
MLX5_CMD_OP_ALLOC_Q_COUNTER = 0x771,
MLX5_CMD_OP_DEALLOC_Q_COUNTER = 0x772,
MLX5_CMD_OP_QUERY_Q_COUNTER = 0x773,
- MLX5_CMD_OP_SET_RATE_LIMIT = 0x780,
+ MLX5_CMD_OP_SET_PP_RATE_LIMIT = 0x780,
MLX5_CMD_OP_QUERY_RATE_LIMIT = 0x781,
MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT = 0x782,
MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT = 0x783,
@@ -7233,7 +7233,7 @@ struct mlx5_ifc_add_vxlan_udp_dport_in_bits {
u8 vxlan_udp_port[0x10];
};
-struct mlx5_ifc_set_rate_limit_out_bits {
+struct mlx5_ifc_set_pp_rate_limit_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -7242,7 +7242,7 @@ struct mlx5_ifc_set_rate_limit_out_bits {
u8 reserved_at_40[0x40];
};
-struct mlx5_ifc_set_rate_limit_in_bits {
+struct mlx5_ifc_set_pp_rate_limit_in_bits {
u8 opcode[0x10];
u8 reserved_at_10[0x10];
@@ -7255,6 +7255,8 @@ struct mlx5_ifc_set_rate_limit_in_bits {
u8 reserved_at_60[0x20];
u8 rate_limit[0x20];
+
+ u8 reserved_at_a0[0x160];
};
struct mlx5_ifc_access_register_out_bits {
diff --git a/include/linux/pti.h b/include/linux/pti.h
new file mode 100644
index 000000000000..0174883a935a
--- /dev/null
+++ b/include/linux/pti.h
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _INCLUDE_PTI_H
+#define _INCLUDE_PTI_H
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#include <asm/pti.h>
+#else
+static inline void pti_init(void) { }
+#endif
+
+#endif
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 37b4bb2545b3..6866df4f31b5 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -101,12 +101,18 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r)
/* Note: callers invoking this in a loop must use a compiler barrier,
* for example cpu_relax(). Callers must hold producer_lock.
+ * Callers are responsible for making sure pointer that is being queued
+ * points to a valid data.
*/
static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
{
if (unlikely(!r->size) || r->queue[r->producer])
return -ENOSPC;
+ /* Make sure the pointer we are storing points to a valid data. */
+ /* Pairs with smp_read_barrier_depends in __ptr_ring_consume. */
+ smp_wmb();
+
r->queue[r->producer++] = ptr;
if (unlikely(r->producer >= r->size))
r->producer = 0;
@@ -275,6 +281,9 @@ static inline void *__ptr_ring_consume(struct ptr_ring *r)
if (ptr)
__ptr_ring_discard_one(r);
+ /* Make sure anyone accessing data through the pointer is up to date. */
+ /* Pairs with smp_wmb in __ptr_ring_produce. */
+ smp_read_barrier_depends();
return ptr;
}
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4aa40ef02d32..e8418fc77a43 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -214,7 +214,8 @@ struct tcp_sock {
u8 chrono_type:2, /* current chronograph type */
rate_app_limited:1, /* rate_{delivered,interval_us} limited? */
fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
- unused:4;
+ is_sack_reneg:1, /* in recovery from loss with SACK reneg? */
+ unused:3;
u8 nonagle : 4,/* Disable Nagle algorithm? */
thin_lto : 1,/* Use linear timeouts for thin streams */
unused1 : 1,
diff --git a/include/linux/tick.h b/include/linux/tick.h
index cf413b344ddb..5cdac11dd317 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -119,6 +119,7 @@ extern void tick_nohz_idle_exit(void);
extern void tick_nohz_irq_exit(void);
extern ktime_t tick_nohz_get_sleep_length(void);
extern unsigned long tick_nohz_get_idle_calls(void);
+extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu);
extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
#else /* !CONFIG_NO_HZ_COMMON */
diff --git a/include/linux/timer.h b/include/linux/timer.h
index ac66f29c6916..e0ea1fe87572 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -246,9 +246,11 @@ unsigned long round_jiffies_up(unsigned long j);
unsigned long round_jiffies_up_relative(unsigned long j);
#ifdef CONFIG_HOTPLUG_CPU
+int timers_prepare_cpu(unsigned int cpu);
int timers_dead_cpu(unsigned int cpu);
#else
-#define timers_dead_cpu NULL
+#define timers_prepare_cpu NULL
+#define timers_dead_cpu NULL
#endif
#endif
diff --git a/include/net/ip.h b/include/net/ip.h
index 9896f46cbbf1..af8addbaa3c1 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -34,6 +34,7 @@
#include <net/flow_dissector.h>
#define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */
+#define IPV4_MIN_MTU 68 /* RFC 791 */
struct sock;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6ced69940f5c..0a13574134b8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1085,7 +1085,7 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb);
void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
struct rate_sample *rs);
void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
- struct rate_sample *rs);
+ bool is_sack_reneg, struct rate_sample *rs);
void tcp_rate_check_app_limited(struct sock *sk);
/* These functions determine how the current flow behaves in respect of SACK
diff --git a/init/main.c b/init/main.c
index 8a390f60ec81..b32ec72cdf3d 100644
--- a/init/main.c
+++ b/init/main.c
@@ -75,6 +75,7 @@
#include <linux/slab.h>
#include <linux/perf_event.h>
#include <linux/ptrace.h>
+#include <linux/pti.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/sched_clock.h>
@@ -506,6 +507,8 @@ static void __init mm_init(void)
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. */
+ pti_init();
}
asmlinkage __visible void __init start_kernel(void)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 7891aecc6aec..f21bfa3172d8 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1277,9 +1277,9 @@ static struct cpuhp_step cpuhp_bp_states[] = {
* before blk_mq_queue_reinit_notify() from notify_dead(),
* otherwise a RCU stall occurs.
*/
- [CPUHP_TIMERS_DEAD] = {
+ [CPUHP_TIMERS_PREPARE] = {
.name = "timers:dead",
- .startup.single = NULL,
+ .startup.single = timers_prepare_cpu,
.teardown.single = timers_dead_cpu,
},
/* Kicks the plugged cpu into life */
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 2f52ec0f1539..d6717a3331a1 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -244,7 +244,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
#ifdef CONFIG_NO_HZ_COMMON
static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
{
- unsigned long idle_calls = tick_nohz_get_idle_calls();
+ unsigned long idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu);
bool ret = idle_calls == sg_cpu->saved_idle_calls;
sg_cpu->saved_idle_calls = idle_calls;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index c7a899c5ce64..dfa4a117fee3 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -674,6 +674,11 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
ts->next_tick = 0;
}
+static inline bool local_timer_softirq_pending(void)
+{
+ return local_softirq_pending() & TIMER_SOFTIRQ;
+}
+
static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
ktime_t now, int cpu)
{
@@ -690,8 +695,18 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
} while (read_seqretry(&jiffies_lock, seq));
ts->last_jiffies = basejiff;
- if (rcu_needs_cpu(basemono, &next_rcu) ||
- arch_needs_cpu() || irq_work_needs_cpu()) {
+ /*
+ * Keep the periodic tick, when RCU, architecture or irq_work
+ * requests it.
+ * Aside of that check whether the local timer softirq is
+ * pending. If so its a bad idea to call get_next_timer_interrupt()
+ * because there is an already expired timer, so it will request
+ * immeditate expiry, which rearms the hardware timer with a
+ * minimal delta which brings us back to this place
+ * immediately. Lather, rinse and repeat...
+ */
+ if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() ||
+ irq_work_needs_cpu() || local_timer_softirq_pending()) {
next_tick = basemono + TICK_NSEC;
} else {
/*
@@ -1009,6 +1024,19 @@ ktime_t tick_nohz_get_sleep_length(void)
return ts->sleep_length;
}
+/**
+ * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value
+ * for a particular CPU.
+ *
+ * Called from the schedutil frequency scaling governor in scheduler context.
+ */
+unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
+{
+ struct tick_sched *ts = tick_get_tick_sched(cpu);
+
+ return ts->idle_calls;
+}
+
/**
* tick_nohz_get_idle_calls - return the current idle calls counter value
*
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index f2674a056c26..73e3cdbc61f1 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -814,11 +814,10 @@ static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu)
struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu);
/*
- * If the timer is deferrable and nohz is active then we need to use
- * the deferrable base.
+ * If the timer is deferrable and NO_HZ_COMMON is set then we need
+ * to use the deferrable base.
*/
- if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
- (tflags & TIMER_DEFERRABLE))
+ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu);
return base;
}
@@ -828,11 +827,10 @@ static inline struct timer_base *get_timer_this_cpu_base(u32 tflags)
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
/*
- * If the timer is deferrable and nohz is active then we need to use
- * the deferrable base.
+ * If the timer is deferrable and NO_HZ_COMMON is set then we need
+ * to use the deferrable base.
*/
- if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
- (tflags & TIMER_DEFERRABLE))
+ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
base = this_cpu_ptr(&timer_bases[BASE_DEF]);
return base;
}
@@ -984,8 +982,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
if (!ret && pending_only)
goto out_unlock;
- debug_activate(timer, expires);
-
new_base = get_target_base(base, timer->flags);
if (base != new_base) {
@@ -1009,6 +1005,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
}
}
+ debug_activate(timer, expires);
+
timer->expires = expires;
/*
* If 'idx' was calculated above and the base time did not advance
@@ -1644,7 +1642,7 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
base->must_forward_clk = false;
__run_timers(base);
- if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)
+ if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
}
@@ -1803,6 +1801,21 @@ static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *h
}
}
+int timers_prepare_cpu(unsigned int cpu)
+{
+ struct timer_base *base;
+ int b;
+
+ for (b = 0; b < NR_BASES; b++) {
+ base = per_cpu_ptr(&timer_bases[b], cpu);
+ base->clk = jiffies;
+ base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
+ base->is_idle = false;
+ base->must_forward_clk = true;
+ }
+ return 0;
+}
+
int timers_dead_cpu(unsigned int cpu)
{
struct timer_base *old_base;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 81279c6602ff..0476a9372014 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -281,6 +281,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
/* Missed count stored at end */
#define RB_MISSED_STORED (1 << 30)
+#define RB_MISSED_FLAGS (RB_MISSED_EVENTS|RB_MISSED_STORED)
+
struct buffer_data_page {
u64 time_stamp; /* page time stamp */
local_t commit; /* write committed index */
@@ -332,7 +334,9 @@ static void rb_init_page(struct buffer_data_page *bpage)
*/
size_t ring_buffer_page_len(void *page)
{
- return local_read(&((struct buffer_data_page *)page)->commit)
+ struct buffer_data_page *bpage = page;
+
+ return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS)
+ BUF_PAGE_HDR_SIZE;
}
@@ -4439,8 +4443,13 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
{
struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
struct buffer_data_page *bpage = data;
+ struct page *page = virt_to_page(bpage);
unsigned long flags;
+ /* If the page is still in use someplace else, we can't reuse it */
+ if (page_ref_count(page) > 1)
+ goto out;
+
local_irq_save(flags);
arch_spin_lock(&cpu_buffer->lock);
@@ -4452,6 +4461,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
arch_spin_unlock(&cpu_buffer->lock);
local_irq_restore(flags);
+ out:
free_page((unsigned long)bpage);
}
EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 80de14973b42..76bcc80b893e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6769,7 +6769,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
.spd_release = buffer_spd_release,
};
struct buffer_ref *ref;
- int entries, size, i;
+ int entries, i;
ssize_t ret = 0;
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -6823,14 +6823,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
break;
}
- /*
- * zero out any left over data, this is going to
- * user land.
- */
- size = ring_buffer_page_len(ref->page);
- if (size < PAGE_SIZE)
- memset(ref->page + size, 0, PAGE_SIZE - size);
-
page = virt_to_page(ref->page);
spd.pages[i] = page;
@@ -7588,6 +7580,7 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
buf->data = alloc_percpu(struct trace_array_cpu);
if (!buf->data) {
ring_buffer_free(buf->buffer);
+ buf->buffer = NULL;
return -ENOMEM;
}
@@ -7611,7 +7604,9 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
allocate_snapshot ? size : 1);
if (WARN_ON(ret)) {
ring_buffer_free(tr->trace_buffer.buffer);
+ tr->trace_buffer.buffer = NULL;
free_percpu(tr->trace_buffer.data);
+ tr->trace_buffer.data = NULL;
return -ENOMEM;
}
tr->allocated_snapshot = allocate_snapshot;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index de2152730809..08190db0a2dc 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1223,19 +1223,20 @@ static int br_dev_newlink(struct net *src_net, struct net_device *dev,
struct net_bridge *br = netdev_priv(dev);
int err;
+ err = register_netdevice(dev);
+ if (err)
+ return err;
+
if (tb[IFLA_ADDRESS]) {
spin_lock_bh(&br->lock);
br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
spin_unlock_bh(&br->lock);
}
- err = register_netdevice(dev);
- if (err)
- return err;
-
err = br_changelink(dev, tb, data, extack);
if (err)
- unregister_netdevice(dev);
+ br_dev_delete(dev, NULL);
+
return err;
}
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 6cfdc7c84c48..0dd6359e5924 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -266,7 +266,7 @@ struct net *get_net_ns_by_id(struct net *net, int id)
spin_lock_bh(&net->nsid_lock);
peer = idr_find(&net->netns_ids, id);
if (peer)
- get_net(peer);
+ peer = maybe_get_net(peer);
spin_unlock_bh(&net->nsid_lock);
rcu_read_unlock();
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e140ba49b30a..15fa5baa8fae 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1181,12 +1181,12 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
int i, new_frags;
u32 d_off;
- if (!num_frags)
- return 0;
-
if (skb_shared(skb) || skb_unclone(skb, gfp_mask))
return -EINVAL;
+ if (!num_frags)
+ goto release;
+
new_frags = (__skb_pagelen(skb) + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < new_frags; i++) {
page = alloc_page(gfp_mask);
@@ -1242,6 +1242,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
__skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off);
skb_shinfo(skb)->nr_frags = new_frags;
+release:
skb_zcopy_clear(skb, false);
return 0;
}
@@ -3657,8 +3658,6 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags &
SKBTX_SHARED_FRAG;
- if (skb_zerocopy_clone(nskb, head_skb, GFP_ATOMIC))
- goto err;
while (pos < offset + len) {
if (i >= nfrags) {
@@ -3684,6 +3683,8 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC)))
goto err;
+ if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
+ goto err;
*nskb_frag = *frag;
__skb_frag_ref(nskb_frag);
@@ -4296,7 +4297,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
struct sock *sk = skb->sk;
if (!skb_may_tx_timestamp(sk, false))
- return;
+ goto err;
/* Take a reference to prevent skb_orphan() from freeing the socket,
* but only if the socket refcount is not zero.
@@ -4305,7 +4306,11 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
*skb_hwtstamps(skb) = *hwtstamps;
__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false);
sock_put(sk);
+ return;
}
+
+err:
+ kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index d7adc0616599..bffa88ecc534 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1420,7 +1420,7 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
static bool inetdev_valid_mtu(unsigned int mtu)
{
- return mtu >= 68;
+ return mtu >= IPV4_MIN_MTU;
}
static void inetdev_send_gratuitous_arp(struct net_device *dev,
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 37819ab4cc74..d72874150905 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1274,14 +1274,19 @@ static int __net_init ip_fib_net_init(struct net *net)
static void ip_fib_net_exit(struct net *net)
{
- unsigned int i;
+ int i;
rtnl_lock();
#ifdef CONFIG_IP_MULTIPLE_TABLES
RCU_INIT_POINTER(net->ipv4.fib_main, NULL);
RCU_INIT_POINTER(net->ipv4.fib_default, NULL);
#endif
- for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+ /* Destroy the tables in reverse order to guarantee that the
+ * local table, ID 255, is destroyed before the main table, ID
+ * 254. This is necessary as the local table may contain
+ * references to data contained in the main table.
+ */
+ for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) {
struct hlist_head *head = &net->ipv4.fib_table_hash[i];
struct hlist_node *tmp;
struct fib_table *tb;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 01ed22139ac2..aff3751df950 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -706,7 +706,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
int type = nla_type(nla);
- u32 val;
+ u32 fi_val, val;
if (!type)
continue;
@@ -723,7 +723,11 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
val = nla_get_u32(nla);
}
- if (fi->fib_metrics->metrics[type - 1] != val)
+ fi_val = fi->fib_metrics->metrics[type - 1];
+ if (type == RTAX_FEATURES)
+ fi_val &= ~DST_FEATURE_ECN_CA;
+
+ if (fi_val != val)
return false;
}
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index ab183af0b5b6..c621266e0306 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -89,6 +89,7 @@
#include <linux/rtnetlink.h>
#include <linux/times.h>
#include <linux/pkt_sched.h>
+#include <linux/byteorder/generic.h>
#include <net/net_namespace.h>
#include <net/arp.h>
@@ -321,6 +322,23 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted)
return scount;
}
+/* source address selection per RFC 3376 section 4.2.13 */
+static __be32 igmpv3_get_srcaddr(struct net_device *dev,
+ const struct flowi4 *fl4)
+{
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+ if (!in_dev)
+ return htonl(INADDR_ANY);
+
+ for_ifa(in_dev) {
+ if (inet_ifa_match(fl4->saddr, ifa))
+ return fl4->saddr;
+ } endfor_ifa(in_dev);
+
+ return htonl(INADDR_ANY);
+}
+
static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
{
struct sk_buff *skb;
@@ -368,7 +386,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
pip->frag_off = htons(IP_DF);
pip->ttl = 1;
pip->daddr = fl4.daddr;
- pip->saddr = fl4.saddr;
+ pip->saddr = igmpv3_get_srcaddr(dev, &fl4);
pip->protocol = IPPROTO_IGMP;
pip->tot_len = 0; /* filled in later */
ip_select_ident(net, skb, NULL);
@@ -404,16 +422,17 @@ static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel)
}
static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc,
- int type, struct igmpv3_grec **ppgr)
+ int type, struct igmpv3_grec **ppgr, unsigned int mtu)
{
struct net_device *dev = pmc->interface->dev;
struct igmpv3_report *pih;
struct igmpv3_grec *pgr;
- if (!skb)
- skb = igmpv3_newpack(dev, dev->mtu);
- if (!skb)
- return NULL;
+ if (!skb) {
+ skb = igmpv3_newpack(dev, mtu);
+ if (!skb)
+ return NULL;
+ }
pgr = skb_put(skb, sizeof(struct igmpv3_grec));
pgr->grec_type = type;
pgr->grec_auxwords = 0;
@@ -436,12 +455,17 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
struct igmpv3_grec *pgr = NULL;
struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list;
int scount, stotal, first, isquery, truncate;
+ unsigned int mtu;
if (pmc->multiaddr == IGMP_ALL_HOSTS)
return skb;
if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
return skb;
+ mtu = READ_ONCE(dev->mtu);
+ if (mtu < IPV4_MIN_MTU)
+ return skb;
+
isquery = type == IGMPV3_MODE_IS_INCLUDE ||
type == IGMPV3_MODE_IS_EXCLUDE;
truncate = type == IGMPV3_MODE_IS_EXCLUDE ||
@@ -462,7 +486,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
igmpv3_sendpack(skb);
- skb = igmpv3_newpack(dev, dev->mtu);
+ skb = igmpv3_newpack(dev, mtu);
}
}
first = 1;
@@ -498,12 +522,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
pgr->grec_nsrcs = htons(scount);
if (skb)
igmpv3_sendpack(skb);
- skb = igmpv3_newpack(dev, dev->mtu);
+ skb = igmpv3_newpack(dev, mtu);
first = 1;
scount = 0;
}
if (first) {
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
first = 0;
}
if (!skb)
@@ -538,7 +562,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
igmpv3_sendpack(skb);
skb = NULL; /* add_grhead will get a new one */
}
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
}
}
if (pgr)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index e9805ad664ac..4e90082b23a6 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -349,8 +349,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
dev->needed_headroom = t_hlen + hlen;
mtu -= (dev->hard_header_len + t_hlen);
- if (mtu < 68)
- mtu = 68;
+ if (mtu < IPV4_MIN_MTU)
+ mtu = IPV4_MIN_MTU;
return mtu;
}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 33b70bfd1122..125c1eab3eaa 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -513,11 +513,16 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
int err;
struct ip_options_data opt_copy;
struct raw_frag_vec rfv;
+ int hdrincl;
err = -EMSGSIZE;
if (len > 0xFFFF)
goto out;
+ /* hdrincl should be READ_ONCE(inet->hdrincl)
+ * but READ_ONCE() doesn't work with bit fields
+ */
+ hdrincl = inet->hdrincl;
/*
* Check the flags.
*/
@@ -593,7 +598,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
/* Linux does not mangle headers on raw sockets,
* so that IP options + IP_HDRINCL is non-sense.
*/
- if (inet->hdrincl)
+ if (hdrincl)
goto done;
if (ipc.opt->opt.srr) {
if (!daddr)
@@ -615,12 +620,12 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
- inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
- (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
+ (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0, sk->sk_uid);
- if (!inet->hdrincl) {
+ if (!hdrincl) {
rfv.msg = msg;
rfv.hlen = 0;
@@ -645,7 +650,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
goto do_confirm;
back_from_confirm:
- if (inet->hdrincl)
+ if (hdrincl)
err = raw_send_hdrinc(sk, &fl4, msg, len,
&rt, msg->msg_flags, &ipc.sockc);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5091402720ab..a0c72b09cefc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2356,6 +2356,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->snd_cwnd_cnt = 0;
tp->window_clamp = 0;
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
tcp_clear_retrans(tp);
inet_csk_delack_init(sk);
/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 69ee877574d0..8322f26e770e 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -110,7 +110,8 @@ struct bbr {
u32 lt_last_lost; /* LT intvl start: tp->lost */
u32 pacing_gain:10, /* current gain for setting pacing rate */
cwnd_gain:10, /* current gain for setting cwnd */
- full_bw_cnt:3, /* number of rounds without large bw gains */
+ full_bw_reached:1, /* reached full bw in Startup? */
+ full_bw_cnt:2, /* number of rounds without large bw gains */
cycle_idx:3, /* current index in pacing_gain cycle array */
has_seen_rtt:1, /* have we seen an RTT sample yet? */
unused_b:5;
@@ -180,7 +181,7 @@ static bool bbr_full_bw_reached(const struct sock *sk)
{
const struct bbr *bbr = inet_csk_ca(sk);
- return bbr->full_bw_cnt >= bbr_full_bw_cnt;
+ return bbr->full_bw_reached;
}
/* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */
@@ -717,6 +718,7 @@ static void bbr_check_full_bw_reached(struct sock *sk,
return;
}
++bbr->full_bw_cnt;
+ bbr->full_bw_reached = bbr->full_bw_cnt >= bbr_full_bw_cnt;
}
/* If pipe is probably full, drain the queue and then enter steady-state. */
@@ -850,6 +852,7 @@ static void bbr_init(struct sock *sk)
bbr->restore_cwnd = 0;
bbr->round_start = 0;
bbr->idle_restart = 0;
+ bbr->full_bw_reached = 0;
bbr->full_bw = 0;
bbr->full_bw_cnt = 0;
bbr->cycle_mstamp = 0;
@@ -871,6 +874,11 @@ static u32 bbr_sndbuf_expand(struct sock *sk)
*/
static u32 bbr_undo_cwnd(struct sock *sk)
{
+ struct bbr *bbr = inet_csk_ca(sk);
+
+ bbr->full_bw = 0; /* spurious slow-down; reset full pipe detection */
+ bbr->full_bw_cnt = 0;
+ bbr_reset_lt_bw_sampling(sk);
return tcp_sk(sk)->snd_cwnd;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c5447b9f8517..ff48ac654e5a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -521,9 +521,6 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
u32 new_sample = tp->rcv_rtt_est.rtt_us;
long m = sample;
- if (m == 0)
- m = 1;
-
if (new_sample != 0) {
/* If we sample in larger samples in the non-timestamp
* case, we could grossly overestimate the RTT especially
@@ -560,6 +557,8 @@ static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp)
if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq))
return;
delta_us = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcv_rtt_est.time);
+ if (!delta_us)
+ delta_us = 1;
tcp_rcv_rtt_update(tp, delta_us, 1);
new_measure:
@@ -576,8 +575,11 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
(TCP_SKB_CB(skb)->end_seq -
TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) {
u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
- u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
+ u32 delta_us;
+ if (!delta)
+ delta = 1;
+ delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
tcp_rcv_rtt_update(tp, delta_us, 0);
}
}
@@ -1975,6 +1977,8 @@ void tcp_enter_loss(struct sock *sk)
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
tp->sacked_out = 0;
tp->fackets_out = 0;
+ /* Mark SACK reneging until we recover from this loss event. */
+ tp->is_sack_reneg = 1;
}
tcp_clear_all_retrans_hints(tp);
@@ -2428,6 +2432,7 @@ static bool tcp_try_undo_recovery(struct sock *sk)
return true;
}
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
return false;
}
@@ -2459,8 +2464,10 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPSPURIOUSRTOS);
inet_csk(sk)->icsk_retransmits = 0;
- if (frto_undo || tcp_is_sack(tp))
+ if (frto_undo || tcp_is_sack(tp)) {
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
+ }
return true;
}
return false;
@@ -3551,6 +3558,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
struct tcp_sacktag_state sack_state;
struct rate_sample rs = { .prior_delivered = 0 };
u32 prior_snd_una = tp->snd_una;
+ bool is_sack_reneg = tp->is_sack_reneg;
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
bool is_dupack = false;
@@ -3666,7 +3674,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */
lost = tp->lost - lost; /* freshly marked lost */
- tcp_rate_gen(sk, delivered, lost, sack_state.rate);
+ tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
tcp_cong_control(sk, ack, delivered, flag, sack_state.rate);
tcp_xmit_recovery(sk, rexmit);
return 1;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5a5ed4f14678..cab4b935e474 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -844,7 +844,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
req->ts_recent,
0,
- tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
+ tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr,
AF_INET),
inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
ip_hdr(skb)->tos);
diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c
index 3330a370d306..c61240e43923 100644
--- a/net/ipv4/tcp_rate.c
+++ b/net/ipv4/tcp_rate.c
@@ -106,7 +106,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
/* Update the connection delivery information and generate a rate sample. */
void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
- struct rate_sample *rs)
+ bool is_sack_reneg, struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 snd_us, ack_us;
@@ -124,8 +124,12 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
rs->acked_sacked = delivered; /* freshly ACKed or SACKed */
rs->losses = lost; /* freshly marked lost */
- /* Return an invalid sample if no timing information is available. */
- if (!rs->prior_mstamp) {
+ /* Return an invalid sample if no timing information is available or
+ * in recovery from loss with SACK reneging. Rate samples taken during
+ * a SACK reneging event may overestimate bw by including packets that
+ * were SACKed before the reneg.
+ */
+ if (!rs->prior_mstamp || is_sack_reneg) {
rs->delivered = -1;
rs->interval_us = -1;
return;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 655dd8d7f064..e9af1879cd53 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -264,6 +264,7 @@ void tcp_delack_timer_handler(struct sock *sk)
icsk->icsk_ack.pingpong = 0;
icsk->icsk_ack.ato = TCP_ATO_MIN;
}
+ tcp_mstamp_refresh(tcp_sk(sk));
tcp_send_ack(sk);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS);
}
@@ -627,6 +628,7 @@ static void tcp_keepalive_timer (unsigned long data)
goto out;
}
+ tcp_mstamp_refresh(tp);
if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) {
if (tp->linger2 >= 0) {
const int tmo = tcp_fin_time(sk) - TCP_TIMEWAIT_LEN;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2ec39404c449..c5318f5f6a14 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -231,7 +231,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.proxy_ndp = 0,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
- .accept_dad = 1,
+ .accept_dad = 0,
.suppress_frag_ndisc = 1,
.accept_ra_mtu = 1,
.stable_secret = {
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index fe5262fd6aa5..bcbd5f3bf8bd 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -210,7 +210,6 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
np->mcast_hops = IPV6_DEFAULT_MCASTHOPS;
np->mc_loop = 1;
np->pmtudisc = IPV6_PMTUDISC_WANT;
- np->autoflowlabel = ip6_default_np_autolabel(net);
np->repflow = net->ipv6.sysctl.flowlabel_reflect;
sk->sk_ipv6only = net->ipv6.sysctl.bindv6only;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 5d6bee070871..7a2df6646486 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1020,6 +1020,36 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
eth_random_addr(dev->perm_addr);
}
+#define GRE6_FEATURES (NETIF_F_SG | \
+ NETIF_F_FRAGLIST | \
+ NETIF_F_HIGHDMA | \
+ NETIF_F_HW_CSUM)
+
+static void ip6gre_tnl_init_features(struct net_device *dev)
+{
+ struct ip6_tnl *nt = netdev_priv(dev);
+
+ dev->features |= GRE6_FEATURES;
+ dev->hw_features |= GRE6_FEATURES;
+
+ if (!(nt->parms.o_flags & TUNNEL_SEQ)) {
+ /* TCP offload with GRE SEQ is not supported, nor
+ * can we support 2 levels of outer headers requiring
+ * an update.
+ */
+ if (!(nt->parms.o_flags & TUNNEL_CSUM) ||
+ nt->encap.type == TUNNEL_ENCAP_NONE) {
+ dev->features |= NETIF_F_GSO_SOFTWARE;
+ dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+ }
+
+ /* Can use a lockless transmit, unless we generate
+ * output sequences
+ */
+ dev->features |= NETIF_F_LLTX;
+ }
+}
+
static int ip6gre_tunnel_init_common(struct net_device *dev)
{
struct ip6_tnl *tunnel;
@@ -1054,6 +1084,8 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
if (!(tunnel->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
dev->mtu -= 8;
+ ip6gre_tnl_init_features(dev);
+
return 0;
}
@@ -1302,11 +1334,6 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = {
.ndo_get_iflink = ip6_tnl_get_iflink,
};
-#define GRE6_FEATURES (NETIF_F_SG | \
- NETIF_F_FRAGLIST | \
- NETIF_F_HIGHDMA | \
- NETIF_F_HW_CSUM)
-
static void ip6gre_tap_setup(struct net_device *dev)
{
@@ -1386,26 +1413,6 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
nt->net = dev_net(dev);
ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
- dev->features |= GRE6_FEATURES;
- dev->hw_features |= GRE6_FEATURES;
-
- if (!(nt->parms.o_flags & TUNNEL_SEQ)) {
- /* TCP offload with GRE SEQ is not supported, nor
- * can we support 2 levels of outer headers requiring
- * an update.
- */
- if (!(nt->parms.o_flags & TUNNEL_CSUM) ||
- (nt->encap.type == TUNNEL_ENCAP_NONE)) {
- dev->features |= NETIF_F_GSO_SOFTWARE;
- dev->hw_features |= NETIF_F_GSO_SOFTWARE;
- }
-
- /* Can use a lockless transmit, unless we generate
- * output sequences
- */
- dev->features |= NETIF_F_LLTX;
- }
-
err = register_netdevice(dev);
if (err)
goto out;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5110a418cc4d..f7dd51c42314 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -166,6 +166,14 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
!(IP6CB(skb)->flags & IP6SKB_REROUTED));
}
+static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
+{
+ if (!np->autoflowlabel_set)
+ return ip6_default_np_autolabel(net);
+ else
+ return np->autoflowlabel;
+}
+
/*
* xmit an sk_buff (used by TCP, SCTP and DCCP)
* Note : socket lock is not held for SYNACK packets, but might be modified
@@ -230,7 +238,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
hlimit = ip6_dst_hoplimit(dst);
ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
- np->autoflowlabel, fl6));
+ ip6_autoflowlabel(net, np), fl6));
hdr->payload_len = htons(seg_len);
hdr->nexthdr = proto;
@@ -1626,7 +1634,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
ip6_flow_hdr(hdr, v6_cork->tclass,
ip6_make_flowlabel(net, skb, fl6->flowlabel,
- np->autoflowlabel, fl6));
+ ip6_autoflowlabel(net, np), fl6));
hdr->hop_limit = v6_cork->hop_limit;
hdr->nexthdr = proto;
hdr->saddr = fl6->saddr;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a1c24443cd9e..ef958d50746b 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -912,7 +912,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto,
if (t->parms.collect_md) {
tun_dst = ipv6_tun_rx_dst(skb, 0, 0, 0);
if (!tun_dst)
- return 0;
+ goto drop;
}
ret = __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate,
log_ecn_error);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index a5e466d4e093..90dbfa78a390 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -878,6 +878,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
break;
case IPV6_AUTOFLOWLABEL:
np->autoflowlabel = valbool;
+ np->autoflowlabel_set = 1;
retv = 0;
break;
case IPV6_RECVFRAGSIZE:
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 12b7c27ce5ce..9a38a2c641fa 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1682,16 +1682,16 @@ static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel)
}
static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc,
- int type, struct mld2_grec **ppgr)
+ int type, struct mld2_grec **ppgr, unsigned int mtu)
{
- struct net_device *dev = pmc->idev->dev;
struct mld2_report *pmr;
struct mld2_grec *pgr;
- if (!skb)
- skb = mld_newpack(pmc->idev, dev->mtu);
- if (!skb)
- return NULL;
+ if (!skb) {
+ skb = mld_newpack(pmc->idev, mtu);
+ if (!skb)
+ return NULL;
+ }
pgr = skb_put(skb, sizeof(struct mld2_grec));
pgr->grec_type = type;
pgr->grec_auxwords = 0;
@@ -1714,10 +1714,15 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
struct mld2_grec *pgr = NULL;
struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list;
int scount, stotal, first, isquery, truncate;
+ unsigned int mtu;
if (pmc->mca_flags & MAF_NOREPORT)
return skb;
+ mtu = READ_ONCE(dev->mtu);
+ if (mtu < IPV6_MIN_MTU)
+ return skb;
+
isquery = type == MLD2_MODE_IS_INCLUDE ||
type == MLD2_MODE_IS_EXCLUDE;
truncate = type == MLD2_MODE_IS_EXCLUDE ||
@@ -1738,7 +1743,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(idev, dev->mtu);
+ skb = mld_newpack(idev, mtu);
}
}
first = 1;
@@ -1774,12 +1779,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
pgr->grec_nsrcs = htons(scount);
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(idev, dev->mtu);
+ skb = mld_newpack(idev, mtu);
first = 1;
scount = 0;
}
if (first) {
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
first = 0;
}
if (!skb)
@@ -1814,7 +1819,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
mld_sendpack(skb);
skb = NULL; /* add_grhead will get a new one */
}
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
}
}
if (pgr)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 598efa8cfe25..ca8d3266e92e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3700,19 +3700,13 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
if (!ipv6_addr_any(&fl6.saddr))
flags |= RT6_LOOKUP_F_HAS_SADDR;
- if (!fibmatch)
- dst = ip6_route_input_lookup(net, dev, &fl6, flags);
- else
- dst = ip6_route_lookup(net, &fl6, 0);
+ dst = ip6_route_input_lookup(net, dev, &fl6, flags);
rcu_read_unlock();
} else {
fl6.flowi6_oif = oif;
- if (!fibmatch)
- dst = ip6_route_output(net, NULL, &fl6);
- else
- dst = ip6_route_lookup(net, &fl6, 0);
+ dst = ip6_route_output(net, NULL, &fl6);
}
@@ -3729,6 +3723,15 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
goto errout;
}
+ if (fibmatch && rt->dst.from) {
+ struct rt6_info *ort = container_of(rt->dst.from,
+ struct rt6_info, dst);
+
+ dst_hold(&ort->dst);
+ ip6_rt_put(rt);
+ rt = ort;
+ }
+
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb) {
ip6_rt_put(rt);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 32ded300633d..237cc6187c5a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -988,7 +988,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
req->ts_recent, sk->sk_bound_dev_if,
- tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
+ tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr),
0, 0);
}
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 15c99dfa3d72..aac9d68b4636 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -254,6 +254,9 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
struct sock *sk = skb->sk;
int ret = -ENOMEM;
+ if (!net_eq(dev_net(dev), sock_net(sk)))
+ return 0;
+
dev_hold(dev);
if (is_vmalloc_addr(skb->head))
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index cfb652a4e007..dbe1079a1651 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -532,6 +532,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
return -EINVAL;
skb_reset_network_header(skb);
+ key->eth.type = skb->protocol;
} else {
eth = eth_hdr(skb);
ether_addr_copy(key->eth.src, eth->h_source);
@@ -545,15 +546,23 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
if (unlikely(parse_vlan(skb, key)))
return -ENOMEM;
- skb->protocol = parse_ethertype(skb);
- if (unlikely(skb->protocol == htons(0)))
+ key->eth.type = parse_ethertype(skb);
+ if (unlikely(key->eth.type == htons(0)))
return -ENOMEM;
+ /* Multiple tagged packets need to retain TPID to satisfy
+ * skb_vlan_pop(), which will later shift the ethertype into
+ * skb->protocol.
+ */
+ if (key->eth.cvlan.tci & htons(VLAN_TAG_PRESENT))
+ skb->protocol = key->eth.cvlan.tpid;
+ else
+ skb->protocol = key->eth.type;
+
skb_reset_network_header(skb);
__skb_push(skb, skb->data - skb_mac_header(skb));
}
skb_reset_mac_len(skb);
- key->eth.type = skb->protocol;
/* Network layer. */
if (key->eth.type == htons(ETH_P_IP)) {
diff --git a/net/rds/send.c b/net/rds/send.c
index b52cdc8ae428..f72466c63f0c 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1009,6 +1009,9 @@ static int rds_rdma_bytes(struct msghdr *msg, size_t *rdma_bytes)
continue;
if (cmsg->cmsg_type == RDS_CMSG_RDMA_ARGS) {
+ if (cmsg->cmsg_len <
+ CMSG_LEN(sizeof(struct rds_rdma_args)))
+ return -EINVAL;
args = CMSG_DATA(cmsg);
*rdma_bytes += args->remote_vec.bytes;
}
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 44de4ee51ce9..a08a32fa0949 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -59,11 +59,12 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
struct net_device *dev = qdisc_dev(sch);
int err;
+ net_inc_ingress_queue();
+
err = tcf_block_get(&q->block, &dev->ingress_cl_list);
if (err)
return err;
- net_inc_ingress_queue();
sch->flags |= TCQ_F_CPUSTATS;
return 0;
@@ -153,6 +154,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
struct net_device *dev = qdisc_dev(sch);
int err;
+ net_inc_ingress_queue();
+ net_inc_egress_queue();
+
err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list);
if (err)
return err;
@@ -161,9 +165,6 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
if (err)
return err;
- net_inc_ingress_queue();
- net_inc_egress_queue();
-
sch->flags |= TCQ_F_CPUSTATS;
return 0;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index d6163f7aefb1..df806b8819aa 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3874,13 +3874,17 @@ static int sctp_setsockopt_reset_streams(struct sock *sk,
struct sctp_association *asoc;
int retval = -EINVAL;
- if (optlen < sizeof(struct sctp_reset_streams))
+ if (optlen < sizeof(*params))
return -EINVAL;
params = memdup_user(optval, optlen);
if (IS_ERR(params))
return PTR_ERR(params);
+ if (params->srs_number_streams * sizeof(__u16) >
+ optlen - sizeof(*params))
+ goto out;
+
asoc = sctp_id2assoc(sk, params->srs_assoc_id);
if (!asoc)
goto out;
@@ -4413,7 +4417,7 @@ static int sctp_init_sock(struct sock *sk)
SCTP_DBG_OBJCNT_INC(sock);
local_bh_disable();
- percpu_counter_inc(&sctp_sockets_allocated);
+ sk_sockets_allocated_inc(sk);
sock_prot_inuse_add(net, sk->sk_prot, 1);
/* Nothing can fail after this block, otherwise
@@ -4457,7 +4461,7 @@ static void sctp_destroy_sock(struct sock *sk)
}
sctp_endpoint_free(sp->ep);
local_bh_disable();
- percpu_counter_dec(&sctp_sockets_allocated);
+ sk_sockets_allocated_dec(sk);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
local_bh_enable();
}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index d50edd6e0019..98a44ecb11e7 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -709,11 +709,11 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
switch (sk->sk_state) {
case TIPC_ESTABLISHED:
+ case TIPC_CONNECTING:
if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
mask |= POLLOUT;
/* fall thru' */
case TIPC_LISTEN:
- case TIPC_CONNECTING:
if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= (POLLIN | POLLRDNORM);
break;
diff --git a/security/Kconfig b/security/Kconfig
index e8e449444e65..6614b9312b45 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -54,6 +54,17 @@ config SECURITY_NETWORK
implement socket and networking access controls.
If you are unsure how to answer this question, answer N.
+config PAGE_TABLE_ISOLATION
+ bool "Remove the kernel mapping in user mode"
+ depends on X86_64 && !UML
+ default y
+ help
+ This feature reduces the number of hardware side channels by
+ ensuring that the majority of kernel addresses are not mapped
+ into userspace.
+
+ See Documentation/x86/pagetable-isolation.txt for more details.
+
config SECURITY_INFINIBAND
bool "Infiniband Security Hooks"
depends on SECURITY && INFINIBAND
diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index 038a180d3f81..cbe818eda336 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -325,7 +325,7 @@ static int hdac_component_master_match(struct device *dev, void *data)
*/
int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *aops)
{
- if (WARN_ON(!hdac_acomp))
+ if (!hdac_acomp)
return -ENODEV;
hdac_acomp->audio_ops = aops;
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index a81aacf684b2..37e1cf8218ff 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -271,6 +271,8 @@ enum {
CXT_FIXUP_HP_SPECTRE,
CXT_FIXUP_HP_GATE_MIC,
CXT_FIXUP_MUTE_LED_GPIO,
+ CXT_FIXUP_HEADSET_MIC,
+ CXT_FIXUP_HP_MIC_NO_PRESENCE,
};
/* for hda_fixup_thinkpad_acpi() */
@@ -350,6 +352,18 @@ static void cxt_fixup_headphone_mic(struct hda_codec *codec,
}
}
+static void cxt_fixup_headset_mic(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ struct conexant_spec *spec = codec->spec;
+
+ switch (action) {
+ case HDA_FIXUP_ACT_PRE_PROBE:
+ spec->parse_flags |= HDA_PINCFG_HEADSET_MIC;
+ break;
+ }
+}
+
/* OPLC XO 1.5 fixup */
/* OLPC XO-1.5 supports DC input mode (e.g. for use with analog sensors)
@@ -880,6 +894,19 @@ static const struct hda_fixup cxt_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = cxt_fixup_mute_led_gpio,
},
+ [CXT_FIXUP_HEADSET_MIC] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = cxt_fixup_headset_mic,
+ },
+ [CXT_FIXUP_HP_MIC_NO_PRESENCE] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x1a, 0x02a1113c },
+ { }
+ },
+ .chained = true,
+ .chain_id = CXT_FIXUP_HEADSET_MIC,
+ },
};
static const struct snd_pci_quirk cxt5045_fixups[] = {
@@ -934,6 +961,8 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO),
SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO),
+ SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),
SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO),
SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 9ac4b9076ee2..acdb196ddb44 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -324,8 +324,12 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
case 0x10ec0292:
alc_update_coef_idx(codec, 0x4, 1<<15, 0);
break;
- case 0x10ec0215:
case 0x10ec0225:
+ case 0x10ec0295:
+ case 0x10ec0299:
+ alc_update_coef_idx(codec, 0x67, 0xf000, 0x3000);
+ /* fallthrough */
+ case 0x10ec0215:
case 0x10ec0233:
case 0x10ec0236:
case 0x10ec0255:
@@ -336,10 +340,8 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
case 0x10ec0286:
case 0x10ec0288:
case 0x10ec0285:
- case 0x10ec0295:
case 0x10ec0298:
case 0x10ec0289:
- case 0x10ec0299:
alc_update_coef_idx(codec, 0x10, 1<<9, 0);
break;
case 0x10ec0275:
@@ -6305,6 +6307,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+ SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x3112, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
@@ -6557,6 +6560,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x1b, 0x01011020},
{0x21, 0x02211010}),
+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x12, 0x90a60130},
+ {0x14, 0x90170110},
+ {0x1b, 0x01011020},
+ {0x21, 0x0221101f}),
SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x12, 0x90a60160},
{0x14, 0x90170120},
diff --git a/sound/soc/codecs/da7218.c b/sound/soc/codecs/da7218.c
index b2d42ec1dcd9..56564ce90cb6 100644
--- a/sound/soc/codecs/da7218.c
+++ b/sound/soc/codecs/da7218.c
@@ -2520,7 +2520,7 @@ static struct da7218_pdata *da7218_of_to_pdata(struct snd_soc_codec *codec)
}
if (da7218->dev_id == DA7218_DEV_ID) {
- hpldet_np = of_find_node_by_name(np, "da7218_hpldet");
+ hpldet_np = of_get_child_by_name(np, "da7218_hpldet");
if (!hpldet_np)
return pdata;
diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c
index 18933bf6473f..8c7063e1aa46 100644
--- a/sound/soc/codecs/msm8916-wcd-analog.c
+++ b/sound/soc/codecs/msm8916-wcd-analog.c
@@ -267,7 +267,7 @@
#define MSM8916_WCD_ANALOG_RATES (SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |\
SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_48000)
#define MSM8916_WCD_ANALOG_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
- SNDRV_PCM_FMTBIT_S24_LE)
+ SNDRV_PCM_FMTBIT_S32_LE)
static int btn_mask = SND_JACK_BTN_0 | SND_JACK_BTN_1 |
SND_JACK_BTN_2 | SND_JACK_BTN_3 | SND_JACK_BTN_4;
diff --git a/sound/soc/codecs/msm8916-wcd-digital.c b/sound/soc/codecs/msm8916-wcd-digital.c
index 66df8f810f0d..694db27b11fa 100644
--- a/sound/soc/codecs/msm8916-wcd-digital.c
+++ b/sound/soc/codecs/msm8916-wcd-digital.c
@@ -194,7 +194,7 @@
SNDRV_PCM_RATE_32000 | \
SNDRV_PCM_RATE_48000)
#define MSM8916_WCD_DIGITAL_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
- SNDRV_PCM_FMTBIT_S24_LE)
+ SNDRV_PCM_FMTBIT_S32_LE)
struct msm8916_wcd_digital_priv {
struct clk *ahbclk, *mclk;
@@ -645,7 +645,7 @@ static int msm8916_wcd_digital_hw_params(struct snd_pcm_substream *substream,
RX_I2S_CTL_RX_I2S_MODE_MASK,
RX_I2S_CTL_RX_I2S_MODE_16);
break;
- case SNDRV_PCM_FORMAT_S24_LE:
+ case SNDRV_PCM_FORMAT_S32_LE:
snd_soc_update_bits(dai->codec, LPASS_CDC_CLK_TX_I2S_CTL,
TX_I2S_CTL_TX_I2S_MODE_MASK,
TX_I2S_CTL_TX_I2S_MODE_32);
diff --git a/sound/soc/codecs/tlv320aic31xx.h b/sound/soc/codecs/tlv320aic31xx.h
index 730fb2058869..1ff3edb7bbb6 100644
--- a/sound/soc/codecs/tlv320aic31xx.h
+++ b/sound/soc/codecs/tlv320aic31xx.h
@@ -116,7 +116,7 @@ struct aic31xx_pdata {
/* INT2 interrupt control */
#define AIC31XX_INT2CTRL AIC31XX_REG(0, 49)
/* GPIO1 control */
-#define AIC31XX_GPIO1 AIC31XX_REG(0, 50)
+#define AIC31XX_GPIO1 AIC31XX_REG(0, 51)
#define AIC31XX_DACPRB AIC31XX_REG(0, 60)
/* ADC Instruction Set Register */
diff --git a/sound/soc/codecs/twl4030.c b/sound/soc/codecs/twl4030.c
index c482b2e7a7d2..cfe72b9d4356 100644
--- a/sound/soc/codecs/twl4030.c
+++ b/sound/soc/codecs/twl4030.c
@@ -232,7 +232,7 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec)
struct twl4030_codec_data *pdata = dev_get_platdata(codec->dev);
struct device_node *twl4030_codec_node = NULL;
- twl4030_codec_node = of_find_node_by_name(codec->dev->parent->of_node,
+ twl4030_codec_node = of_get_child_by_name(codec->dev->parent->of_node,
"codec");
if (!pdata && twl4030_codec_node) {
@@ -241,9 +241,11 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec)
GFP_KERNEL);
if (!pdata) {
dev_err(codec->dev, "Can not allocate memory\n");
+ of_node_put(twl4030_codec_node);
return NULL;
}
twl4030_setup_pdata_of(pdata, twl4030_codec_node);
+ of_node_put(twl4030_codec_node);
}
return pdata;
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 65c059b5ffd7..66e32f5d2917 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1733,7 +1733,7 @@ static int wm_adsp_load(struct wm_adsp *dsp)
le64_to_cpu(footer->timestamp));
while (pos < firmware->size &&
- pos - firmware->size > sizeof(*region)) {
+ sizeof(*region) < firmware->size - pos) {
region = (void *)&(firmware->data[pos]);
region_name = "Unknown";
reg = 0;
@@ -1782,8 +1782,8 @@ static int wm_adsp_load(struct wm_adsp *dsp)
regions, le32_to_cpu(region->len), offset,
region_name);
- if ((pos + le32_to_cpu(region->len) + sizeof(*region)) >
- firmware->size) {
+ if (le32_to_cpu(region->len) >
+ firmware->size - pos - sizeof(*region)) {
adsp_err(dsp,
"%s.%d: %s region len %d bytes exceeds file length %zu\n",
file, regions, region_name,
@@ -2253,7 +2253,7 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp)
blocks = 0;
while (pos < firmware->size &&
- pos - firmware->size > sizeof(*blk)) {
+ sizeof(*blk) < firmware->size - pos) {
blk = (void *)(&firmware->data[pos]);
type = le16_to_cpu(blk->type);
@@ -2327,8 +2327,8 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp)
}
if (reg) {
- if ((pos + le32_to_cpu(blk->len) + sizeof(*blk)) >
- firmware->size) {
+ if (le32_to_cpu(blk->len) >
+ firmware->size - pos - sizeof(*blk)) {
adsp_err(dsp,
"%s.%d: %s region len %d bytes exceeds file length %zu\n",
file, blocks, region_name,
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index 64598d1183f8..3ffbb498cc70 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -1452,12 +1452,6 @@ static int fsl_ssi_probe(struct platform_device *pdev)
sizeof(fsl_ssi_ac97_dai));
fsl_ac97_data = ssi_private;
-
- ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev);
- if (ret) {
- dev_err(&pdev->dev, "could not set AC'97 ops\n");
- return ret;
- }
} else {
/* Initialize this copy of the CPU DAI driver structure */
memcpy(&ssi_private->cpu_dai_drv, &fsl_ssi_dai_template,
@@ -1568,6 +1562,14 @@ static int fsl_ssi_probe(struct platform_device *pdev)
return ret;
}
+ if (fsl_ssi_is_ac97(ssi_private)) {
+ ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev);
+ if (ret) {
+ dev_err(&pdev->dev, "could not set AC'97 ops\n");
+ goto error_ac97_ops;
+ }
+ }
+
ret = devm_snd_soc_register_component(&pdev->dev, &fsl_ssi_component,
&ssi_private->cpu_dai_drv, 1);
if (ret) {
@@ -1651,6 +1653,10 @@ static int fsl_ssi_probe(struct platform_device *pdev)
fsl_ssi_debugfs_remove(&ssi_private->dbg_stats);
error_asoc_register:
+ if (fsl_ssi_is_ac97(ssi_private))
+ snd_soc_set_ac97_ops(NULL);
+
+error_ac97_ops:
if (ssi_private->soc->imx)
fsl_ssi_imx_clean(pdev, ssi_private);
diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c
index 0304ffb714f2..1aef72df20a1 100644
--- a/tools/testing/selftests/x86/ldt_gdt.c
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -122,8 +122,7 @@ static void check_valid_segment(uint16_t index, int ldt,
* NB: Different Linux versions do different things with the
* accessed bit in set_thread_area().
*/
- if (ar != expected_ar &&
- (ldt || ar != (expected_ar | AR_ACCESSED))) {
+ if (ar != expected_ar && ar != (expected_ar | AR_ACCESSED)) {
printf("[FAIL]\t%s entry %hu has AR 0x%08X but expected 0x%08X\n",
(ldt ? "LDT" : "GDT"), index, ar, expected_ar);
nerrs++;
diff --git a/tools/usb/usbip/src/utils.c b/tools/usb/usbip/src/utils.c
index 2b3d6d235015..3d7b42e77299 100644
--- a/tools/usb/usbip/src/utils.c
+++ b/tools/usb/usbip/src/utils.c
@@ -30,6 +30,7 @@ int modify_match_busid(char *busid, int add)
char command[SYSFS_BUS_ID_SIZE + 4];
char match_busid_attr_path[SYSFS_PATH_MAX];
int rc;
+ int cmd_size;
snprintf(match_busid_attr_path, sizeof(match_busid_attr_path),
"%s/%s/%s/%s/%s/%s", SYSFS_MNT_PATH, SYSFS_BUS_NAME,
@@ -37,12 +38,14 @@ int modify_match_busid(char *busid, int add)
attr_name);
if (add)
- snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s", busid);
+ cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s",
+ busid);
else
- snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s", busid);
+ cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s",
+ busid);
rc = write_sysfs_attribute(match_busid_attr_path, command,
- sizeof(command));
+ cmd_size);
if (rc < 0) {
dbg("failed to write match_busid: %s", strerror(errno));
return -1;
7 years, 8 months
- 1
- 0
Re: [Linux-stable-mirror] Linux 4.9.74
by Greg KH
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 86a6746f6833..152ec4e87b57 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2795,6 +2795,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
nopat [X86] Disable PAT (page attribute table extension of
pagetables) support.
+ nopcid [X86-64] Disable the PCID cpu feature.
+
norandmaps Don't use address space randomization. Equivalent to
echo 0 > /proc/sys/kernel/randomize_va_space
diff --git a/Makefile b/Makefile
index 64eb0bf614ee..075e429732e7 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 4
PATCHLEVEL = 9
-SUBLEVEL = 73
+SUBLEVEL = 74
EXTRAVERSION =
NAME = Roaring Lionus
@@ -788,6 +788,9 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign)
# disable invalid "can't wrap" optimizations for signed / pointers
KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow)
+# Make sure -fstack-check isn't enabled (like gentoo apparently did)
+KBUILD_CFLAGS += $(call cc-option,-fno-stack-check,)
+
# conserve stack if available
KBUILD_CFLAGS += $(call cc-option,-fconserve-stack)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b9c546a305a4..da8156fd3d58 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -45,7 +45,7 @@ config X86
select ARCH_USE_CMPXCHG_LOCKREF if X86_64
select ARCH_USE_QUEUED_RWLOCKS
select ARCH_USE_QUEUED_SPINLOCKS
- select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP
+ select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
select ARCH_WANTS_DYNAMIC_TASK_STRUCT
select ARCH_WANT_FRAME_POINTERS
select ARCH_WANT_IPC_PARSE_VERSION if X86_32
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 85599ad4d024..21c5ac15657b 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -21,11 +21,13 @@
# define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31))
# define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31))
# define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31))
+# define DISABLE_PCID 0
#else
# define DISABLE_VME 0
# define DISABLE_K6_MTRR 0
# define DISABLE_CYRIX_ARR 0
# define DISABLE_CENTAUR_MCR 0
+# define DISABLE_PCID (1<<(X86_FEATURE_PCID & 31))
#endif /* CONFIG_X86_64 */
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
@@ -43,7 +45,7 @@
#define DISABLED_MASK1 0
#define DISABLED_MASK2 0
#define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
-#define DISABLED_MASK4 0
+#define DISABLED_MASK4 (DISABLE_PCID)
#define DISABLED_MASK5 0
#define DISABLED_MASK6 0
#define DISABLED_MASK7 0
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 59405a248fc2..9b76cd331990 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -22,8 +22,8 @@ typedef struct {
#ifdef CONFIG_SMP
unsigned int irq_resched_count;
unsigned int irq_call_count;
- unsigned int irq_tlb_count;
#endif
+ unsigned int irq_tlb_count;
#ifdef CONFIG_X86_THERMAL_VECTOR
unsigned int irq_thermal_count;
#endif
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 72198c64e646..8b272a08d1a8 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -33,12 +33,6 @@ typedef struct {
#endif
} mm_context_t;
-#ifdef CONFIG_SMP
void leave_mm(int cpu);
-#else
-static inline void leave_mm(int cpu)
-{
-}
-#endif
#endif /* _ASM_X86_MMU_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index f9dd22469388..d23e35584f15 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -99,10 +99,8 @@ static inline void load_mm_ldt(struct mm_struct *mm)
static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
-#ifdef CONFIG_SMP
if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
-#endif
}
static inline int init_new_context(struct task_struct *tsk,
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index fc5abff9b7fd..7d2ea6b1f7d9 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -7,6 +7,7 @@
#include <asm/processor.h>
#include <asm/cpufeature.h>
#include <asm/special_insns.h>
+#include <asm/smp.h>
static inline void __invpcid(unsigned long pcid, unsigned long addr,
unsigned long type)
@@ -65,10 +66,8 @@ static inline void invpcid_flush_all_nonglobals(void)
#endif
struct tlb_state {
-#ifdef CONFIG_SMP
struct mm_struct *active_mm;
int state;
-#endif
/*
* Access to this CR4 shadow and to H/W CR4 is protected by
@@ -192,6 +191,14 @@ static inline void __flush_tlb_all(void)
__flush_tlb_global();
else
__flush_tlb();
+
+ /*
+ * Note: if we somehow had PCID but not PGE, then this wouldn't work --
+ * we'd end up flushing kernel translations for the current ASID but
+ * we might fail to flush kernel translations for other cached ASIDs.
+ *
+ * To avoid this issue, we force PCID off if PGE is off.
+ */
}
static inline void __flush_tlb_one(unsigned long addr)
@@ -205,7 +212,6 @@ static inline void __flush_tlb_one(unsigned long addr)
/*
* TLB flushing:
*
- * - flush_tlb() flushes the current mm struct TLBs
* - flush_tlb_all() flushes all processes TLBs
* - flush_tlb_mm(mm) flushes the specified mm context TLB's
* - flush_tlb_page(vma, vmaddr) flushes one page
@@ -217,84 +223,6 @@ static inline void __flush_tlb_one(unsigned long addr)
* and page-granular flushes are available only on i486 and up.
*/
-#ifndef CONFIG_SMP
-
-/* "_up" is for UniProcessor.
- *
- * This is a helper for other header functions. *Not* intended to be called
- * directly. All global TLB flushes need to either call this, or to bump the
- * vm statistics themselves.
- */
-static inline void __flush_tlb_up(void)
-{
- count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
- __flush_tlb();
-}
-
-static inline void flush_tlb_all(void)
-{
- count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
- __flush_tlb_all();
-}
-
-static inline void flush_tlb(void)
-{
- __flush_tlb_up();
-}
-
-static inline void local_flush_tlb(void)
-{
- __flush_tlb_up();
-}
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
- if (mm == current->active_mm)
- __flush_tlb_up();
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma,
- unsigned long addr)
-{
- if (vma->vm_mm == current->active_mm)
- __flush_tlb_one(addr);
-}
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
-{
- if (vma->vm_mm == current->active_mm)
- __flush_tlb_up();
-}
-
-static inline void flush_tlb_mm_range(struct mm_struct *mm,
- unsigned long start, unsigned long end, unsigned long vmflag)
-{
- if (mm == current->active_mm)
- __flush_tlb_up();
-}
-
-static inline void native_flush_tlb_others(const struct cpumask *cpumask,
- struct mm_struct *mm,
- unsigned long start,
- unsigned long end)
-{
-}
-
-static inline void reset_lazy_tlbstate(void)
-{
-}
-
-static inline void flush_tlb_kernel_range(unsigned long start,
- unsigned long end)
-{
- flush_tlb_all();
-}
-
-#else /* SMP */
-
-#include <asm/smp.h>
-
#define local_flush_tlb() __flush_tlb()
#define flush_tlb_mm(mm) flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL)
@@ -303,13 +231,14 @@ static inline void flush_tlb_kernel_range(unsigned long start,
flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags)
extern void flush_tlb_all(void);
-extern void flush_tlb_current_task(void);
-extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
unsigned long end, unsigned long vmflag);
extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
-#define flush_tlb() flush_tlb_current_task()
+static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
+{
+ flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE);
+}
void native_flush_tlb_others(const struct cpumask *cpumask,
struct mm_struct *mm,
@@ -324,8 +253,6 @@ static inline void reset_lazy_tlbstate(void)
this_cpu_write(cpu_tlbstate.active_mm, &init_mm);
}
-#endif /* SMP */
-
#ifndef CONFIG_PARAVIRT
#define flush_tlb_others(mask, mm, start, end) \
native_flush_tlb_others(mask, mm, start, end)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bd17db15a2c1..0b6124315441 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -19,6 +19,14 @@
void __init check_bugs(void)
{
+#ifdef CONFIG_X86_32
+ /*
+ * Regardless of whether PCID is enumerated, the SDM says
+ * that it can't be enabled in 32-bit mode.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_PCID);
+#endif
+
identify_boot_cpu();
#ifndef CONFIG_SMP
pr_info("CPU: ");
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4eece91ada37..91588be529b9 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -163,6 +163,24 @@ static int __init x86_mpx_setup(char *s)
}
__setup("nompx", x86_mpx_setup);
+#ifdef CONFIG_X86_64
+static int __init x86_pcid_setup(char *s)
+{
+ /* require an exact match without trailing characters */
+ if (strlen(s))
+ return 0;
+
+ /* do not emit a message if the feature is not present */
+ if (!boot_cpu_has(X86_FEATURE_PCID))
+ return 1;
+
+ setup_clear_cpu_cap(X86_FEATURE_PCID);
+ pr_info("nopcid: PCID feature disabled\n");
+ return 1;
+}
+__setup("nopcid", x86_pcid_setup);
+#endif
+
static int __init x86_noinvpcid_setup(char *s)
{
/* noinvpcid doesn't accept parameters */
@@ -306,6 +324,25 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
}
}
+static void setup_pcid(struct cpuinfo_x86 *c)
+{
+ if (cpu_has(c, X86_FEATURE_PCID)) {
+ if (cpu_has(c, X86_FEATURE_PGE)) {
+ cr4_set_bits(X86_CR4_PCIDE);
+ } else {
+ /*
+ * flush_tlb_all(), as currently implemented, won't
+ * work if PCID is on but PGE is not. Since that
+ * combination doesn't exist on real hardware, there's
+ * no reason to try to fully support it, but it's
+ * polite to avoid corrupting data if we're on
+ * an improperly configured VM.
+ */
+ clear_cpu_cap(c, X86_FEATURE_PCID);
+ }
+ }
+}
+
/*
* Protection Keys are not available in 32-bit mode.
*/
@@ -1064,6 +1101,9 @@ static void identify_cpu(struct cpuinfo_x86 *c)
setup_smep(c);
setup_smap(c);
+ /* Set up PCID */
+ setup_pcid(c);
+
/*
* The vendor-specific functions might have changed features.
* Now we do "generic changes."
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 067f9813fd2c..ce020a69bba9 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -106,6 +106,10 @@ void __noreturn machine_real_restart(unsigned int type)
load_cr3(initial_page_table);
#else
write_cr3(real_mode_header->trampoline_pgd);
+
+ /* Exiting long mode will fail if CR4.PCIDE is set. */
+ if (static_cpu_has(X86_FEATURE_PCID))
+ cr4_clear_bits(X86_CR4_PCIDE);
#endif
/* Jump to the identity-mapped low memory code */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 9fe7b9e1ae30..e803d72ef525 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -115,25 +115,16 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
spin_lock_irqsave(&rtc_lock, flags);
CMOS_WRITE(0xa, 0xf);
spin_unlock_irqrestore(&rtc_lock, flags);
- local_flush_tlb();
- pr_debug("1.\n");
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
start_eip >> 4;
- pr_debug("2.\n");
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
start_eip & 0xf;
- pr_debug("3.\n");
}
static inline void smpboot_restore_warm_reset_vector(void)
{
unsigned long flags;
- /*
- * Install writable page 0 entry to set BIOS data area.
- */
- local_flush_tlb();
-
/*
* Paranoid: Set warm reset code and vector here back
* to default values.
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 01f30e56f99e..4b3012888ada 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -191,7 +191,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
pte_unmap_unlock(pte, ptl);
out:
up_write(&mm->mmap_sem);
- flush_tlb();
+ flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, 0UL);
}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 889e7619a091..0381638168d1 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -764,10 +764,8 @@ void __init zone_sizes_init(void)
}
DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
-#ifdef CONFIG_SMP
.active_mm = &init_mm,
.state = 0,
-#endif
.cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */
};
EXPORT_SYMBOL_GPL(cpu_tlbstate);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 75fb01109f94..53b72fb4e781 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -15,7 +15,7 @@
#include <linux/debugfs.h>
/*
- * Smarter SMP flushing macros.
+ * TLB flushing, formerly SMP-only
* c/o Linus Torvalds.
*
* These mean you can really definitely utterly forget about
@@ -28,8 +28,6 @@
* Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
*/
-#ifdef CONFIG_SMP
-
struct flush_tlb_info {
struct mm_struct *flush_mm;
unsigned long flush_start;
@@ -59,8 +57,6 @@ void leave_mm(int cpu)
}
EXPORT_SYMBOL_GPL(leave_mm);
-#endif /* CONFIG_SMP */
-
void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
@@ -91,10 +87,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
set_pgd(pgd, init_mm.pgd[stack_pgd_index]);
}
-#ifdef CONFIG_SMP
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
this_cpu_write(cpu_tlbstate.active_mm, next);
-#endif
cpumask_set_cpu(cpu, mm_cpumask(next));
@@ -152,9 +146,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
if (unlikely(prev->context.ldt != next->context.ldt))
load_mm_ldt(next);
#endif
- }
-#ifdef CONFIG_SMP
- else {
+ } else {
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
@@ -181,11 +173,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
load_mm_ldt(next);
}
}
-#endif
}
-#ifdef CONFIG_SMP
-
/*
* The flush IPI assumes that a thread switch happens in this order:
* [cpu0: the cpu that switches]
@@ -287,23 +276,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
smp_call_function_many(cpumask, flush_tlb_func, &info, 1);
}
-void flush_tlb_current_task(void)
-{
- struct mm_struct *mm = current->mm;
-
- preempt_disable();
-
- count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-
- /* This is an implicit full barrier that synchronizes with switch_mm. */
- local_flush_tlb();
-
- trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
- if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
- flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
- preempt_enable();
-}
-
/*
* See Documentation/x86/tlb.txt for details. We choose 33
* because it is large enough to cover the vast majority (at
@@ -324,6 +296,12 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
unsigned long base_pages_to_flush = TLB_FLUSH_ALL;
preempt_disable();
+
+ if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB))
+ base_pages_to_flush = (end - start) >> PAGE_SHIFT;
+ if (base_pages_to_flush > tlb_single_page_flush_ceiling)
+ base_pages_to_flush = TLB_FLUSH_ALL;
+
if (current->active_mm != mm) {
/* Synchronize with switch_mm. */
smp_mb();
@@ -340,15 +318,11 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
goto out;
}
- if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB))
- base_pages_to_flush = (end - start) >> PAGE_SHIFT;
-
/*
* Both branches below are implicit full barriers (MOV to CR or
* INVLPG) that synchronize with switch_mm.
*/
- if (base_pages_to_flush > tlb_single_page_flush_ceiling) {
- base_pages_to_flush = TLB_FLUSH_ALL;
+ if (base_pages_to_flush == TLB_FLUSH_ALL) {
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
local_flush_tlb();
} else {
@@ -369,33 +343,6 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
preempt_enable();
}
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
-{
- struct mm_struct *mm = vma->vm_mm;
-
- preempt_disable();
-
- if (current->active_mm == mm) {
- if (current->mm) {
- /*
- * Implicit full barrier (INVLPG) that synchronizes
- * with switch_mm.
- */
- __flush_tlb_one(start);
- } else {
- leave_mm(smp_processor_id());
-
- /* Synchronize with switch_mm. */
- smp_mb();
- }
- }
-
- if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
- flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE);
-
- preempt_enable();
-}
-
static void do_flush_tlb_all(void *info)
{
count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
@@ -480,5 +427,3 @@ static int __init create_tlb_single_page_flush_ceiling(void)
return 0;
}
late_initcall(create_tlb_single_page_flush_ceiling);
-
-#endif /* CONFIG_SMP */
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 8f1f7efa848c..2bea87cc0ff2 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -444,6 +444,12 @@ static void __init xen_init_cpuid_mask(void)
~((1 << X86_FEATURE_MTRR) | /* disable MTRR */
(1 << X86_FEATURE_ACC)); /* thermal monitoring */
+ /*
+ * Xen PV would need some work to support PCID: CR3 handling as well
+ * as xen_flush_tlb_others() would need updating.
+ */
+ cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_PCID % 32)); /* disable PCID */
+
if (!xen_initial_domain())
cpuid_leaf1_edx_mask &=
~((1 << X86_FEATURE_ACPI)); /* disable ACPI */
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index 19c6477af19f..a856371bbe58 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -575,10 +575,10 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
ret = -EAGAIN;
goto skip_cqe;
}
- if (unlikely((CQE_WRID_MSN(hw_cqe) != (wq->rq.msn)))) {
+ if (unlikely(!CQE_STATUS(hw_cqe) &&
+ CQE_WRID_MSN(hw_cqe) != wq->rq.msn)) {
t4_set_wq_in_error(wq);
- hw_cqe->header |= htonl(CQE_STATUS_V(T4_ERR_MSN));
- goto proc_cqe;
+ hw_cqe->header |= cpu_to_be32(CQE_STATUS_V(T4_ERR_MSN));
}
goto proc_cqe;
}
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index edae2dcc4927..bb22d325e965 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -14226,7 +14226,9 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
/* Reset PHY, otherwise the read DMA engine will be in a mode that
* breaks all requests to 256 bytes.
*/
- if (tg3_asic_rev(tp) == ASIC_REV_57766)
+ if (tg3_asic_rev(tp) == ASIC_REV_57766 ||
+ tg3_asic_rev(tp) == ASIC_REV_5717 ||
+ tg3_asic_rev(tp) == ASIC_REV_5719)
reset_phy = true;
err = tg3_restart_hw(tp, reset_phy);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 849b8712ec81..917091871259 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -172,10 +172,12 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
#endif /* CONFIG_M5272 */
/* The FEC stores dest/src/type/vlan, data, and checksum for receive packets.
+ *
+ * 2048 byte skbufs are allocated. However, alignment requirements
+ * varies between FEC variants. Worst case is 64, so round down by 64.
*/
-#define PKT_MAXBUF_SIZE 1522
+#define PKT_MAXBUF_SIZE (round_down(2048 - 64, 64))
#define PKT_MINBUF_SIZE 64
-#define PKT_MAXBLR_SIZE 1536
/* FEC receive acceleration */
#define FEC_RACC_IPDIS (1 << 1)
@@ -813,6 +815,12 @@ static void fec_enet_bd_init(struct net_device *dev)
for (i = 0; i < txq->bd.ring_size; i++) {
/* Initialize the BD for every fragment in the page. */
bdp->cbd_sc = cpu_to_fec16(0);
+ if (bdp->cbd_bufaddr &&
+ !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
+ dma_unmap_single(&fep->pdev->dev,
+ fec32_to_cpu(bdp->cbd_bufaddr),
+ fec16_to_cpu(bdp->cbd_datlen),
+ DMA_TO_DEVICE);
if (txq->tx_skbuff[i]) {
dev_kfree_skb_any(txq->tx_skbuff[i]);
txq->tx_skbuff[i] = NULL;
@@ -847,7 +855,7 @@ static void fec_enet_enable_ring(struct net_device *ndev)
for (i = 0; i < fep->num_rx_queues; i++) {
rxq = fep->rx_queue[i];
writel(rxq->bd.dma, fep->hwp + FEC_R_DES_START(i));
- writel(PKT_MAXBLR_SIZE, fep->hwp + FEC_R_BUFF_SIZE(i));
+ writel(PKT_MAXBUF_SIZE, fep->hwp + FEC_R_BUFF_SIZE(i));
/* enable DMA1/2 */
if (i)
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index a0d1b084ecec..7aeb7fedb364 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -232,7 +232,8 @@ static int orion_mdio_probe(struct platform_device *pdev)
dev->regs + MVMDIO_ERR_INT_MASK);
} else if (dev->err_interrupt == -EPROBE_DEFER) {
- return -EPROBE_DEFER;
+ ret = -EPROBE_DEFER;
+ goto out_mdio;
}
mutex_init(&dev->lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index f7fabecc104f..4c3f1cb7e2c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -367,7 +367,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
case MLX5_CMD_OP_ALLOC_Q_COUNTER:
case MLX5_CMD_OP_QUERY_Q_COUNTER:
- case MLX5_CMD_OP_SET_RATE_LIMIT:
+ case MLX5_CMD_OP_SET_PP_RATE_LIMIT:
case MLX5_CMD_OP_QUERY_RATE_LIMIT:
case MLX5_CMD_OP_ALLOC_PD:
case MLX5_CMD_OP_ALLOC_UAR:
@@ -502,7 +502,7 @@ const char *mlx5_command_str(int command)
MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
- MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT);
+ MLX5_COMMAND_STR_CASE(SET_PP_RATE_LIMIT);
MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
MLX5_COMMAND_STR_CASE(ALLOC_PD);
MLX5_COMMAND_STR_CASE(DEALLOC_PD);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 9d3722930c95..38981db43bc3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3038,6 +3038,7 @@ static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv,
struct sk_buff *skb,
netdev_features_t features)
{
+ unsigned int offset = 0;
struct udphdr *udph;
u16 proto;
u16 port = 0;
@@ -3047,7 +3048,7 @@ static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv,
proto = ip_hdr(skb)->protocol;
break;
case htons(ETH_P_IPV6):
- proto = ipv6_hdr(skb)->nexthdr;
+ proto = ipv6_find_hdr(skb, &offset, -1, NULL, NULL);
break;
default:
goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index d0a4005fe63a..9346f3985edf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -303,8 +303,8 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
err_cmd:
memset(din, 0, sizeof(din));
memset(dout, 0, sizeof(dout));
- MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
- MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
+ MLX5_SET(destroy_qp_in, din, opcode, MLX5_CMD_OP_DESTROY_QP);
+ MLX5_SET(destroy_qp_in, din, qpn, qp->qpn);
mlx5_cmd_exec(dev, din, sizeof(din), dout, sizeof(dout));
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
index 104902a93a0b..2be9ec5fd651 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
@@ -60,16 +60,16 @@ static struct mlx5_rl_entry *find_rl_entry(struct mlx5_rl_table *table,
return ret_entry;
}
-static int mlx5_set_rate_limit_cmd(struct mlx5_core_dev *dev,
+static int mlx5_set_pp_rate_limit_cmd(struct mlx5_core_dev *dev,
u32 rate, u16 index)
{
- u32 in[MLX5_ST_SZ_DW(set_rate_limit_in)] = {0};
- u32 out[MLX5_ST_SZ_DW(set_rate_limit_out)] = {0};
+ u32 in[MLX5_ST_SZ_DW(set_pp_rate_limit_in)] = {0};
+ u32 out[MLX5_ST_SZ_DW(set_pp_rate_limit_out)] = {0};
- MLX5_SET(set_rate_limit_in, in, opcode,
- MLX5_CMD_OP_SET_RATE_LIMIT);
- MLX5_SET(set_rate_limit_in, in, rate_limit_index, index);
- MLX5_SET(set_rate_limit_in, in, rate_limit, rate);
+ MLX5_SET(set_pp_rate_limit_in, in, opcode,
+ MLX5_CMD_OP_SET_PP_RATE_LIMIT);
+ MLX5_SET(set_pp_rate_limit_in, in, rate_limit_index, index);
+ MLX5_SET(set_pp_rate_limit_in, in, rate_limit, rate);
return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
}
@@ -108,7 +108,7 @@ int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index)
entry->refcount++;
} else {
/* new rate limit */
- err = mlx5_set_rate_limit_cmd(dev, rate, entry->index);
+ err = mlx5_set_pp_rate_limit_cmd(dev, rate, entry->index);
if (err) {
mlx5_core_err(dev, "Failed configuring rate: %u (%d)\n",
rate, err);
@@ -144,7 +144,7 @@ void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate)
entry->refcount--;
if (!entry->refcount) {
/* need to remove rate */
- mlx5_set_rate_limit_cmd(dev, 0, entry->index);
+ mlx5_set_pp_rate_limit_cmd(dev, 0, entry->index);
entry->rate = 0;
}
@@ -197,8 +197,8 @@ void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev)
/* Clear all configured rates */
for (i = 0; i < table->max_size; i++)
if (table->rl_entry[i].rate)
- mlx5_set_rate_limit_cmd(dev, 0,
- table->rl_entry[i].index);
+ mlx5_set_pp_rate_limit_cmd(dev, 0,
+ table->rl_entry[i].index);
kfree(dev->priv.rl_table.rl_entry);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index 07a9ba6cfc70..2f74953e4561 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -71,9 +71,9 @@ struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
struct mlx5e_vxlan *vxlan;
- spin_lock(&vxlan_db->lock);
+ spin_lock_bh(&vxlan_db->lock);
vxlan = radix_tree_lookup(&vxlan_db->tree, port);
- spin_unlock(&vxlan_db->lock);
+ spin_unlock_bh(&vxlan_db->lock);
return vxlan;
}
@@ -88,8 +88,12 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
struct mlx5e_vxlan *vxlan;
int err;
- if (mlx5e_vxlan_lookup_port(priv, port))
+ mutex_lock(&priv->state_lock);
+ vxlan = mlx5e_vxlan_lookup_port(priv, port);
+ if (vxlan) {
+ atomic_inc(&vxlan->refcount);
goto free_work;
+ }
if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
goto free_work;
@@ -99,10 +103,11 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
goto err_delete_port;
vxlan->udp_port = port;
+ atomic_set(&vxlan->refcount, 1);
- spin_lock_irq(&vxlan_db->lock);
+ spin_lock_bh(&vxlan_db->lock);
err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan);
- spin_unlock_irq(&vxlan_db->lock);
+ spin_unlock_bh(&vxlan_db->lock);
if (err)
goto err_free;
@@ -113,35 +118,39 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
err_delete_port:
mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
free_work:
+ mutex_unlock(&priv->state_lock);
kfree(vxlan_work);
}
-static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port)
+static void mlx5e_vxlan_del_port(struct work_struct *work)
{
+ struct mlx5e_vxlan_work *vxlan_work =
+ container_of(work, struct mlx5e_vxlan_work, work);
+ struct mlx5e_priv *priv = vxlan_work->priv;
struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
+ u16 port = vxlan_work->port;
struct mlx5e_vxlan *vxlan;
+ bool remove = false;
- spin_lock_irq(&vxlan_db->lock);
- vxlan = radix_tree_delete(&vxlan_db->tree, port);
- spin_unlock_irq(&vxlan_db->lock);
-
+ mutex_lock(&priv->state_lock);
+ spin_lock_bh(&vxlan_db->lock);
+ vxlan = radix_tree_lookup(&vxlan_db->tree, port);
if (!vxlan)
- return;
-
- mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlan->udp_port);
-
- kfree(vxlan);
-}
+ goto out_unlock;
-static void mlx5e_vxlan_del_port(struct work_struct *work)
-{
- struct mlx5e_vxlan_work *vxlan_work =
- container_of(work, struct mlx5e_vxlan_work, work);
- struct mlx5e_priv *priv = vxlan_work->priv;
- u16 port = vxlan_work->port;
+ if (atomic_dec_and_test(&vxlan->refcount)) {
+ radix_tree_delete(&vxlan_db->tree, port);
+ remove = true;
+ }
- __mlx5e_vxlan_core_del_port(priv, port);
+out_unlock:
+ spin_unlock_bh(&vxlan_db->lock);
+ if (remove) {
+ mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+ kfree(vxlan);
+ }
+ mutex_unlock(&priv->state_lock);
kfree(vxlan_work);
}
@@ -171,12 +180,11 @@ void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
struct mlx5e_vxlan *vxlan;
unsigned int port = 0;
- spin_lock_irq(&vxlan_db->lock);
+ /* Lockless since we are the only radix-tree consumers, wq is disabled */
while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) {
port = vxlan->udp_port;
- spin_unlock_irq(&vxlan_db->lock);
- __mlx5e_vxlan_core_del_port(priv, (u16)port);
- spin_lock_irq(&vxlan_db->lock);
+ radix_tree_delete(&vxlan_db->tree, port);
+ mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+ kfree(vxlan);
}
- spin_unlock_irq(&vxlan_db->lock);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
index 5def12c048e3..5ef6ae7d568a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
@@ -36,6 +36,7 @@
#include "en.h"
struct mlx5e_vxlan {
+ atomic_t refcount;
u16 udp_port;
};
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index fbf5945ce00d..2032a6de026b 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -624,6 +624,7 @@ static int ksz9031_read_status(struct phy_device *phydev)
phydev->link = 0;
if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev))
phydev->drv->config_intr(phydev);
+ return genphy_config_aneg(phydev);
}
return 0;
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 105fbfb47e3a..db65d9ad4488 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -907,6 +907,7 @@ static const struct usb_device_id products[] = {
{QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */
{QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */
{QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */
+ {QMI_FIXED_INTF(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */
{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */
{QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index e72234efb648..9b5fc502f6a1 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -576,9 +576,9 @@ enum qeth_cq {
};
struct qeth_ipato {
- int enabled;
- int invert4;
- int invert6;
+ bool enabled;
+ bool invert4;
+ bool invert6;
struct list_head entries;
};
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 838ed6213118..df8f74cb1406 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1475,9 +1475,9 @@ static int qeth_setup_card(struct qeth_card *card)
qeth_set_intial_options(card);
/* IP address takeover */
INIT_LIST_HEAD(&card->ipato.entries);
- card->ipato.enabled = 0;
- card->ipato.invert4 = 0;
- card->ipato.invert6 = 0;
+ card->ipato.enabled = false;
+ card->ipato.invert4 = false;
+ card->ipato.invert6 = false;
/* init QDIO stuff */
qeth_init_qdio_info(card);
INIT_DELAYED_WORK(&card->buffer_reclaim_work, qeth_buffer_reclaim_work);
diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h
index 26f79533e62e..eedf9b01a496 100644
--- a/drivers/s390/net/qeth_l3.h
+++ b/drivers/s390/net/qeth_l3.h
@@ -80,7 +80,7 @@ void qeth_l3_del_vipa(struct qeth_card *, enum qeth_prot_versions, const u8 *);
int qeth_l3_add_rxip(struct qeth_card *, enum qeth_prot_versions, const u8 *);
void qeth_l3_del_rxip(struct qeth_card *card, enum qeth_prot_versions,
const u8 *);
-int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *, struct qeth_ipaddr *);
+void qeth_l3_update_ipato(struct qeth_card *card);
struct qeth_ipaddr *qeth_l3_get_addr_buffer(enum qeth_prot_versions);
int qeth_l3_add_ip(struct qeth_card *, struct qeth_ipaddr *);
int qeth_l3_delete_ip(struct qeth_card *, struct qeth_ipaddr *);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index f91e70c369ed..1487f8a0c575 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -168,8 +168,8 @@ static void qeth_l3_convert_addr_to_bits(u8 *addr, u8 *bits, int len)
}
}
-int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
- struct qeth_ipaddr *addr)
+static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
+ struct qeth_ipaddr *addr)
{
struct qeth_ipato_entry *ipatoe;
u8 addr_bits[128] = {0, };
@@ -178,6 +178,8 @@ int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
if (!card->ipato.enabled)
return 0;
+ if (addr->type != QETH_IP_TYPE_NORMAL)
+ return 0;
qeth_l3_convert_addr_to_bits((u8 *) &addr->u, addr_bits,
(addr->proto == QETH_PROT_IPV4)? 4:16);
@@ -293,8 +295,7 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
memcpy(addr, tmp_addr, sizeof(struct qeth_ipaddr));
addr->ref_counter = 1;
- if (addr->type == QETH_IP_TYPE_NORMAL &&
- qeth_l3_is_addr_covered_by_ipato(card, addr)) {
+ if (qeth_l3_is_addr_covered_by_ipato(card, addr)) {
QETH_CARD_TEXT(card, 2, "tkovaddr");
addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
}
@@ -607,6 +608,27 @@ int qeth_l3_setrouting_v6(struct qeth_card *card)
/*
* IP address takeover related functions
*/
+
+/**
+ * qeth_l3_update_ipato() - Update 'takeover' property, for all NORMAL IPs.
+ *
+ * Caller must hold ip_lock.
+ */
+void qeth_l3_update_ipato(struct qeth_card *card)
+{
+ struct qeth_ipaddr *addr;
+ unsigned int i;
+
+ hash_for_each(card->ip_htable, i, addr, hnode) {
+ if (addr->type != QETH_IP_TYPE_NORMAL)
+ continue;
+ if (qeth_l3_is_addr_covered_by_ipato(card, addr))
+ addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
+ else
+ addr->set_flags &= ~QETH_IPA_SETIP_TAKEOVER_FLAG;
+ }
+}
+
static void qeth_l3_clear_ipato_list(struct qeth_card *card)
{
struct qeth_ipato_entry *ipatoe, *tmp;
@@ -618,6 +640,7 @@ static void qeth_l3_clear_ipato_list(struct qeth_card *card)
kfree(ipatoe);
}
+ qeth_l3_update_ipato(card);
spin_unlock_bh(&card->ip_lock);
}
@@ -642,8 +665,10 @@ int qeth_l3_add_ipato_entry(struct qeth_card *card,
}
}
- if (!rc)
+ if (!rc) {
list_add_tail(&new->entry, &card->ipato.entries);
+ qeth_l3_update_ipato(card);
+ }
spin_unlock_bh(&card->ip_lock);
@@ -666,6 +691,7 @@ void qeth_l3_del_ipato_entry(struct qeth_card *card,
(proto == QETH_PROT_IPV4)? 4:16) &&
(ipatoe->mask_bits == mask_bits)) {
list_del(&ipatoe->entry);
+ qeth_l3_update_ipato(card);
kfree(ipatoe);
}
}
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index cffe42f5775d..d6bdfc6e905a 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -372,8 +372,8 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct qeth_card *card = dev_get_drvdata(dev);
- struct qeth_ipaddr *addr;
- int i, rc = 0;
+ bool enable;
+ int rc = 0;
if (!card)
return -EINVAL;
@@ -386,25 +386,18 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
}
if (sysfs_streq(buf, "toggle")) {
- card->ipato.enabled = (card->ipato.enabled)? 0 : 1;
- } else if (sysfs_streq(buf, "1")) {
- card->ipato.enabled = 1;
- hash_for_each(card->ip_htable, i, addr, hnode) {
- if ((addr->type == QETH_IP_TYPE_NORMAL) &&
- qeth_l3_is_addr_covered_by_ipato(card, addr))
- addr->set_flags |=
- QETH_IPA_SETIP_TAKEOVER_FLAG;
- }
- } else if (sysfs_streq(buf, "0")) {
- card->ipato.enabled = 0;
- hash_for_each(card->ip_htable, i, addr, hnode) {
- if (addr->set_flags &
- QETH_IPA_SETIP_TAKEOVER_FLAG)
- addr->set_flags &=
- ~QETH_IPA_SETIP_TAKEOVER_FLAG;
- }
- } else
+ enable = !card->ipato.enabled;
+ } else if (kstrtobool(buf, &enable)) {
rc = -EINVAL;
+ goto out;
+ }
+
+ if (card->ipato.enabled != enable) {
+ card->ipato.enabled = enable;
+ spin_lock_bh(&card->ip_lock);
+ qeth_l3_update_ipato(card);
+ spin_unlock_bh(&card->ip_lock);
+ }
out:
mutex_unlock(&card->conf_mutex);
return rc ? rc : count;
@@ -430,20 +423,27 @@ static ssize_t qeth_l3_dev_ipato_invert4_store(struct device *dev,
const char *buf, size_t count)
{
struct qeth_card *card = dev_get_drvdata(dev);
+ bool invert;
int rc = 0;
if (!card)
return -EINVAL;
mutex_lock(&card->conf_mutex);
- if (sysfs_streq(buf, "toggle"))
- card->ipato.invert4 = (card->ipato.invert4)? 0 : 1;
- else if (sysfs_streq(buf, "1"))
- card->ipato.invert4 = 1;
- else if (sysfs_streq(buf, "0"))
- card->ipato.invert4 = 0;
- else
+ if (sysfs_streq(buf, "toggle")) {
+ invert = !card->ipato.invert4;
+ } else if (kstrtobool(buf, &invert)) {
rc = -EINVAL;
+ goto out;
+ }
+
+ if (card->ipato.invert4 != invert) {
+ card->ipato.invert4 = invert;
+ spin_lock_bh(&card->ip_lock);
+ qeth_l3_update_ipato(card);
+ spin_unlock_bh(&card->ip_lock);
+ }
+out:
mutex_unlock(&card->conf_mutex);
return rc ? rc : count;
}
@@ -609,20 +609,27 @@ static ssize_t qeth_l3_dev_ipato_invert6_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct qeth_card *card = dev_get_drvdata(dev);
+ bool invert;
int rc = 0;
if (!card)
return -EINVAL;
mutex_lock(&card->conf_mutex);
- if (sysfs_streq(buf, "toggle"))
- card->ipato.invert6 = (card->ipato.invert6)? 0 : 1;
- else if (sysfs_streq(buf, "1"))
- card->ipato.invert6 = 1;
- else if (sysfs_streq(buf, "0"))
- card->ipato.invert6 = 0;
- else
+ if (sysfs_streq(buf, "toggle")) {
+ invert = !card->ipato.invert6;
+ } else if (kstrtobool(buf, &invert)) {
rc = -EINVAL;
+ goto out;
+ }
+
+ if (card->ipato.invert6 != invert) {
+ card->ipato.invert6 = invert;
+ spin_lock_bh(&card->ip_lock);
+ qeth_l3_update_ipato(card);
+ spin_unlock_bh(&card->ip_lock);
+ }
+out:
mutex_unlock(&card->conf_mutex);
return rc ? rc : count;
}
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index bdf0e6e89991..faf50df81622 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -1764,7 +1764,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
{
struct n_tty_data *ldata = tty->disc_data;
- if (!old || (old->c_lflag ^ tty->termios.c_lflag) & ICANON) {
+ if (!old || (old->c_lflag ^ tty->termios.c_lflag) & (ICANON | EXTPROC)) {
bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE);
ldata->line_start = ldata->read_tail;
if (!L_ICANON(tty) || !read_cnt(ldata)) {
@@ -2427,7 +2427,7 @@ static int n_tty_ioctl(struct tty_struct *tty, struct file *file,
return put_user(tty_chars_in_buffer(tty), (int __user *) arg);
case TIOCINQ:
down_write(&tty->termios_rwsem);
- if (L_ICANON(tty))
+ if (L_ICANON(tty) && !L_EXTPROC(tty))
retval = inq_canon(ldata);
else
retval = read_cnt(ldata);
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index c220c2c0893f..e99f1c5b1df6 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -446,7 +446,7 @@ EXPORT_SYMBOL_GPL(tty_prepare_flip_string);
* Callers other than flush_to_ldisc() need to exclude the kworker
* from concurrent use of the line discipline, see paste_selection().
*
- * Returns the number of bytes not processed
+ * Returns the number of bytes processed
*/
int tty_ldisc_receive_buf(struct tty_ldisc *ld, unsigned char *p,
char *f, int count)
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index ba9b29bc441f..7c54a19b20e0 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -1002,7 +1002,7 @@ int usb_get_bos_descriptor(struct usb_device *dev)
case USB_SSP_CAP_TYPE:
ssp_cap = (struct usb_ssp_cap_descriptor *)buffer;
ssac = (le32_to_cpu(ssp_cap->bmAttributes) &
- USB_SSP_SUBLINK_SPEED_ATTRIBS) + 1;
+ USB_SSP_SUBLINK_SPEED_ATTRIBS);
if (length >= USB_DT_USB_SSP_CAP_SIZE(ssac))
dev->bos->ssp_cap = ssp_cap;
break;
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 50010282c010..c05c4f877750 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -57,10 +57,11 @@ static const struct usb_device_id usb_quirk_list[] = {
/* Microsoft LifeCam-VX700 v2.0 */
{ USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },
- /* Logitech HD Pro Webcams C920, C920-C and C930e */
+ /* Logitech HD Pro Webcams C920, C920-C, C925e and C930e */
{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
{ USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT },
{ USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
+ { USB_DEVICE(0x046d, 0x085b), .driver_info = USB_QUIRK_DELAY_INIT },
/* Logitech ConferenceCam CC3000e */
{ USB_DEVICE(0x046d, 0x0847), .driver_info = USB_QUIRK_DELAY_INIT },
@@ -154,6 +155,9 @@ static const struct usb_device_id usb_quirk_list[] = {
/* Genesys Logic hub, internally used by KY-688 USB 3.1 Type-C Hub */
{ USB_DEVICE(0x05e3, 0x0612), .driver_info = USB_QUIRK_NO_LPM },
+ /* ELSA MicroLink 56K */
+ { USB_DEVICE(0x05cc, 0x2267), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Genesys Logic hub, internally used by Moshi USB to Ethernet Adapter */
{ USB_DEVICE(0x05e3, 0x0616), .driver_info = USB_QUIRK_NO_LPM },
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index c87ef38e7416..f6782a347cde 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -189,6 +189,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
xhci->quirks |= XHCI_TRUST_TX_LENGTH;
xhci->quirks |= XHCI_BROKEN_STREAMS;
}
+ if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
+ pdev->device == 0x0014)
+ xhci->quirks |= XHCI_TRUST_TX_LENGTH;
if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
pdev->device == 0x0015)
xhci->quirks |= XHCI_RESET_ON_RESUME;
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 3249f42b4b93..0c743e4cca1e 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1017,6 +1017,7 @@ static const struct usb_device_id id_table_combined[] = {
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
{ USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_BT_USB_PID) },
{ USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_WL_USB_PID) },
+ { USB_DEVICE(AIRBUS_DS_VID, AIRBUS_DS_P8GR) },
{ } /* Terminating entry */
};
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index f9d15bd62785..543d2801632b 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -913,6 +913,12 @@
#define ICPDAS_I7561U_PID 0x0104
#define ICPDAS_I7563U_PID 0x0105
+/*
+ * Airbus Defence and Space
+ */
+#define AIRBUS_DS_VID 0x1e8e /* Vendor ID */
+#define AIRBUS_DS_P8GR 0x6001 /* Tetra P8GR */
+
/*
* RT Systems programming cables for various ham radios
*/
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index ffa8ec917ff5..a818c43a02ec 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -236,6 +236,8 @@ static void option_instat_callback(struct urb *urb);
/* These Quectel products use Qualcomm's vendor ID */
#define QUECTEL_PRODUCT_UC20 0x9003
#define QUECTEL_PRODUCT_UC15 0x9090
+/* These Yuga products use Qualcomm's vendor ID */
+#define YUGA_PRODUCT_CLM920_NC5 0x9625
#define QUECTEL_VENDOR_ID 0x2c7c
/* These Quectel products use Quectel's vendor ID */
@@ -283,6 +285,7 @@ static void option_instat_callback(struct urb *urb);
#define TELIT_PRODUCT_LE922_USBCFG3 0x1043
#define TELIT_PRODUCT_LE922_USBCFG5 0x1045
#define TELIT_PRODUCT_ME910 0x1100
+#define TELIT_PRODUCT_ME910_DUAL_MODEM 0x1101
#define TELIT_PRODUCT_LE920 0x1200
#define TELIT_PRODUCT_LE910 0x1201
#define TELIT_PRODUCT_LE910_USBCFG4 0x1206
@@ -648,6 +651,11 @@ static const struct option_blacklist_info telit_me910_blacklist = {
.reserved = BIT(1) | BIT(3),
};
+static const struct option_blacklist_info telit_me910_dual_modem_blacklist = {
+ .sendsetup = BIT(0),
+ .reserved = BIT(3),
+};
+
static const struct option_blacklist_info telit_le910_blacklist = {
.sendsetup = BIT(0),
.reserved = BIT(1) | BIT(2),
@@ -677,6 +685,10 @@ static const struct option_blacklist_info cinterion_rmnet2_blacklist = {
.reserved = BIT(4) | BIT(5),
};
+static const struct option_blacklist_info yuga_clm920_nc5_blacklist = {
+ .reserved = BIT(1) | BIT(4),
+};
+
static const struct usb_device_id option_ids[] = {
{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) },
{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) },
@@ -1181,6 +1193,9 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)},
{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+ /* Yuga products use Qualcomm vendor ID */
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, YUGA_PRODUCT_CLM920_NC5),
+ .driver_info = (kernel_ulong_t)&yuga_clm920_nc5_blacklist },
/* Quectel products using Quectel vendor ID */
{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
@@ -1247,6 +1262,8 @@ static const struct usb_device_id option_ids[] = {
.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
.driver_info = (kernel_ulong_t)&telit_me910_blacklist },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
+ .driver_info = (kernel_ulong_t)&telit_me910_dual_modem_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
.driver_info = (kernel_ulong_t)&telit_le910_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4),
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 4516291df1b8..fb6dc16c754a 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -166,6 +166,8 @@ static const struct usb_device_id id_table[] = {
{DEVICE_SWI(0x1199, 0x9079)}, /* Sierra Wireless EM74xx */
{DEVICE_SWI(0x1199, 0x907a)}, /* Sierra Wireless EM74xx QDL */
{DEVICE_SWI(0x1199, 0x907b)}, /* Sierra Wireless EM74xx */
+ {DEVICE_SWI(0x1199, 0x9090)}, /* Sierra Wireless EM7565 QDL */
+ {DEVICE_SWI(0x1199, 0x9091)}, /* Sierra Wireless EM7565 */
{DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
{DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
{DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
@@ -346,6 +348,7 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id)
break;
case 2:
dev_dbg(dev, "NMEA GPS interface found\n");
+ sendsetup = true;
break;
case 3:
dev_dbg(dev, "Modem port found\n");
diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c
index c653ce533430..1886d8e4f14e 100644
--- a/drivers/usb/usbip/stub_dev.c
+++ b/drivers/usb/usbip/stub_dev.c
@@ -163,8 +163,7 @@ static void stub_shutdown_connection(struct usbip_device *ud)
* step 1?
*/
if (ud->tcp_socket) {
- dev_dbg(&sdev->udev->dev, "shutdown tcp_socket %p\n",
- ud->tcp_socket);
+ dev_dbg(&sdev->udev->dev, "shutdown sockfd\n");
kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
}
diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c
index af10f7b131a4..325b4c05acdd 100644
--- a/drivers/usb/usbip/stub_main.c
+++ b/drivers/usb/usbip/stub_main.c
@@ -252,11 +252,12 @@ void stub_device_cleanup_urbs(struct stub_device *sdev)
struct stub_priv *priv;
struct urb *urb;
- dev_dbg(&sdev->udev->dev, "free sdev %p\n", sdev);
+ dev_dbg(&sdev->udev->dev, "Stub device cleaning up urbs\n");
while ((priv = stub_priv_pop(sdev))) {
urb = priv->urb;
- dev_dbg(&sdev->udev->dev, "free urb %p\n", urb);
+ dev_dbg(&sdev->udev->dev, "free urb seqnum %lu\n",
+ priv->seqnum);
usb_kill_urb(urb);
kmem_cache_free(stub_priv_cache, priv);
diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c
index 283a9be77a22..5b807185f79e 100644
--- a/drivers/usb/usbip/stub_rx.c
+++ b/drivers/usb/usbip/stub_rx.c
@@ -225,9 +225,6 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev,
if (priv->seqnum != pdu->u.cmd_unlink.seqnum)
continue;
- dev_info(&priv->urb->dev->dev, "unlink urb %p\n",
- priv->urb);
-
/*
* This matched urb is not completed yet (i.e., be in
* flight in usb hcd hardware/driver). Now we are
@@ -266,8 +263,8 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev,
ret = usb_unlink_urb(priv->urb);
if (ret != -EINPROGRESS)
dev_err(&priv->urb->dev->dev,
- "failed to unlink a urb %p, ret %d\n",
- priv->urb, ret);
+ "failed to unlink a urb # %lu, ret %d\n",
+ priv->seqnum, ret);
return 0;
}
diff --git a/drivers/usb/usbip/stub_tx.c b/drivers/usb/usbip/stub_tx.c
index 87ff94be4235..96aa375b80d9 100644
--- a/drivers/usb/usbip/stub_tx.c
+++ b/drivers/usb/usbip/stub_tx.c
@@ -102,7 +102,7 @@ void stub_complete(struct urb *urb)
/* link a urb to the queue of tx. */
spin_lock_irqsave(&sdev->priv_lock, flags);
if (sdev->ud.tcp_socket == NULL) {
- usbip_dbg_stub_tx("ignore urb for closed connection %p", urb);
+ usbip_dbg_stub_tx("ignore urb for closed connection\n");
/* It will be freed in stub_device_cleanup_urbs(). */
} else if (priv->unlinking) {
stub_enqueue_ret_unlink(sdev, priv->seqnum, urb->status);
@@ -204,8 +204,8 @@ static int stub_send_ret_submit(struct stub_device *sdev)
/* 1. setup usbip_header */
setup_ret_submit_pdu(&pdu_header, urb);
- usbip_dbg_stub_tx("setup txdata seqnum: %d urb: %p\n",
- pdu_header.base.seqnum, urb);
+ usbip_dbg_stub_tx("setup txdata seqnum: %d\n",
+ pdu_header.base.seqnum);
usbip_header_correct_endian(&pdu_header, 1);
iov[iovnum].iov_base = &pdu_header;
diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c
index 8b232290be6b..e24b24fa0f16 100644
--- a/drivers/usb/usbip/usbip_common.c
+++ b/drivers/usb/usbip/usbip_common.c
@@ -335,13 +335,10 @@ int usbip_recv(struct socket *sock, void *buf, int size)
char *bp = buf;
int osize = size;
- usbip_dbg_xmit("enter\n");
-
- if (!sock || !buf || !size) {
- pr_err("invalid arg, sock %p buff %p size %d\n", sock, buf,
- size);
+ if (!sock || !buf || !size)
return -EINVAL;
- }
+
+ usbip_dbg_xmit("enter\n");
do {
sock->sk->sk_allocation = GFP_NOIO;
@@ -354,11 +351,8 @@ int usbip_recv(struct socket *sock, void *buf, int size)
msg.msg_flags = MSG_NOSIGNAL;
result = kernel_recvmsg(sock, &msg, &iov, 1, size, MSG_WAITALL);
- if (result <= 0) {
- pr_debug("receive sock %p buf %p size %u ret %d total %d\n",
- sock, buf, size, result, total);
+ if (result <= 0)
goto err;
- }
size -= result;
buf += result;
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index d6dc165e924b..7f161b095176 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -506,9 +506,6 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb,
struct vhci_device *vdev;
unsigned long flags;
- usbip_dbg_vhci_hc("enter, usb_hcd %p urb %p mem_flags %d\n",
- hcd, urb, mem_flags);
-
if (portnum > VHCI_HC_PORTS) {
pr_err("invalid port number %d\n", portnum);
return -ENODEV;
@@ -671,8 +668,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
struct vhci_device *vdev;
unsigned long flags;
- pr_info("dequeue a urb %p\n", urb);
-
spin_lock_irqsave(&vhci->lock, flags);
priv = urb->hcpriv;
@@ -700,7 +695,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
/* tcp connection is closed */
spin_lock(&vdev->priv_lock);
- pr_info("device %p seems to be disconnected\n", vdev);
list_del(&priv->list);
kfree(priv);
urb->hcpriv = NULL;
@@ -712,8 +706,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
* vhci_rx will receive RET_UNLINK and give back the URB.
* Otherwise, we give back it here.
*/
- pr_info("gives back urb %p\n", urb);
-
usb_hcd_unlink_urb_from_ep(hcd, urb);
spin_unlock_irqrestore(&vhci->lock, flags);
@@ -741,8 +733,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
unlink->unlink_seqnum = priv->seqnum;
- pr_info("device %p seems to be still connected\n", vdev);
-
/* send cmd_unlink and try to cancel the pending URB in the
* peer */
list_add_tail(&unlink->list, &vdev->unlink_tx);
@@ -823,7 +813,7 @@ static void vhci_shutdown_connection(struct usbip_device *ud)
/* need this? see stub_dev.c */
if (ud->tcp_socket) {
- pr_debug("shutdown tcp_socket %p\n", ud->tcp_socket);
+ pr_debug("shutdown tcp_socket\n");
kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
}
diff --git a/drivers/usb/usbip/vhci_rx.c b/drivers/usb/usbip/vhci_rx.c
index fc2d319e2360..5943deeec115 100644
--- a/drivers/usb/usbip/vhci_rx.c
+++ b/drivers/usb/usbip/vhci_rx.c
@@ -37,24 +37,23 @@ struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, __u32 seqnum)
urb = priv->urb;
status = urb->status;
- usbip_dbg_vhci_rx("find urb %p vurb %p seqnum %u\n",
- urb, priv, seqnum);
+ usbip_dbg_vhci_rx("find urb seqnum %u\n", seqnum);
switch (status) {
case -ENOENT:
/* fall through */
case -ECONNRESET:
- dev_info(&urb->dev->dev,
- "urb %p was unlinked %ssynchronuously.\n", urb,
- status == -ENOENT ? "" : "a");
+ dev_dbg(&urb->dev->dev,
+ "urb seq# %u was unlinked %ssynchronuously\n",
+ seqnum, status == -ENOENT ? "" : "a");
break;
case -EINPROGRESS:
/* no info output */
break;
default:
- dev_info(&urb->dev->dev,
- "urb %p may be in a error, status %d\n", urb,
- status);
+ dev_dbg(&urb->dev->dev,
+ "urb seq# %u may be in a error, status %d\n",
+ seqnum, status);
}
list_del(&priv->list);
@@ -80,8 +79,8 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
spin_unlock_irqrestore(&vdev->priv_lock, flags);
if (!urb) {
- pr_err("cannot find a urb of seqnum %u\n", pdu->base.seqnum);
- pr_info("max seqnum %d\n",
+ pr_err("cannot find a urb of seqnum %u max seqnum %d\n",
+ pdu->base.seqnum,
atomic_read(&vhci->seqnum));
usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
return;
@@ -104,7 +103,7 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
if (usbip_dbg_flag_vhci_rx)
usbip_dump_urb(urb);
- usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
+ usbip_dbg_vhci_rx("now giveback urb %u\n", pdu->base.seqnum);
spin_lock_irqsave(&vhci->lock, flags);
usb_hcd_unlink_urb_from_ep(vhci_to_hcd(vhci), urb);
@@ -170,7 +169,7 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev,
pr_info("the urb (seqnum %d) was already given back\n",
pdu->base.seqnum);
} else {
- usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
+ usbip_dbg_vhci_rx("now giveback urb %d\n", pdu->base.seqnum);
/* If unlink is successful, status is -ECONNRESET */
urb->status = pdu->u.ret_unlink.status;
diff --git a/drivers/usb/usbip/vhci_tx.c b/drivers/usb/usbip/vhci_tx.c
index 3e7878fe2fd4..a9a663a578b6 100644
--- a/drivers/usb/usbip/vhci_tx.c
+++ b/drivers/usb/usbip/vhci_tx.c
@@ -83,7 +83,8 @@ static int vhci_send_cmd_submit(struct vhci_device *vdev)
memset(&msg, 0, sizeof(msg));
memset(&iov, 0, sizeof(iov));
- usbip_dbg_vhci_tx("setup txdata urb %p\n", urb);
+ usbip_dbg_vhci_tx("setup txdata urb seqnum %lu\n",
+ priv->seqnum);
/* 1. setup usbip_header */
setup_cmd_submit_pdu(&pdu_header, urb);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 965cc5693a46..c9447a689522 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -48,7 +48,7 @@ enum cpuhp_state {
CPUHP_ARM_SHMOBILE_SCU_PREPARE,
CPUHP_SH_SH3X_PREPARE,
CPUHP_BLK_MQ_PREPARE,
- CPUHP_TIMERS_DEAD,
+ CPUHP_TIMERS_PREPARE,
CPUHP_NOTF_ERR_INJ_PREPARE,
CPUHP_MIPS_SOC_PREPARE,
CPUHP_BRINGUP_CPU,
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index a0649973ee5b..b9dfca557a6c 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -246,7 +246,8 @@ struct ipv6_pinfo {
* 100: prefer care-of address
*/
dontfrag:1,
- autoflowlabel:1;
+ autoflowlabel:1,
+ autoflowlabel_set:1;
__u8 min_hopcount;
__u8 tclass;
__be32 rcv_flowinfo;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6045d4d58065..25ed105bbcfb 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -143,7 +143,7 @@ enum {
MLX5_CMD_OP_ALLOC_Q_COUNTER = 0x771,
MLX5_CMD_OP_DEALLOC_Q_COUNTER = 0x772,
MLX5_CMD_OP_QUERY_Q_COUNTER = 0x773,
- MLX5_CMD_OP_SET_RATE_LIMIT = 0x780,
+ MLX5_CMD_OP_SET_PP_RATE_LIMIT = 0x780,
MLX5_CMD_OP_QUERY_RATE_LIMIT = 0x781,
MLX5_CMD_OP_ALLOC_PD = 0x800,
MLX5_CMD_OP_DEALLOC_PD = 0x801,
@@ -6689,7 +6689,7 @@ struct mlx5_ifc_add_vxlan_udp_dport_in_bits {
u8 vxlan_udp_port[0x10];
};
-struct mlx5_ifc_set_rate_limit_out_bits {
+struct mlx5_ifc_set_pp_rate_limit_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -6698,7 +6698,7 @@ struct mlx5_ifc_set_rate_limit_out_bits {
u8 reserved_at_40[0x40];
};
-struct mlx5_ifc_set_rate_limit_in_bits {
+struct mlx5_ifc_set_pp_rate_limit_in_bits {
u8 opcode[0x10];
u8 reserved_at_10[0x10];
@@ -6711,6 +6711,8 @@ struct mlx5_ifc_set_rate_limit_in_bits {
u8 reserved_at_60[0x20];
u8 rate_limit[0x20];
+
+ u8 reserved_at_a0[0x160];
};
struct mlx5_ifc_access_register_out_bits {
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index b83507c0640c..e38f471a5402 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -99,12 +99,18 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r)
/* Note: callers invoking this in a loop must use a compiler barrier,
* for example cpu_relax(). Callers must hold producer_lock.
+ * Callers are responsible for making sure pointer that is being queued
+ * points to a valid data.
*/
static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
{
if (unlikely(!r->size) || r->queue[r->producer])
return -ENOSPC;
+ /* Make sure the pointer we are storing points to a valid data. */
+ /* Pairs with smp_read_barrier_depends in __ptr_ring_consume. */
+ smp_wmb();
+
r->queue[r->producer++] = ptr;
if (unlikely(r->producer >= r->size))
r->producer = 0;
@@ -244,6 +250,9 @@ static inline void *__ptr_ring_consume(struct ptr_ring *r)
if (ptr)
__ptr_ring_discard_one(r);
+ /* Make sure anyone accessing data through the pointer is up to date. */
+ /* Pairs with smp_wmb in __ptr_ring_produce. */
+ smp_read_barrier_depends();
return ptr;
}
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 647532b0eb03..f50b717ce644 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -219,7 +219,8 @@ struct tcp_sock {
} rack;
u16 advmss; /* Advertised MSS */
u8 rate_app_limited:1, /* rate_{delivered,interval_us} limited? */
- unused:7;
+ is_sack_reneg:1, /* in recovery from loss with SACK reneg? */
+ unused:6;
u8 nonagle : 4,/* Disable Nagle algorithm? */
thin_lto : 1,/* Use linear timeouts for thin streams */
thin_dupack : 1,/* Fast retransmit on first dupack */
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 51d601f192d4..ec86e4e55ea3 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -274,9 +274,11 @@ unsigned long round_jiffies_up(unsigned long j);
unsigned long round_jiffies_up_relative(unsigned long j);
#ifdef CONFIG_HOTPLUG_CPU
+int timers_prepare_cpu(unsigned int cpu);
int timers_dead_cpu(unsigned int cpu);
#else
-#define timers_dead_cpu NULL
+#define timers_prepare_cpu NULL
+#define timers_dead_cpu NULL
#endif
#endif
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 4d6ec58a8d45..2edb150f1a4d 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -89,10 +89,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
#endif
#endif
#ifdef CONFIG_DEBUG_TLBFLUSH
-#ifdef CONFIG_SMP
NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */
NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
-#endif /* CONFIG_SMP */
NR_TLB_LOCAL_FLUSH_ALL,
NR_TLB_LOCAL_FLUSH_ONE,
#endif /* CONFIG_DEBUG_TLBFLUSH */
diff --git a/include/net/ip.h b/include/net/ip.h
index 51c6b9786c46..0e3dcd5a134d 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -33,6 +33,8 @@
#include <net/flow.h>
#include <net/flow_dissector.h>
+#define IPV4_MIN_MTU 68 /* RFC 791 */
+
struct sock;
struct inet_skb_parm {
diff --git a/include/net/tcp.h b/include/net/tcp.h
index fba4fc46871d..caf35e062639 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1001,7 +1001,7 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb);
void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
struct rate_sample *rs);
void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
- struct skb_mstamp *now, struct rate_sample *rs);
+ bool is_sack_reneg, struct skb_mstamp *now, struct rate_sample *rs);
void tcp_rate_check_app_limited(struct sock *sk);
/* These functions determine how the current flow behaves in respect of SACK
diff --git a/kernel/cpu.c b/kernel/cpu.c
index e1436ca4aed0..802eb3361a0a 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1309,9 +1309,9 @@ static struct cpuhp_step cpuhp_bp_states[] = {
* before blk_mq_queue_reinit_notify() from notify_dead(),
* otherwise a RCU stall occurs.
*/
- [CPUHP_TIMERS_DEAD] = {
+ [CPUHP_TIMERS_PREPARE] = {
.name = "timers:dead",
- .startup.single = NULL,
+ .startup.single = timers_prepare_cpu,
.teardown.single = timers_dead_cpu,
},
/* Kicks the plugged cpu into life */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3bcb61b52f6c..dae1a45be504 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -663,6 +663,11 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
}
+static inline bool local_timer_softirq_pending(void)
+{
+ return local_softirq_pending() & TIMER_SOFTIRQ;
+}
+
static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
ktime_t now, int cpu)
{
@@ -679,8 +684,18 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
} while (read_seqretry(&jiffies_lock, seq));
ts->last_jiffies = basejiff;
- if (rcu_needs_cpu(basemono, &next_rcu) ||
- arch_needs_cpu() || irq_work_needs_cpu()) {
+ /*
+ * Keep the periodic tick, when RCU, architecture or irq_work
+ * requests it.
+ * Aside of that check whether the local timer softirq is
+ * pending. If so its a bad idea to call get_next_timer_interrupt()
+ * because there is an already expired timer, so it will request
+ * immeditate expiry, which rearms the hardware timer with a
+ * minimal delta which brings us back to this place
+ * immediately. Lather, rinse and repeat...
+ */
+ if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() ||
+ irq_work_needs_cpu() || local_timer_softirq_pending()) {
next_tick = basemono + TICK_NSEC;
} else {
/*
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 7d670362891a..e872f7f05e8a 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -849,11 +849,10 @@ static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu)
struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu);
/*
- * If the timer is deferrable and nohz is active then we need to use
- * the deferrable base.
+ * If the timer is deferrable and NO_HZ_COMMON is set then we need
+ * to use the deferrable base.
*/
- if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
- (tflags & TIMER_DEFERRABLE))
+ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu);
return base;
}
@@ -863,11 +862,10 @@ static inline struct timer_base *get_timer_this_cpu_base(u32 tflags)
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
/*
- * If the timer is deferrable and nohz is active then we need to use
- * the deferrable base.
+ * If the timer is deferrable and NO_HZ_COMMON is set then we need
+ * to use the deferrable base.
*/
- if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
- (tflags & TIMER_DEFERRABLE))
+ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
base = this_cpu_ptr(&timer_bases[BASE_DEF]);
return base;
}
@@ -1021,8 +1019,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
if (!ret && pending_only)
goto out_unlock;
- debug_activate(timer, expires);
-
new_base = get_target_base(base, timer->flags);
if (base != new_base) {
@@ -1046,6 +1042,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
}
}
+ debug_activate(timer, expires);
+
timer->expires = expires;
/*
* If 'idx' was calculated above and the base time did not advance
@@ -1684,7 +1682,7 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
base->must_forward_clk = false;
__run_timers(base);
- if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)
+ if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
}
@@ -1853,6 +1851,21 @@ static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *h
}
}
+int timers_prepare_cpu(unsigned int cpu)
+{
+ struct timer_base *base;
+ int b;
+
+ for (b = 0; b < NR_BASES; b++) {
+ base = per_cpu_ptr(&timer_bases[b], cpu);
+ base->clk = jiffies;
+ base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
+ base->is_idle = false;
+ base->must_forward_clk = true;
+ }
+ return 0;
+}
+
int timers_dead_cpu(unsigned int cpu)
{
struct timer_base *old_base;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f5c016e8fc88..3e1d11f4fe44 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -280,6 +280,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
/* Missed count stored at end */
#define RB_MISSED_STORED (1 << 30)
+#define RB_MISSED_FLAGS (RB_MISSED_EVENTS|RB_MISSED_STORED)
+
struct buffer_data_page {
u64 time_stamp; /* page time stamp */
local_t commit; /* write committed index */
@@ -331,7 +333,9 @@ static void rb_init_page(struct buffer_data_page *bpage)
*/
size_t ring_buffer_page_len(void *page)
{
- return local_read(&((struct buffer_data_page *)page)->commit)
+ struct buffer_data_page *bpage = page;
+
+ return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS)
+ BUF_PAGE_HDR_SIZE;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4214cd960b8e..15b02645ce8b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6181,7 +6181,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
.spd_release = buffer_spd_release,
};
struct buffer_ref *ref;
- int entries, size, i;
+ int entries, i;
ssize_t ret = 0;
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -6232,14 +6232,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
break;
}
- /*
- * zero out any left over data, this is going to
- * user land.
- */
- size = ring_buffer_page_len(ref->page);
- if (size < PAGE_SIZE)
- memset(ref->page + size, 0, PAGE_SIZE - size);
-
page = virt_to_page(ref->page);
spd.pages[i] = page;
@@ -6963,6 +6955,7 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
buf->data = alloc_percpu(struct trace_array_cpu);
if (!buf->data) {
ring_buffer_free(buf->buffer);
+ buf->buffer = NULL;
return -ENOMEM;
}
@@ -6986,7 +6979,9 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
allocate_snapshot ? size : 1);
if (WARN_ON(ret)) {
ring_buffer_free(tr->trace_buffer.buffer);
+ tr->trace_buffer.buffer = NULL;
free_percpu(tr->trace_buffer.data);
+ tr->trace_buffer.data = NULL;
return -ENOMEM;
}
tr->allocated_snapshot = allocate_snapshot;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 5d4006e589cb..4f831225d34f 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1092,19 +1092,20 @@ static int br_dev_newlink(struct net *src_net, struct net_device *dev,
struct net_bridge *br = netdev_priv(dev);
int err;
+ err = register_netdevice(dev);
+ if (err)
+ return err;
+
if (tb[IFLA_ADDRESS]) {
spin_lock_bh(&br->lock);
br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
spin_unlock_bh(&br->lock);
}
- err = register_netdevice(dev);
- if (err)
- return err;
-
err = br_changelink(dev, tb, data);
if (err)
- unregister_netdevice(dev);
+ br_dev_delete(dev, NULL);
+
return err;
}
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 7001da910c6b..b7efe2f19f83 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -263,7 +263,7 @@ struct net *get_net_ns_by_id(struct net *net, int id)
spin_lock_irqsave(&net->nsid_lock, flags);
peer = idr_find(&net->netns_ids, id);
if (peer)
- get_net(peer);
+ peer = maybe_get_net(peer);
spin_unlock_irqrestore(&net->nsid_lock, flags);
rcu_read_unlock();
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index aec5605944d3..a64515583bc1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3823,7 +3823,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
struct sock *sk = skb->sk;
if (!skb_may_tx_timestamp(sk, false))
- return;
+ goto err;
/* Take a reference to prevent skb_orphan() from freeing the socket,
* but only if the socket refcount is not zero.
@@ -3832,7 +3832,11 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
*skb_hwtstamps(skb) = *hwtstamps;
__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
sock_put(sk);
+ return;
}
+
+err:
+ kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 062a67ca9a21..f08f984ebc56 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1380,7 +1380,7 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
static bool inetdev_valid_mtu(unsigned int mtu)
{
- return mtu >= 68;
+ return mtu >= IPV4_MIN_MTU;
}
static void inetdev_send_gratuitous_arp(struct net_device *dev,
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 968d8e165e3d..ffae472e250a 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1253,14 +1253,19 @@ static int __net_init ip_fib_net_init(struct net *net)
static void ip_fib_net_exit(struct net *net)
{
- unsigned int i;
+ int i;
rtnl_lock();
#ifdef CONFIG_IP_MULTIPLE_TABLES
RCU_INIT_POINTER(net->ipv4.fib_main, NULL);
RCU_INIT_POINTER(net->ipv4.fib_default, NULL);
#endif
- for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+ /* Destroy the tables in reverse order to guarantee that the
+ * local table, ID 255, is destroyed before the main table, ID
+ * 254. This is necessary as the local table may contain
+ * references to data contained in the main table.
+ */
+ for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) {
struct hlist_head *head = &net->ipv4.fib_table_hash[i];
struct hlist_node *tmp;
struct fib_table *tb;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 08575e3bd135..7bff0c65046f 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -89,6 +89,7 @@
#include <linux/rtnetlink.h>
#include <linux/times.h>
#include <linux/pkt_sched.h>
+#include <linux/byteorder/generic.h>
#include <net/net_namespace.h>
#include <net/arp.h>
@@ -321,6 +322,23 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted)
return scount;
}
+/* source address selection per RFC 3376 section 4.2.13 */
+static __be32 igmpv3_get_srcaddr(struct net_device *dev,
+ const struct flowi4 *fl4)
+{
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+ if (!in_dev)
+ return htonl(INADDR_ANY);
+
+ for_ifa(in_dev) {
+ if (inet_ifa_match(fl4->saddr, ifa))
+ return fl4->saddr;
+ } endfor_ifa(in_dev);
+
+ return htonl(INADDR_ANY);
+}
+
static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
{
struct sk_buff *skb;
@@ -368,7 +386,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
pip->frag_off = htons(IP_DF);
pip->ttl = 1;
pip->daddr = fl4.daddr;
- pip->saddr = fl4.saddr;
+ pip->saddr = igmpv3_get_srcaddr(dev, &fl4);
pip->protocol = IPPROTO_IGMP;
pip->tot_len = 0; /* filled in later */
ip_select_ident(net, skb, NULL);
@@ -404,16 +422,17 @@ static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel)
}
static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc,
- int type, struct igmpv3_grec **ppgr)
+ int type, struct igmpv3_grec **ppgr, unsigned int mtu)
{
struct net_device *dev = pmc->interface->dev;
struct igmpv3_report *pih;
struct igmpv3_grec *pgr;
- if (!skb)
- skb = igmpv3_newpack(dev, dev->mtu);
- if (!skb)
- return NULL;
+ if (!skb) {
+ skb = igmpv3_newpack(dev, mtu);
+ if (!skb)
+ return NULL;
+ }
pgr = (struct igmpv3_grec *)skb_put(skb, sizeof(struct igmpv3_grec));
pgr->grec_type = type;
pgr->grec_auxwords = 0;
@@ -436,12 +455,17 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
struct igmpv3_grec *pgr = NULL;
struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list;
int scount, stotal, first, isquery, truncate;
+ unsigned int mtu;
if (pmc->multiaddr == IGMP_ALL_HOSTS)
return skb;
if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
return skb;
+ mtu = READ_ONCE(dev->mtu);
+ if (mtu < IPV4_MIN_MTU)
+ return skb;
+
isquery = type == IGMPV3_MODE_IS_INCLUDE ||
type == IGMPV3_MODE_IS_EXCLUDE;
truncate = type == IGMPV3_MODE_IS_EXCLUDE ||
@@ -462,7 +486,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
igmpv3_sendpack(skb);
- skb = igmpv3_newpack(dev, dev->mtu);
+ skb = igmpv3_newpack(dev, mtu);
}
}
first = 1;
@@ -498,12 +522,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
pgr->grec_nsrcs = htons(scount);
if (skb)
igmpv3_sendpack(skb);
- skb = igmpv3_newpack(dev, dev->mtu);
+ skb = igmpv3_newpack(dev, mtu);
first = 1;
scount = 0;
}
if (first) {
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
first = 0;
}
if (!skb)
@@ -538,7 +562,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
igmpv3_sendpack(skb);
skb = NULL; /* add_grhead will get a new one */
}
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
}
}
if (pgr)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index bd7f1836bb70..96536a0d6e2d 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -346,8 +346,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
dev->needed_headroom = t_hlen + hlen;
mtu -= (dev->hard_header_len + t_hlen);
- if (mtu < 68)
- mtu = 68;
+ if (mtu < IPV4_MIN_MTU)
+ mtu = IPV4_MIN_MTU;
return mtu;
}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 9879b73d5565..59d8770055ed 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -502,11 +502,16 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
int err;
struct ip_options_data opt_copy;
struct raw_frag_vec rfv;
+ int hdrincl;
err = -EMSGSIZE;
if (len > 0xFFFF)
goto out;
+ /* hdrincl should be READ_ONCE(inet->hdrincl)
+ * but READ_ONCE() doesn't work with bit fields
+ */
+ hdrincl = inet->hdrincl;
/*
* Check the flags.
*/
@@ -582,7 +587,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
/* Linux does not mangle headers on raw sockets,
* so that IP options + IP_HDRINCL is non-sense.
*/
- if (inet->hdrincl)
+ if (hdrincl)
goto done;
if (ipc.opt->opt.srr) {
if (!daddr)
@@ -604,12 +609,12 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
- inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
- (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
+ (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0);
- if (!inet->hdrincl) {
+ if (!hdrincl) {
rfv.msg = msg;
rfv.hlen = 0;
@@ -634,7 +639,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
goto do_confirm;
back_from_confirm:
- if (inet->hdrincl)
+ if (hdrincl)
err = raw_send_hdrinc(sk, &fl4, msg, len,
&rt, msg->msg_flags, &ipc.sockc);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index dd33c785ce16..05d2bde00864 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2297,6 +2297,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->snd_cwnd_cnt = 0;
tp->window_clamp = 0;
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
tcp_clear_retrans(tp);
inet_csk_delack_init(sk);
/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index cb8db347c680..97f9cac98348 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -81,7 +81,8 @@ struct bbr {
u32 lt_last_lost; /* LT intvl start: tp->lost */
u32 pacing_gain:10, /* current gain for setting pacing rate */
cwnd_gain:10, /* current gain for setting cwnd */
- full_bw_cnt:3, /* number of rounds without large bw gains */
+ full_bw_reached:1, /* reached full bw in Startup? */
+ full_bw_cnt:2, /* number of rounds without large bw gains */
cycle_idx:3, /* current index in pacing_gain cycle array */
has_seen_rtt:1, /* have we seen an RTT sample yet? */
unused_b:5;
@@ -151,7 +152,7 @@ static bool bbr_full_bw_reached(const struct sock *sk)
{
const struct bbr *bbr = inet_csk_ca(sk);
- return bbr->full_bw_cnt >= bbr_full_bw_cnt;
+ return bbr->full_bw_reached;
}
/* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */
@@ -688,6 +689,7 @@ static void bbr_check_full_bw_reached(struct sock *sk,
return;
}
++bbr->full_bw_cnt;
+ bbr->full_bw_reached = bbr->full_bw_cnt >= bbr_full_bw_cnt;
}
/* If pipe is probably full, drain the queue and then enter steady-state. */
@@ -821,6 +823,7 @@ static void bbr_init(struct sock *sk)
bbr->restore_cwnd = 0;
bbr->round_start = 0;
bbr->idle_restart = 0;
+ bbr->full_bw_reached = 0;
bbr->full_bw = 0;
bbr->full_bw_cnt = 0;
bbr->cycle_mstamp.v64 = 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 05255a286888..2f107e46355c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1966,6 +1966,8 @@ void tcp_enter_loss(struct sock *sk)
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
tp->sacked_out = 0;
tp->fackets_out = 0;
+ /* Mark SACK reneging until we recover from this loss event. */
+ tp->is_sack_reneg = 1;
}
tcp_clear_all_retrans_hints(tp);
@@ -2463,6 +2465,7 @@ static bool tcp_try_undo_recovery(struct sock *sk)
return true;
}
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
return false;
}
@@ -2494,8 +2497,10 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPSPURIOUSRTOS);
inet_csk(sk)->icsk_retransmits = 0;
- if (frto_undo || tcp_is_sack(tp))
+ if (frto_undo || tcp_is_sack(tp)) {
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
+ }
return true;
}
return false;
@@ -3589,6 +3594,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
struct tcp_sacktag_state sack_state;
struct rate_sample rs = { .prior_delivered = 0 };
u32 prior_snd_una = tp->snd_una;
+ bool is_sack_reneg = tp->is_sack_reneg;
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
bool is_dupack = false;
@@ -3711,7 +3717,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
tcp_schedule_loss_probe(sk);
delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */
lost = tp->lost - lost; /* freshly marked lost */
- tcp_rate_gen(sk, delivered, lost, &now, &rs);
+ tcp_rate_gen(sk, delivered, lost, is_sack_reneg, &now, &rs);
tcp_cong_control(sk, ack, delivered, flag, &rs);
tcp_xmit_recovery(sk, rexmit);
return 1;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d577ec07a0d8..b3960738464e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -828,7 +828,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
tcp_time_stamp,
req->ts_recent,
0,
- tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
+ tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr,
AF_INET),
inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
ip_hdr(skb)->tos);
diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c
index 9be1581a5a08..18309f58ab8d 100644
--- a/net/ipv4/tcp_rate.c
+++ b/net/ipv4/tcp_rate.c
@@ -106,7 +106,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
/* Update the connection delivery information and generate a rate sample. */
void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
- struct skb_mstamp *now, struct rate_sample *rs)
+ bool is_sack_reneg, struct skb_mstamp *now, struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 snd_us, ack_us;
@@ -124,8 +124,12 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
rs->acked_sacked = delivered; /* freshly ACKed or SACKed */
rs->losses = lost; /* freshly marked lost */
- /* Return an invalid sample if no timing information is available. */
- if (!rs->prior_mstamp.v64) {
+ /* Return an invalid sample if no timing information is available or
+ * in recovery from loss with SACK reneging. Rate samples taken during
+ * a SACK reneging event may overestimate bw by including packets that
+ * were SACKed before the reneg.
+ */
+ if (!rs->prior_mstamp.v64 || is_sack_reneg) {
rs->delivered = -1;
rs->interval_us = -1;
return;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 8285a1c108c9..5cad76f87536 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -209,7 +209,6 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
np->mcast_hops = IPV6_DEFAULT_MCASTHOPS;
np->mc_loop = 1;
np->pmtudisc = IPV6_PMTUDISC_WANT;
- np->autoflowlabel = ip6_default_np_autolabel(sock_net(sk));
sk->sk_ipv6only = net->ipv6.sysctl.bindv6only;
/* Init the ipv4 part of the socket since we can have sockets
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6e01c9a8dfd3..506efba33a89 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -156,6 +156,14 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
!(IP6CB(skb)->flags & IP6SKB_REROUTED));
}
+static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
+{
+ if (!np->autoflowlabel_set)
+ return ip6_default_np_autolabel(net);
+ else
+ return np->autoflowlabel;
+}
+
/*
* xmit an sk_buff (used by TCP, SCTP and DCCP)
* Note : socket lock is not held for SYNACK packets, but might be modified
@@ -219,7 +227,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
hlimit = ip6_dst_hoplimit(dst);
ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
- np->autoflowlabel, fl6));
+ ip6_autoflowlabel(net, np), fl6));
hdr->payload_len = htons(seg_len);
hdr->nexthdr = proto;
@@ -1691,7 +1699,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
ip6_flow_hdr(hdr, v6_cork->tclass,
ip6_make_flowlabel(net, skb, fl6->flowlabel,
- np->autoflowlabel, fl6));
+ ip6_autoflowlabel(net, np), fl6));
hdr->hop_limit = v6_cork->hop_limit;
hdr->nexthdr = proto;
hdr->saddr = fl6->saddr;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 12b2fd512f32..11d22d642488 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -911,7 +911,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto,
if (t->parms.collect_md) {
tun_dst = ipv6_tun_rx_dst(skb, 0, 0, 0);
if (!tun_dst)
- return 0;
+ goto drop;
}
ret = __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate,
log_ecn_error);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 38bee173dc2b..6e3871c7f8f7 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -874,6 +874,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
break;
case IPV6_AUTOFLOWLABEL:
np->autoflowlabel = valbool;
+ np->autoflowlabel_set = 1;
retv = 0;
break;
}
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 1bdc703cb966..ca8fac6e5a09 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1682,16 +1682,16 @@ static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel)
}
static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc,
- int type, struct mld2_grec **ppgr)
+ int type, struct mld2_grec **ppgr, unsigned int mtu)
{
- struct net_device *dev = pmc->idev->dev;
struct mld2_report *pmr;
struct mld2_grec *pgr;
- if (!skb)
- skb = mld_newpack(pmc->idev, dev->mtu);
- if (!skb)
- return NULL;
+ if (!skb) {
+ skb = mld_newpack(pmc->idev, mtu);
+ if (!skb)
+ return NULL;
+ }
pgr = (struct mld2_grec *)skb_put(skb, sizeof(struct mld2_grec));
pgr->grec_type = type;
pgr->grec_auxwords = 0;
@@ -1714,10 +1714,15 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
struct mld2_grec *pgr = NULL;
struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list;
int scount, stotal, first, isquery, truncate;
+ unsigned int mtu;
if (pmc->mca_flags & MAF_NOREPORT)
return skb;
+ mtu = READ_ONCE(dev->mtu);
+ if (mtu < IPV6_MIN_MTU)
+ return skb;
+
isquery = type == MLD2_MODE_IS_INCLUDE ||
type == MLD2_MODE_IS_EXCLUDE;
truncate = type == MLD2_MODE_IS_EXCLUDE ||
@@ -1738,7 +1743,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(idev, dev->mtu);
+ skb = mld_newpack(idev, mtu);
}
}
first = 1;
@@ -1774,12 +1779,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
pgr->grec_nsrcs = htons(scount);
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(idev, dev->mtu);
+ skb = mld_newpack(idev, mtu);
first = 1;
scount = 0;
}
if (first) {
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
first = 0;
}
if (!skb)
@@ -1814,7 +1819,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
mld_sendpack(skb);
skb = NULL; /* add_grhead will get a new one */
}
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
}
}
if (pgr)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7ac2365aa6fb..eb624547382f 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -962,7 +962,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
tcp_rsk(req)->rcv_nxt,
req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
- tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
+ tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr),
0, 0);
}
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 1ff497bd9c20..e1c123d4cdda 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -261,6 +261,9 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
struct sock *sk = skb->sk;
int ret = -ENOMEM;
+ if (!net_eq(dev_net(dev), sock_net(sk)))
+ return 0;
+
dev_hold(dev);
if (is_vmalloc_addr(skb->head))
diff --git a/net/rds/send.c b/net/rds/send.c
index ad247dc71ebb..ef53d164e146 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1006,6 +1006,9 @@ static int rds_rdma_bytes(struct msghdr *msg, size_t *rdma_bytes)
continue;
if (cmsg->cmsg_type == RDS_CMSG_RDMA_ARGS) {
+ if (cmsg->cmsg_len <
+ CMSG_LEN(sizeof(struct rds_rdma_args)))
+ return -EINVAL;
args = CMSG_DATA(cmsg);
*rdma_bytes += args->remote_vec.bytes;
}
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index c2ab864da50d..7181ce6c62bf 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4246,7 +4246,7 @@ static int sctp_init_sock(struct sock *sk)
SCTP_DBG_OBJCNT_INC(sock);
local_bh_disable();
- percpu_counter_inc(&sctp_sockets_allocated);
+ sk_sockets_allocated_inc(sk);
sock_prot_inuse_add(net, sk->sk_prot, 1);
/* Nothing can fail after this block, otherwise
@@ -4290,7 +4290,7 @@ static void sctp_destroy_sock(struct sock *sk)
}
sctp_endpoint_free(sp->ep);
local_bh_disable();
- percpu_counter_dec(&sctp_sockets_allocated);
+ sk_sockets_allocated_dec(sk);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
local_bh_enable();
}
diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index c9af022676c2..47c3e97c3136 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -319,7 +319,7 @@ static int hdac_component_master_match(struct device *dev, void *data)
*/
int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *aops)
{
- if (WARN_ON(!hdac_acomp))
+ if (!hdac_acomp)
return -ENODEV;
hdac_acomp->audio_ops = aops;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index ba40596b9d92..4ef3b0067876 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5971,6 +5971,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x1b, 0x01011020},
{0x21, 0x02211010}),
+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x12, 0x90a60130},
+ {0x14, 0x90170110},
+ {0x1b, 0x01011020},
+ {0x21, 0x0221101f}),
SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x12, 0x90a60160},
{0x14, 0x90170120},
diff --git a/sound/soc/codecs/da7218.c b/sound/soc/codecs/da7218.c
index c69e97654fc6..f88632426c0a 100644
--- a/sound/soc/codecs/da7218.c
+++ b/sound/soc/codecs/da7218.c
@@ -2519,7 +2519,7 @@ static struct da7218_pdata *da7218_of_to_pdata(struct snd_soc_codec *codec)
}
if (da7218->dev_id == DA7218_DEV_ID) {
- hpldet_np = of_find_node_by_name(np, "da7218_hpldet");
+ hpldet_np = of_get_child_by_name(np, "da7218_hpldet");
if (!hpldet_np)
return pdata;
diff --git a/sound/soc/codecs/tlv320aic31xx.h b/sound/soc/codecs/tlv320aic31xx.h
index 5acd5b69fb83..f9b6c5a81b47 100644
--- a/sound/soc/codecs/tlv320aic31xx.h
+++ b/sound/soc/codecs/tlv320aic31xx.h
@@ -115,7 +115,7 @@ struct aic31xx_pdata {
/* INT2 interrupt control */
#define AIC31XX_INT2CTRL AIC31XX_REG(0, 49)
/* GPIO1 control */
-#define AIC31XX_GPIO1 AIC31XX_REG(0, 50)
+#define AIC31XX_GPIO1 AIC31XX_REG(0, 51)
#define AIC31XX_DACPRB AIC31XX_REG(0, 60)
/* ADC Instruction Set Register */
diff --git a/sound/soc/codecs/twl4030.c b/sound/soc/codecs/twl4030.c
index a2104d68169d..26fd6a664b9b 100644
--- a/sound/soc/codecs/twl4030.c
+++ b/sound/soc/codecs/twl4030.c
@@ -232,7 +232,7 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec)
struct twl4030_codec_data *pdata = dev_get_platdata(codec->dev);
struct device_node *twl4030_codec_node = NULL;
- twl4030_codec_node = of_find_node_by_name(codec->dev->parent->of_node,
+ twl4030_codec_node = of_get_child_by_name(codec->dev->parent->of_node,
"codec");
if (!pdata && twl4030_codec_node) {
@@ -241,9 +241,11 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec)
GFP_KERNEL);
if (!pdata) {
dev_err(codec->dev, "Can not allocate memory\n");
+ of_node_put(twl4030_codec_node);
return NULL;
}
twl4030_setup_pdata_of(pdata, twl4030_codec_node);
+ of_node_put(twl4030_codec_node);
}
return pdata;
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 757af795cebd..c03c9da076c2 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1465,7 +1465,7 @@ static int wm_adsp_load(struct wm_adsp *dsp)
le64_to_cpu(footer->timestamp));
while (pos < firmware->size &&
- pos - firmware->size > sizeof(*region)) {
+ sizeof(*region) < firmware->size - pos) {
region = (void *)&(firmware->data[pos]);
region_name = "Unknown";
reg = 0;
@@ -1526,8 +1526,8 @@ static int wm_adsp_load(struct wm_adsp *dsp)
regions, le32_to_cpu(region->len), offset,
region_name);
- if ((pos + le32_to_cpu(region->len) + sizeof(*region)) >
- firmware->size) {
+ if (le32_to_cpu(region->len) >
+ firmware->size - pos - sizeof(*region)) {
adsp_err(dsp,
"%s.%d: %s region len %d bytes exceeds file length %zu\n",
file, regions, region_name,
@@ -1992,7 +1992,7 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp)
blocks = 0;
while (pos < firmware->size &&
- pos - firmware->size > sizeof(*blk)) {
+ sizeof(*blk) < firmware->size - pos) {
blk = (void *)(&firmware->data[pos]);
type = le16_to_cpu(blk->type);
@@ -2066,8 +2066,8 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp)
}
if (reg) {
- if ((pos + le32_to_cpu(blk->len) + sizeof(*blk)) >
- firmware->size) {
+ if (le32_to_cpu(blk->len) >
+ firmware->size - pos - sizeof(*blk)) {
adsp_err(dsp,
"%s.%d: %s region len %d bytes exceeds file length %zu\n",
file, blocks, region_name,
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index fde08660b63b..1c03490e1182 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -1467,12 +1467,6 @@ static int fsl_ssi_probe(struct platform_device *pdev)
sizeof(fsl_ssi_ac97_dai));
fsl_ac97_data = ssi_private;
-
- ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev);
- if (ret) {
- dev_err(&pdev->dev, "could not set AC'97 ops\n");
- return ret;
- }
} else {
/* Initialize this copy of the CPU DAI driver structure */
memcpy(&ssi_private->cpu_dai_drv, &fsl_ssi_dai_template,
@@ -1583,6 +1577,14 @@ static int fsl_ssi_probe(struct platform_device *pdev)
return ret;
}
+ if (fsl_ssi_is_ac97(ssi_private)) {
+ ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev);
+ if (ret) {
+ dev_err(&pdev->dev, "could not set AC'97 ops\n");
+ goto error_ac97_ops;
+ }
+ }
+
ret = devm_snd_soc_register_component(&pdev->dev, &fsl_ssi_component,
&ssi_private->cpu_dai_drv, 1);
if (ret) {
@@ -1666,6 +1668,10 @@ static int fsl_ssi_probe(struct platform_device *pdev)
fsl_ssi_debugfs_remove(&ssi_private->dbg_stats);
error_asoc_register:
+ if (fsl_ssi_is_ac97(ssi_private))
+ snd_soc_set_ac97_ops(NULL);
+
+error_ac97_ops:
if (ssi_private->soc->imx)
fsl_ssi_imx_clean(pdev, ssi_private);
diff --git a/tools/objtool/arch/x86/insn/x86-opcode-map.txt b/tools/objtool/arch/x86/insn/x86-opcode-map.txt
index 767be7c76034..1754e094bc28 100644
--- a/tools/objtool/arch/x86/insn/x86-opcode-map.txt
+++ b/tools/objtool/arch/x86/insn/x86-opcode-map.txt
@@ -896,7 +896,7 @@ EndTable
GrpTable: Grp3_1
0: TEST Eb,Ib
-1:
+1: TEST Eb,Ib
2: NOT Eb
3: NEG Eb
4: MUL AL,Eb
diff --git a/tools/usb/usbip/src/utils.c b/tools/usb/usbip/src/utils.c
index 2b3d6d235015..3d7b42e77299 100644
--- a/tools/usb/usbip/src/utils.c
+++ b/tools/usb/usbip/src/utils.c
@@ -30,6 +30,7 @@ int modify_match_busid(char *busid, int add)
char command[SYSFS_BUS_ID_SIZE + 4];
char match_busid_attr_path[SYSFS_PATH_MAX];
int rc;
+ int cmd_size;
snprintf(match_busid_attr_path, sizeof(match_busid_attr_path),
"%s/%s/%s/%s/%s/%s", SYSFS_MNT_PATH, SYSFS_BUS_NAME,
@@ -37,12 +38,14 @@ int modify_match_busid(char *busid, int add)
attr_name);
if (add)
- snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s", busid);
+ cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s",
+ busid);
else
- snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s", busid);
+ cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s",
+ busid);
rc = write_sysfs_attribute(match_busid_attr_path, command,
- sizeof(command));
+ cmd_size);
if (rc < 0) {
dbg("failed to write match_busid: %s", strerror(errno));
return -1;
7 years, 8 months
- 1
- 0
Re: [Linux-stable-mirror] Linux 4.4.109
by Greg KH
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 5d593ecadb90..b4a83a490212 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2555,6 +2555,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
nopat [X86] Disable PAT (page attribute table extension of
pagetables) support.
+ nopcid [X86-64] Disable the PCID cpu feature.
+
norandmaps Don't use address space randomization. Equivalent to
echo 0 > /proc/sys/kernel/randomize_va_space
diff --git a/Makefile b/Makefile
index 99f9834c4ba6..5d67056e24dd 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 4
PATCHLEVEL = 4
-SUBLEVEL = 108
+SUBLEVEL = 109
EXTRAVERSION =
NAME = Blurry Fish Butt
@@ -782,6 +782,9 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign)
# disable invalid "can't wrap" optimizations for signed / pointers
KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow)
+# Make sure -fstack-check isn't enabled (like gentoo apparently did)
+KBUILD_CFLAGS += $(call cc-option,-fno-stack-check,)
+
# conserve stack if available
KBUILD_CFLAGS += $(call cc-option,-fconserve-stack)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index d1e65ce545b3..b2ab164a8094 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -401,8 +401,12 @@ static __u64 power_pmu_bhrb_to(u64 addr)
int ret;
__u64 target;
- if (is_kernel_addr(addr))
- return branch_target((unsigned int *)addr);
+ if (is_kernel_addr(addr)) {
+ if (probe_kernel_read(&instr, (void *)addr, sizeof(instr)))
+ return 0;
+
+ return branch_target(&instr);
+ }
/* Userspace: need copy instruction here then translate it */
pagefault_disable();
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7e40905f6d4c..39d2dc66faa5 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -42,7 +42,7 @@ config X86
select ARCH_USE_CMPXCHG_LOCKREF if X86_64
select ARCH_USE_QUEUED_RWLOCKS
select ARCH_USE_QUEUED_SPINLOCKS
- select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP
+ select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
select ARCH_WANTS_DYNAMIC_TASK_STRUCT
select ARCH_WANT_FRAME_POINTERS
select ARCH_WANT_IPC_PARSE_VERSION if X86_32
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index f226df064660..8b17c2ad1048 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -21,11 +21,13 @@
# define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31))
# define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31))
# define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31))
+# define DISABLE_PCID 0
#else
# define DISABLE_VME 0
# define DISABLE_K6_MTRR 0
# define DISABLE_CYRIX_ARR 0
# define DISABLE_CENTAUR_MCR 0
+# define DISABLE_PCID (1<<(X86_FEATURE_PCID & 31))
#endif /* CONFIG_X86_64 */
/*
@@ -35,7 +37,7 @@
#define DISABLED_MASK1 0
#define DISABLED_MASK2 0
#define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
-#define DISABLED_MASK4 0
+#define DISABLED_MASK4 (DISABLE_PCID)
#define DISABLED_MASK5 0
#define DISABLED_MASK6 0
#define DISABLED_MASK7 0
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 59405a248fc2..9b76cd331990 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -22,8 +22,8 @@ typedef struct {
#ifdef CONFIG_SMP
unsigned int irq_resched_count;
unsigned int irq_call_count;
- unsigned int irq_tlb_count;
#endif
+ unsigned int irq_tlb_count;
#ifdef CONFIG_X86_THERMAL_VECTOR
unsigned int irq_thermal_count;
#endif
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 55234d5e7160..7680b76adafc 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -24,12 +24,6 @@ typedef struct {
atomic_t perf_rdpmc_allowed; /* nonzero if rdpmc is allowed */
} mm_context_t;
-#ifdef CONFIG_SMP
void leave_mm(int cpu);
-#else
-static inline void leave_mm(int cpu)
-{
-}
-#endif
#endif /* _ASM_X86_MMU_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 44fc93987869..9bfc5fd77015 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -98,10 +98,8 @@ static inline void load_mm_ldt(struct mm_struct *mm)
static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
-#ifdef CONFIG_SMP
if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
-#endif
}
extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 4dc534175b5e..9fc5968da820 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -6,6 +6,7 @@
#include <asm/processor.h>
#include <asm/special_insns.h>
+#include <asm/smp.h>
static inline void __invpcid(unsigned long pcid, unsigned long addr,
unsigned long type)
@@ -64,10 +65,8 @@ static inline void invpcid_flush_all_nonglobals(void)
#endif
struct tlb_state {
-#ifdef CONFIG_SMP
struct mm_struct *active_mm;
int state;
-#endif
/*
* Access to this CR4 shadow and to H/W CR4 is protected by
@@ -191,6 +190,14 @@ static inline void __flush_tlb_all(void)
__flush_tlb_global();
else
__flush_tlb();
+
+ /*
+ * Note: if we somehow had PCID but not PGE, then this wouldn't work --
+ * we'd end up flushing kernel translations for the current ASID but
+ * we might fail to flush kernel translations for other cached ASIDs.
+ *
+ * To avoid this issue, we force PCID off if PGE is off.
+ */
}
static inline void __flush_tlb_one(unsigned long addr)
@@ -204,7 +211,6 @@ static inline void __flush_tlb_one(unsigned long addr)
/*
* TLB flushing:
*
- * - flush_tlb() flushes the current mm struct TLBs
* - flush_tlb_all() flushes all processes TLBs
* - flush_tlb_mm(mm) flushes the specified mm context TLB's
* - flush_tlb_page(vma, vmaddr) flushes one page
@@ -216,84 +222,6 @@ static inline void __flush_tlb_one(unsigned long addr)
* and page-granular flushes are available only on i486 and up.
*/
-#ifndef CONFIG_SMP
-
-/* "_up" is for UniProcessor.
- *
- * This is a helper for other header functions. *Not* intended to be called
- * directly. All global TLB flushes need to either call this, or to bump the
- * vm statistics themselves.
- */
-static inline void __flush_tlb_up(void)
-{
- count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
- __flush_tlb();
-}
-
-static inline void flush_tlb_all(void)
-{
- count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
- __flush_tlb_all();
-}
-
-static inline void flush_tlb(void)
-{
- __flush_tlb_up();
-}
-
-static inline void local_flush_tlb(void)
-{
- __flush_tlb_up();
-}
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
- if (mm == current->active_mm)
- __flush_tlb_up();
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma,
- unsigned long addr)
-{
- if (vma->vm_mm == current->active_mm)
- __flush_tlb_one(addr);
-}
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
-{
- if (vma->vm_mm == current->active_mm)
- __flush_tlb_up();
-}
-
-static inline void flush_tlb_mm_range(struct mm_struct *mm,
- unsigned long start, unsigned long end, unsigned long vmflag)
-{
- if (mm == current->active_mm)
- __flush_tlb_up();
-}
-
-static inline void native_flush_tlb_others(const struct cpumask *cpumask,
- struct mm_struct *mm,
- unsigned long start,
- unsigned long end)
-{
-}
-
-static inline void reset_lazy_tlbstate(void)
-{
-}
-
-static inline void flush_tlb_kernel_range(unsigned long start,
- unsigned long end)
-{
- flush_tlb_all();
-}
-
-#else /* SMP */
-
-#include <asm/smp.h>
-
#define local_flush_tlb() __flush_tlb()
#define flush_tlb_mm(mm) flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL)
@@ -302,13 +230,14 @@ static inline void flush_tlb_kernel_range(unsigned long start,
flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags)
extern void flush_tlb_all(void);
-extern void flush_tlb_current_task(void);
-extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
unsigned long end, unsigned long vmflag);
extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
-#define flush_tlb() flush_tlb_current_task()
+static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
+{
+ flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE);
+}
void native_flush_tlb_others(const struct cpumask *cpumask,
struct mm_struct *mm,
@@ -323,8 +252,6 @@ static inline void reset_lazy_tlbstate(void)
this_cpu_write(cpu_tlbstate.active_mm, &init_mm);
}
-#endif /* SMP */
-
#ifndef CONFIG_PARAVIRT
#define flush_tlb_others(mask, mm, start, end) \
native_flush_tlb_others(mask, mm, start, end)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bd17db15a2c1..0b6124315441 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -19,6 +19,14 @@
void __init check_bugs(void)
{
+#ifdef CONFIG_X86_32
+ /*
+ * Regardless of whether PCID is enumerated, the SDM says
+ * that it can't be enabled in 32-bit mode.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_PCID);
+#endif
+
identify_boot_cpu();
#ifndef CONFIG_SMP
pr_info("CPU: ");
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c84b62956e8d..aa1e7246b06b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -162,6 +162,24 @@ static int __init x86_mpx_setup(char *s)
}
__setup("nompx", x86_mpx_setup);
+#ifdef CONFIG_X86_64
+static int __init x86_pcid_setup(char *s)
+{
+ /* require an exact match without trailing characters */
+ if (strlen(s))
+ return 0;
+
+ /* do not emit a message if the feature is not present */
+ if (!boot_cpu_has(X86_FEATURE_PCID))
+ return 1;
+
+ setup_clear_cpu_cap(X86_FEATURE_PCID);
+ pr_info("nopcid: PCID feature disabled\n");
+ return 1;
+}
+__setup("nopcid", x86_pcid_setup);
+#endif
+
static int __init x86_noinvpcid_setup(char *s)
{
/* noinvpcid doesn't accept parameters */
@@ -303,6 +321,25 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
}
}
+static void setup_pcid(struct cpuinfo_x86 *c)
+{
+ if (cpu_has(c, X86_FEATURE_PCID)) {
+ if (cpu_has(c, X86_FEATURE_PGE)) {
+ cr4_set_bits(X86_CR4_PCIDE);
+ } else {
+ /*
+ * flush_tlb_all(), as currently implemented, won't
+ * work if PCID is on but PGE is not. Since that
+ * combination doesn't exist on real hardware, there's
+ * no reason to try to fully support it, but it's
+ * polite to avoid corrupting data if we're on
+ * an improperly configured VM.
+ */
+ clear_cpu_cap(c, X86_FEATURE_PCID);
+ }
+ }
+}
+
/*
* Some CPU features depend on higher CPUID levels, which may not always
* be available due to CPUID level capping or broken virtualization
@@ -934,6 +971,9 @@ static void identify_cpu(struct cpuinfo_x86 *c)
setup_smep(c);
setup_smap(c);
+ /* Set up PCID */
+ setup_pcid(c);
+
/*
* The vendor-specific functions might have changed features.
* Now we do "generic changes."
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index f660d63f40fe..9a16932c7258 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -93,6 +93,10 @@ void __noreturn machine_real_restart(unsigned int type)
load_cr3(initial_page_table);
#else
write_cr3(real_mode_header->trampoline_pgd);
+
+ /* Exiting long mode will fail if CR4.PCIDE is set. */
+ if (static_cpu_has(X86_FEATURE_PCID))
+ cr4_clear_bits(X86_CR4_PCIDE);
#endif
/* Jump to the identity-mapped low memory code */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fbabe4fcc7fb..fe89f938e0f0 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -104,25 +104,16 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
spin_lock_irqsave(&rtc_lock, flags);
CMOS_WRITE(0xa, 0xf);
spin_unlock_irqrestore(&rtc_lock, flags);
- local_flush_tlb();
- pr_debug("1.\n");
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
start_eip >> 4;
- pr_debug("2.\n");
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
start_eip & 0xf;
- pr_debug("3.\n");
}
static inline void smpboot_restore_warm_reset_vector(void)
{
unsigned long flags;
- /*
- * Install writable page 0 entry to set BIOS data area.
- */
- local_flush_tlb();
-
/*
* Paranoid: Set warm reset code and vector here back
* to default values.
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 524619351961..510e80da7de4 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -187,7 +187,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
pte_unmap_unlock(pte, ptl);
out:
up_write(&mm->mmap_sem);
- flush_tlb();
+ flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, 0UL);
}
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 684edebb4a0c..00045499f6c2 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2383,9 +2383,21 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
}
static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
- u64 cr0, u64 cr4)
+ u64 cr0, u64 cr3, u64 cr4)
{
int bad;
+ u64 pcid;
+
+ /* In order to later set CR4.PCIDE, CR3[11:0] must be zero. */
+ pcid = 0;
+ if (cr4 & X86_CR4_PCIDE) {
+ pcid = cr3 & 0xfff;
+ cr3 &= ~0xfff;
+ }
+
+ bad = ctxt->ops->set_cr(ctxt, 3, cr3);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
/*
* First enable PAE, long mode needs it before CR0.PG = 1 is set.
@@ -2404,6 +2416,12 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
bad = ctxt->ops->set_cr(ctxt, 4, cr4);
if (bad)
return X86EMUL_UNHANDLEABLE;
+ if (pcid) {
+ bad = ctxt->ops->set_cr(ctxt, 3, cr3 | pcid);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+ }
+
}
return X86EMUL_CONTINUE;
@@ -2414,11 +2432,11 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
struct desc_struct desc;
struct desc_ptr dt;
u16 selector;
- u32 val, cr0, cr4;
+ u32 val, cr0, cr3, cr4;
int i;
cr0 = GET_SMSTATE(u32, smbase, 0x7ffc);
- ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8));
+ cr3 = GET_SMSTATE(u32, smbase, 0x7ff8);
ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0);
@@ -2460,14 +2478,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
- return rsm_enter_protected_mode(ctxt, cr0, cr4);
+ return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
}
static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
{
struct desc_struct desc;
struct desc_ptr dt;
- u64 val, cr0, cr4;
+ u64 val, cr0, cr3, cr4;
u32 base3;
u16 selector;
int i, r;
@@ -2484,7 +2502,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
cr0 = GET_SMSTATE(u64, smbase, 0x7f58);
- ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u64, smbase, 0x7f50));
+ cr3 = GET_SMSTATE(u64, smbase, 0x7f50);
cr4 = GET_SMSTATE(u64, smbase, 0x7f48);
ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
val = GET_SMSTATE(u64, smbase, 0x7ed0);
@@ -2512,7 +2530,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
dt.address = GET_SMSTATE(u64, smbase, 0x7e68);
ctxt->ops->set_gdt(ctxt, &dt);
- r = rsm_enter_protected_mode(ctxt, cr0, cr4);
+ r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
if (r != X86EMUL_CONTINUE)
return r;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e5f44f33de89..796f1ec67469 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6941,7 +6941,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
#endif
kvm_rip_write(vcpu, regs->rip);
- kvm_set_rflags(vcpu, regs->rflags);
+ kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED);
vcpu->arch.exception.pending = false;
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 3aebbd6c6f5f..ed4b372860e4 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -753,10 +753,8 @@ void __init zone_sizes_init(void)
}
DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
-#ifdef CONFIG_SMP
.active_mm = &init_mm,
.state = 0,
-#endif
.cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */
};
EXPORT_SYMBOL_GPL(cpu_tlbstate);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 45ba87466e6a..7a4cdb632508 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -15,7 +15,7 @@
#include <linux/debugfs.h>
/*
- * Smarter SMP flushing macros.
+ * TLB flushing, formerly SMP-only
* c/o Linus Torvalds.
*
* These mean you can really definitely utterly forget about
@@ -28,8 +28,6 @@
* Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
*/
-#ifdef CONFIG_SMP
-
struct flush_tlb_info {
struct mm_struct *flush_mm;
unsigned long flush_start;
@@ -59,8 +57,6 @@ void leave_mm(int cpu)
}
EXPORT_SYMBOL_GPL(leave_mm);
-#endif /* CONFIG_SMP */
-
void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
@@ -77,10 +73,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
unsigned cpu = smp_processor_id();
if (likely(prev != next)) {
-#ifdef CONFIG_SMP
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
this_cpu_write(cpu_tlbstate.active_mm, next);
-#endif
cpumask_set_cpu(cpu, mm_cpumask(next));
/*
@@ -137,9 +131,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
if (unlikely(prev->context.ldt != next->context.ldt))
load_mm_ldt(next);
#endif
- }
-#ifdef CONFIG_SMP
- else {
+ } else {
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
@@ -166,11 +158,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
load_mm_ldt(next);
}
}
-#endif
}
-#ifdef CONFIG_SMP
-
/*
* The flush IPI assumes that a thread switch happens in this order:
* [cpu0: the cpu that switches]
@@ -272,23 +261,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
smp_call_function_many(cpumask, flush_tlb_func, &info, 1);
}
-void flush_tlb_current_task(void)
-{
- struct mm_struct *mm = current->mm;
-
- preempt_disable();
-
- count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-
- /* This is an implicit full barrier that synchronizes with switch_mm. */
- local_flush_tlb();
-
- trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
- if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
- flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
- preempt_enable();
-}
-
/*
* See Documentation/x86/tlb.txt for details. We choose 33
* because it is large enough to cover the vast majority (at
@@ -309,6 +281,12 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
unsigned long base_pages_to_flush = TLB_FLUSH_ALL;
preempt_disable();
+
+ if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB))
+ base_pages_to_flush = (end - start) >> PAGE_SHIFT;
+ if (base_pages_to_flush > tlb_single_page_flush_ceiling)
+ base_pages_to_flush = TLB_FLUSH_ALL;
+
if (current->active_mm != mm) {
/* Synchronize with switch_mm. */
smp_mb();
@@ -325,15 +303,11 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
goto out;
}
- if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB))
- base_pages_to_flush = (end - start) >> PAGE_SHIFT;
-
/*
* Both branches below are implicit full barriers (MOV to CR or
* INVLPG) that synchronize with switch_mm.
*/
- if (base_pages_to_flush > tlb_single_page_flush_ceiling) {
- base_pages_to_flush = TLB_FLUSH_ALL;
+ if (base_pages_to_flush == TLB_FLUSH_ALL) {
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
local_flush_tlb();
} else {
@@ -354,33 +328,6 @@ out:
preempt_enable();
}
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
-{
- struct mm_struct *mm = vma->vm_mm;
-
- preempt_disable();
-
- if (current->active_mm == mm) {
- if (current->mm) {
- /*
- * Implicit full barrier (INVLPG) that synchronizes
- * with switch_mm.
- */
- __flush_tlb_one(start);
- } else {
- leave_mm(smp_processor_id());
-
- /* Synchronize with switch_mm. */
- smp_mb();
- }
- }
-
- if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
- flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE);
-
- preempt_enable();
-}
-
static void do_flush_tlb_all(void *info)
{
count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
@@ -465,5 +412,3 @@ static int __init create_tlb_single_page_flush_ceiling(void)
return 0;
}
late_initcall(create_tlb_single_page_flush_ceiling);
-
-#endif /* CONFIG_SMP */
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index ffa41591bff9..cbef64b508e1 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -433,6 +433,12 @@ static void __init xen_init_cpuid_mask(void)
~((1 << X86_FEATURE_MTRR) | /* disable MTRR */
(1 << X86_FEATURE_ACC)); /* thermal monitoring */
+ /*
+ * Xen PV would need some work to support PCID: CR3 handling as well
+ * as xen_flush_tlb_others() would need updating.
+ */
+ cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_PCID % 32)); /* disable PCID */
+
if (!xen_initial_domain())
cpuid_leaf1_edx_mask &=
~((1 << X86_FEATURE_ACPI)); /* disable ACPI */
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index b4f3930266b1..f620fe09d20a 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -80,6 +80,7 @@ static int mcryptd_init_queue(struct mcryptd_queue *queue,
pr_debug("cpu_queue #%d %p\n", cpu, queue->cpu_queue);
crypto_init_queue(&cpu_queue->queue, max_cpu_qlen);
INIT_WORK(&cpu_queue->work, mcryptd_queue_worker);
+ spin_lock_init(&cpu_queue->q_lock);
}
return 0;
}
@@ -103,15 +104,16 @@ static int mcryptd_enqueue_request(struct mcryptd_queue *queue,
int cpu, err;
struct mcryptd_cpu_queue *cpu_queue;
- cpu = get_cpu();
- cpu_queue = this_cpu_ptr(queue->cpu_queue);
- rctx->tag.cpu = cpu;
+ cpu_queue = raw_cpu_ptr(queue->cpu_queue);
+ spin_lock(&cpu_queue->q_lock);
+ cpu = smp_processor_id();
+ rctx->tag.cpu = smp_processor_id();
err = crypto_enqueue_request(&cpu_queue->queue, request);
pr_debug("enqueue request: cpu %d cpu_queue %p request %p\n",
cpu, cpu_queue, request);
+ spin_unlock(&cpu_queue->q_lock);
queue_work_on(cpu, kcrypto_wq, &cpu_queue->work);
- put_cpu();
return err;
}
@@ -164,16 +166,11 @@ static void mcryptd_queue_worker(struct work_struct *work)
cpu_queue = container_of(work, struct mcryptd_cpu_queue, work);
i = 0;
while (i < MCRYPTD_BATCH || single_task_running()) {
- /*
- * preempt_disable/enable is used to prevent
- * being preempted by mcryptd_enqueue_request()
- */
- local_bh_disable();
- preempt_disable();
+
+ spin_lock_bh(&cpu_queue->q_lock);
backlog = crypto_get_backlog(&cpu_queue->queue);
req = crypto_dequeue_request(&cpu_queue->queue);
- preempt_enable();
- local_bh_enable();
+ spin_unlock_bh(&cpu_queue->q_lock);
if (!req) {
mcryptd_opportunistic_flush();
@@ -188,7 +185,7 @@ static void mcryptd_queue_worker(struct work_struct *work)
++i;
}
if (cpu_queue->queue.qlen)
- queue_work(kcrypto_wq, &cpu_queue->work);
+ queue_work_on(smp_processor_id(), kcrypto_wq, &cpu_queue->work);
}
void mcryptd_flusher(struct work_struct *__work)
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 6682c5daf742..4c9be45ea328 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -1020,7 +1020,7 @@ skip:
/* The record may be cleared by others, try read next record */
if (len == -ENOENT)
goto skip;
- else if (len < sizeof(*rcd)) {
+ else if (len < 0 || len < sizeof(*rcd)) {
rc = -EIO;
goto out;
}
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index bc147582bed9..6d62b69c898e 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -579,10 +579,10 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
ret = -EAGAIN;
goto skip_cqe;
}
- if (unlikely((CQE_WRID_MSN(hw_cqe) != (wq->rq.msn)))) {
+ if (unlikely(!CQE_STATUS(hw_cqe) &&
+ CQE_WRID_MSN(hw_cqe) != wq->rq.msn)) {
t4_set_wq_in_error(wq);
- hw_cqe->header |= htonl(CQE_STATUS_V(T4_ERR_MSN));
- goto proc_cqe;
+ hw_cqe->header |= cpu_to_be32(CQE_STATUS_V(T4_ERR_MSN));
}
goto proc_cqe;
}
diff --git a/drivers/mfd/cros_ec_spi.c b/drivers/mfd/cros_ec_spi.c
index 6a0f6ec67c6b..ee7847a1ca06 100644
--- a/drivers/mfd/cros_ec_spi.c
+++ b/drivers/mfd/cros_ec_spi.c
@@ -660,6 +660,7 @@ static int cros_ec_spi_probe(struct spi_device *spi)
sizeof(struct ec_response_get_protocol_info);
ec_dev->dout_size = sizeof(struct ec_host_request);
+ ec_spi->last_transfer_ns = ktime_get_ns();
err = cros_ec_register(ec_dev);
if (err) {
diff --git a/drivers/mfd/twl4030-audio.c b/drivers/mfd/twl4030-audio.c
index 0a1606480023..cc832d309599 100644
--- a/drivers/mfd/twl4030-audio.c
+++ b/drivers/mfd/twl4030-audio.c
@@ -159,13 +159,18 @@ unsigned int twl4030_audio_get_mclk(void)
EXPORT_SYMBOL_GPL(twl4030_audio_get_mclk);
static bool twl4030_audio_has_codec(struct twl4030_audio_data *pdata,
- struct device_node *node)
+ struct device_node *parent)
{
+ struct device_node *node;
+
if (pdata && pdata->codec)
return true;
- if (of_find_node_by_name(node, "codec"))
+ node = of_get_child_by_name(parent, "codec");
+ if (node) {
+ of_node_put(node);
return true;
+ }
return false;
}
diff --git a/drivers/mfd/twl6040.c b/drivers/mfd/twl6040.c
index 08a693cd38cc..72aab60ae846 100644
--- a/drivers/mfd/twl6040.c
+++ b/drivers/mfd/twl6040.c
@@ -97,12 +97,16 @@ static struct reg_sequence twl6040_patch[] = {
};
-static bool twl6040_has_vibra(struct device_node *node)
+static bool twl6040_has_vibra(struct device_node *parent)
{
-#ifdef CONFIG_OF
- if (of_find_node_by_name(node, "vibra"))
+ struct device_node *node;
+
+ node = of_get_child_by_name(parent, "vibra");
+ if (node) {
+ of_node_put(node);
return true;
-#endif
+ }
+
return false;
}
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 3613469dc5c6..ab53e0cfb4dc 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -14228,7 +14228,9 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
/* Reset PHY, otherwise the read DMA engine will be in a mode that
* breaks all requests to 256 bytes.
*/
- if (tg3_asic_rev(tp) == ASIC_REV_57766)
+ if (tg3_asic_rev(tp) == ASIC_REV_57766 ||
+ tg3_asic_rev(tp) == ASIC_REV_5717 ||
+ tg3_asic_rev(tp) == ASIC_REV_5719)
reset_phy = true;
err = tg3_restart_hw(tp, reset_phy);
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index fc2fb25343f4..c122b3b99cd8 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -241,7 +241,8 @@ static int orion_mdio_probe(struct platform_device *pdev)
dev->regs + MVMDIO_ERR_INT_MASK);
} else if (dev->err_interrupt == -EPROBE_DEFER) {
- return -EPROBE_DEFER;
+ ret = -EPROBE_DEFER;
+ goto out_mdio;
}
mutex_init(&dev->lock);
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 15056f06754a..7430dd44019e 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -914,6 +914,10 @@ static void mvneta_port_disable(struct mvneta_port *pp)
val &= ~MVNETA_GMAC0_PORT_ENABLE;
mvreg_write(pp, MVNETA_GMAC_CTRL_0, val);
+ pp->link = 0;
+ pp->duplex = -1;
+ pp->speed = 0;
+
udelay(200);
}
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index c8b85f1069ff..920391165f18 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -541,6 +541,7 @@ static int ksz9031_read_status(struct phy_device *phydev)
phydev->link = 0;
if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev))
phydev->drv->config_intr(phydev);
+ return genphy_config_aneg(phydev);
}
return 0;
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 2cbecbda1ae3..b0ea8dee5f06 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -737,6 +737,7 @@ static const struct usb_device_id products[] = {
{QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */
{QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */
{QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */
+ {QMI_FIXED_INTF(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */
{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */
{QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */
diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c
index d0c2759076a2..312cb5b74dec 100644
--- a/drivers/parisc/lba_pci.c
+++ b/drivers/parisc/lba_pci.c
@@ -1654,3 +1654,36 @@ void lba_set_iregs(struct parisc_device *lba, u32 ibase, u32 imask)
iounmap(base_addr);
}
+
+/*
+ * The design of the Diva management card in rp34x0 machines (rp3410, rp3440)
+ * seems rushed, so that many built-in components simply don't work.
+ * The following quirks disable the serial AUX port and the built-in ATI RV100
+ * Radeon 7000 graphics card which both don't have any external connectors and
+ * thus are useless, and even worse, e.g. the AUX port occupies ttyS0 and as
+ * such makes those machines the only PARISC machines on which we can't use
+ * ttyS0 as boot console.
+ */
+static void quirk_diva_ati_card(struct pci_dev *dev)
+{
+ if (dev->subsystem_vendor != PCI_VENDOR_ID_HP ||
+ dev->subsystem_device != 0x1292)
+ return;
+
+ dev_info(&dev->dev, "Hiding Diva built-in ATI card");
+ dev->device = 0;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_RADEON_QY,
+ quirk_diva_ati_card);
+
+static void quirk_diva_aux_disable(struct pci_dev *dev)
+{
+ if (dev->subsystem_vendor != PCI_VENDOR_ID_HP ||
+ dev->subsystem_device != 0x1291)
+ return;
+
+ dev_info(&dev->dev, "Hiding Diva built-in AUX serial device");
+ dev->device = 0;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_DIVA_AUX,
+ quirk_diva_aux_disable);
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index fca925543fae..32bd8ab79d53 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -944,7 +944,12 @@ static int pci_pm_thaw_noirq(struct device *dev)
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_resume_early(dev);
- pci_update_current_state(pci_dev, PCI_D0);
+ /*
+ * pci_restore_state() requires the device to be in D0 (because of MSI
+ * restoration among other things), so force it into D0 in case the
+ * driver's "freeze" callbacks put it into a low-power state directly.
+ */
+ pci_set_power_state(pci_dev, PCI_D0);
pci_restore_state(pci_dev);
if (drv && drv->pm && drv->pm->thaw_noirq)
diff --git a/drivers/spi/spi-xilinx.c b/drivers/spi/spi-xilinx.c
index 3009121173cd..3c6ea5c3ddd2 100644
--- a/drivers/spi/spi-xilinx.c
+++ b/drivers/spi/spi-xilinx.c
@@ -271,6 +271,7 @@ static int xilinx_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t)
while (remaining_words) {
int n_words, tx_words, rx_words;
u32 sr;
+ int stalled;
n_words = min(remaining_words, xspi->buffer_size);
@@ -299,7 +300,17 @@ static int xilinx_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t)
/* Read out all the data from the Rx FIFO */
rx_words = n_words;
+ stalled = 10;
while (rx_words) {
+ if (rx_words == n_words && !(stalled--) &&
+ !(sr & XSPI_SR_TX_EMPTY_MASK) &&
+ (sr & XSPI_SR_RX_EMPTY_MASK)) {
+ dev_err(&spi->dev,
+ "Detected stall. Check C_SPI_MODE and C_SPI_MEMORY\n");
+ xspi_init_hw(xspi);
+ return -EIO;
+ }
+
if ((sr & XSPI_SR_TX_EMPTY_MASK) && (rx_words > 1)) {
xilinx_spi_rx(xspi);
rx_words--;
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 84e71bd19082..41dda25da049 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -1801,7 +1801,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
{
struct n_tty_data *ldata = tty->disc_data;
- if (!old || (old->c_lflag ^ tty->termios.c_lflag) & ICANON) {
+ if (!old || (old->c_lflag ^ tty->termios.c_lflag) & (ICANON | EXTPROC)) {
bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE);
ldata->line_start = ldata->read_tail;
if (!L_ICANON(tty) || !read_cnt(ldata)) {
@@ -2493,7 +2493,7 @@ static int n_tty_ioctl(struct tty_struct *tty, struct file *file,
return put_user(tty_chars_in_buffer(tty), (int __user *) arg);
case TIOCINQ:
down_write(&tty->termios_rwsem);
- if (L_ICANON(tty))
+ if (L_ICANON(tty) && !L_EXTPROC(tty))
retval = inq_canon(ldata);
else
retval = read_cnt(ldata);
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index f6fde903fcad..22dcccf2d286 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -973,7 +973,7 @@ int usb_get_bos_descriptor(struct usb_device *dev)
case USB_SSP_CAP_TYPE:
ssp_cap = (struct usb_ssp_cap_descriptor *)buffer;
ssac = (le32_to_cpu(ssp_cap->bmAttributes) &
- USB_SSP_SUBLINK_SPEED_ATTRIBS) + 1;
+ USB_SSP_SUBLINK_SPEED_ATTRIBS);
if (length >= USB_DT_USB_SSP_CAP_SIZE(ssac))
dev->bos->ssp_cap = ssp_cap;
break;
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 50010282c010..c05c4f877750 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -57,10 +57,11 @@ static const struct usb_device_id usb_quirk_list[] = {
/* Microsoft LifeCam-VX700 v2.0 */
{ USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },
- /* Logitech HD Pro Webcams C920, C920-C and C930e */
+ /* Logitech HD Pro Webcams C920, C920-C, C925e and C930e */
{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
{ USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT },
{ USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
+ { USB_DEVICE(0x046d, 0x085b), .driver_info = USB_QUIRK_DELAY_INIT },
/* Logitech ConferenceCam CC3000e */
{ USB_DEVICE(0x046d, 0x0847), .driver_info = USB_QUIRK_DELAY_INIT },
@@ -154,6 +155,9 @@ static const struct usb_device_id usb_quirk_list[] = {
/* Genesys Logic hub, internally used by KY-688 USB 3.1 Type-C Hub */
{ USB_DEVICE(0x05e3, 0x0612), .driver_info = USB_QUIRK_NO_LPM },
+ /* ELSA MicroLink 56K */
+ { USB_DEVICE(0x05cc, 0x2267), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Genesys Logic hub, internally used by Moshi USB to Ethernet Adapter */
{ USB_DEVICE(0x05e3, 0x0616), .driver_info = USB_QUIRK_NO_LPM },
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index e8f990642281..cbf3be66f89c 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -184,6 +184,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
xhci->quirks |= XHCI_TRUST_TX_LENGTH;
xhci->quirks |= XHCI_BROKEN_STREAMS;
}
+ if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
+ pdev->device == 0x0014)
+ xhci->quirks |= XHCI_TRUST_TX_LENGTH;
if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
pdev->device == 0x0015)
xhci->quirks |= XHCI_RESET_ON_RESUME;
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 30344efc123f..64fe9dc25ed4 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1017,6 +1017,7 @@ static const struct usb_device_id id_table_combined[] = {
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
{ USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_BT_USB_PID) },
{ USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_WL_USB_PID) },
+ { USB_DEVICE(AIRBUS_DS_VID, AIRBUS_DS_P8GR) },
{ } /* Terminating entry */
};
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index f9d15bd62785..543d2801632b 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -913,6 +913,12 @@
#define ICPDAS_I7561U_PID 0x0104
#define ICPDAS_I7563U_PID 0x0105
+/*
+ * Airbus Defence and Space
+ */
+#define AIRBUS_DS_VID 0x1e8e /* Vendor ID */
+#define AIRBUS_DS_P8GR 0x6001 /* Tetra P8GR */
+
/*
* RT Systems programming cables for various ham radios
*/
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index ffa8ec917ff5..a818c43a02ec 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -236,6 +236,8 @@ static void option_instat_callback(struct urb *urb);
/* These Quectel products use Qualcomm's vendor ID */
#define QUECTEL_PRODUCT_UC20 0x9003
#define QUECTEL_PRODUCT_UC15 0x9090
+/* These Yuga products use Qualcomm's vendor ID */
+#define YUGA_PRODUCT_CLM920_NC5 0x9625
#define QUECTEL_VENDOR_ID 0x2c7c
/* These Quectel products use Quectel's vendor ID */
@@ -283,6 +285,7 @@ static void option_instat_callback(struct urb *urb);
#define TELIT_PRODUCT_LE922_USBCFG3 0x1043
#define TELIT_PRODUCT_LE922_USBCFG5 0x1045
#define TELIT_PRODUCT_ME910 0x1100
+#define TELIT_PRODUCT_ME910_DUAL_MODEM 0x1101
#define TELIT_PRODUCT_LE920 0x1200
#define TELIT_PRODUCT_LE910 0x1201
#define TELIT_PRODUCT_LE910_USBCFG4 0x1206
@@ -648,6 +651,11 @@ static const struct option_blacklist_info telit_me910_blacklist = {
.reserved = BIT(1) | BIT(3),
};
+static const struct option_blacklist_info telit_me910_dual_modem_blacklist = {
+ .sendsetup = BIT(0),
+ .reserved = BIT(3),
+};
+
static const struct option_blacklist_info telit_le910_blacklist = {
.sendsetup = BIT(0),
.reserved = BIT(1) | BIT(2),
@@ -677,6 +685,10 @@ static const struct option_blacklist_info cinterion_rmnet2_blacklist = {
.reserved = BIT(4) | BIT(5),
};
+static const struct option_blacklist_info yuga_clm920_nc5_blacklist = {
+ .reserved = BIT(1) | BIT(4),
+};
+
static const struct usb_device_id option_ids[] = {
{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) },
{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) },
@@ -1181,6 +1193,9 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)},
{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+ /* Yuga products use Qualcomm vendor ID */
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, YUGA_PRODUCT_CLM920_NC5),
+ .driver_info = (kernel_ulong_t)&yuga_clm920_nc5_blacklist },
/* Quectel products using Quectel vendor ID */
{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
@@ -1247,6 +1262,8 @@ static const struct usb_device_id option_ids[] = {
.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
.driver_info = (kernel_ulong_t)&telit_me910_blacklist },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
+ .driver_info = (kernel_ulong_t)&telit_me910_dual_modem_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
.driver_info = (kernel_ulong_t)&telit_le910_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4),
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 4516291df1b8..fb6dc16c754a 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -166,6 +166,8 @@ static const struct usb_device_id id_table[] = {
{DEVICE_SWI(0x1199, 0x9079)}, /* Sierra Wireless EM74xx */
{DEVICE_SWI(0x1199, 0x907a)}, /* Sierra Wireless EM74xx QDL */
{DEVICE_SWI(0x1199, 0x907b)}, /* Sierra Wireless EM74xx */
+ {DEVICE_SWI(0x1199, 0x9090)}, /* Sierra Wireless EM7565 QDL */
+ {DEVICE_SWI(0x1199, 0x9091)}, /* Sierra Wireless EM7565 */
{DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
{DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
{DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
@@ -346,6 +348,7 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id)
break;
case 2:
dev_dbg(dev, "NMEA GPS interface found\n");
+ sendsetup = true;
break;
case 3:
dev_dbg(dev, "Modem port found\n");
diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c
index af10f7b131a4..325b4c05acdd 100644
--- a/drivers/usb/usbip/stub_main.c
+++ b/drivers/usb/usbip/stub_main.c
@@ -252,11 +252,12 @@ void stub_device_cleanup_urbs(struct stub_device *sdev)
struct stub_priv *priv;
struct urb *urb;
- dev_dbg(&sdev->udev->dev, "free sdev %p\n", sdev);
+ dev_dbg(&sdev->udev->dev, "Stub device cleaning up urbs\n");
while ((priv = stub_priv_pop(sdev))) {
urb = priv->urb;
- dev_dbg(&sdev->udev->dev, "free urb %p\n", urb);
+ dev_dbg(&sdev->udev->dev, "free urb seqnum %lu\n",
+ priv->seqnum);
usb_kill_urb(urb);
kmem_cache_free(stub_priv_cache, priv);
diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c
index 00e475c51a12..7de54a66044f 100644
--- a/drivers/usb/usbip/stub_rx.c
+++ b/drivers/usb/usbip/stub_rx.c
@@ -230,9 +230,6 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev,
if (priv->seqnum != pdu->u.cmd_unlink.seqnum)
continue;
- dev_info(&priv->urb->dev->dev, "unlink urb %p\n",
- priv->urb);
-
/*
* This matched urb is not completed yet (i.e., be in
* flight in usb hcd hardware/driver). Now we are
@@ -271,8 +268,8 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev,
ret = usb_unlink_urb(priv->urb);
if (ret != -EINPROGRESS)
dev_err(&priv->urb->dev->dev,
- "failed to unlink a urb %p, ret %d\n",
- priv->urb, ret);
+ "failed to unlink a urb # %lu, ret %d\n",
+ priv->seqnum, ret);
return 0;
}
diff --git a/drivers/usb/usbip/stub_tx.c b/drivers/usb/usbip/stub_tx.c
index af858d52608a..f4dd30c56f36 100644
--- a/drivers/usb/usbip/stub_tx.c
+++ b/drivers/usb/usbip/stub_tx.c
@@ -201,8 +201,8 @@ static int stub_send_ret_submit(struct stub_device *sdev)
/* 1. setup usbip_header */
setup_ret_submit_pdu(&pdu_header, urb);
- usbip_dbg_stub_tx("setup txdata seqnum: %d urb: %p\n",
- pdu_header.base.seqnum, urb);
+ usbip_dbg_stub_tx("setup txdata seqnum: %d\n",
+ pdu_header.base.seqnum);
usbip_header_correct_endian(&pdu_header, 1);
iov[iovnum].iov_base = &pdu_header;
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index 81b2b9f808b5..f9af04d7f02f 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -467,9 +467,6 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb,
int ret = 0;
struct vhci_device *vdev;
- usbip_dbg_vhci_hc("enter, usb_hcd %p urb %p mem_flags %d\n",
- hcd, urb, mem_flags);
-
/* patch to usb_sg_init() is in 2.5.60 */
BUG_ON(!urb->transfer_buffer && urb->transfer_buffer_length);
@@ -627,8 +624,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
struct vhci_priv *priv;
struct vhci_device *vdev;
- pr_info("dequeue a urb %p\n", urb);
-
spin_lock(&the_controller->lock);
priv = urb->hcpriv;
@@ -656,7 +651,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
/* tcp connection is closed */
spin_lock(&vdev->priv_lock);
- pr_info("device %p seems to be disconnected\n", vdev);
list_del(&priv->list);
kfree(priv);
urb->hcpriv = NULL;
@@ -668,8 +662,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
* vhci_rx will receive RET_UNLINK and give back the URB.
* Otherwise, we give back it here.
*/
- pr_info("gives back urb %p\n", urb);
-
usb_hcd_unlink_urb_from_ep(hcd, urb);
spin_unlock(&the_controller->lock);
@@ -698,8 +690,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
unlink->unlink_seqnum = priv->seqnum;
- pr_info("device %p seems to be still connected\n", vdev);
-
/* send cmd_unlink and try to cancel the pending URB in the
* peer */
list_add_tail(&unlink->list, &vdev->unlink_tx);
diff --git a/drivers/usb/usbip/vhci_rx.c b/drivers/usb/usbip/vhci_rx.c
index 00e4a54308e4..bc4eb0855314 100644
--- a/drivers/usb/usbip/vhci_rx.c
+++ b/drivers/usb/usbip/vhci_rx.c
@@ -37,24 +37,23 @@ struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, __u32 seqnum)
urb = priv->urb;
status = urb->status;
- usbip_dbg_vhci_rx("find urb %p vurb %p seqnum %u\n",
- urb, priv, seqnum);
+ usbip_dbg_vhci_rx("find urb seqnum %u\n", seqnum);
switch (status) {
case -ENOENT:
/* fall through */
case -ECONNRESET:
- dev_info(&urb->dev->dev,
- "urb %p was unlinked %ssynchronuously.\n", urb,
- status == -ENOENT ? "" : "a");
+ dev_dbg(&urb->dev->dev,
+ "urb seq# %u was unlinked %ssynchronuously\n",
+ seqnum, status == -ENOENT ? "" : "a");
break;
case -EINPROGRESS:
/* no info output */
break;
default:
- dev_info(&urb->dev->dev,
- "urb %p may be in a error, status %d\n", urb,
- status);
+ dev_dbg(&urb->dev->dev,
+ "urb seq# %u may be in a error, status %d\n",
+ seqnum, status);
}
list_del(&priv->list);
@@ -78,8 +77,8 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
spin_unlock(&vdev->priv_lock);
if (!urb) {
- pr_err("cannot find a urb of seqnum %u\n", pdu->base.seqnum);
- pr_info("max seqnum %d\n",
+ pr_err("cannot find a urb of seqnum %u max seqnum %d\n",
+ pdu->base.seqnum,
atomic_read(&the_controller->seqnum));
usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
return;
@@ -102,7 +101,7 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
if (usbip_dbg_flag_vhci_rx)
usbip_dump_urb(urb);
- usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
+ usbip_dbg_vhci_rx("now giveback urb %u\n", pdu->base.seqnum);
spin_lock(&the_controller->lock);
usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
@@ -165,7 +164,7 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev,
pr_info("the urb (seqnum %d) was already given back\n",
pdu->base.seqnum);
} else {
- usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
+ usbip_dbg_vhci_rx("now giveback urb %d\n", pdu->base.seqnum);
/* If unlink is successful, status is -ECONNRESET */
urb->status = pdu->u.ret_unlink.status;
diff --git a/drivers/usb/usbip/vhci_tx.c b/drivers/usb/usbip/vhci_tx.c
index 409fd99f3257..3c5796c8633a 100644
--- a/drivers/usb/usbip/vhci_tx.c
+++ b/drivers/usb/usbip/vhci_tx.c
@@ -82,7 +82,8 @@ static int vhci_send_cmd_submit(struct vhci_device *vdev)
memset(&msg, 0, sizeof(msg));
memset(&iov, 0, sizeof(iov));
- usbip_dbg_vhci_tx("setup txdata urb %p\n", urb);
+ usbip_dbg_vhci_tx("setup txdata urb seqnum %lu\n",
+ priv->seqnum);
/* 1. setup usbip_header */
setup_cmd_submit_pdu(&pdu_header, urb);
diff --git a/include/crypto/mcryptd.h b/include/crypto/mcryptd.h
index c23ee1f7ee80..c2ff077168d3 100644
--- a/include/crypto/mcryptd.h
+++ b/include/crypto/mcryptd.h
@@ -26,6 +26,7 @@ static inline struct mcryptd_ahash *__mcryptd_ahash_cast(
struct mcryptd_cpu_queue {
struct crypto_queue queue;
+ spinlock_t q_lock;
struct work_struct work;
};
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 402753bccafa..7b8e3afcc291 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -215,7 +215,8 @@ struct ipv6_pinfo {
* 100: prefer care-of address
*/
dontfrag:1,
- autoflowlabel:1;
+ autoflowlabel:1,
+ autoflowlabel_set:1;
__u8 min_hopcount;
__u8 tclass;
__be32 rcv_flowinfo;
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index e623d392db0c..8ef3a61fdc74 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -80,10 +80,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
#endif
#endif
#ifdef CONFIG_DEBUG_TLBFLUSH
-#ifdef CONFIG_SMP
NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */
NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
-#endif /* CONFIG_SMP */
NR_TLB_LOCAL_FLUSH_ALL,
NR_TLB_LOCAL_FLUSH_ONE,
#endif /* CONFIG_DEBUG_TLBFLUSH */
diff --git a/include/net/ip.h b/include/net/ip.h
index 7476bb10ff37..639398af273b 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -33,6 +33,8 @@
#include <net/flow.h>
#include <net/flow_dissector.h>
+#define IPV4_MIN_MTU 68 /* RFC 791 */
+
struct sock;
struct inet_skb_parm {
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 22c57e191a23..e5d228f7224c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -568,6 +568,11 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
}
+static inline bool local_timer_softirq_pending(void)
+{
+ return local_softirq_pending() & TIMER_SOFTIRQ;
+}
+
static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
ktime_t now, int cpu)
{
@@ -584,8 +589,18 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
} while (read_seqretry(&jiffies_lock, seq));
ts->last_jiffies = basejiff;
- if (rcu_needs_cpu(basemono, &next_rcu) ||
- arch_needs_cpu() || irq_work_needs_cpu()) {
+ /*
+ * Keep the periodic tick, when RCU, architecture or irq_work
+ * requests it.
+ * Aside of that check whether the local timer softirq is
+ * pending. If so its a bad idea to call get_next_timer_interrupt()
+ * because there is an already expired timer, so it will request
+ * immeditate expiry, which rearms the hardware timer with a
+ * minimal delta which brings us back to this place
+ * immediately. Lather, rinse and repeat...
+ */
+ if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() ||
+ irq_work_needs_cpu() || local_timer_softirq_pending()) {
next_tick = basemono + TICK_NSEC;
} else {
/*
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 1275175b0946..d9cd6191760b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -280,6 +280,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
/* Missed count stored at end */
#define RB_MISSED_STORED (1 << 30)
+#define RB_MISSED_FLAGS (RB_MISSED_EVENTS|RB_MISSED_STORED)
+
struct buffer_data_page {
u64 time_stamp; /* page time stamp */
local_t commit; /* write committed index */
@@ -331,7 +333,9 @@ static void rb_init_page(struct buffer_data_page *bpage)
*/
size_t ring_buffer_page_len(void *page)
{
- return local_read(&((struct buffer_data_page *)page)->commit)
+ struct buffer_data_page *bpage = page;
+
+ return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS)
+ BUF_PAGE_HDR_SIZE;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 61d0960559c8..8aef4e63ac57 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5754,7 +5754,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
.spd_release = buffer_spd_release,
};
struct buffer_ref *ref;
- int entries, size, i;
+ int entries, i;
ssize_t ret = 0;
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -5805,14 +5805,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
break;
}
- /*
- * zero out any left over data, this is going to
- * user land.
- */
- size = ring_buffer_page_len(ref->page);
- if (size < PAGE_SIZE)
- memset(ref->page + size, 0, PAGE_SIZE - size);
-
page = virt_to_page(ref->page);
spd.pages[i] = page;
@@ -6539,6 +6531,7 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
buf->data = alloc_percpu(struct trace_array_cpu);
if (!buf->data) {
ring_buffer_free(buf->buffer);
+ buf->buffer = NULL;
return -ENOMEM;
}
@@ -6562,7 +6555,9 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
allocate_snapshot ? size : 1);
if (WARN_ON(ret)) {
ring_buffer_free(tr->trace_buffer.buffer);
+ tr->trace_buffer.buffer = NULL;
free_percpu(tr->trace_buffer.data);
+ tr->trace_buffer.data = NULL;
return -ENOMEM;
}
tr->allocated_snapshot = allocate_snapshot;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index a1f697ec4fc2..0ce26a0f7913 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1067,19 +1067,20 @@ static int br_dev_newlink(struct net *src_net, struct net_device *dev,
struct net_bridge *br = netdev_priv(dev);
int err;
+ err = register_netdevice(dev);
+ if (err)
+ return err;
+
if (tb[IFLA_ADDRESS]) {
spin_lock_bh(&br->lock);
br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
spin_unlock_bh(&br->lock);
}
- err = register_netdevice(dev);
- if (err)
- return err;
-
err = br_changelink(dev, tb, data);
if (err)
- unregister_netdevice(dev);
+ br_dev_delete(dev, NULL);
+
return err;
}
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 2e9a1c2818c7..b5c351d2830b 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -261,7 +261,7 @@ struct net *get_net_ns_by_id(struct net *net, int id)
spin_lock_irqsave(&net->nsid_lock, flags);
peer = idr_find(&net->netns_ids, id);
if (peer)
- get_net(peer);
+ peer = maybe_get_net(peer);
spin_unlock_irqrestore(&net->nsid_lock, flags);
rcu_read_unlock();
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d33609c2f276..86b619501350 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3676,7 +3676,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
struct sock *sk = skb->sk;
if (!skb_may_tx_timestamp(sk, false))
- return;
+ goto err;
/* Take a reference to prevent skb_orphan() from freeing the socket,
* but only if the socket refcount is not zero.
@@ -3685,7 +3685,11 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
*skb_hwtstamps(skb) = *hwtstamps;
__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
sock_put(sk);
+ return;
}
+
+err:
+ kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 0212591b0077..63f99e9a821b 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1358,7 +1358,7 @@ skip:
static bool inetdev_valid_mtu(unsigned int mtu)
{
- return mtu >= 68;
+ return mtu >= IPV4_MIN_MTU;
}
static void inetdev_send_gratuitous_arp(struct net_device *dev,
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 0cb240c749bf..c9e68ff48a72 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1252,7 +1252,7 @@ fail:
static void ip_fib_net_exit(struct net *net)
{
- unsigned int i;
+ int i;
rtnl_lock();
#ifdef CONFIG_IP_MULTIPLE_TABLES
@@ -1260,7 +1260,12 @@ static void ip_fib_net_exit(struct net *net)
RCU_INIT_POINTER(net->ipv4.fib_main, NULL);
RCU_INIT_POINTER(net->ipv4.fib_default, NULL);
#endif
- for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+ /* Destroy the tables in reverse order to guarantee that the
+ * local table, ID 255, is destroyed before the main table, ID
+ * 254. This is necessary as the local table may contain
+ * references to data contained in the main table.
+ */
+ for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) {
struct hlist_head *head = &net->ipv4.fib_table_hash[i];
struct hlist_node *tmp;
struct fib_table *tb;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 3809d523d012..b60106d34346 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -89,6 +89,7 @@
#include <linux/rtnetlink.h>
#include <linux/times.h>
#include <linux/pkt_sched.h>
+#include <linux/byteorder/generic.h>
#include <net/net_namespace.h>
#include <net/arp.h>
@@ -327,6 +328,23 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted)
return scount;
}
+/* source address selection per RFC 3376 section 4.2.13 */
+static __be32 igmpv3_get_srcaddr(struct net_device *dev,
+ const struct flowi4 *fl4)
+{
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+ if (!in_dev)
+ return htonl(INADDR_ANY);
+
+ for_ifa(in_dev) {
+ if (inet_ifa_match(fl4->saddr, ifa))
+ return fl4->saddr;
+ } endfor_ifa(in_dev);
+
+ return htonl(INADDR_ANY);
+}
+
static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
{
struct sk_buff *skb;
@@ -374,7 +392,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
pip->frag_off = htons(IP_DF);
pip->ttl = 1;
pip->daddr = fl4.daddr;
- pip->saddr = fl4.saddr;
+ pip->saddr = igmpv3_get_srcaddr(dev, &fl4);
pip->protocol = IPPROTO_IGMP;
pip->tot_len = 0; /* filled in later */
ip_select_ident(net, skb, NULL);
@@ -410,16 +428,17 @@ static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel)
}
static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc,
- int type, struct igmpv3_grec **ppgr)
+ int type, struct igmpv3_grec **ppgr, unsigned int mtu)
{
struct net_device *dev = pmc->interface->dev;
struct igmpv3_report *pih;
struct igmpv3_grec *pgr;
- if (!skb)
- skb = igmpv3_newpack(dev, dev->mtu);
- if (!skb)
- return NULL;
+ if (!skb) {
+ skb = igmpv3_newpack(dev, mtu);
+ if (!skb)
+ return NULL;
+ }
pgr = (struct igmpv3_grec *)skb_put(skb, sizeof(struct igmpv3_grec));
pgr->grec_type = type;
pgr->grec_auxwords = 0;
@@ -441,12 +460,17 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
struct igmpv3_grec *pgr = NULL;
struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list;
int scount, stotal, first, isquery, truncate;
+ unsigned int mtu;
if (pmc->multiaddr == IGMP_ALL_HOSTS)
return skb;
if (ipv4_is_local_multicast(pmc->multiaddr) && !sysctl_igmp_llm_reports)
return skb;
+ mtu = READ_ONCE(dev->mtu);
+ if (mtu < IPV4_MIN_MTU)
+ return skb;
+
isquery = type == IGMPV3_MODE_IS_INCLUDE ||
type == IGMPV3_MODE_IS_EXCLUDE;
truncate = type == IGMPV3_MODE_IS_EXCLUDE ||
@@ -467,7 +491,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
igmpv3_sendpack(skb);
- skb = igmpv3_newpack(dev, dev->mtu);
+ skb = igmpv3_newpack(dev, mtu);
}
}
first = 1;
@@ -494,12 +518,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
pgr->grec_nsrcs = htons(scount);
if (skb)
igmpv3_sendpack(skb);
- skb = igmpv3_newpack(dev, dev->mtu);
+ skb = igmpv3_newpack(dev, mtu);
first = 1;
scount = 0;
}
if (first) {
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
first = 0;
}
if (!skb)
@@ -533,7 +557,7 @@ empty_source:
igmpv3_sendpack(skb);
skb = NULL; /* add_grhead will get a new one */
}
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
}
}
if (pgr)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 3310ac75e3f3..c18245e05d26 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -400,8 +400,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
dev->needed_headroom = t_hlen + hlen;
mtu -= (dev->hard_header_len + t_hlen);
- if (mtu < 68)
- mtu = 68;
+ if (mtu < IPV4_MIN_MTU)
+ mtu = IPV4_MIN_MTU;
return mtu;
}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8f2cd7d09720..4d3d4291c82f 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -500,11 +500,16 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
int err;
struct ip_options_data opt_copy;
struct raw_frag_vec rfv;
+ int hdrincl;
err = -EMSGSIZE;
if (len > 0xFFFF)
goto out;
+ /* hdrincl should be READ_ONCE(inet->hdrincl)
+ * but READ_ONCE() doesn't work with bit fields
+ */
+ hdrincl = inet->hdrincl;
/*
* Check the flags.
*/
@@ -579,7 +584,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
/* Linux does not mangle headers on raw sockets,
* so that IP options + IP_HDRINCL is non-sense.
*/
- if (inet->hdrincl)
+ if (hdrincl)
goto done;
if (ipc.opt->opt.srr) {
if (!daddr)
@@ -601,9 +606,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
- inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
- (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
+ (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0);
if (!saddr && ipc.oif) {
@@ -612,7 +617,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
goto done;
}
- if (!inet->hdrincl) {
+ if (!hdrincl) {
rfv.msg = msg;
rfv.hlen = 0;
@@ -637,7 +642,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
goto do_confirm;
back_from_confirm:
- if (inet->hdrincl)
+ if (hdrincl)
err = raw_send_hdrinc(sk, &fl4, msg, len,
&rt, msg->msg_flags);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a5d790c13ef5..61c93a93f228 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -823,7 +823,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
tcp_time_stamp,
req->ts_recent,
0,
- tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
+ tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr,
AF_INET),
inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
ip_hdr(skb)->tos);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 83ec6639b04d..637a0e41b0aa 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -200,7 +200,6 @@ lookup_protocol:
np->mcast_hops = IPV6_DEFAULT_MCASTHOPS;
np->mc_loop = 1;
np->pmtudisc = IPV6_PMTUDISC_WANT;
- np->autoflowlabel = ip6_default_np_autolabel(sock_net(sk));
sk->sk_ipv6only = net->ipv6.sysctl.bindv6only;
/* Init the ipv4 part of the socket since we can have sockets
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 71624cf26832..1b4f5f2d2929 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -148,6 +148,14 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
!(IP6CB(skb)->flags & IP6SKB_REROUTED));
}
+static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
+{
+ if (!np->autoflowlabel_set)
+ return ip6_default_np_autolabel(net);
+ else
+ return np->autoflowlabel;
+}
+
/*
* xmit an sk_buff (used by TCP, SCTP and DCCP)
* Note : socket lock is not held for SYNACK packets, but might be modified
@@ -211,7 +219,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
hlimit = ip6_dst_hoplimit(dst);
ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
- np->autoflowlabel, fl6));
+ ip6_autoflowlabel(net, np), fl6));
hdr->payload_len = htons(seg_len);
hdr->nexthdr = proto;
@@ -1675,7 +1683,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
ip6_flow_hdr(hdr, v6_cork->tclass,
ip6_make_flowlabel(net, skb, fl6->flowlabel,
- np->autoflowlabel, fl6));
+ ip6_autoflowlabel(net, np), fl6));
hdr->hop_limit = v6_cork->hop_limit;
hdr->nexthdr = proto;
hdr->saddr = fl6->saddr;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index a4a30d2ca66f..435e26210587 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -872,6 +872,7 @@ pref_skip_coa:
break;
case IPV6_AUTOFLOWLABEL:
np->autoflowlabel = valbool;
+ np->autoflowlabel_set = 1;
retv = 0;
break;
}
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index d64ee7e83664..06640685ff43 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1668,16 +1668,16 @@ static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel)
}
static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc,
- int type, struct mld2_grec **ppgr)
+ int type, struct mld2_grec **ppgr, unsigned int mtu)
{
- struct net_device *dev = pmc->idev->dev;
struct mld2_report *pmr;
struct mld2_grec *pgr;
- if (!skb)
- skb = mld_newpack(pmc->idev, dev->mtu);
- if (!skb)
- return NULL;
+ if (!skb) {
+ skb = mld_newpack(pmc->idev, mtu);
+ if (!skb)
+ return NULL;
+ }
pgr = (struct mld2_grec *)skb_put(skb, sizeof(struct mld2_grec));
pgr->grec_type = type;
pgr->grec_auxwords = 0;
@@ -1700,10 +1700,15 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
struct mld2_grec *pgr = NULL;
struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list;
int scount, stotal, first, isquery, truncate;
+ unsigned int mtu;
if (pmc->mca_flags & MAF_NOREPORT)
return skb;
+ mtu = READ_ONCE(dev->mtu);
+ if (mtu < IPV6_MIN_MTU)
+ return skb;
+
isquery = type == MLD2_MODE_IS_INCLUDE ||
type == MLD2_MODE_IS_EXCLUDE;
truncate = type == MLD2_MODE_IS_EXCLUDE ||
@@ -1724,7 +1729,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(idev, dev->mtu);
+ skb = mld_newpack(idev, mtu);
}
}
first = 1;
@@ -1751,12 +1756,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
pgr->grec_nsrcs = htons(scount);
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(idev, dev->mtu);
+ skb = mld_newpack(idev, mtu);
first = 1;
scount = 0;
}
if (first) {
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
first = 0;
}
if (!skb)
@@ -1790,7 +1795,7 @@ empty_source:
mld_sendpack(skb);
skb = NULL; /* add_grhead will get a new one */
}
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
}
}
if (pgr)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 59c908ff251a..74cbcc4b399c 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -949,7 +949,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
tcp_rsk(req)->rcv_nxt,
req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
- tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
+ tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr),
0, 0);
}
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 5fabe68e20dd..48e1608414e6 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -261,6 +261,9 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
struct sock *sk = skb->sk;
int ret = -ENOMEM;
+ if (!net_eq(dev_net(dev), sock_net(sk)))
+ return 0;
+
dev_hold(dev);
if (is_vmalloc_addr(skb->head))
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 61189c576963..a870d27ca778 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4153,7 +4153,7 @@ static int sctp_init_sock(struct sock *sk)
SCTP_DBG_OBJCNT_INC(sock);
local_bh_disable();
- percpu_counter_inc(&sctp_sockets_allocated);
+ sk_sockets_allocated_inc(sk);
sock_prot_inuse_add(net, sk->sk_prot, 1);
/* Nothing can fail after this block, otherwise
@@ -4197,7 +4197,7 @@ static void sctp_destroy_sock(struct sock *sk)
}
sctp_endpoint_free(sp->ep);
local_bh_disable();
- percpu_counter_dec(&sctp_sockets_allocated);
+ sk_sockets_allocated_dec(sk);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
local_bh_enable();
}
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index b450a27588c8..16f8124b1150 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -579,15 +579,14 @@ static int snd_rawmidi_info_user(struct snd_rawmidi_substream *substream,
return 0;
}
-int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info)
+static int __snd_rawmidi_info_select(struct snd_card *card,
+ struct snd_rawmidi_info *info)
{
struct snd_rawmidi *rmidi;
struct snd_rawmidi_str *pstr;
struct snd_rawmidi_substream *substream;
- mutex_lock(®ister_mutex);
rmidi = snd_rawmidi_search(card, info->device);
- mutex_unlock(®ister_mutex);
if (!rmidi)
return -ENXIO;
if (info->stream < 0 || info->stream > 1)
@@ -603,6 +602,16 @@ int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info
}
return -ENXIO;
}
+
+int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info)
+{
+ int ret;
+
+ mutex_lock(®ister_mutex);
+ ret = __snd_rawmidi_info_select(card, info);
+ mutex_unlock(®ister_mutex);
+ return ret;
+}
EXPORT_SYMBOL(snd_rawmidi_info_select);
static int snd_rawmidi_info_select_user(struct snd_card *card,
diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index cce9ae5ec93b..bd7bcf428bcf 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -183,7 +183,7 @@ static int hdac_component_master_match(struct device *dev, void *data)
*/
int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *aops)
{
- if (WARN_ON(!hdac_acomp))
+ if (!hdac_acomp)
return -ENODEV;
hdac_acomp->audio_ops = aops;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 2159b18f76bf..5875a08d555e 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5953,6 +5953,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x1b, 0x01011020},
{0x21, 0x02211010}),
+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x12, 0x90a60130},
+ {0x14, 0x90170110},
+ {0x1b, 0x01011020},
+ {0x21, 0x0221101f}),
SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x12, 0x90a60160},
{0x14, 0x90170120},
diff --git a/sound/soc/codecs/twl4030.c b/sound/soc/codecs/twl4030.c
index a5a4e9f75c57..a06395507225 100644
--- a/sound/soc/codecs/twl4030.c
+++ b/sound/soc/codecs/twl4030.c
@@ -232,7 +232,7 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec)
struct twl4030_codec_data *pdata = dev_get_platdata(codec->dev);
struct device_node *twl4030_codec_node = NULL;
- twl4030_codec_node = of_find_node_by_name(codec->dev->parent->of_node,
+ twl4030_codec_node = of_get_child_by_name(codec->dev->parent->of_node,
"codec");
if (!pdata && twl4030_codec_node) {
@@ -241,9 +241,11 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec)
GFP_KERNEL);
if (!pdata) {
dev_err(codec->dev, "Can not allocate memory\n");
+ of_node_put(twl4030_codec_node);
return NULL;
}
twl4030_setup_pdata_of(pdata, twl4030_codec_node);
+ of_node_put(twl4030_codec_node);
}
return pdata;
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index 95d2392303eb..7ca67613e0d4 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -1408,12 +1408,6 @@ static int fsl_ssi_probe(struct platform_device *pdev)
sizeof(fsl_ssi_ac97_dai));
fsl_ac97_data = ssi_private;
-
- ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev);
- if (ret) {
- dev_err(&pdev->dev, "could not set AC'97 ops\n");
- return ret;
- }
} else {
/* Initialize this copy of the CPU DAI driver structure */
memcpy(&ssi_private->cpu_dai_drv, &fsl_ssi_dai_template,
@@ -1473,6 +1467,14 @@ static int fsl_ssi_probe(struct platform_device *pdev)
return ret;
}
+ if (fsl_ssi_is_ac97(ssi_private)) {
+ ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev);
+ if (ret) {
+ dev_err(&pdev->dev, "could not set AC'97 ops\n");
+ goto error_ac97_ops;
+ }
+ }
+
ret = devm_snd_soc_register_component(&pdev->dev, &fsl_ssi_component,
&ssi_private->cpu_dai_drv, 1);
if (ret) {
@@ -1556,6 +1558,10 @@ error_sound_card:
fsl_ssi_debugfs_remove(&ssi_private->dbg_stats);
error_asoc_register:
+ if (fsl_ssi_is_ac97(ssi_private))
+ snd_soc_set_ac97_ops(NULL);
+
+error_ac97_ops:
if (ssi_private->soc->imx)
fsl_ssi_imx_clean(pdev, ssi_private);
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 0ed9ae030ce1..c9ae29068c7c 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -2101,20 +2101,25 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid,
kctl->private_value = (unsigned long)namelist;
kctl->private_free = usb_mixer_selector_elem_free;
- nameid = uac_selector_unit_iSelector(desc);
+ /* check the static mapping table at first */
len = check_mapped_name(map, kctl->id.name, sizeof(kctl->id.name));
- if (len)
- ;
- else if (nameid)
- len = snd_usb_copy_string_desc(state, nameid, kctl->id.name,
- sizeof(kctl->id.name));
- else
- len = get_term_name(state, &state->oterm,
- kctl->id.name, sizeof(kctl->id.name), 0);
-
if (!len) {
- strlcpy(kctl->id.name, "USB", sizeof(kctl->id.name));
+ /* no mapping ? */
+ /* if iSelector is given, use it */
+ nameid = uac_selector_unit_iSelector(desc);
+ if (nameid)
+ len = snd_usb_copy_string_desc(state, nameid,
+ kctl->id.name,
+ sizeof(kctl->id.name));
+ /* ... or pick up the terminal name at next */
+ if (!len)
+ len = get_term_name(state, &state->oterm,
+ kctl->id.name, sizeof(kctl->id.name), 0);
+ /* ... or use the fixed string "USB" as the last resort */
+ if (!len)
+ strlcpy(kctl->id.name, "USB", sizeof(kctl->id.name));
+ /* and add the proper suffix */
if (desc->bDescriptorSubtype == UAC2_CLOCK_SELECTOR)
append_ctl_name(kctl, " Clock Source");
else if ((state->oterm.type & 0xff00) == 0x0100)
diff --git a/tools/usb/usbip/src/utils.c b/tools/usb/usbip/src/utils.c
index 2b3d6d235015..3d7b42e77299 100644
--- a/tools/usb/usbip/src/utils.c
+++ b/tools/usb/usbip/src/utils.c
@@ -30,6 +30,7 @@ int modify_match_busid(char *busid, int add)
char command[SYSFS_BUS_ID_SIZE + 4];
char match_busid_attr_path[SYSFS_PATH_MAX];
int rc;
+ int cmd_size;
snprintf(match_busid_attr_path, sizeof(match_busid_attr_path),
"%s/%s/%s/%s/%s/%s", SYSFS_MNT_PATH, SYSFS_BUS_NAME,
@@ -37,12 +38,14 @@ int modify_match_busid(char *busid, int add)
attr_name);
if (add)
- snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s", busid);
+ cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s",
+ busid);
else
- snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s", busid);
+ cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s",
+ busid);
rc = write_sysfs_attribute(match_busid_attr_path, command,
- sizeof(command));
+ cmd_size);
if (rc < 0) {
dbg("failed to write match_busid: %s", strerror(errno));
return -1;
7 years, 8 months
- 1
- 0
Re: [Linux-stable-mirror] Linux 3.18.91
by Greg KH
diff --git a/Makefile b/Makefile
index abbfbbb7a029..d114d0641a7e 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 3
PATCHLEVEL = 18
-SUBLEVEL = 90
+SUBLEVEL = 91
EXTRAVERSION =
NAME = Diseased Newt
@@ -762,6 +762,9 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign)
# disable invalid "can't wrap" optimizations for signed / pointers
KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow)
+# Make sure -fstack-check isn't enabled (like gentoo apparently did)
+KBUILD_CFLAGS += $(call cc-option,-fno-stack-check,)
+
# conserve stack if available
KBUILD_CFLAGS += $(call cc-option,-fconserve-stack)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index ffa07eb5fff0..ba5f0580d5b0 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -396,8 +396,12 @@ static __u64 power_pmu_bhrb_to(u64 addr)
int ret;
__u64 target;
- if (is_kernel_addr(addr))
- return branch_target((unsigned int *)addr);
+ if (is_kernel_addr(addr)) {
+ if (probe_kernel_read(&instr, (void *)addr, sizeof(instr)))
+ return 0;
+
+ return branch_target(&instr);
+ }
/* Userspace: need copy instruction here then translate it */
pagefault_disable();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c8105be39b00..0dcbe370374f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6644,7 +6644,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
#endif
kvm_rip_write(vcpu, regs->rip);
- kvm_set_rflags(vcpu, regs->rflags);
+ kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED);
vcpu->arch.exception.pending = false;
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index 02a1c10fa909..8cd2bc32c7fb 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -80,6 +80,7 @@ static int mcryptd_init_queue(struct mcryptd_queue *queue,
pr_debug("cpu_queue #%d %p\n", cpu, queue->cpu_queue);
crypto_init_queue(&cpu_queue->queue, max_cpu_qlen);
INIT_WORK(&cpu_queue->work, mcryptd_queue_worker);
+ spin_lock_init(&cpu_queue->q_lock);
}
return 0;
}
@@ -103,15 +104,16 @@ static int mcryptd_enqueue_request(struct mcryptd_queue *queue,
int cpu, err;
struct mcryptd_cpu_queue *cpu_queue;
- cpu = get_cpu();
- cpu_queue = this_cpu_ptr(queue->cpu_queue);
- rctx->tag.cpu = cpu;
+ cpu_queue = raw_cpu_ptr(queue->cpu_queue);
+ spin_lock(&cpu_queue->q_lock);
+ cpu = smp_processor_id();
+ rctx->tag.cpu = smp_processor_id();
err = crypto_enqueue_request(&cpu_queue->queue, request);
pr_debug("enqueue request: cpu %d cpu_queue %p request %p\n",
cpu, cpu_queue, request);
+ spin_unlock(&cpu_queue->q_lock);
queue_work_on(cpu, kcrypto_wq, &cpu_queue->work);
- put_cpu();
return err;
}
@@ -164,16 +166,11 @@ static void mcryptd_queue_worker(struct work_struct *work)
cpu_queue = container_of(work, struct mcryptd_cpu_queue, work);
i = 0;
while (i < MCRYPTD_BATCH || single_task_running()) {
- /*
- * preempt_disable/enable is used to prevent
- * being preempted by mcryptd_enqueue_request()
- */
- local_bh_disable();
- preempt_disable();
+
+ spin_lock_bh(&cpu_queue->q_lock);
backlog = crypto_get_backlog(&cpu_queue->queue);
req = crypto_dequeue_request(&cpu_queue->queue);
- preempt_enable();
- local_bh_enable();
+ spin_unlock_bh(&cpu_queue->q_lock);
if (!req) {
mcryptd_opportunistic_flush();
@@ -188,7 +185,7 @@ static void mcryptd_queue_worker(struct work_struct *work)
++i;
}
if (cpu_queue->queue.qlen)
- queue_work(kcrypto_wq, &cpu_queue->work);
+ queue_work_on(smp_processor_id(), kcrypto_wq, &cpu_queue->work);
}
void mcryptd_flusher(struct work_struct *__work)
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index ed65e9c4b5b0..ba4930c0e98c 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -1023,7 +1023,7 @@ skip:
/* The record may be cleared by others, try read next record */
if (len == -ENOENT)
goto skip;
- else if (len < sizeof(*rcd)) {
+ else if (len < 0 || len < sizeof(*rcd)) {
rc = -EIO;
goto out;
}
diff --git a/drivers/mfd/twl4030-audio.c b/drivers/mfd/twl4030-audio.c
index 07fe542e6fc0..9372f5e6b677 100644
--- a/drivers/mfd/twl4030-audio.c
+++ b/drivers/mfd/twl4030-audio.c
@@ -159,13 +159,18 @@ unsigned int twl4030_audio_get_mclk(void)
EXPORT_SYMBOL_GPL(twl4030_audio_get_mclk);
static bool twl4030_audio_has_codec(struct twl4030_audio_data *pdata,
- struct device_node *node)
+ struct device_node *parent)
{
+ struct device_node *node;
+
if (pdata && pdata->codec)
return true;
- if (of_find_node_by_name(node, "codec"))
+ node = of_get_child_by_name(parent, "codec");
+ if (node) {
+ of_node_put(node);
return true;
+ }
return false;
}
diff --git a/drivers/mfd/twl6040.c b/drivers/mfd/twl6040.c
index 9687645162ae..902acc48bc6c 100644
--- a/drivers/mfd/twl6040.c
+++ b/drivers/mfd/twl6040.c
@@ -97,12 +97,16 @@ static struct reg_default twl6040_patch[] = {
};
-static bool twl6040_has_vibra(struct device_node *node)
+static bool twl6040_has_vibra(struct device_node *parent)
{
-#ifdef CONFIG_OF
- if (of_find_node_by_name(node, "vibra"))
+ struct device_node *node;
+
+ node = of_get_child_by_name(parent, "vibra");
+ if (node) {
+ of_node_put(node);
return true;
-#endif
+ }
+
return false;
}
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index a79e73781c0b..05a2f3b304c3 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -14202,7 +14202,9 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
/* Reset PHY, otherwise the read DMA engine will be in a mode that
* breaks all requests to 256 bytes.
*/
- if (tg3_asic_rev(tp) == ASIC_REV_57766)
+ if (tg3_asic_rev(tp) == ASIC_REV_57766 ||
+ tg3_asic_rev(tp) == ASIC_REV_5717 ||
+ tg3_asic_rev(tp) == ASIC_REV_5719)
reset_phy = true;
err = tg3_restart_hw(tp, reset_phy);
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index fc2fb25343f4..c122b3b99cd8 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -241,7 +241,8 @@ static int orion_mdio_probe(struct platform_device *pdev)
dev->regs + MVMDIO_ERR_INT_MASK);
} else if (dev->err_interrupt == -EPROBE_DEFER) {
- return -EPROBE_DEFER;
+ ret = -EPROBE_DEFER;
+ goto out_mdio;
}
mutex_init(&dev->lock);
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e6a7b50a4781..a53e7c6172a3 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -851,6 +851,10 @@ static void mvneta_port_disable(struct mvneta_port *pp)
val &= ~MVNETA_GMAC0_PORT_ENABLE;
mvreg_write(pp, MVNETA_GMAC_CTRL_0, val);
+ pp->link = 0;
+ pp->duplex = -1;
+ pp->speed = 0;
+
udelay(200);
}
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index f098cc9707aa..cdaeb9295afc 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -778,6 +778,7 @@ static const struct usb_device_id products[] = {
{QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */
{QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */
{QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */
+ {QMI_FIXED_INTF(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */
{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */
{QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */
diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c
index 4590515a275c..23817b0c88cb 100644
--- a/drivers/parisc/lba_pci.c
+++ b/drivers/parisc/lba_pci.c
@@ -1652,3 +1652,36 @@ void lba_set_iregs(struct parisc_device *lba, u32 ibase, u32 imask)
iounmap(base_addr);
}
+
+/*
+ * The design of the Diva management card in rp34x0 machines (rp3410, rp3440)
+ * seems rushed, so that many built-in components simply don't work.
+ * The following quirks disable the serial AUX port and the built-in ATI RV100
+ * Radeon 7000 graphics card which both don't have any external connectors and
+ * thus are useless, and even worse, e.g. the AUX port occupies ttyS0 and as
+ * such makes those machines the only PARISC machines on which we can't use
+ * ttyS0 as boot console.
+ */
+static void quirk_diva_ati_card(struct pci_dev *dev)
+{
+ if (dev->subsystem_vendor != PCI_VENDOR_ID_HP ||
+ dev->subsystem_device != 0x1292)
+ return;
+
+ dev_info(&dev->dev, "Hiding Diva built-in ATI card");
+ dev->device = 0;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_RADEON_QY,
+ quirk_diva_ati_card);
+
+static void quirk_diva_aux_disable(struct pci_dev *dev)
+{
+ if (dev->subsystem_vendor != PCI_VENDOR_ID_HP ||
+ dev->subsystem_device != 0x1291)
+ return;
+
+ dev_info(&dev->dev, "Hiding Diva built-in AUX serial device");
+ dev->device = 0;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_DIVA_AUX,
+ quirk_diva_aux_disable);
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index e7adfbd2d482..0ad37e69746d 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -924,7 +924,12 @@ static int pci_pm_thaw_noirq(struct device *dev)
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_resume_early(dev);
- pci_update_current_state(pci_dev, PCI_D0);
+ /*
+ * pci_restore_state() requires the device to be in D0 (because of MSI
+ * restoration among other things), so force it into D0 in case the
+ * driver's "freeze" callbacks put it into a low-power state directly.
+ */
+ pci_set_power_state(pci_dev, PCI_D0);
pci_restore_state(pci_dev);
if (drv && drv->pm && drv->pm->thaw_noirq)
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 7b64a5fdd916..c5bd4ca18b09 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -1809,7 +1809,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
{
struct n_tty_data *ldata = tty->disc_data;
- if (!old || (old->c_lflag ^ tty->termios.c_lflag) & ICANON) {
+ if (!old || (old->c_lflag ^ tty->termios.c_lflag) & (ICANON | EXTPROC)) {
bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE);
ldata->line_start = ldata->read_tail;
if (!L_ICANON(tty) || !read_cnt(ldata)) {
@@ -2525,7 +2525,7 @@ static int n_tty_ioctl(struct tty_struct *tty, struct file *file,
return put_user(tty_chars_in_buffer(tty), (int __user *) arg);
case TIOCINQ:
down_write(&tty->termios_rwsem);
- if (L_ICANON(tty))
+ if (L_ICANON(tty) && !L_EXTPROC(tty))
retval = inq_canon(ldata);
else
retval = read_cnt(ldata);
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 1ef86b4e7927..e34b84e0d782 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -53,10 +53,11 @@ static const struct usb_device_id usb_quirk_list[] = {
/* Microsoft LifeCam-VX700 v2.0 */
{ USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },
- /* Logitech HD Pro Webcams C920, C920-C and C930e */
+ /* Logitech HD Pro Webcams C920, C920-C, C925e and C930e */
{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
{ USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT },
{ USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
+ { USB_DEVICE(0x046d, 0x085b), .driver_info = USB_QUIRK_DELAY_INIT },
/* Logitech ConferenceCam CC3000e */
{ USB_DEVICE(0x046d, 0x0847), .driver_info = USB_QUIRK_DELAY_INIT },
@@ -147,6 +148,9 @@ static const struct usb_device_id usb_quirk_list[] = {
/* Genesys Logic hub, internally used by KY-688 USB 3.1 Type-C Hub */
{ USB_DEVICE(0x05e3, 0x0612), .driver_info = USB_QUIRK_NO_LPM },
+ /* ELSA MicroLink 56K */
+ { USB_DEVICE(0x05cc, 0x2267), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Genesys Logic hub, internally used by Moshi USB to Ethernet Adapter */
{ USB_DEVICE(0x05e3, 0x0616), .driver_info = USB_QUIRK_NO_LPM },
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 6bc448701a9c..e8b6bef4e78d 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -171,6 +171,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
xhci->quirks |= XHCI_TRUST_TX_LENGTH;
xhci->quirks |= XHCI_BROKEN_STREAMS;
}
+ if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
+ pdev->device == 0x0014)
+ xhci->quirks |= XHCI_TRUST_TX_LENGTH;
if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
pdev->device == 0x0015)
xhci->quirks |= XHCI_RESET_ON_RESUME;
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 71d032822cd9..9db1338002a2 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -276,6 +276,7 @@ static void option_instat_callback(struct urb *urb);
#define TELIT_PRODUCT_LE922_USBCFG3 0x1043
#define TELIT_PRODUCT_LE922_USBCFG5 0x1045
#define TELIT_PRODUCT_ME910 0x1100
+#define TELIT_PRODUCT_ME910_DUAL_MODEM 0x1101
#define TELIT_PRODUCT_LE920 0x1200
#define TELIT_PRODUCT_LE910 0x1201
#define TELIT_PRODUCT_LE910_USBCFG4 0x1206
@@ -644,6 +645,11 @@ static const struct option_blacklist_info telit_me910_blacklist = {
.reserved = BIT(1) | BIT(3),
};
+static const struct option_blacklist_info telit_me910_dual_modem_blacklist = {
+ .sendsetup = BIT(0),
+ .reserved = BIT(3),
+};
+
static const struct option_blacklist_info telit_le910_blacklist = {
.sendsetup = BIT(0),
.reserved = BIT(1) | BIT(2),
@@ -1242,6 +1248,8 @@ static const struct usb_device_id option_ids[] = {
.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
.driver_info = (kernel_ulong_t)&telit_me910_blacklist },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
+ .driver_info = (kernel_ulong_t)&telit_me910_dual_modem_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
.driver_info = (kernel_ulong_t)&telit_le910_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4),
diff --git a/include/crypto/mcryptd.h b/include/crypto/mcryptd.h
index c23ee1f7ee80..c2ff077168d3 100644
--- a/include/crypto/mcryptd.h
+++ b/include/crypto/mcryptd.h
@@ -26,6 +26,7 @@ static inline struct mcryptd_ahash *__mcryptd_ahash_cast(
struct mcryptd_cpu_queue {
struct crypto_queue queue;
+ spinlock_t q_lock;
struct work_struct work;
};
diff --git a/include/net/ip.h b/include/net/ip.h
index 7f0cd17668ae..55da8ad90582 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -33,6 +33,8 @@
#include <net/flow.h>
#include <net/flow_keys.h>
+#define IPV4_MIN_MTU 68 /* RFC 791 */
+
struct sock;
struct inet_skb_parm {
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f4856805ca89..68fcf6829bc5 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -336,6 +336,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
/* Missed count stored at end */
#define RB_MISSED_STORED (1 << 30)
+#define RB_MISSED_FLAGS (RB_MISSED_EVENTS|RB_MISSED_STORED)
+
struct buffer_data_page {
u64 time_stamp; /* page time stamp */
local_t commit; /* write committed index */
@@ -387,7 +389,9 @@ static void rb_init_page(struct buffer_data_page *bpage)
*/
size_t ring_buffer_page_len(void *page)
{
- return local_read(&((struct buffer_data_page *)page)->commit)
+ struct buffer_data_page *bpage = page;
+
+ return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS)
+ BUF_PAGE_HDR_SIZE;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e61b862309af..c8717cde9249 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5502,7 +5502,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
.spd_release = buffer_spd_release,
};
struct buffer_ref *ref;
- int entries, size, i;
+ int entries, i;
ssize_t ret = 0;
mutex_lock(&trace_types_lock);
@@ -5563,14 +5563,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
break;
}
- /*
- * zero out any left over data, this is going to
- * user land.
- */
- size = ring_buffer_page_len(ref->page);
- if (size < PAGE_SIZE)
- memset(ref->page + size, 0, PAGE_SIZE - size);
-
page = virt_to_page(ref->page);
spd.pages[i] = page;
@@ -6252,6 +6244,7 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
buf->data = alloc_percpu(struct trace_array_cpu);
if (!buf->data) {
ring_buffer_free(buf->buffer);
+ buf->buffer = NULL;
return -ENOMEM;
}
@@ -6275,7 +6268,9 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
allocate_snapshot ? size : 1);
if (WARN_ON(ret)) {
ring_buffer_free(tr->trace_buffer.buffer);
+ tr->trace_buffer.buffer = NULL;
free_percpu(tr->trace_buffer.data);
+ tr->trace_buffer.data = NULL;
return -ENOMEM;
}
tr->allocated_snapshot = allocate_snapshot;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 464293c34b7a..618d55f4aa77 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1328,7 +1328,7 @@ skip:
static bool inetdev_valid_mtu(unsigned int mtu)
{
- return mtu >= 68;
+ return mtu >= IPV4_MIN_MTU;
}
static void inetdev_send_gratuitous_arp(struct net_device *dev,
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 1ea62ccfa884..71882e83bbbd 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -89,6 +89,7 @@
#include <linux/rtnetlink.h>
#include <linux/times.h>
#include <linux/pkt_sched.h>
+#include <linux/byteorder/generic.h>
#include <net/net_namespace.h>
#include <net/arp.h>
@@ -318,6 +319,23 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted)
return scount;
}
+/* source address selection per RFC 3376 section 4.2.13 */
+static __be32 igmpv3_get_srcaddr(struct net_device *dev,
+ const struct flowi4 *fl4)
+{
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+ if (!in_dev)
+ return htonl(INADDR_ANY);
+
+ for_ifa(in_dev) {
+ if (inet_ifa_match(fl4->saddr, ifa))
+ return fl4->saddr;
+ } endfor_ifa(in_dev);
+
+ return htonl(INADDR_ANY);
+}
+
static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
{
struct sk_buff *skb;
@@ -366,7 +384,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
pip->frag_off = htons(IP_DF);
pip->ttl = 1;
pip->daddr = fl4.daddr;
- pip->saddr = fl4.saddr;
+ pip->saddr = igmpv3_get_srcaddr(dev, &fl4);
pip->protocol = IPPROTO_IGMP;
pip->tot_len = 0; /* filled in later */
ip_select_ident(skb, NULL);
@@ -402,16 +420,17 @@ static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel)
}
static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc,
- int type, struct igmpv3_grec **ppgr)
+ int type, struct igmpv3_grec **ppgr, unsigned int mtu)
{
struct net_device *dev = pmc->interface->dev;
struct igmpv3_report *pih;
struct igmpv3_grec *pgr;
- if (!skb)
- skb = igmpv3_newpack(dev, dev->mtu);
- if (!skb)
- return NULL;
+ if (!skb) {
+ skb = igmpv3_newpack(dev, mtu);
+ if (!skb)
+ return NULL;
+ }
pgr = (struct igmpv3_grec *)skb_put(skb, sizeof(struct igmpv3_grec));
pgr->grec_type = type;
pgr->grec_auxwords = 0;
@@ -433,10 +452,15 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
struct igmpv3_grec *pgr = NULL;
struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list;
int scount, stotal, first, isquery, truncate;
+ unsigned int mtu;
if (pmc->multiaddr == IGMP_ALL_HOSTS)
return skb;
+ mtu = READ_ONCE(dev->mtu);
+ if (mtu < IPV4_MIN_MTU)
+ return skb;
+
isquery = type == IGMPV3_MODE_IS_INCLUDE ||
type == IGMPV3_MODE_IS_EXCLUDE;
truncate = type == IGMPV3_MODE_IS_EXCLUDE ||
@@ -457,7 +481,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
igmpv3_sendpack(skb);
- skb = igmpv3_newpack(dev, dev->mtu);
+ skb = igmpv3_newpack(dev, mtu);
}
}
first = 1;
@@ -484,12 +508,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
pgr->grec_nsrcs = htons(scount);
if (skb)
igmpv3_sendpack(skb);
- skb = igmpv3_newpack(dev, dev->mtu);
+ skb = igmpv3_newpack(dev, mtu);
first = 1;
scount = 0;
}
if (first) {
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
first = 0;
}
if (!skb)
@@ -523,7 +547,7 @@ empty_source:
igmpv3_sendpack(skb);
skb = NULL; /* add_grhead will get a new one */
}
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
}
}
if (pgr)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 682257242971..7e01368f51ed 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -395,8 +395,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
dev->needed_headroom = t_hlen + hlen;
mtu -= (dev->hard_header_len + t_hlen);
- if (mtu < 68)
- mtu = 68;
+ if (mtu < IPV4_MIN_MTU)
+ mtu = IPV4_MIN_MTU;
return mtu;
}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 2ec944318859..b127807c0bbf 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -483,11 +483,16 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
u8 tos;
int err;
struct ip_options_data opt_copy;
+ int hdrincl;
err = -EMSGSIZE;
if (len > 0xFFFF)
goto out;
+ /* hdrincl should be READ_ONCE(inet->hdrincl)
+ * but READ_ONCE() doesn't work with bit fields
+ */
+ hdrincl = inet->hdrincl;
/*
* Check the flags.
*/
@@ -560,7 +565,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
/* Linux does not mangle headers on raw sockets,
* so that IP options + IP_HDRINCL is non-sense.
*/
- if (inet->hdrincl)
+ if (hdrincl)
goto done;
if (ipc.opt->opt.srr) {
if (!daddr)
@@ -582,12 +587,12 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
- inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
- (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
+ (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0);
- if (!inet->hdrincl) {
+ if (!hdrincl) {
err = raw_probe_proto_opt(&fl4, msg);
if (err)
goto done;
@@ -609,7 +614,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
goto do_confirm;
back_from_confirm:
- if (inet->hdrincl)
+ if (hdrincl)
err = raw_send_hdrinc(sk, &fl4, msg->msg_iov, len,
&rt, msg->msg_flags);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d3d62be2376b..488bd86e2f71 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -810,7 +810,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
tcp_time_stamp,
req->ts_recent,
0,
- tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
+ tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr,
AF_INET),
inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
ip_hdr(skb)->tos);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 5aedf76fe287..9cc16fa524a6 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1670,16 +1670,16 @@ static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel)
}
static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc,
- int type, struct mld2_grec **ppgr)
+ int type, struct mld2_grec **ppgr, unsigned int mtu)
{
- struct net_device *dev = pmc->idev->dev;
struct mld2_report *pmr;
struct mld2_grec *pgr;
- if (!skb)
- skb = mld_newpack(pmc->idev, dev->mtu);
- if (!skb)
- return NULL;
+ if (!skb) {
+ skb = mld_newpack(pmc->idev, mtu);
+ if (!skb)
+ return NULL;
+ }
pgr = (struct mld2_grec *)skb_put(skb, sizeof(struct mld2_grec));
pgr->grec_type = type;
pgr->grec_auxwords = 0;
@@ -1702,10 +1702,15 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
struct mld2_grec *pgr = NULL;
struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list;
int scount, stotal, first, isquery, truncate;
+ unsigned int mtu;
if (pmc->mca_flags & MAF_NOREPORT)
return skb;
+ mtu = READ_ONCE(dev->mtu);
+ if (mtu < IPV6_MIN_MTU)
+ return skb;
+
isquery = type == MLD2_MODE_IS_INCLUDE ||
type == MLD2_MODE_IS_EXCLUDE;
truncate = type == MLD2_MODE_IS_EXCLUDE ||
@@ -1726,7 +1731,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(idev, dev->mtu);
+ skb = mld_newpack(idev, mtu);
}
}
first = 1;
@@ -1753,12 +1758,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
pgr->grec_nsrcs = htons(scount);
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(idev, dev->mtu);
+ skb = mld_newpack(idev, mtu);
first = 1;
scount = 0;
}
if (first) {
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
first = 0;
}
if (!skb)
@@ -1792,7 +1797,7 @@ empty_source:
mld_sendpack(skb);
skb = NULL; /* add_grhead will get a new one */
}
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
}
}
if (pgr)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b8e05f16659c..4dfac3865600 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1001,7 +1001,7 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
tcp_rsk(req)->rcv_nxt, req->rcv_wnd,
tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
- tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
+ tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr),
0, 0);
}
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 2d80cbde47ba..19ec93dff753 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -270,6 +270,9 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
struct sock *sk = skb->sk;
int ret = -ENOMEM;
+ if (!net_eq(dev_net(dev), sock_net(sk)))
+ return 0;
+
dev_hold(dev);
if (is_vmalloc_addr(skb->head))
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 8e019692bb42..4477a5443f65 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4166,7 +4166,7 @@ static int sctp_init_sock(struct sock *sk)
SCTP_DBG_OBJCNT_INC(sock);
local_bh_disable();
- percpu_counter_inc(&sctp_sockets_allocated);
+ sk_sockets_allocated_inc(sk);
sock_prot_inuse_add(net, sk->sk_prot, 1);
/* Nothing can fail after this block, otherwise
@@ -4210,7 +4210,7 @@ static void sctp_destroy_sock(struct sock *sk)
}
sctp_endpoint_free(sp->ep);
local_bh_disable();
- percpu_counter_dec(&sctp_sockets_allocated);
+ sk_sockets_allocated_dec(sk);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
local_bh_enable();
}
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index 857741431fc6..f7be2556eb93 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -589,15 +589,14 @@ static int snd_rawmidi_info_user(struct snd_rawmidi_substream *substream,
return 0;
}
-int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info)
+static int __snd_rawmidi_info_select(struct snd_card *card,
+ struct snd_rawmidi_info *info)
{
struct snd_rawmidi *rmidi;
struct snd_rawmidi_str *pstr;
struct snd_rawmidi_substream *substream;
- mutex_lock(®ister_mutex);
rmidi = snd_rawmidi_search(card, info->device);
- mutex_unlock(®ister_mutex);
if (!rmidi)
return -ENXIO;
if (info->stream < 0 || info->stream > 1)
@@ -613,6 +612,16 @@ int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info
}
return -ENXIO;
}
+
+int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info)
+{
+ int ret;
+
+ mutex_lock(®ister_mutex);
+ ret = __snd_rawmidi_info_select(card, info);
+ mutex_unlock(®ister_mutex);
+ return ret;
+}
EXPORT_SYMBOL(snd_rawmidi_info_select);
static int snd_rawmidi_info_select_user(struct snd_card *card,
diff --git a/sound/soc/codecs/twl4030.c b/sound/soc/codecs/twl4030.c
index b6b0cb399599..d048cda405e7 100644
--- a/sound/soc/codecs/twl4030.c
+++ b/sound/soc/codecs/twl4030.c
@@ -232,7 +232,7 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec)
struct twl4030_codec_data *pdata = dev_get_platdata(codec->dev);
struct device_node *twl4030_codec_node = NULL;
- twl4030_codec_node = of_find_node_by_name(codec->dev->parent->of_node,
+ twl4030_codec_node = of_get_child_by_name(codec->dev->parent->of_node,
"codec");
if (!pdata && twl4030_codec_node) {
@@ -241,9 +241,11 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec)
GFP_KERNEL);
if (!pdata) {
dev_err(codec->dev, "Can not allocate memory\n");
+ of_node_put(twl4030_codec_node);
return NULL;
}
twl4030_setup_pdata_of(pdata, twl4030_codec_node);
+ of_node_put(twl4030_codec_node);
}
return pdata;
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 92ad24ef1c5b..91c98bbc04fa 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -2094,20 +2094,25 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid,
kctl->private_value = (unsigned long)namelist;
kctl->private_free = usb_mixer_selector_elem_free;
- nameid = uac_selector_unit_iSelector(desc);
+ /* check the static mapping table at first */
len = check_mapped_name(map, kctl->id.name, sizeof(kctl->id.name));
- if (len)
- ;
- else if (nameid)
- len = snd_usb_copy_string_desc(state, nameid, kctl->id.name,
- sizeof(kctl->id.name));
- else
- len = get_term_name(state, &state->oterm,
- kctl->id.name, sizeof(kctl->id.name), 0);
-
if (!len) {
- strlcpy(kctl->id.name, "USB", sizeof(kctl->id.name));
+ /* no mapping ? */
+ /* if iSelector is given, use it */
+ nameid = uac_selector_unit_iSelector(desc);
+ if (nameid)
+ len = snd_usb_copy_string_desc(state, nameid,
+ kctl->id.name,
+ sizeof(kctl->id.name));
+ /* ... or pick up the terminal name at next */
+ if (!len)
+ len = get_term_name(state, &state->oterm,
+ kctl->id.name, sizeof(kctl->id.name), 0);
+ /* ... or use the fixed string "USB" as the last resort */
+ if (!len)
+ strlcpy(kctl->id.name, "USB", sizeof(kctl->id.name));
+ /* and add the proper suffix */
if (desc->bDescriptorSubtype == UAC2_CLOCK_SELECTOR)
append_ctl_name(kctl, " Clock Source");
else if ((state->oterm.type & 0xff00) == 0x0100)
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] [PATCH v2 23/27] stating: ccree: fix allocation of void sized buf
by Gilad Ben-Yossef
We were allocating buffers using sizeof(*struct->field) where field was
type void. Fix it by having a local variable with the real type.
Cc: stable(a)vger.kernel.org
Signed-off-by: Gilad Ben-Yossef <gilad(a)benyossef.com>
---
drivers/staging/ccree/ssi_ivgen.c | 9 ++++-----
drivers/staging/ccree/ssi_sram_mgr.c | 9 ++++++---
2 files changed, 10 insertions(+), 8 deletions(-)
diff --git a/drivers/staging/ccree/ssi_ivgen.c b/drivers/staging/ccree/ssi_ivgen.c
index 94a0502..9d8d307 100644
--- a/drivers/staging/ccree/ssi_ivgen.c
+++ b/drivers/staging/ccree/ssi_ivgen.c
@@ -175,13 +175,10 @@ int cc_ivgen_init(struct cc_drvdata *drvdata)
int rc;
/* Allocate "this" context */
- drvdata->ivgen_handle = kzalloc(sizeof(*drvdata->ivgen_handle),
- GFP_KERNEL);
- if (!drvdata->ivgen_handle)
+ ivgen_ctx = kzalloc(sizeof(*ivgen_ctx), GFP_KERNEL);
+ if (!ivgen_ctx)
return -ENOMEM;
- ivgen_ctx = drvdata->ivgen_handle;
-
/* Allocate pool's header for initial enc. key/IV */
ivgen_ctx->pool_meta = dma_alloc_coherent(device, CC_IVPOOL_META_SIZE,
&ivgen_ctx->pool_meta_dma,
@@ -200,6 +197,8 @@ int cc_ivgen_init(struct cc_drvdata *drvdata)
goto out;
}
+ drvdata->ivgen_handle = ivgen_ctx;
+
return cc_init_iv_sram(drvdata);
out:
diff --git a/drivers/staging/ccree/ssi_sram_mgr.c b/drivers/staging/ccree/ssi_sram_mgr.c
index e178385..3a93299 100644
--- a/drivers/staging/ccree/ssi_sram_mgr.c
+++ b/drivers/staging/ccree/ssi_sram_mgr.c
@@ -32,13 +32,16 @@ void cc_sram_mgr_fini(struct cc_drvdata *drvdata)
*/
int cc_sram_mgr_init(struct cc_drvdata *drvdata)
{
+ struct cc_sram_ctx *ctx;
+
/* Allocate "this" context */
- drvdata->sram_mgr_handle = kzalloc(sizeof(*drvdata->sram_mgr_handle),
- GFP_KERNEL);
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
- if (!drvdata->sram_mgr_handle)
+ if (!ctx)
return -ENOMEM;
+ drvdata->sram_mgr_handle = ctx;
+
return 0;
}
--
2.7.4
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] [PATCH v2 14/27] staging: ccree: handle end of sg list gracefully
by Gilad Ben-Yossef
If we are asked for number of entries of an offset bigger than the
sg list we should not crash.
Cc: stable(a)vger.kernel.org
Signed-off-by: Gilad Ben-Yossef <gilad(a)benyossef.com>
---
drivers/staging/ccree/ssi_buffer_mgr.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/staging/ccree/ssi_buffer_mgr.c b/drivers/staging/ccree/ssi_buffer_mgr.c
index 13cb062..9e3f557 100644
--- a/drivers/staging/ccree/ssi_buffer_mgr.c
+++ b/drivers/staging/ccree/ssi_buffer_mgr.c
@@ -94,7 +94,7 @@ static unsigned int cc_get_sgl_nents(struct device *dev,
{
unsigned int nents = 0;
- while (nbytes) {
+ while (nbytes && sg_list) {
if (sg_list->length) {
nents++;
/* get the number of bytes in the last entry */
--
2.7.4
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] [PATCH v2 13/27] staging: ccree: check DMA pool buf !NULL before free
by Gilad Ben-Yossef
If we ran out of DMA pool buffers, we get into the unmap
code path with a NULL before. Deal with this by checking
the virtual mapping is not NULL.
Cc: stable(a)vger.kernel.org
Signed-off-by: Gilad Ben-Yossef <gilad(a)benyossef.com>
---
drivers/staging/ccree/ssi_buffer_mgr.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/staging/ccree/ssi_buffer_mgr.c b/drivers/staging/ccree/ssi_buffer_mgr.c
index 5e3cff3..13cb062 100644
--- a/drivers/staging/ccree/ssi_buffer_mgr.c
+++ b/drivers/staging/ccree/ssi_buffer_mgr.c
@@ -465,7 +465,8 @@ void cc_unmap_blkcipher_request(struct device *dev, void *ctx,
DMA_TO_DEVICE);
}
/* Release pool */
- if (req_ctx->dma_buf_type == CC_DMA_BUF_MLLI) {
+ if (req_ctx->dma_buf_type == CC_DMA_BUF_MLLI &&
+ req_ctx->mlli_params.mlli_virt_addr) {
dma_pool_free(req_ctx->mlli_params.curr_pool,
req_ctx->mlli_params.mlli_virt_addr,
req_ctx->mlli_params.mlli_dma_addr);
--
2.7.4
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] [PATCH v2 11/27] stating: ccree: revert "staging: ccree: fix leak of import() after init()"
by Gilad Ben-Yossef
This reverts commit c5f39d07860c ("staging: ccree: fix leak of import()
after init()") and commit aece09024414 ("staging: ccree: Uninitialized
return in ssi_ahash_import()").
This is the wrong solution and ends up relying on uninitialized memory,
although it was not obvious to me at the time.
Cc: stable(a)vger.kernel.org
Signed-off-by: Gilad Ben-Yossef <gilad(a)benyossef.com>
---
drivers/staging/ccree/ssi_hash.c | 11 ++++-------
1 file changed, 4 insertions(+), 7 deletions(-)
diff --git a/drivers/staging/ccree/ssi_hash.c b/drivers/staging/ccree/ssi_hash.c
index ffcd1f0..e05c87d 100644
--- a/drivers/staging/ccree/ssi_hash.c
+++ b/drivers/staging/ccree/ssi_hash.c
@@ -1673,7 +1673,7 @@ static int cc_hash_import(struct ahash_request *req, const void *in)
struct device *dev = drvdata_to_dev(ctx->drvdata);
struct ahash_req_ctx *state = ahash_request_ctx(req);
u32 tmp;
- int rc = 0;
+ int rc;
memcpy(&tmp, in, sizeof(u32));
if (tmp != CC_EXPORT_MAGIC) {
@@ -1682,12 +1682,9 @@ static int cc_hash_import(struct ahash_request *req, const void *in)
}
in += sizeof(u32);
- /* call init() to allocate bufs if the user hasn't */
- if (!state->digest_buff) {
- rc = cc_hash_init(req);
- if (rc)
- goto out;
- }
+ rc = cc_hash_init(req);
+ if (rc)
+ goto out;
dma_sync_single_for_cpu(dev, state->digest_buff_dma_addr,
ctx->inter_digestsize, DMA_BIDIRECTIONAL);
--
2.7.4
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] [PATCH 4.14 000/146] 4.14.11-stable review
by Greg Kroah-Hartman
This is the start of the stable review cycle for the 4.14.11 release.
There are 146 patches in this series, all will be posted as a response
to this one. If anyone has any issues with these being applied, please
let me know.
Responses should be made by Wed Jan 3 14:00:12 UTC 2018.
Anything received after that time might be too late.
The whole patch series can be found in one patch at:
kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.14.11-rc1.gz
or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.14.y
and the diffstat can be found below.
thanks,
greg k-h
-------------
Pseudo-Shortlog of commits:
Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Linux 4.14.11-rc1
Johan Hovold <johan(a)kernel.org>
tty: fix tty_ldisc_receive_buf() documentation
Linus Torvalds <torvalds(a)linux-foundation.org>
n_tty: fix EXTPROC vs ICANON interaction with TIOCINQ (aka FIONREAD)
Thomas Gleixner <tglx(a)linutronix.de>
x86/ldt: Make LDT pgtable free conditional
Thomas Gleixner <tglx(a)linutronix.de>
x86/ldt: Plug memory leak in error path
Andy Lutomirski <luto(a)kernel.org>
x86/espfix/64: Fix espfix double-fault handling on 5-level systems
Linus Torvalds <torvalds(a)linux-foundation.org>
x86-32: Fix kexec with stack canary (CONFIG_CC_STACKPROTECTOR)
Thomas Gleixner <tglx(a)linutronix.de>
x86/mm: Remove preempt_disable/enable() from __native_flush_tlb()
Thomas Gleixner <tglx(a)linutronix.de>
x86/smpboot: Remove stale TLB flush invocations
Thomas Gleixner <tglx(a)linutronix.de>
nohz: Prevent a timer interrupt storm in tick_nohz_stop_sched_tick()
Sushmita Susheelendra <ssusheel(a)codeaurora.org>
staging: android: ion: Fix dma direction for dma_sync_sg_for_cpu/device
Sudeep Holla <sudeep.holla(a)arm.com>
drivers: base: cacheinfo: fix cache type for non-architected system cache
Johan Hovold <johan(a)kernel.org>
phy: tegra: fix device-tree node lookups
Todd Kjos <tkjos(a)android.com>
binder: fix proc->files use-after-free
Thomas Gleixner <tglx(a)linutronix.de>
timers: Reinitialize per cpu bases on hotplug
Thomas Gleixner <tglx(a)linutronix.de>
timers: Invoke timer_start_debug() where it makes sense
Anna-Maria Gleixner <anna-maria(a)linutronix.de>
timers: Use deferrable base independent of base::nohz_active
Daniel Thompson <daniel.thompson(a)linaro.org>
usb: xhci: Add XHCI_TRUST_TX_LENGTH for Renesas uPD720201
Mathias Nyman <mathias.nyman(a)linux.intel.com>
USB: Fix off by one in type-specific length check of BOS SSP capability
Oliver Neukum <oneukum(a)suse.com>
usb: add RESET_RESUME for ELSA MicroLink 56K
Dmitry Fleytman Dmitry Fleytman <dmitry.fleytman(a)gmail.com>
usb: Add device quirk for Logitech HD Pro Webcam C925e
SZ Lin (林上智) <sz.lin(a)moxa.com>
USB: serial: option: adding support for YUGA CLM920-NC5
Daniele Palmas <dnlplm(a)gmail.com>
USB: serial: option: add support for Telit ME910 PID 0x1101
Reinhard Speyerer <rspmn(a)arcor.de>
USB: serial: qcserial: add Sierra Wireless EM7565
Max Schulze <max.schulze(a)posteo.de>
USB: serial: ftdi_sio: add id for Airbus DS P8GR
Johan Hovold <johan(a)kernel.org>
USB: chipidea: msm: fix ulpi-node lookup
Shuah Khan <shuah(a)kernel.org>
usbip: vhci: stop printing kernel pointer addresses in messages
Shuah Khan <shuah(a)kernel.org>
usbip: stub: stop printing kernel pointer addresses in messages
Shuah Khan <shuah(a)kernel.org>
usbip: prevent leaking socket pointer address in messages
Juan Zea <juan.zea(a)qindel.com>
usbip: fix usbip bind writing random string after command in match_busid
Jan Engelhardt <jengelh(a)inai.de>
sparc64: repair calling incorrect hweight function from stubs
Willem de Bruijn <willemb(a)google.com>
skbuff: in skb_copy_ubufs unclone before releasing zerocopy
Willem de Bruijn <willemb(a)google.com>
skbuff: skb_copy_ubufs must release uarg even without user frags
Willem de Bruijn <willemb(a)google.com>
skbuff: orphan frags before zerocopy clone
Saeed Mahameed <saeedm(a)mellanox.com>
Revert "mlx5: move affinity hints assignments to generic code"
Nicolas Dichtel <nicolas.dichtel(a)6wind.com>
ipv6: set all.accept_dad to 0 by default
Phil Sutter <phil(a)nwl.cc>
ipv4: fib: Fix metrics match when deleting a route
Russell King <rmk+kernel(a)armlinux.org.uk>
phylink: ensure AN is enabled
Russell King <rmk+kernel(a)armlinux.org.uk>
phylink: ensure the PHY interface mode is appropriately set
Calvin Owens <calvinowens(a)fb.com>
bnxt_en: Fix sources of spurious netpoll warnings
Jiri Pirko <jiri(a)mellanox.com>
net: sched: fix static key imbalance in case of ingress/clsact_init error
Alexey Kodanev <alexey.kodanev(a)oracle.com>
vxlan: restore dev->mtu setting based on lower device
Kamal Heib <kamalh(a)mellanox.com>
net/mlx5: FPGA, return -EINVAL if size is zero
Eric Dumazet <edumazet(a)google.com>
tcp: refresh tcp_mstamp from timers callbacks
Ido Schimmel <idosch(a)mellanox.com>
ipv6: Honor specified parameters in fibmatch lookup
Zhao Qiang <qiang.zhao(a)nxp.com>
net: phy: marvell: Limit 88m1101 autoneg errata to 88E1145 as well.
Wei Wang <weiwan(a)google.com>
tcp: fix potential underestimation on rcv_rtt
Yuval Mintz <yuvalm(a)mellanox.com>
mlxsw: spectrum: Disable MAC learning for ovs port
Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan(a)gmail.com>
tipc: fix hanging poll() for stream sockets
Xin Long <lucien.xin(a)gmail.com>
sctp: make sure stream nums can match optlen in sctp_setsockopt_reset_streams
Julian Wiedmann <jwi(a)linux.vnet.ibm.com>
s390/qeth: fix error handling in checksum cmd callback
Florian Fainelli <f.fainelli(a)gmail.com>
net: dsa: bcm_sf2: Clear IDDQ_GLOBAL_PWR bit for PHY
Bert Kenward <bkenward(a)solarflare.com>
sfc: pass valid pointers from efx_enqueue_unwind
Eric Garver <e(a)erig.me>
openvswitch: Fix pop_vlan action for double tagged frames
Moni Shoua <monis(a)mellanox.com>
net/mlx5: Fix error flow in CREATE_QP command
Gal Pressman <galp(a)mellanox.com>
net/mlx5e: Prevent possible races in VXLAN control flow
Gal Pressman <galp(a)mellanox.com>
net/mlx5e: Add refcount to VXLAN structure
Gal Pressman <galp(a)mellanox.com>
net/mlx5e: Fix features check of IPv6 traffic
Gal Pressman <galp(a)mellanox.com>
net/mlx5e: Fix possible deadlock of VXLAN lock
Eran Ben Elisha <eranbe(a)mellanox.com>
net/mlx5: Fix rate limit packet pacing naming and struct
Yousuk Seung <ysseung(a)google.com>
tcp: invalidate rate samples during SACK reneging
Willem de Bruijn <willemb(a)google.com>
sock: free skb in skb_complete_tx_timestamp on error
Grygorii Strashko <grygorii.strashko(a)ti.com>
net: phy: micrel: ksz9031: reconfigure autoneg after phy autoneg workaround
Eric W. Biederman <ebiederm(a)xmission.com>
net: Fix double free and memory corruption in get_net_ns_by_id()
Nikolay Aleksandrov <nikolay(a)cumulusnetworks.com>
net: bridge: fix early call to br_stp_change_bridge_id and plug newlink leaks
Ido Schimmel <idosch(a)mellanox.com>
ipv4: Fix use-after-free when flushing FIB tables
Alexey Kodanev <alexey.kodanev(a)oracle.com>
ip6_gre: fix device features for ioctl setup
Nikita V. Shirokov <tehnerd(a)fb.com>
adding missing rcu_read_unlock in ipxip6_rcv
Tonghao Zhang <xiangxia.m.yue(a)gmail.com>
sctp: Replace use of sockets_allocated with specified macro.
Tobias Jordan <Tobias.Jordan(a)elektrobit.com>
net: mvmdio: disable/unprepare clocks in EPROBE_DEFER case
Mohamed Ghannam <simo.ghannam(a)gmail.com>
net: ipv4: fix for a race condition in raw_sendmsg
Julian Wiedmann <jwi(a)linux.vnet.ibm.com>
s390/qeth: update takeover IPs after configuration change
Julian Wiedmann <jwi(a)linux.vnet.ibm.com>
s390/qeth: lock IP table while applying takeover changes
Julian Wiedmann <jwi(a)linux.vnet.ibm.com>
s390/qeth: don't apply takeover changes to RXIP
Julian Wiedmann <jwi(a)linux.vnet.ibm.com>
s390/qeth: apply takeover changes when mode is toggled
Neal Cardwell <ncardwell(a)google.com>
tcp_bbr: reset long-term bandwidth sampling on loss recovery undo
Neal Cardwell <ncardwell(a)google.com>
tcp_bbr: reset full pipe detection on loss recovery undo
Brian King <brking(a)linux.vnet.ibm.com>
tg3: Fix rx hang on MTU change with 5717/5719
Christoph Paasch <cpaasch(a)apple.com>
tcp md5sig: Use skb's saddr when replying to an incoming segment
Neal Cardwell <ncardwell(a)google.com>
tcp_bbr: record "full bw reached" decision in new full_bw_reached bit
Avinash Repaka <avinash.repaka(a)oracle.com>
RDS: Check cmsg_len before dereferencing CMSG_DATA
Michael S. Tsirkin <mst(a)redhat.com>
ptr_ring: add barriers
Shaohua Li <shli(a)fb.com>
net: reevalulate autoflowlabel setting after sysctl setting
Sebastian Sjoholm <ssjoholm(a)mac.com>
net: qmi_wwan: add Sierra EM7565 1199:9091
Kevin Cernekee <cernekee(a)chromium.org>
netlink: Add netns check on taps
Kevin Cernekee <cernekee(a)chromium.org>
net: igmp: Use correct source address on IGMPv3 reports
Fugang Duan <fugang.duan(a)nxp.com>
net: fec: unmap the xmit buffer that are not transferred by DMA
Eric Dumazet <edumazet(a)google.com>
ipv6: mcast: better catch silly mtu values
Eric Dumazet <edumazet(a)google.com>
ipv4: igmp: guard against silly MTU values
Linus Torvalds <torvalds(a)linux-foundation.org>
kbuild: add '-fno-stack-check' to kernel build options
Ming Lei <ming.lei(a)redhat.com>
block: don't let passthrough IO go into .make_request_fn()
Jens Axboe <axboe(a)kernel.dk>
block: fix blk_rq_append_bio
Joel Fernandes <joelaf(a)google.com>
cpufreq: schedutil: Use idle_calls counter of the remote CPU
Takashi Iwai <tiwai(a)suse.de>
ALSA: hda - Fix missing COEF init for ALC225/295/299
Hui Wang <hui.wang(a)canonical.com>
ALSA: hda - fix headset mic detection issue on a Dell machine
Hui Wang <hui.wang(a)canonical.com>
ALSA: hda - change the location for one mic on a Lenovo machine
Hui Wang <hui.wang(a)canonical.com>
ALSA: hda - Add MIC_NO_PRESENCE fixup for 2 HP machines
Takashi Iwai <tiwai(a)suse.de>
ALSA: hda: Drop useless WARN_ON()
Moni Shoua <monis(a)mellanox.com>
IB/core: Verify that QP is security enabled in create and destroy
Moni Shoua <monis(a)mellanox.com>
IB/uverbs: Fix command checking as part of ib_uverbs_ex_modify_qp()
Majd Dibbiny <majd(a)mellanox.com>
IB/mlx5: Serialize access to the VMA list
Michael J. Ruhl <michael.j.ruhl(a)intel.com>
IB/hfi: Only read capability registers if the capability exists
Christophe Leroy <christophe.leroy(a)c-s.fr>
gpio: fix "gpio-line-names" property retrieval
Andrew F. Davis <afd(a)ti.com>
ASoC: tlv320aic31xx: Fix GPIO1 register definition
Johan Hovold <johan(a)kernel.org>
ASoC: twl4030: fix child-node lookup
Maciej S. Szmigiero <mail(a)maciej.szmigiero.name>
ASoC: fsl_ssi: AC'97 ops need regmap, clock and cleaning up on failure
Johan Hovold <johan(a)kernel.org>
ASoC: da7218: fix fix child-node lookup
Ben Hutchings <ben.hutchings(a)codethink.co.uk>
ASoC: wm_adsp: Fix validation of firmware and coeff lengths
Srinivas Kandagatla <srinivas.kandagatla(a)linaro.org>
ASoC: codecs: msm8916-wcd: Fix supported formats
Steve Wise <swise(a)opengridcomputing.com>
iw_cxgb4: Only validate the MSN for successful completions
Steven Rostedt (VMware) <rostedt(a)goodmis.org>
ring-buffer: Do no reuse reader page if still in use
Steven Rostedt (VMware) <rostedt(a)goodmis.org>
ring-buffer: Mask out the info bits when returning buffer page length
Thomas Gleixner <tglx(a)linutronix.de>
x86/ldt: Make the LDT mapping RO
Thomas Gleixner <tglx(a)linutronix.de>
x86/mm/dump_pagetables: Allow dumping current pagetables
Thomas Gleixner <tglx(a)linutronix.de>
x86/mm/dump_pagetables: Check user space page table for WX pages
Borislav Petkov <bp(a)suse.de>
x86/mm/dump_pagetables: Add page table directory to the debugfs VFS hierarchy
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/mm/pti: Add Kconfig
Vlastimil Babka <vbabka(a)suse.cz>
x86/dumpstack: Indicate in Oops whether PTI is configured and enabled
Peter Zijlstra <peterz(a)infradead.org>
x86/mm: Clarify the whole ASID/kernel PCID/user PCID naming
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/mm: Use INVPCID for __native_flush_tlb_single()
Peter Zijlstra <peterz(a)infradead.org>
x86/mm: Optimize RESTORE_CR3
Peter Zijlstra <peterz(a)infradead.org>
x86/mm: Use/Fix PCID to optimize user/kernel switches
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/mm: Abstract switching CR3
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/mm: Allow flushing for future ASID switches
Andy Lutomirski <luto(a)kernel.org>
x86/pti: Map the vsyscall page if needed
Andy Lutomirski <luto(a)kernel.org>
x86/pti: Put the LDT in its own PGD if PTI is on
Andy Lutomirski <luto(a)kernel.org>
x86/mm/64: Make a full PGD-entry size hole in the memory map
Hugh Dickins <hughd(a)google.com>
x86/events/intel/ds: Map debug buffers in cpu_entry_area
Thomas Gleixner <tglx(a)linutronix.de>
x86/cpu_entry_area: Add debugstore entries to cpu_entry_area
Andy Lutomirski <luto(a)kernel.org>
x86/mm/pti: Map ESPFIX into user space
Thomas Gleixner <tglx(a)linutronix.de>
x86/mm/pti: Share entry text PMD
Thomas Gleixner <tglx(a)linutronix.de>
x86/entry: Align entry text section to PMD boundary
Andy Lutomirski <luto(a)kernel.org>
x86/mm/pti: Share cpu_entry_area with user space page tables
Thomas Gleixner <tglx(a)linutronix.de>
x86/mm/pti: Force entry through trampoline when PTI active
Andy Lutomirski <luto(a)kernel.org>
x86/mm/pti: Add functions to clone kernel PMDs
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/mm/pti: Populate user PGD
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/mm/pti: Allocate a separate user PGD
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/mm/pti: Allow NX poison to be set in p4d/pgd
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/mm/pti: Add mapping helper functions
Borislav Petkov <bp(a)suse.de>
x86/pti: Add the pti= cmdline option and documentation
Thomas Gleixner <tglx(a)linutronix.de>
x86/mm/pti: Add infrastructure for page table isolation
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/mm/pti: Prepare the x86/entry assembly code for entry/exit CR3 switching
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/mm/pti: Disable global pages if PAGE_TABLE_ISOLATION=y
Thomas Gleixner <tglx(a)linutronix.de>
x86/cpufeatures: Add X86_BUG_CPU_INSECURE
Jing Xia <jing.xia(a)spreadtrum.com>
tracing: Fix crash when it fails to alloc ring buffer
Steven Rostedt (VMware) <rostedt(a)goodmis.org>
tracing: Fix possible double free on failure of allocating trace buffer
Steven Rostedt (VMware) <rostedt(a)goodmis.org>
tracing: Remove extra zeroing out of the ring buffer page
-------------
Diffstat:
Documentation/admin-guide/kernel-parameters.txt | 8 +
Documentation/x86/x86_64/mm.txt | 5 +-
Makefile | 7 +-
arch/sparc/lib/hweight.S | 4 +-
arch/x86/boot/compressed/pagetable.c | 3 +
arch/x86/entry/calling.h | 145 ++++++++
arch/x86/entry/entry_64.S | 48 ++-
arch/x86/entry/entry_64_compat.S | 24 +-
arch/x86/entry/vsyscall/vsyscall_64.c | 6 +-
arch/x86/events/intel/ds.c | 130 ++++---
arch/x86/events/perf_event.h | 23 +-
arch/x86/include/asm/cpu_entry_area.h | 13 +
arch/x86/include/asm/cpufeatures.h | 4 +-
arch/x86/include/asm/desc.h | 2 +
arch/x86/include/asm/disabled-features.h | 8 +-
arch/x86/include/asm/intel_ds.h | 36 ++
arch/x86/include/asm/mmu_context.h | 59 +++-
arch/x86/include/asm/pgalloc.h | 11 +
arch/x86/include/asm/pgtable.h | 30 +-
arch/x86/include/asm/pgtable_64.h | 92 +++++
arch/x86/include/asm/pgtable_64_types.h | 8 +-
arch/x86/include/asm/processor-flags.h | 5 +
arch/x86/include/asm/processor.h | 23 +-
arch/x86/include/asm/pti.h | 14 +
arch/x86/include/asm/tlbflush.h | 208 +++++++++--
arch/x86/include/asm/vsyscall.h | 1 +
arch/x86/include/uapi/asm/processor-flags.h | 7 +-
arch/x86/kernel/asm-offsets.c | 4 +
arch/x86/kernel/cpu/common.c | 9 +-
arch/x86/kernel/dumpstack.c | 6 +-
arch/x86/kernel/head_64.S | 30 +-
arch/x86/kernel/ldt.c | 151 +++++++-
arch/x86/kernel/machine_kexec_32.c | 4 +-
arch/x86/kernel/smpboot.c | 9 -
arch/x86/kernel/tls.c | 11 +-
arch/x86/kernel/traps.c | 2 +-
arch/x86/kernel/vmlinux.lds.S | 8 +
arch/x86/mm/Makefile | 7 +-
arch/x86/mm/cpu_entry_area.c | 27 ++
arch/x86/mm/debug_pagetables.c | 80 ++++-
arch/x86/mm/dump_pagetables.c | 43 ++-
arch/x86/mm/init.c | 80 +++--
arch/x86/mm/pgtable.c | 5 +-
arch/x86/mm/pti.c | 387 +++++++++++++++++++++
arch/x86/mm/tlb.c | 58 ++-
arch/x86/platform/efi/efi_64.c | 5 +-
block/blk-map.c | 38 +-
block/bounce.c | 6 +-
drivers/android/binder.c | 44 ++-
drivers/base/cacheinfo.c | 13 +
drivers/gpio/gpiolib-acpi.c | 2 +-
drivers/gpio/gpiolib-devprop.c | 17 +-
drivers/gpio/gpiolib-of.c | 3 +-
drivers/gpio/gpiolib.h | 3 +-
drivers/infiniband/core/security.c | 3 +
drivers/infiniband/core/uverbs_cmd.c | 4 +-
drivers/infiniband/core/verbs.c | 3 +-
drivers/infiniband/hw/cxgb4/cq.c | 6 +-
drivers/infiniband/hw/hfi1/hfi.h | 1 -
drivers/infiniband/hw/hfi1/pcie.c | 30 +-
drivers/infiniband/hw/mlx5/main.c | 8 +
drivers/infiniband/hw/mlx5/mlx5_ib.h | 4 +
drivers/net/dsa/bcm_sf2.c | 2 +-
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 +-
drivers/net/ethernet/broadcom/tg3.c | 4 +-
drivers/net/ethernet/freescale/fec_main.c | 6 +
drivers/net/ethernet/marvell/mvmdio.c | 3 +-
drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 +-
drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 +
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 48 +--
drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c | 6 +
drivers/net/ethernet/mellanox/mlx5/core/main.c | 75 +++-
drivers/net/ethernet/mellanox/mlx5/core/qp.c | 4 +-
drivers/net/ethernet/mellanox/mlx5/core/rl.c | 22 +-
drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 64 ++--
drivers/net/ethernet/mellanox/mlx5/core/vxlan.h | 1 +
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 18 +
drivers/net/ethernet/sfc/tx.c | 5 +-
drivers/net/phy/marvell.c | 2 +-
drivers/net/phy/micrel.c | 1 +
drivers/net/phy/phylink.c | 2 +
drivers/net/usb/qmi_wwan.c | 1 +
drivers/net/vxlan.c | 5 +
drivers/phy/tegra/xusb.c | 58 +--
drivers/s390/net/qeth_core.h | 6 +-
drivers/s390/net/qeth_core_main.c | 15 +-
drivers/s390/net/qeth_l3.h | 2 +-
drivers/s390/net/qeth_l3_main.c | 36 +-
drivers/s390/net/qeth_l3_sys.c | 75 ++--
drivers/scsi/osd/osd_initiator.c | 4 +-
drivers/staging/android/ion/ion.c | 4 +-
drivers/target/target_core_pscsi.c | 4 +-
drivers/tty/n_tty.c | 4 +-
drivers/tty/tty_buffer.c | 2 +-
drivers/usb/chipidea/ci_hdrc_msm.c | 2 +-
drivers/usb/core/config.c | 2 +-
drivers/usb/core/quirks.c | 6 +-
drivers/usb/host/xhci-pci.c | 3 +
drivers/usb/serial/ftdi_sio.c | 1 +
drivers/usb/serial/ftdi_sio_ids.h | 6 +
drivers/usb/serial/option.c | 17 +
drivers/usb/serial/qcserial.c | 3 +
drivers/usb/usbip/stub_dev.c | 3 +-
drivers/usb/usbip/stub_main.c | 5 +-
drivers/usb/usbip/stub_rx.c | 7 +-
drivers/usb/usbip/stub_tx.c | 6 +-
drivers/usb/usbip/usbip_common.c | 16 +-
drivers/usb/usbip/vhci_hcd.c | 12 +-
drivers/usb/usbip/vhci_rx.c | 23 +-
drivers/usb/usbip/vhci_tx.c | 3 +-
include/linux/blkdev.h | 23 +-
include/linux/cpuhotplug.h | 2 +-
include/linux/ipv6.h | 3 +-
include/linux/mlx5/driver.h | 1 +
include/linux/mlx5/mlx5_ifc.h | 8 +-
include/linux/pti.h | 11 +
include/linux/ptr_ring.h | 9 +
include/linux/tcp.h | 3 +-
include/linux/tick.h | 1 +
include/linux/timer.h | 4 +-
include/net/ip.h | 1 +
include/net/tcp.h | 2 +-
init/main.c | 3 +
kernel/cpu.c | 4 +-
kernel/sched/cpufreq_schedutil.c | 2 +-
kernel/time/tick-sched.c | 32 +-
kernel/time/timer.c | 35 +-
kernel/trace/ring_buffer.c | 12 +-
kernel/trace/trace.c | 13 +-
net/bridge/br_netlink.c | 11 +-
net/core/net_namespace.c | 2 +-
net/core/skbuff.c | 17 +-
net/ipv4/devinet.c | 2 +-
net/ipv4/fib_frontend.c | 9 +-
net/ipv4/fib_semantics.c | 8 +-
net/ipv4/igmp.c | 44 ++-
net/ipv4/ip_tunnel.c | 4 +-
net/ipv4/raw.c | 15 +-
net/ipv4/tcp.c | 1 +
net/ipv4/tcp_bbr.c | 12 +-
net/ipv4/tcp_input.c | 20 +-
net/ipv4/tcp_ipv4.c | 2 +-
net/ipv4/tcp_rate.c | 10 +-
net/ipv4/tcp_timer.c | 2 +
net/ipv6/addrconf.c | 2 +-
net/ipv6/af_inet6.c | 1 -
net/ipv6/ip6_gre.c | 57 +--
net/ipv6/ip6_output.c | 12 +-
net/ipv6/ip6_tunnel.c | 2 +-
net/ipv6/ipv6_sockglue.c | 1 +
net/ipv6/mcast.c | 25 +-
net/ipv6/route.c | 19 +-
net/ipv6/tcp_ipv6.c | 2 +-
net/netlink/af_netlink.c | 3 +
net/openvswitch/flow.c | 15 +-
net/rds/send.c | 3 +
net/sched/sch_ingress.c | 9 +-
net/sctp/socket.c | 10 +-
net/tipc/socket.c | 2 +-
security/Kconfig | 10 +
sound/hda/hdac_i915.c | 2 +-
sound/pci/hda/patch_conexant.c | 29 ++
sound/pci/hda/patch_realtek.c | 14 +-
sound/soc/codecs/da7218.c | 2 +-
sound/soc/codecs/msm8916-wcd-analog.c | 2 +-
sound/soc/codecs/msm8916-wcd-digital.c | 4 +-
sound/soc/codecs/tlv320aic31xx.h | 2 +-
sound/soc/codecs/twl4030.c | 4 +-
sound/soc/codecs/wm_adsp.c | 12 +-
sound/soc/fsl/fsl_ssi.c | 18 +-
tools/testing/selftests/x86/ldt_gdt.c | 3 +-
tools/usb/usbip/src/utils.c | 9 +-
172 files changed, 2568 insertions(+), 672 deletions(-)
7 years, 8 months
- 4
- 146
[Linux-stable-mirror] v4.9.74 build: 0 failures 0 warnings (v4.9.74)
by Build bot for Mark Brown
Tree/Branch: v4.9.74
Git describe: v4.9.74
Commit: 07bcb2489b Linux 4.9.74
Build Time: 100 min 59 sec
Passed: 10 / 10 (100.00 %)
Failed: 0 / 10 ( 0.00 %)
Errors: 0
Warnings: 0
Section Mismatches: 0
-------------------------------------------------------------------------------
defconfigs with issues (other than build errors):
-------------------------------------------------------------------------------
===============================================================================
Detailed per-defconfig build reports below:
-------------------------------------------------------------------------------
Passed with no errors, warnings or mismatches:
arm64-allnoconfig
arm64-allmodconfig
arm-multi_v5_defconfig
arm-multi_v7_defconfig
x86_64-defconfig
arm-allmodconfig
arm-allnoconfig
x86_64-allnoconfig
arm-multi_v4t_defconfig
arm64-defconfig
close failed in file object destructor:
sys.excepthook is missing
lost sys.stderr
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] v4.4.109 build: 0 failures 0 warnings (v4.4.109)
by Build bot for Mark Brown
Tree/Branch: v4.4.109
Git describe: v4.4.109
Commit: e68d6189c7 Linux 4.4.109
Build Time: 87 min 3 sec
Passed: 9 / 9 (100.00 %)
Failed: 0 / 9 ( 0.00 %)
Errors: 0
Warnings: 0
Section Mismatches: 0
-------------------------------------------------------------------------------
defconfigs with issues (other than build errors):
-------------------------------------------------------------------------------
===============================================================================
Detailed per-defconfig build reports below:
-------------------------------------------------------------------------------
Passed with no errors, warnings or mismatches:
arm64-allnoconfig
arm64-allmodconfig
arm-multi_v5_defconfig
arm-multi_v7_defconfig
x86_64-defconfig
arm-allmodconfig
arm-allnoconfig
x86_64-allnoconfig
arm64-defconfig
close failed in file object destructor:
sys.excepthook is missing
lost sys.stderr
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] [PATCH] rpmsg: virtio_rpmsg_bus: fix rpmsg_probe() for virtio-mmio transport
by Anup Patel
When virtio-rpmsg device is provided via virtio-mmio transport, the
dma_alloc_coherent() (called by rpmsg_probe()) fails on ARM/ARM64
systems because "vdev->dev.parent->parent" device is used as parameter
to dma_alloc_coherent().
The "vdev->dev.parent->parent" device represents underlying remoteproc
platform device when virtio-rpmsg device is provided via virtio-remoteproc
transport. When virtio-rpmsg device is provided via virtio-mmio transport,
the "vdev->dev.parent->parent" device represents the parent device of
virtio-mmio platform device and dma_alloc_coherent() fails for this device
because generally there is no corresponding platform device and dma_ops
are not setup for "vdev->dev.parent->parent".
This patch fixes dma_alloc_coherent() usage in rpmsg_probe() by trying
dma_alloc_coherent() with "vdev->dev.parent" device when it fails with
"vdev->dev.parent->parent" device.
Fixes: b5ab5e24e960 ("remoteproc: maintain a generic child device for
each rproc")
Signed-off-by: Anup Patel <anup(a)brainfault.org>
Cc: stable(a)vger.kernel.org
---
drivers/rpmsg/virtio_rpmsg_bus.c | 18 +++++++++++++-----
1 file changed, 13 insertions(+), 5 deletions(-)
diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c
index 82b8300..7f8710a 100644
--- a/drivers/rpmsg/virtio_rpmsg_bus.c
+++ b/drivers/rpmsg/virtio_rpmsg_bus.c
@@ -64,6 +64,7 @@
struct virtproc_info {
struct virtio_device *vdev;
struct virtqueue *rvq, *svq;
+ struct device *bufs_dev;
void *rbufs, *sbufs;
unsigned int num_bufs;
unsigned int buf_size;
@@ -924,9 +925,16 @@ static int rpmsg_probe(struct virtio_device *vdev)
total_buf_space, &vrp->bufs_dma,
GFP_KERNEL);
if (!bufs_va) {
- err = -ENOMEM;
- goto vqs_del;
- }
+ bufs_va = dma_alloc_coherent(vdev->dev.parent,
+ total_buf_space, &vrp->bufs_dma,
+ GFP_KERNEL);
+ if (!bufs_va) {
+ err = -ENOMEM;
+ goto vqs_del;
+ } else
+ vrp->bufs_dev = vdev->dev.parent;
+ } else
+ vrp->bufs_dev = vdev->dev.parent->parent;
dev_dbg(&vdev->dev, "buffers: va %p, dma %pad\n",
bufs_va, &vrp->bufs_dma);
@@ -988,7 +996,7 @@ static int rpmsg_probe(struct virtio_device *vdev)
return 0;
free_coherent:
- dma_free_coherent(vdev->dev.parent->parent, total_buf_space,
+ dma_free_coherent(vrp->bufs_dev, total_buf_space,
bufs_va, vrp->bufs_dma);
vqs_del:
vdev->config->del_vqs(vrp->vdev);
@@ -1023,7 +1031,7 @@ static void rpmsg_remove(struct virtio_device *vdev)
vdev->config->del_vqs(vrp->vdev);
- dma_free_coherent(vdev->dev.parent->parent, total_buf_space,
+ dma_free_coherent(vrp->bufs_dev, total_buf_space,
vrp->rbufs, vrp->bufs_dma);
kfree(vrp);
--
2.7.4
7 years, 8 months
- 1
- 1
[Linux-stable-mirror] v4.14.11 build: 0 failures 0 warnings (v4.14.11)
by Build bot for Mark Brown
Tree/Branch: v4.14.11
Git describe: v4.14.11
Commit: 0d59679df5 Linux 4.14.11
Build Time: 118 min 58 sec
Passed: 10 / 10 (100.00 %)
Failed: 0 / 10 ( 0.00 %)
Errors: 0
Warnings: 0
Section Mismatches: 0
-------------------------------------------------------------------------------
defconfigs with issues (other than build errors):
-------------------------------------------------------------------------------
===============================================================================
Detailed per-defconfig build reports below:
-------------------------------------------------------------------------------
Passed with no errors, warnings or mismatches:
arm64-allnoconfig
arm64-allmodconfig
arm-multi_v5_defconfig
arm-multi_v7_defconfig
x86_64-defconfig
arm-allmodconfig
arm-allnoconfig
x86_64-allnoconfig
arm-multi_v4t_defconfig
arm64-defconfig
close failed in file object destructor:
sys.excepthook is missing
lost sys.stderr
7 years, 8 months
- 1
- 0
Re: [Linux-stable-mirror] stable/linux-4.1.y build: 169 builds: 2 failed, 167 passed, 13 errors, 253 warnings (v4.1.48)
by Arnd Bergmann
On Wed, Dec 20, 2017 at 11:49 PM, kernelci.org bot <bot(a)kernelci.org> wrote:
> Errors summary:
> 1 arch/mips/sgi-ip22/Platform:29: *** gcc doesn't support needed option -mr10k-cache-barrier=store. Stop.
This needs a backport of
c018595d83a3 ("MIPS: ip22: Fix ip28 build for modern gcc")
> 6 include/linux/irqdesc.h:94:33: error: 'NR_IRQS' undeclared here (not in a function)
> 1 arch/mips/jz4740/gpio.c:46:32: error: initializer element is not constant
> 1 arch/mips/jz4740/gpio.c:45:32: error: initializer element is not constant
> 1 arch/mips/jz4740/gpio.c:44:32: error: initializer element is not constant
> 1 arch/mips/jz4740/gpio.c:43:32: error: initializer element is not constant
> 1 arch/mips/jz4740/gpio.c:426:14: error: implicit declaration of function 'JZ4740_IRQ_INTC_GPIO' [-Werror=implicit-function-declaration]
> 1 arch/mips/jz4740/gpio.c:268:9: error: implicit declaration of function 'JZ4740_IRQ_GPIO' [-Werror=implicit-function-declaration]
Not sure, may have been fixed by
832f5dacfa0b ("MIPS: Remove all the uses of custom gpio.h")
which doesn't look appropriate for stable backports
> Warnings summary:
> 81 include/linux/blkdev.h:624:26: warning: switch condition has boolean value [-Wswitch-bool]
> 23 drivers/mtd/mtd_blkdevs.c:100:2: warning: switch condition has boolean value [-Wswitch-bool]
10fbd36e362a ("blk: rq_data_dir() should not return a boolean")
> 35 mm/page_alloc.c:5435:34: warning: array subscript is below array bounds [-Warray-bounds]
I think this was fixed by
90cae1fe1c35 ("mm/init: fix zone boundary creation")
which was intended to address another problem but got backported to 4.4
> 20 arch/arm/include/asm/cmpxchg.h:122:3: warning: value computed is not used [-Wunused-value]
> 5 arch/arm/include/asm/cmpxchg.h:205:3: warning: value computed is not used [-Wunused-value]
d975440bf80c ("asm-generic: cmpxchg: avoid warnings from macro-ized
cmpxchg() implementations")
> 10 drivers/rtc/rtc-pcf8563.c:444:5: warning: 'alm_pending' may be used uninitialized in this function [-Wmaybe-uninitialized]
cd1420d3a909 ("rtc: pfc8563: fix uninitialized variable warning")
> 6 crypto/wp512.c:987:1: warning: the frame size of 1112 bytes is larger than 1024 bytes [-Wframe-larger-than=]
> 1 crypto/wp512.c:987:1: warning: the frame size of 1344 bytes is larger than 1024 bytes [-Wframe-larger-than=]
> 1 crypto/wp512.c:987:1: warning: the frame size of 1280 bytes is larger than 1024 bytes [-Wframe-larger-than=]
> 1 crypto/wp512.c:987:1: warning: the frame size of 1152 bytes is larger than 1024 bytes [-Wframe-larger-than=]
> 1 crypto/wp512.c:987:1: warning: the frame size of 1144 bytes is larger than 1024 bytes [-Wframe-larger-than=]
> 1 crypto/wp512.c:987:1: warning: the frame size of 1120 bytes is larger than 1024 bytes [-Wframe-larger-than=]
> 1 crypto/serpent_generic.c:436:1: warning: the frame size of 1472 bytes is larger than 1024 bytes [-Wframe-larger-than=]
> 1 crypto/serpent_generic.c:436:1: warning: the frame size of 1456 bytes is larger than 1024 bytes [-Wframe-larger-than=]
7d6e9105026 ("crypto: improve gcc optimization flags for serpent and wp512")
> 4 fs/nfsd/nfs4state.c:3962:3: warning: 'old_deny_bmap' may be used uninitialized in this function [-Wmaybe-uninitialized]
6ac75368e1a6 ("nfsd: work around a gcc-5.1 warning")
> 3 drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c:1478:8: warning: 'skb' may be used uninitialized in this function [-Wmaybe-uninitialized]
22f44150aad7 ("brcmfmac: avoid gcc-5.1 warning")
> 2 lib/iommu-common.c:15:24: warning: large integer implicitly truncated to unsigned type [-Woverflow]
447f6a95a9c8 ("lib/iommu-common.c: do not use 0xffffffffffffffffl for
computing align_mask")
> 2 drivers/hid/hid-input.c:1163:67: warning: logical not is only applied to the left hand side of comparison [-Wlogical-not-parentheses]
09a5c34e8d6b ("HID: hid-input: Add parentheses to quell gcc warning")
> 2 drivers/atm/iphase.c:1176:12: warning: this 'if' clause does not guard... [-Wmisleading-indentation]
cbb41b91e68a ("atm: iphase: fix misleading indention")
> 2 arch/x86/include/asm/msr.h:209:23: warning: right shift count >= width of type [-Wshift-count-overflow]
cf991de2f614 ("x86/asm/msr: Make wrmsrl_safe() a function")
47edb65178cb ("x86/asm/msr: Make wrmsrl() a function")
> 1 fs/gfs2/dir.c:978:8: warning: 'leaf_no' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 fs/gfs2/dir.c:759:9: warning: 'leaf_no' may be used uninitialized in this function [-Wmaybe-uninitialized]
d39cb4a59729 ("gfs2: avoid uninitialized variable warning")
> 1 drivers/net/ethernet/ti/cpmac.c:1238:2: warning: #warning FIXME: unhardcode gpio&reset bits [-Wcpp]
d43e6fb4ac4a ("cpmac: remove hopeless #warning")
> 1 drivers/scsi/mvsas/mv_sas.c:736:3: warning: this 'else' clause does not guard... [-Wmisleading-indentation]
7789cd39274c ("mvsas: fix misleading indentation")
> 1 drivers/scsi/bfa/bfa_ioc.c:3673:4: warning: this 'if' clause does not guard... [-Wmisleading-indentation]
> 1 drivers/scsi/bfa/bfa_ioc.c:3665:3: warning: this 'if' clause does not guard... [-Wmisleading-indentation]
b7f4d6343820 ("bfa: Fix indentation")
> 1 arch/mips/ralink/rt305x.c:94:13: warning: 'rt305x_wdt_reset' defined but not used [-Wunused-function]
886f9c69fc68 ("MIPS: ralink: Remove unused rt*_wdt_reset functions")
> 1 arch/mips/ralink/prom.c:65:2: warning: 'argv' is used uninitialized in this function [-Wuninitialized]
> 1 arch/mips/ralink/prom.c:65:2: warning: 'argc' is used uninitialized in this function [-Wuninitialized]
9c48568b3692 ("MIPS: ralink: Cosmetic change to prom_init().")
> 1 arch/mips/dec/int-handler.S:198: Warning: macro instruction expanded into multiple instructions in a branch delay slot
> 1 arch/mips/dec/int-handler.S:149: Warning: macro instruction expanded into multiple instructions in a branch delay slot
3021773c7c3e ("MIPS: DEC: Avoid la pseudo-instruction in delay slots")
> 1 arch/arm/kernel/head-nommu.S:167: Warning: Use of r13 as a source register is deprecated when r15 is the destination register.
970d96f9a81b ("ARM: 8383/1: nommu: avoid deprecated source register on mov")
> 1 .config:871:warning: override: NOHIGHMEM changes choice state
> 1 .config:870:warning: override: SLOB changes choice state
> 1 .config:868:warning: override: KERNEL_XZ changes choice state
> 1 .config:829:warning: override: SLOB changes choice state
> 1 .config:827:warning: override: KERNEL_XZ changes choice state
> 1 .config:794:warning: override: SLOB changes choice state
> 1 .config:771:warning: override: SLOB changes choice state
236dec051078 ("kconfig: tinyconfig: provide whole choice blocks to
avoid warnings")
> 1 drivers/scsi/be2iscsi/be_main.c:3168:18: warning: logical not is only applied to the left hand side of comparison [-Wlogical-not-parentheses]
dd29dae00d39 ("be2iscsi: Fix bogus WARN_ON length check")
> 1 drivers/scsi/aic94xx/aic94xx_sds.c:597:2: warning: 'offs' may be used uninitialized in this function [-Wmaybe-uninitialized]
36dd5acd1965 ("aic94xx: Skip reading user settings if flash is not found")
> 1 drivers/rtc/rtc-armada38x.c:91:22: warning: unused variable 'flags' [-Wunused-variable]
d80238bbcad3 ("rtc: armada38x: Remove unused variable from
armada38x_rtc_set_time()")
> 1 drivers/net/wireless/iwlegacy/3945.c:1022:5: warning: suggest explicit braces to avoid ambiguous 'else' [-Wparentheses]
2cce76c3fab4 ("iwlegacy: avoid warning about missing braces")
> 1 drivers/net/ethernet/neterion/vxge/vxge-main.c:2149:13: warning: 'adaptive_coalesce_rx_interrupts' defined but not used [-Wunused-function]
> 1 drivers/net/ethernet/neterion/vxge/vxge-main.c:2121:13: warning: 'adaptive_coalesce_tx_interrupts' defined but not used [-Wunused-function]
57e7c8cef224 ("net: vxge: avoid unused function warnings")
> 1 drivers/net/ethernet/dec/tulip/winbond-840.c:910:2: warning: #warning Processor architecture undefined [-Wcpp]
de92718883dd ("net: tulip: turn compile-time warning into dev_warn()")
> 1 drivers/net/ethernet/dec/tulip/uli526x.c:1086:4: warning: this 'else' clause does not guard... [-Wmisleading-indentation]
e1395a321eab ("drivers/net/ethernet/dec/tulip/uli526x.c: fix
misleading indentation in uli526x_timer")
> 1 drivers/mtd/maps/pmcmsp-flash.c:149:30: warning: passing argument 1 of 'strncpy' discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers]
79ad07d45743 ("mtd: pmcmsp-flash: Allocating too much in init_msp_flash()")
906b268477bc ("mtd: pmcmsp: use kstrndup instead of kmalloc+strncpy")
> 1 drivers/media/platform/coda/./trace.h:12:0: warning: "TRACE_SYSTEM_STRING" redefined
> 1 include/trace/ftrace.h:28:0: warning: "TRACE_SYSTEM_STRING" redefined
ae1c75d6ce3a ("[media] coda: remove extraneous TRACE_SYSTEM_STRING")
> 1 drivers/net/fddi/defxx.c:595:10: warning: '*((void *)&bar_len+8)' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 drivers/net/fddi/defxx.c:595:10: warning: '*((void *)&bar_len+4)' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 drivers/net/fddi/defxx.c:594:5: warning: '*((void *)&bar_start+8)' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 drivers/net/fddi/defxx.c:594:5: warning: '*((void *)&bar_start+4)' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 drivers/net/fddi/defxx.c:586:10: warning: 'bar_start' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 drivers/net/fddi/defxx.c:586:10: warning: 'bar_len' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 drivers/net/fddi/defxx.c:583:10: warning: 'bar_start' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 drivers/net/fddi/defxx.c:583:10: warning: 'bar_len' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 drivers/net/fddi/defxx.c:3720:5: warning: '*((void *)&bar_start+8)' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 drivers/net/fddi/defxx.c:3720:5: warning: '*((void *)&bar_start+16)' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 include/linux/ioport.h:199:37: warning: 'bar_start' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 include/linux/ioport.h:198:33: warning: 'bar_start' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 include/linux/ioport.h:198:33: warning: 'bar_len' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 include/linux/ioport.h:198:33: warning: '*((void *)&bar_len+8)' may be used uninitialized in this function [-Wmaybe-uninitialized]
> 1 include/linux/ioport.h:198:33: warning: '*((void *)&bar_len+16)' may be used uninitialized in this function [-Wmaybe-uninitialized]
62f2aaabcf41 ("defxx: fix build warning")
> 1 include/linux/kernel.h:729:17: warning: comparison of distinct pointer types lacks a cast
> 1 include/asm-generic/div64.h:43:28: warning: comparison of distinct pointer types lacks a cast
30544af54837 ("e1000e: fix call to do_div() to use u64 arg")
> 1 drivers/scsi/megaraid/megaraid_sas_fusion.c:1723:3: warning: this 'if' clause does not guard... [-Wmisleading-indentation]
4a5c814d9339 ("megaraid_sas : Add separate functions for building
sysPD IOs and non RW LDIOs")
not sure if that is appropriate for stable or even applies.
Arnd
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] [PATCH 3.18 00/32] 3.18.91-stable review
by Greg Kroah-Hartman
This is the start of the stable review cycle for the 3.18.91 release.
There are 32 patches in this series, all will be posted as a response
to this one. If anyone has any issues with these being applied, please
let me know.
Responses should be made by Wed Jan 3 13:59:44 UTC 2018.
Anything received after that time might be too late.
The whole patch series can be found in one patch at:
kernel.org/pub/linux/kernel/v3.x/stable-review/patch-3.18.91-rc1.gz
or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-3.18.y
and the diffstat can be found below.
thanks,
greg k-h
-------------
Pseudo-Shortlog of commits:
Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Linux 3.18.91-rc1
Linus Torvalds <torvalds(a)linux-foundation.org>
n_tty: fix EXTPROC vs ICANON interaction with TIOCINQ (aka FIONREAD)
Daniel Thompson <daniel.thompson(a)linaro.org>
usb: xhci: Add XHCI_TRUST_TX_LENGTH for Renesas uPD720201
Oliver Neukum <oneukum(a)suse.com>
usb: add RESET_RESUME for ELSA MicroLink 56K
Dmitry Fleytman Dmitry Fleytman <dmitry.fleytman(a)gmail.com>
usb: Add device quirk for Logitech HD Pro Webcam C925e
Daniele Palmas <dnlplm(a)gmail.com>
USB: serial: option: add support for Telit ME910 PID 0x1101
Mohamed Ghannam <simo.ghannam(a)gmail.com>
net: ipv4: fix for a race condition in raw_sendmsg
Tonghao Zhang <xiangxia.m.yue(a)gmail.com>
sctp: Replace use of sockets_allocated with specified macro.
Tobias Jordan <Tobias.Jordan(a)elektrobit.com>
net: mvmdio: disable/unprepare clocks in EPROBE_DEFER case
Brian King <brking(a)linux.vnet.ibm.com>
tg3: Fix rx hang on MTU change with 5717/5719
Christoph Paasch <cpaasch(a)apple.com>
tcp md5sig: Use skb's saddr when replying to an incoming segment
Sebastian Sjoholm <ssjoholm(a)mac.com>
net: qmi_wwan: add Sierra EM7565 1199:9091
Kevin Cernekee <cernekee(a)chromium.org>
netlink: Add netns check on taps
Kevin Cernekee <cernekee(a)chromium.org>
net: igmp: Use correct source address on IGMPv3 reports
Eric Dumazet <edumazet(a)google.com>
ipv6: mcast: better catch silly mtu values
Eric Dumazet <edumazet(a)google.com>
ipv4: igmp: guard against silly MTU values
Linus Torvalds <torvalds(a)linux-foundation.org>
kbuild: add '-fno-stack-check' to kernel build options
Johan Hovold <johan(a)kernel.org>
ASoC: twl4030: fix child-node lookup
Steven Rostedt (VMware) <rostedt(a)goodmis.org>
ring-buffer: Mask out the info bits when returning buffer page length
Jing Xia <jing.xia(a)spreadtrum.com>
tracing: Fix crash when it fails to alloc ring buffer
Steven Rostedt (VMware) <rostedt(a)goodmis.org>
tracing: Fix possible double free on failure of allocating trace buffer
Steven Rostedt (VMware) <rostedt(a)goodmis.org>
tracing: Remove extra zeroing out of the ring buffer page
Yelena Krivosheev <yelena(a)marvell.com>
net: mvneta: clear interface link status on port disable
Ravi Bangoria <ravi.bangoria(a)linux.vnet.ibm.com>
powerpc/perf: Dereference BHRB entries safely
Wanpeng Li <wanpeng.li(a)hotmail.com>
KVM: X86: Fix load RFLAGS w/o the fixed bit
Helge Deller <deller(a)gmx.de>
parisc: Hide Diva-built-in serial aux and graphics card
Rafael J. Wysocki <rafael.j.wysocki(a)intel.com>
PCI / PM: Force devices to D0 in pci_pm_thaw_noirq()
Takashi Iwai <tiwai(a)suse.de>
ALSA: usb-audio: Fix the missing ctl name suffix at parsing SU
Takashi Iwai <tiwai(a)suse.de>
ALSA: rawmidi: Avoid racy info ioctl via ctl device
Johan Hovold <johan(a)kernel.org>
mfd: twl6040: Fix child-node lookup
Johan Hovold <johan(a)kernel.org>
mfd: twl4030-audio: Fix sibling-node lookup
Sebastian Andrzej Siewior <bigeasy(a)linutronix.de>
crypto: mcryptd - protect the per-CPU queue with a lock
Takashi Iwai <tiwai(a)suse.de>
ACPI: APEI / ERST: Fix missing error handling in erst_reader()
-------------
Diffstat:
Makefile | 7 ++++--
arch/powerpc/perf/core-book3s.c | 8 +++++--
arch/x86/kvm/x86.c | 2 +-
crypto/mcryptd.c | 23 ++++++++----------
drivers/acpi/apei/erst.c | 2 +-
drivers/mfd/twl4030-audio.c | 9 +++++--
drivers/mfd/twl6040.c | 12 ++++++----
drivers/net/ethernet/broadcom/tg3.c | 4 +++-
drivers/net/ethernet/marvell/mvmdio.c | 3 ++-
drivers/net/ethernet/marvell/mvneta.c | 4 ++++
drivers/net/usb/qmi_wwan.c | 1 +
drivers/parisc/lba_pci.c | 33 ++++++++++++++++++++++++++
drivers/pci/pci-driver.c | 7 +++++-
drivers/tty/n_tty.c | 4 ++--
drivers/usb/core/quirks.c | 6 ++++-
drivers/usb/host/xhci-pci.c | 3 +++
drivers/usb/serial/option.c | 8 +++++++
include/crypto/mcryptd.h | 1 +
include/net/ip.h | 2 ++
kernel/trace/ring_buffer.c | 6 ++++-
kernel/trace/trace.c | 13 ++++-------
net/ipv4/devinet.c | 2 +-
net/ipv4/igmp.c | 44 +++++++++++++++++++++++++++--------
net/ipv4/ip_tunnel.c | 4 ++--
net/ipv4/raw.c | 15 ++++++++----
net/ipv4/tcp_ipv4.c | 2 +-
net/ipv6/mcast.c | 25 ++++++++++++--------
net/ipv6/tcp_ipv6.c | 2 +-
net/netlink/af_netlink.c | 3 +++
net/sctp/socket.c | 4 ++--
sound/core/rawmidi.c | 15 +++++++++---
sound/soc/codecs/twl4030.c | 4 +++-
sound/usb/mixer.c | 27 ++++++++++++---------
33 files changed, 217 insertions(+), 88 deletions(-)
7 years, 8 months
- 3
- 30
[Linux-stable-mirror] v3.18.91 build: 0 failures 1 warnings (v3.18.91)
by Build bot for Mark Brown
Tree/Branch: v3.18.91
Git describe: v3.18.91
Commit: 788ccf7552 Linux 3.18.91
Build Time: 67 min 1 sec
Passed: 9 / 9 (100.00 %)
Failed: 0 / 9 ( 0.00 %)
Errors: 0
Warnings: 1
Section Mismatches: 0
-------------------------------------------------------------------------------
defconfigs with issues (other than build errors):
2 warnings 0 mismatches : x86_64-defconfig
-------------------------------------------------------------------------------
Warnings Summary: 1
2 ../include/linux/ftrace.h:632:36: warning: calling '__builtin_return_address' with a nonzero argument is unsafe [-Wframe-address]
===============================================================================
Detailed per-defconfig build reports below:
-------------------------------------------------------------------------------
x86_64-defconfig : PASS, 0 errors, 2 warnings, 0 section mismatches
Warnings:
../include/linux/ftrace.h:632:36: warning: calling '__builtin_return_address' with a nonzero argument is unsafe [-Wframe-address]
../include/linux/ftrace.h:632:36: warning: calling '__builtin_return_address' with a nonzero argument is unsafe [-Wframe-address]
-------------------------------------------------------------------------------
Passed with no errors, warnings or mismatches:
arm64-allnoconfig
arm64-allmodconfig
arm-multi_v5_defconfig
arm-multi_v7_defconfig
arm-allmodconfig
arm-allnoconfig
x86_64-allnoconfig
arm64-defconfig
close failed in file object destructor:
sys.excepthook is missing
lost sys.stderr
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] [PATCH 1/3] x86/tsc: Future-proof native_calibrate_tsc()
by Len Brown
From: Len Brown <len.brown(a)intel.com>
If native_calibrate_tsc() can not discover the TSC frequency,
via CPUID or via built-in table, it must return without
setting X86_FEATURE_TSC_KNOWN_FREQ. Otherwise, X86_FEATURE_TSC_KNOWN_FREQ
will prevent TSC refined calibration.
This patch allows Linux to correctly support future Intel hardware,
that has (cpu_khz != tsc_khz), and support for CPUID.15
without support for CPUID.15.crystal_khz.
This patch is needed since X86_FEATURE_TSC_KNOWN_FREQ was added in Linux-4.10:
commit 4ca4df0b7eb0
("x86/tsc: Mark TSC frequency determined by CPUID as known")
If not applied, such systems will run with tsc_khz = cpu_khz,
which may result in under-stated TSC rate, and time-of-day drift.
Signed-off-by: Len Brown <len.brown(a)intel.com>
Cc: Bin Gao <bin.gao(a)intel.com>
Cc: <stable(a)vger.kernel.org> # v4.10+
---
arch/x86/kernel/tsc.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 8ea117f8142e..ce4b71119c36 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -612,6 +612,8 @@ unsigned long native_calibrate_tsc(void)
}
}
+ if (crystal_khz == 0)
+ return 0;
/*
* TSC frequency determined by CPUID is a "hardware reported"
* frequency and is the most accurate one so far we have. This
--
2.14.0-rc0
7 years, 8 months
- 2
- 3
[Linux-stable-mirror] [PATCH] drm/i915: Apply Display WA #1183 on skl, kbl, and cfl
by Lucas De Marchi
Display WA #1183 was recently added to workaround
"Failures when enabling DPLL0 with eDP link rate 2.16
or 4.32 GHz and CD clock frequency 308.57 or 617.14 MHz
(CDCLK_CTL CD Frequency Select 10b or 11b) used in this
enabling or in previous enabling."
This workaround was designed to minimize the impact only
to save the bad case with that link rates. But HW engineers
indicated that it should be safe to apply broadly, although
they were expecting the DPLL0 link rate to be unchanged on
runtime.
We need to cover 2 cases: when we are in fact enabling DPLL0
and when we are just changing the frequency with small
differences.
This is based on previous patch by Rodrigo Vivi with suggestions
from Ville Syrjälä.
Cc: Arthur J Runyan <arthur.j.runyan(a)intel.com>
Cc: Ville Syrjälä <ville.syrjala(a)linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi(a)intel.com>
Cc: stable(a)vger.kernel.org
Signed-off-by: Lucas De Marchi <lucas.demarchi(a)intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi(a)intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171204232210.4958-1-lucas.d…
[ Lucas: Backport to 4.15 adding back variable that has been removed on
commits not meant to be backported ]
Signed-off-by: Lucas De Marchi <lucas.demarchi(a)intel.com>
---
drivers/gpu/drm/i915/i915_reg.h | 2 ++
drivers/gpu/drm/i915/intel_cdclk.c | 35 ++++++++++++++++++++++++---------
drivers/gpu/drm/i915/intel_runtime_pm.c | 10 ++++++++++
3 files changed, 38 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 3866c49bc390..333f40bc03bb 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -6977,6 +6977,7 @@ enum {
#define RESET_PCH_HANDSHAKE_ENABLE (1<<4)
#define GEN8_CHICKEN_DCPR_1 _MMIO(0x46430)
+#define SKL_SELECT_ALTERNATE_DC_EXIT (1<<30)
#define MASK_WAKEMEM (1<<13)
#define SKL_DFSM _MMIO(0x51000)
@@ -8522,6 +8523,7 @@ enum skl_power_gate {
#define BXT_CDCLK_CD2X_DIV_SEL_2 (2<<22)
#define BXT_CDCLK_CD2X_DIV_SEL_4 (3<<22)
#define BXT_CDCLK_CD2X_PIPE(pipe) ((pipe)<<20)
+#define CDCLK_DIVMUX_CD_OVERRIDE (1<<19)
#define BXT_CDCLK_CD2X_PIPE_NONE BXT_CDCLK_CD2X_PIPE(3)
#define BXT_CDCLK_SSA_PRECHARGE_ENABLE (1<<16)
#define CDCLK_FREQ_DECIMAL_MASK (0x7ff)
diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index b2a6d62b71c0..60cf4e58389a 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -860,16 +860,10 @@ static void skl_set_preferred_cdclk_vco(struct drm_i915_private *dev_priv,
static void skl_dpll0_enable(struct drm_i915_private *dev_priv, int vco)
{
- int min_cdclk = skl_calc_cdclk(0, vco);
u32 val;
WARN_ON(vco != 8100000 && vco != 8640000);
- /* select the minimum CDCLK before enabling DPLL 0 */
- val = CDCLK_FREQ_337_308 | skl_cdclk_decimal(min_cdclk);
- I915_WRITE(CDCLK_CTL, val);
- POSTING_READ(CDCLK_CTL);
-
/*
* We always enable DPLL0 with the lowest link rate possible, but still
* taking into account the VCO required to operate the eDP panel at the
@@ -923,7 +917,7 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv,
{
int cdclk = cdclk_state->cdclk;
int vco = cdclk_state->vco;
- u32 freq_select, pcu_ack;
+ u32 freq_select, pcu_ack, cdclk_ctl;
int ret;
WARN_ON((cdclk == 24000) != (vco == 0));
@@ -940,7 +934,7 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv,
return;
}
- /* set CDCLK_CTL */
+ /* Choose frequency for this cdclk */
switch (cdclk) {
case 450000:
case 432000:
@@ -968,10 +962,33 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv,
dev_priv->cdclk.hw.vco != vco)
skl_dpll0_disable(dev_priv);
+ cdclk_ctl = I915_READ(CDCLK_CTL);
+
+ if (dev_priv->cdclk.hw.vco != vco) {
+ /* Wa Display #1183: skl,kbl,cfl */
+ cdclk_ctl &= ~(CDCLK_FREQ_SEL_MASK | CDCLK_FREQ_DECIMAL_MASK);
+ cdclk_ctl |= freq_select | skl_cdclk_decimal(cdclk);
+ I915_WRITE(CDCLK_CTL, cdclk_ctl);
+ }
+
+ /* Wa Display #1183: skl,kbl,cfl */
+ cdclk_ctl |= CDCLK_DIVMUX_CD_OVERRIDE;
+ I915_WRITE(CDCLK_CTL, cdclk_ctl);
+ POSTING_READ(CDCLK_CTL);
+
if (dev_priv->cdclk.hw.vco != vco)
skl_dpll0_enable(dev_priv, vco);
- I915_WRITE(CDCLK_CTL, freq_select | skl_cdclk_decimal(cdclk));
+ /* Wa Display #1183: skl,kbl,cfl */
+ cdclk_ctl &= ~(CDCLK_FREQ_SEL_MASK | CDCLK_FREQ_DECIMAL_MASK);
+ I915_WRITE(CDCLK_CTL, cdclk_ctl);
+
+ cdclk_ctl |= freq_select | skl_cdclk_decimal(cdclk);
+ I915_WRITE(CDCLK_CTL, cdclk_ctl);
+
+ /* Wa Display #1183: skl,kbl,cfl */
+ cdclk_ctl &= ~CDCLK_DIVMUX_CD_OVERRIDE;
+ I915_WRITE(CDCLK_CTL, cdclk_ctl);
POSTING_READ(CDCLK_CTL);
/* inform PCU of the change */
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 8af286c63d3b..e0bc2debdad0 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -598,6 +598,11 @@ void gen9_enable_dc5(struct drm_i915_private *dev_priv)
DRM_DEBUG_KMS("Enabling DC5\n");
+ /* Wa Display #1183: skl,kbl,cfl */
+ if (IS_GEN9_BC(dev_priv))
+ I915_WRITE(GEN8_CHICKEN_DCPR_1, I915_READ(GEN8_CHICKEN_DCPR_1) |
+ SKL_SELECT_ALTERNATE_DC_EXIT);
+
gen9_set_dc_state(dev_priv, DC_STATE_EN_UPTO_DC5);
}
@@ -625,6 +630,11 @@ void skl_disable_dc6(struct drm_i915_private *dev_priv)
{
DRM_DEBUG_KMS("Disabling DC6\n");
+ /* Wa Display #1183: skl,kbl,cfl */
+ if (IS_GEN9_BC(dev_priv))
+ I915_WRITE(GEN8_CHICKEN_DCPR_1, I915_READ(GEN8_CHICKEN_DCPR_1) |
+ SKL_SELECT_ALTERNATE_DC_EXIT);
+
gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
}
--
2.14.3
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "tcp_bbr: reset long-term bandwidth sampling on loss recovery undo" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
tcp_bbr: reset long-term bandwidth sampling on loss recovery undo
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
tcp_bbr-reset-long-term-bandwidth-sampling-on-loss-recovery-undo.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From 600647d467c6d04b3954b41a6ee1795b5ae00550 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell(a)google.com>
Date: Thu, 7 Dec 2017 12:43:32 -0500
Subject: tcp_bbr: reset long-term bandwidth sampling on loss recovery undo
From: Neal Cardwell <ncardwell(a)google.com>
commit 600647d467c6d04b3954b41a6ee1795b5ae00550 upstream.
Fix BBR so that upon notification of a loss recovery undo BBR resets
long-term bandwidth sampling.
Under high reordering, reordering events can be interpreted as loss.
If the reordering and spurious loss estimates are high enough, this
can cause BBR to spuriously estimate that we are seeing loss rates
high enough to trigger long-term bandwidth estimation. To avoid that
problem, this commit resets long-term bandwidth sampling on loss
recovery undo events.
Signed-off-by: Neal Cardwell <ncardwell(a)google.com>
Reviewed-by: Yuchung Cheng <ycheng(a)google.com>
Acked-by: Soheil Hassas Yeganeh <soheil(a)google.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
net/ipv4/tcp_bbr.c | 1 +
1 file changed, 1 insertion(+)
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -847,6 +847,7 @@ static u32 bbr_undo_cwnd(struct sock *sk
bbr->full_bw = 0; /* spurious slow-down; reset full pipe detection */
bbr->full_bw_cnt = 0;
+ bbr_reset_lt_bw_sampling(sk);
return tcp_sk(sk)->snd_cwnd;
}
Patches currently in stable-queue which might be from ncardwell(a)google.com are
queue-4.9/tcp_bbr-reset-full-pipe-detection-on-loss-recovery-undo.patch
queue-4.9/tcp_bbr-reset-long-term-bandwidth-sampling-on-loss-recovery-undo.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] Patch "tcp_bbr: reset full pipe detection on loss recovery undo" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
tcp_bbr: reset full pipe detection on loss recovery undo
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
tcp_bbr-reset-full-pipe-detection-on-loss-recovery-undo.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From 2f6c498e4f15d27852c04ed46d804a39137ba364 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell(a)google.com>
Date: Thu, 7 Dec 2017 12:43:31 -0500
Subject: tcp_bbr: reset full pipe detection on loss recovery undo
From: Neal Cardwell <ncardwell(a)google.com>
commit 2f6c498e4f15d27852c04ed46d804a39137ba364 upstream.
Fix BBR so that upon notification of a loss recovery undo BBR resets
the full pipe detection (STARTUP exit) state machine.
Under high reordering, reordering events can be interpreted as loss.
If the reordering and spurious loss estimates are high enough, this
could previously cause BBR to spuriously estimate that the pipe is
full.
Since spurious loss recovery means that our overall sending will have
slowed down spuriously, this commit gives a flow more time to probe
robustly for bandwidth and decide the pipe is really full.
Signed-off-by: Neal Cardwell <ncardwell(a)google.com>
Reviewed-by: Yuchung Cheng <ycheng(a)google.com>
Acked-by: Soheil Hassas Yeganeh <soheil(a)google.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
net/ipv4/tcp_bbr.c | 4 ++++
1 file changed, 4 insertions(+)
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -843,6 +843,10 @@ static u32 bbr_sndbuf_expand(struct sock
*/
static u32 bbr_undo_cwnd(struct sock *sk)
{
+ struct bbr *bbr = inet_csk_ca(sk);
+
+ bbr->full_bw = 0; /* spurious slow-down; reset full pipe detection */
+ bbr->full_bw_cnt = 0;
return tcp_sk(sk)->snd_cwnd;
}
Patches currently in stable-queue which might be from ncardwell(a)google.com are
queue-4.9/tcp_bbr-reset-full-pipe-detection-on-loss-recovery-undo.patch
queue-4.9/tcp_bbr-reset-long-term-bandwidth-sampling-on-loss-recovery-undo.patch
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] [PATCH 2/2] pktcdvd: Fix a recently introduced NULL pointer dereference
by Bart Van Assche
Call bdev_get_queue(bdev) after bdev->bd_disk has been initialized
instead of just before that pointer has been initialized. This patch
avoids that the following command
pktsetup 1 /dev/sr0
triggers the following kernel crash:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000548
IP: pkt_setup_dev+0x2db/0x670 [pktcdvd]
CPU: 2 PID: 724 Comm: pktsetup Not tainted 4.15.0-rc4-dbg+ #1
Call Trace:
pkt_ctl_ioctl+0xce/0x1c0 [pktcdvd]
do_vfs_ioctl+0x8e/0x670
SyS_ioctl+0x3c/0x70
entry_SYSCALL_64_fastpath+0x23/0x9a
Reported-by: Maciej S. Szmigiero <mail(a)maciej.szmigiero.name>
Fixes: commit ca18d6f769d2 ("block: Make most scsi_req_init() calls implicit")
Signed-off-by: Bart Van Assche <bart.vanassche(a)wdc.com>
Tested-by: Maciej S. Szmigiero <mail(a)maciej.szmigiero.name>
Cc: Maciej S. Szmigiero <mail(a)maciej.szmigiero.name>
Cc: <stable(a)vger.kernel.org> # v4.13
---
drivers/block/pktcdvd.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 2659b2534073..531a0915066b 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2579,14 +2579,14 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
bdev = bdget(dev);
if (!bdev)
return -ENOMEM;
+ ret = blkdev_get(bdev, FMODE_READ | FMODE_NDELAY, NULL);
+ if (ret)
+ return ret;
if (!blk_queue_scsi_passthrough(bdev_get_queue(bdev))) {
WARN_ONCE(true, "Attempt to register a non-SCSI queue\n");
- bdput(bdev);
+ blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
return -EINVAL;
}
- ret = blkdev_get(bdev, FMODE_READ | FMODE_NDELAY, NULL);
- if (ret)
- return ret;
/* This is safe, since we have a reference from open(). */
__module_get(THIS_MODULE);
--
2.15.1
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] [PATCH 1/2] pktcdvd: Fix pkt_setup_dev() error path
by Bart Van Assche
Commit 523e1d399ce0 ("block: make gendisk hold a reference to its queue")
modified add_disk() and disk_release() but did not update any of the
error paths that trigger a put_disk() call after disk->queue has been
assigned. That introduced the following behavior in the pktcdvd driver
if pkt_new_dev() fails:
Kernel BUG at 00000000e98fd882 [verbose debug info unavailable]
Since disk_release() calls blk_put_queue() anyway if disk->queue != NULL,
fix this by removing the blk_cleanup_queue() call from the pkt_setup_dev()
error path.
Fixes: commit 523e1d399ce0 ("block: make gendisk hold a reference to its queue")
Signed-off-by: Bart Van Assche <bart.vanassche(a)wdc.com>
Cc: Tejun Heo <tj(a)kernel.org>
Cc: Maciej S. Szmigiero <mail(a)maciej.szmigiero.name>
Cc: <stable(a)vger.kernel.org> # v3.2
---
drivers/block/pktcdvd.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 67974796c350..2659b2534073 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2745,7 +2745,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
pd->pkt_dev = MKDEV(pktdev_major, idx);
ret = pkt_new_dev(pd, dev);
if (ret)
- goto out_new_dev;
+ goto out_mem2;
/* inherit events of the host device */
disk->events = pd->bdev->bd_disk->events;
@@ -2763,8 +2763,6 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
mutex_unlock(&ctl_mutex);
return 0;
-out_new_dev:
- blk_cleanup_queue(disk->queue);
out_mem2:
put_disk(disk);
out_mem:
--
2.15.1
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] patch "mei: me: allow runtime pm for platform with D0i3" added to char-misc-testing
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
mei: me: allow runtime pm for platform with D0i3
to my char-misc git tree which can be found at
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
in the char-misc-testing branch.
The patch will show up in the next release of the linux-next tree
(usually sometime within the next 24 hours during the week.)
The patch will be merged to the char-misc-next branch sometime soon,
after it passes testing, and the merge window is open.
If you have any questions about this process, please let me know.
>From cc365dcf0e56271bedf3de95f88922abe248e951 Mon Sep 17 00:00:00 2001
From: Tomas Winkler <tomas.winkler(a)intel.com>
Date: Tue, 2 Jan 2018 12:01:41 +0200
Subject: mei: me: allow runtime pm for platform with D0i3
>From the pci power documentation:
"The driver itself should not call pm_runtime_allow(), though. Instead,
it should let user space or some platform-specific code do that (user space
can do it via sysfs as stated above)..."
However, the S0ix residency cannot be reached without MEI device getting
into low power state. Hence, for mei devices that support D0i3, it's better
to make runtime power management mandatory and not rely on the system
integration such as udev rules.
This policy cannot be applied globally as some older platforms
were found to have broken power management.
Cc: <stable(a)vger.kernel.org> v4.13+
Cc: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com>
Signed-off-by: Tomas Winkler <tomas.winkler(a)intel.com>
Reviewed-by: Alexander Usyskin <alexander.usyskin(a)intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/misc/mei/pci-me.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index f4f17552c9b8..4a0ccda4d04b 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -238,8 +238,11 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
*/
mei_me_set_pm_domain(dev);
- if (mei_pg_is_enabled(dev))
+ if (mei_pg_is_enabled(dev)) {
pm_runtime_put_noidle(&pdev->dev);
+ if (hw->d0i3_supported)
+ pm_runtime_allow(&pdev->dev);
+ }
dev_dbg(&pdev->dev, "initialization successful.\n");
--
2.15.1
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] FAILED: patch "[PATCH] usbip: prevent leaking socket pointer address in messages" failed to apply to 4.4-stable tree
by gregkh＠linuxfoundation.org
The patch below does not apply to the 4.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 90120d15f4c397272aaf41077960a157fc4212bf Mon Sep 17 00:00:00 2001
From: Shuah Khan <shuahkh(a)osg.samsung.com>
Date: Fri, 15 Dec 2017 10:50:09 -0700
Subject: [PATCH] usbip: prevent leaking socket pointer address in messages
usbip driver is leaking socket pointer address in messages. Remove
the messages that aren't useful and print sockfd in the ones that
are useful for debugging.
Signed-off-by: Shuah Khan <shuahkh(a)osg.samsung.com>
Cc: stable <stable(a)vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c
index a3df8ee82faf..e31a6f204397 100644
--- a/drivers/usb/usbip/stub_dev.c
+++ b/drivers/usb/usbip/stub_dev.c
@@ -149,8 +149,7 @@ static void stub_shutdown_connection(struct usbip_device *ud)
* step 1?
*/
if (ud->tcp_socket) {
- dev_dbg(&sdev->udev->dev, "shutdown tcp_socket %p\n",
- ud->tcp_socket);
+ dev_dbg(&sdev->udev->dev, "shutdown sockfd %d\n", ud->sockfd);
kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
}
diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c
index f7978933b402..7b219d9109b4 100644
--- a/drivers/usb/usbip/usbip_common.c
+++ b/drivers/usb/usbip/usbip_common.c
@@ -317,26 +317,20 @@ int usbip_recv(struct socket *sock, void *buf, int size)
struct msghdr msg = {.msg_flags = MSG_NOSIGNAL};
int total = 0;
+ if (!sock || !buf || !size)
+ return -EINVAL;
+
iov_iter_kvec(&msg.msg_iter, READ|ITER_KVEC, &iov, 1, size);
usbip_dbg_xmit("enter\n");
- if (!sock || !buf || !size) {
- pr_err("invalid arg, sock %p buff %p size %d\n", sock, buf,
- size);
- return -EINVAL;
- }
-
do {
- int sz = msg_data_left(&msg);
+ msg_data_left(&msg);
sock->sk->sk_allocation = GFP_NOIO;
result = sock_recvmsg(sock, &msg, MSG_WAITALL);
- if (result <= 0) {
- pr_debug("receive sock %p buf %p size %u ret %d total %d\n",
- sock, buf + total, sz, result, total);
+ if (result <= 0)
goto err;
- }
total += result;
} while (msg_data_left(&msg));
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index 9efab3dc3734..c3e1008aa491 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -965,7 +965,7 @@ static void vhci_shutdown_connection(struct usbip_device *ud)
/* need this? see stub_dev.c */
if (ud->tcp_socket) {
- pr_debug("shutdown tcp_socket %p\n", ud->tcp_socket);
+ pr_debug("shutdown tcp_socket %d\n", ud->sockfd);
kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
}
7 years, 8 months
- 2
- 1
[Linux-stable-mirror] [PATCH 2/3] x86/tsc: Fix erroneous TSC rate on Skylake Xeon
by Len Brown
From: Len Brown <len.brown(a)intel.com>
Linux-4.9 added INTEL_FAM6_SKYLAKE_X to native_calibrate_tsc(),
allowing the kernel to calculate the TSC frequency,
instead of calibrating:
commit 6baf3d61821f
("x86/tsc: Add additional Intel CPU models to the crystal quirk list")
There are several problems with doing this.
The first is that while SKX servers use a 25 MHz crystal,
SKX workstations (with same model #) use a 24 MHz crystal.
This results in a -4.0% time drift rate on SKX workstations.
But even SKX servers have a problem.
SKX subjects the crystal to an EMI reduction circuit that
reduces its actual value by (approximately) -0.25%.
This results in -1 second per 10 minute time drift
as compared to network time on SKX servers.
This also results in an even more subtle symptom on systems
that use the LAPIC timer (versus the TSC deadline timer).
Clock ticks scheduled with the LAPIC timer arrive a few usec
before the time they are expected (according to the slow TSC).
This causes Linux to poll-idle, when it should be in an idle
power saving state. The idle and clock code do not graciously
recover from this error, sometimes resulting in significant polling
and significant power impact.
So stop using native_calibrate_tsc() for INTEL_FAM6_SKYLAKE_X.
native_calibrate_tsc() will return 0, boot will run with
tsc_khz = cpu_khz, and the TSC refined calibration will
update tsc_khz to correct for the difference.
Yes, a future patch can detect 24 vs 25 MHz crystals,
and it can estimate a correction for the EMI circuit impact.
However, that would effect boot-time only, as we'd probably
choose to keep the refined TSC calibration, because the EMI
correction estimate may not be precise.
Signed-off-by: Len Brown <len.brown(a)intel.com>
Cc: Prarit Bhargava <prarit(a)redhat.com>
Cc: <stable(a)vger.kernel.org> # v4.9+
---
arch/x86/kernel/tsc.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 49d772672367..19ca0004caf6 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -602,7 +602,6 @@ unsigned long native_calibrate_tsc(void)
case INTEL_FAM6_KABYLAKE_DESKTOP:
crystal_khz = 24000; /* 24.0 MHz */
break;
- case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_ATOM_DENVERTON:
crystal_khz = 25000; /* 25.0 MHz */
break;
--
2.14.0-rc0
7 years, 8 months
- 2
- 1
[Linux-stable-mirror] v3.2.97 build: 4 failures 20 warnings (v3.2.97)
by Build bot for Mark Brown
Tree/Branch: v3.2.97
Git describe: v3.2.97
Commit: 3993a5061a Linux 3.2.97
Build Time: 0 min 4 sec
Passed: 0 / 4 ( 0.00 %)
Failed: 4 / 4 (100.00 %)
Errors: 6
Warnings: 20
Section Mismatches: 0
Failed defconfigs:
x86_64-allnoconfig
arm-allmodconfig
arm-allnoconfig
x86_64-defconfig
Errors:
x86_64-allnoconfig
/home/broonie/build/linux-stable/scripts/mod/empty.c:1:0: error: code model kernel does not support PIC mode
/home/broonie/build/linux-stable/kernel/bounds.c:1:0: error: code model kernel does not support PIC mode
arm-allnoconfig
/home/broonie/build/linux-stable/arch/arm/include/asm/div64.h:77:7: error: '__LINUX_ARM_ARCH__' undeclared (first use in this function)
/home/broonie/build/linux-stable/arch/arm/include/asm/glue-cache.h:129:2: error: #error Unknown cache maintenance model
/home/broonie/build/linux-stable/arch/arm/include/asm/glue-df.h:107:2: error: #error Unknown data abort handler type
/home/broonie/build/linux-stable/arch/arm/include/asm/glue-pf.h:54:2: error: #error Unknown prefetch abort handler type
x86_64-defconfig
/home/broonie/build/linux-stable/scripts/mod/empty.c:1:0: error: code model kernel does not support PIC mode
/home/broonie/build/linux-stable/kernel/bounds.c:1:0: error: code model kernel does not support PIC mode
-------------------------------------------------------------------------------
defconfigs with issues (other than build errors):
2 warnings 0 mismatches : arm-allmodconfig
19 warnings 0 mismatches : arm-allnoconfig
-------------------------------------------------------------------------------
Errors summary: 6
2 /home/broonie/build/linux-stable/scripts/mod/empty.c:1:0: error: code model kernel does not support PIC mode
2 /home/broonie/build/linux-stable/kernel/bounds.c:1:0: error: code model kernel does not support PIC mode
1 /home/broonie/build/linux-stable/arch/arm/include/asm/glue-pf.h:54:2: error: #error Unknown prefetch abort handler type
1 /home/broonie/build/linux-stable/arch/arm/include/asm/glue-df.h:107:2: error: #error Unknown data abort handler type
1 /home/broonie/build/linux-stable/arch/arm/include/asm/glue-cache.h:129:2: error: #error Unknown cache maintenance model
1 /home/broonie/build/linux-stable/arch/arm/include/asm/div64.h:77:7: error: '__LINUX_ARM_ARCH__' undeclared (first use in this function)
Warnings Summary: 20
2 .config:27:warning: symbol value '' invalid for PHYS_OFFSET
1 /home/broonie/build/linux-stable/arch/arm/include/asm/system.h:342:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/system.h:272:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/system.h:265:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/system.h:131:35: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/system.h:127:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/system.h:121:3: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/system.h:120:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/system.h:114:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/swab.h:25:28: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/processor.h:82:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/processor.h:102:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/irqflags.h:11:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/fpstate.h:32:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/cachetype.h:33:7: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/cachetype.h:28:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/cacheflush.h:196:7: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/cacheflush.h:194:7: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/bitops.h:217:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
1 /home/broonie/build/linux-stable/arch/arm/include/asm/atomic.h:30:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
===============================================================================
Detailed per-defconfig build reports below:
-------------------------------------------------------------------------------
x86_64-allnoconfig : FAIL, 2 errors, 0 warnings, 0 section mismatches
Errors:
/home/broonie/build/linux-stable/scripts/mod/empty.c:1:0: error: code model kernel does not support PIC mode
/home/broonie/build/linux-stable/kernel/bounds.c:1:0: error: code model kernel does not support PIC mode
-------------------------------------------------------------------------------
arm-allmodconfig : FAIL, 0 errors, 2 warnings, 0 section mismatches
Warnings:
.config:27:warning: symbol value '' invalid for PHYS_OFFSET
.config:27:warning: symbol value '' invalid for PHYS_OFFSET
-------------------------------------------------------------------------------
arm-allnoconfig : FAIL, 4 errors, 19 warnings, 0 section mismatches
Errors:
/home/broonie/build/linux-stable/arch/arm/include/asm/div64.h:77:7: error: '__LINUX_ARM_ARCH__' undeclared (first use in this function)
/home/broonie/build/linux-stable/arch/arm/include/asm/glue-cache.h:129:2: error: #error Unknown cache maintenance model
/home/broonie/build/linux-stable/arch/arm/include/asm/glue-df.h:107:2: error: #error Unknown data abort handler type
/home/broonie/build/linux-stable/arch/arm/include/asm/glue-pf.h:54:2: error: #error Unknown prefetch abort handler type
Warnings:
/home/broonie/build/linux-stable/arch/arm/include/asm/irqflags.h:11:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/system.h:114:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/system.h:120:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/system.h:121:3: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/system.h:127:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/system.h:131:35: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/system.h:265:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/system.h:272:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/system.h:342:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/bitops.h:217:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/swab.h:25:28: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/fpstate.h:32:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/processor.h:82:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/processor.h:102:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/atomic.h:30:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/cachetype.h:28:5: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/cachetype.h:33:7: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/cacheflush.h:194:7: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
/home/broonie/build/linux-stable/arch/arm/include/asm/cacheflush.h:196:7: warning: "__LINUX_ARM_ARCH__" is not defined [-Wundef]
-------------------------------------------------------------------------------
x86_64-defconfig : FAIL, 2 errors, 0 warnings, 0 section mismatches
Errors:
/home/broonie/build/linux-stable/scripts/mod/empty.c:1:0: error: code model kernel does not support PIC mode
/home/broonie/build/linux-stable/kernel/bounds.c:1:0: error: code model kernel does not support PIC mode
-------------------------------------------------------------------------------
Passed with no errors, warnings or mismatches:
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] v3.16.52 build: 0 failures 7 warnings (v3.16.52)
by Build bot for Mark Brown
Tree/Branch: v3.16.52
Git describe: v3.16.52
Commit: bde16624c6 Linux 3.16.52
Build Time: 37 min 38 sec
Passed: 9 / 9 (100.00 %)
Failed: 0 / 9 ( 0.00 %)
Errors: 0
Warnings: 7
Section Mismatches: 0
-------------------------------------------------------------------------------
defconfigs with issues (other than build errors):
1 warnings 0 mismatches : arm64-allnoconfig
2 warnings 0 mismatches : arm64-allmodconfig
1 warnings 0 mismatches : arm-multi_v5_defconfig
1 warnings 0 mismatches : arm-multi_v7_defconfig
1 warnings 0 mismatches : x86_64-defconfig
4 warnings 0 mismatches : arm-allmodconfig
1 warnings 0 mismatches : arm-allnoconfig
1 warnings 0 mismatches : x86_64-allnoconfig
3 warnings 0 mismatches : arm64-defconfig
-------------------------------------------------------------------------------
Warnings Summary: 7
7 ../include/linux/stddef.h:8:14: warning: 'return' with a value, in function returning void
2 ../ipc/sem.c:377:6: warning: '___p1' may be used uninitialized in this function [-Wmaybe-uninitialized]
2 ../drivers/net/ethernet/broadcom/genet/bcmgenet.c:1346:17: warning: unused variable 'kdev' [-Wunused-variable]
1 ../drivers/platform/x86/eeepc-laptop.c:279:10: warning: 'value' may be used uninitialized in this function [-Wmaybe-uninitialized]
1 ../drivers/media/platform/davinci/vpfe_capture.c:291:12: warning: 'vpfe_get_ccdc_image_format' defined but not used [-Wunused-function]
1 ../drivers/media/platform/davinci/vpfe_capture.c:1718:1: warning: label 'unlock_out' defined but not used [-Wunused-label]
1 ../arch/x86/kernel/cpu/common.c:961:13: warning: 'syscall32_cpu_init' defined but not used [-Wunused-function]
===============================================================================
Detailed per-defconfig build reports below:
-------------------------------------------------------------------------------
arm64-allnoconfig : PASS, 0 errors, 1 warnings, 0 section mismatches
Warnings:
../include/linux/stddef.h:8:14: warning: 'return' with a value, in function returning void
-------------------------------------------------------------------------------
arm64-allmodconfig : PASS, 0 errors, 2 warnings, 0 section mismatches
Warnings:
../drivers/net/ethernet/broadcom/genet/bcmgenet.c:1346:17: warning: unused variable 'kdev' [-Wunused-variable]
../include/linux/stddef.h:8:14: warning: 'return' with a value, in function returning void
-------------------------------------------------------------------------------
arm-multi_v5_defconfig : PASS, 0 errors, 1 warnings, 0 section mismatches
Warnings:
../include/linux/stddef.h:8:14: warning: 'return' with a value, in function returning void
-------------------------------------------------------------------------------
arm-multi_v7_defconfig : PASS, 0 errors, 1 warnings, 0 section mismatches
Warnings:
../include/linux/stddef.h:8:14: warning: 'return' with a value, in function returning void
-------------------------------------------------------------------------------
x86_64-defconfig : PASS, 0 errors, 1 warnings, 0 section mismatches
Warnings:
../drivers/platform/x86/eeepc-laptop.c:279:10: warning: 'value' may be used uninitialized in this function [-Wmaybe-uninitialized]
-------------------------------------------------------------------------------
arm-allmodconfig : PASS, 0 errors, 4 warnings, 0 section mismatches
Warnings:
../drivers/media/platform/davinci/vpfe_capture.c:1718:1: warning: label 'unlock_out' defined but not used [-Wunused-label]
../drivers/media/platform/davinci/vpfe_capture.c:291:12: warning: 'vpfe_get_ccdc_image_format' defined but not used [-Wunused-function]
../include/linux/stddef.h:8:14: warning: 'return' with a value, in function returning void
../drivers/net/ethernet/broadcom/genet/bcmgenet.c:1346:17: warning: unused variable 'kdev' [-Wunused-variable]
-------------------------------------------------------------------------------
arm-allnoconfig : PASS, 0 errors, 1 warnings, 0 section mismatches
Warnings:
../include/linux/stddef.h:8:14: warning: 'return' with a value, in function returning void
-------------------------------------------------------------------------------
x86_64-allnoconfig : PASS, 0 errors, 1 warnings, 0 section mismatches
Warnings:
../arch/x86/kernel/cpu/common.c:961:13: warning: 'syscall32_cpu_init' defined but not used [-Wunused-function]
-------------------------------------------------------------------------------
arm64-defconfig : PASS, 0 errors, 3 warnings, 0 section mismatches
Warnings:
../ipc/sem.c:377:6: warning: '___p1' may be used uninitialized in this function [-Wmaybe-uninitialized]
../ipc/sem.c:377:6: warning: '___p1' may be used uninitialized in this function [-Wmaybe-uninitialized]
../include/linux/stddef.h:8:14: warning: 'return' with a value, in function returning void
-------------------------------------------------------------------------------
Passed with no errors, warnings or mismatches:
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] [PATCH 1/4] fscache: Fix the default for fscache_maybe_release_page()
by David Howells
Fix the default for fscache_maybe_release_page() for when the cookie isn't
valid or the page isn't cached. It mustn't return false as that indicates
the page cannot yet be freed.
The problem with the default is that if, say, there's no cache, but a
network filesystem's pages are using up almost all the available memory, a
system can OOM because the filesystem ->releasepage() op will not allow
them to be released as fscache_maybe_release_page() incorrectly prevents
it.
This can be tested by writing a sequence of 512MiB files to an AFS mount.
It does not affect NFS or CIFS because both of those wrap the call in a
check of PG_fscache and it shouldn't bother Ceph as that only has
PG_private set whilst writeback is in progress. This might be an issue for
9P, however.
Note that the pages aren't entirely stuck. Removing a file or unmounting
will clear things because that uses ->invalidatepage() instead.
Fixes: 201a15428bd5 ("FS-Cache: Handle pages pending storage that get evicted under OOM conditions")
Reported-by: Marc Dionne <marc.dionne(a)auristor.com>
Signed-off-by: David Howells <dhowells(a)redhat.com>
Reviewed-by: Jeff Layton <jlayton(a)redhat.com>
Acked-by: Al Viro <viro(a)zeniv.linux.org.uk>
Tested-by: Marc Dionne <marc.dionne(a)auristor.com>
cc: stable(a)vger.kernel.org # 2.6.32+
---
include/linux/fscache.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index f4ff47d4a893..fe0c349684fa 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -755,7 +755,7 @@ bool fscache_maybe_release_page(struct fscache_cookie *cookie,
{
if (fscache_cookie_valid(cookie) && PageFsCache(page))
return __fscache_maybe_release_page(cookie, page, gfp);
- return false;
+ return true;
}
/**
7 years, 8 months
- 1
- 0
[Linux-stable-mirror] [PATCH 4.14 00/74] 4.14.10-stable review
by Greg Kroah-Hartman
This is the start of the stable review cycle for the 4.14.10 release.
There are 74 patches in this series, all will be posted as a response
to this one. If anyone has any issues with these being applied, please
let me know.
Responses should be made by Fri Dec 29 16:45:52 UTC 2017.
Anything received after that time might be too late.
The whole patch series can be found in one patch at:
kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.14.10-rc1.gz
or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.14.y
and the diffstat can be found below.
thanks,
greg k-h
-------------
Pseudo-Shortlog of commits:
Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Linux 4.14.10-rc1
John Einar Reitan <john.einar(a)gmail.com>
Revert "ipmi_si: fix memory leak on new_smi"
Yelena Krivosheev <yelena(a)marvell.com>
net: mvneta: eliminate wrong call to handle rx descriptor error
Yelena Krivosheev <yelena(a)marvell.com>
net: mvneta: use proper rxq_number in loop on rx queues
Yelena Krivosheev <yelena(a)marvell.com>
net: mvneta: clear interface link status on port disable
Dan Williams <dan.j.williams(a)intel.com>
libnvdimm, pfn: fix start_pad handling for aligned namespaces
Vishal Verma <vishal.l.verma(a)intel.com>
libnvdimm, btt: Fix an incompatibility in the log layout
Dan Williams <dan.j.williams(a)intel.com>
libnvdimm, dax: fix 1GB-aligned namespaces vs physical misalignment
Maxime Ripard <maxime.ripard(a)free-electrons.com>
drm/sun4i: Fix error path handling
Chris Wilson <chris(a)chris-wilson.co.uk>
drm/i915: Flush pending GTT writes before unbinding
Ravi Bangoria <ravi.bangoria(a)linux.vnet.ibm.com>
powerpc/perf: Dereference BHRB entries safely
Chen-Yu Tsai <wens(a)csie.org>
clk: sunxi: sun9i-mmc: Implement reset callback for reset controls
Paolo Bonzini <pbonzini(a)redhat.com>
kvm: x86: fix RSM when PCID is non-zero
Wanpeng Li <wanpeng.li(a)hotmail.com>
KVM: X86: Fix load RFLAGS w/o the fixed bit
Wanpeng Li <wanpeng.li(a)hotmail.com>
KVM: MMU: Fix infinite loop when there is no available mmu page
Laurent Vivier <lvivier(a)redhat.com>
KVM: PPC: Book3S HV: Fix pending_pri value in kvmppc_xive_get_icp()
Cédric Le Goater <clg(a)kaod.org>
KVM: PPC: Book3S: fix XIVE migration of pending interrupts
Marc Zyngier <marc.zyngier(a)arm.com>
KVM: arm/arm64: Fix HYP unmapping going off limits
Julien Thierry <julien.thierry(a)arm.com>
arm64: kvm: Prevent restoring stale PMSCR_EL1 for vcpu
Mika Westerberg <mika.westerberg(a)linux.intel.com>
pinctrl: cherryview: Mask all interrupts on Intel_Strago based systems
Maxime Chevallier <maxime.chevallier(a)smile.fr>
spi: a3700: Fix clk prescaling for coefficient over 15
Ricardo Ribalda Delgado <ricardo.ribalda(a)gmail.com>
spi: xilinx: Detect stall with Unknown commands
John David Anglin <dave.anglin(a)bell.net>
Revert "parisc: Re-enable interrupts early"
Helge Deller <deller(a)gmx.de>
parisc: Hide Diva-built-in serial aux and graphics card
Helge Deller <deller(a)gmx.de>
parisc: Fix indenting in puts()
Helge Deller <deller(a)gmx.de>
parisc: Align os_hpmc_size on word boundary
Shaohua Li <shli(a)fb.com>
block-throttle: avoid double charge
Jens Axboe <axboe(a)kernel.dk>
block: unalign call_single_data in struct request
Rafael J. Wysocki <rafael.j.wysocki(a)intel.com>
PCI / PM: Force devices to D0 in pci_pm_thaw_noirq()
Takashi Iwai <tiwai(a)suse.de>
ALSA: usb-audio: Fix the missing ctl name suffix at parsing SU
Jussi Laako <jussi(a)sonarnerd.net>
ALSA: usb-audio: Add native DSD support for Esoteric D-05X
Guneshwor Singh <guneshwor.o.singh(a)intel.com>
ALSA: hda - Add vendor id for Cannonlake HDMI codec
Kailang Yang <kailang(a)realtek.com>
ALSA: hda/realtek - Fix Dell AIO LineOut issue
Takashi Iwai <tiwai(a)suse.de>
ALSA: rawmidi: Avoid racy info ioctl via ctl device
Johan Hovold <johan(a)kernel.org>
mfd: twl6040: Fix child-node lookup
Johan Hovold <johan(a)kernel.org>
mfd: twl4030-audio: Fix sibling-node lookup
Jon Hunter <jonathanh(a)nvidia.com>
mfd: cros ec: spi: Don't send first message too soon
Stephan Mueller <smueller(a)chronox.de>
crypto: af_alg - fix race accessing cipher request
Stephan Mueller <smueller(a)chronox.de>
crypto: af_alg - wait for data at beginning of recvmsg
Sebastian Andrzej Siewior <bigeasy(a)linutronix.de>
crypto: mcryptd - protect the per-CPU queue with a lock
Eric Biggers <ebiggers(a)google.com>
crypto: skcipher - set walk.iv for zero-length inputs
Dan Williams <dan.j.williams(a)intel.com>
acpi, nfit: fix health event notification
Takashi Iwai <tiwai(a)suse.de>
ACPI: APEI / ERST: Fix missing error handling in erst_reader()
Thomas Gleixner <tglx(a)linutronix.de>
x86/cpu_entry_area: Prevent wraparound in setup_cpu_entry_area_ptes() on 32bit
Thomas Gleixner <tglx(a)linutronix.de>
init: Invoke init_espfix_bsp() from mm_init()
Thomas Gleixner <tglx(a)linutronix.de>
x86/cpu_entry_area: Move it out of the fixmap
Thomas Gleixner <tglx(a)linutronix.de>
x86/cpu_entry_area: Move it to a separate unit
Peter Zijlstra <peterz(a)infradead.org>
x86/mm: Create asm/invpcid.h
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/mm: Put MMU to hardware ASID translation in one place
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/mm: Remove hard-coded ASID limit checks
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/mm: Move the CR3 construction functions to tlbflush.h
Peter Zijlstra <peterz(a)infradead.org>
x86/mm: Add comments to clarify which TLB-flush functions are supposed to flush what
Peter Zijlstra <peterz(a)infradead.org>
x86/mm: Remove superfluous barriers
Peter Zijlstra <peterz(a)infradead.org>
x86/mm: Use __flush_tlb_one() for kernel memory
Peter Zijlstra <peterz(a)infradead.org>
x86/microcode: Dont abuse the TLB-flush interface
Peter Zijlstra <peterz(a)infradead.org>
x86/uv: Use the right TLB-flush API
Dave Hansen <dave.hansen(a)linux.intel.com>
x86/entry: Rename SYSENTER_stack to CPU_ENTRY_AREA_entry_stack
Peter Zijlstra <peterz(a)infradead.org>
x86/doc: Remove obvious weirdnesses from the x86 MM layout documentation
Andy Lutomirski <luto(a)kernel.org>
x86/mm/64: Improve the memory map documentation
Thomas Gleixner <tglx(a)linutronix.de>
x86/ldt: Prevent LDT inheritance on exec
Peter Zijlstra <peterz(a)infradead.org>
x86/ldt: Rework locking
Thomas Gleixner <tglx(a)linutronix.de>
arch, mm: Allow arch_dup_mmap() to fail
Andy Lutomirski <luto(a)kernel.org>
x86/vsyscall/64: Warn and fail vsyscall emulation in NATIVE mode
Andy Lutomirski <luto(a)kernel.org>
x86/vsyscall/64: Explicitly set _PAGE_USER in the pagetable hierarchy
Thomas Gleixner <tglx(a)linutronix.de>
x86/mm/dump_pagetables: Make the address hints correct and readable
Thomas Gleixner <tglx(a)linutronix.de>
x86/mm/dump_pagetables: Check PAGE_PRESENT for real
Thomas Gleixner <tglx(a)linutronix.de>
x86/Kconfig: Limit NR_CPUS on 32-bit to a sane amount
Ricardo Neri <ricardo.neri-calderon(a)linux.intel.com>
x86/insn-eval: Add utility functions to get segment selector
Randy Dunlap <rdunlap(a)infradead.org>
x86/decoder: Fix and update the opcodes map
Mikulas Patocka <mpatocka(a)redhat.com>
objtool: Fix 64-bit build on 32-bit host
Ingo Molnar <mingo(a)kernel.org>
tools/headers: Sync objtool UAPI header
Josh Poimboeuf <jpoimboe(a)redhat.com>
objtool: Fix cross-build
Josh Poimboeuf <jpoimboe(a)redhat.com>
objtool: Move kernel headers/code sync check to a script
Josh Poimboeuf <jpoimboe(a)redhat.com>
objtool: Move synced files to their original relative locations
Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Revert "ipv6: grab rt->rt6i_ref before allocating pcpu rt"
-------------
Diffstat:
Documentation/x86/x86_64/mm.txt | 24 ++-
Makefile | 4 +-
arch/arm64/kvm/hyp/debug-sr.c | 3 +
arch/parisc/boot/compressed/misc.c | 4 +-
arch/parisc/kernel/entry.S | 12 +-
arch/parisc/kernel/hpmc.S | 1 +
arch/powerpc/include/asm/mmu_context.h | 5 +-
arch/powerpc/kvm/book3s_xive.c | 7 +-
arch/powerpc/perf/core-book3s.c | 8 +-
arch/um/include/asm/mmu_context.h | 3 +-
arch/unicore32/include/asm/mmu_context.h | 5 +-
arch/x86/Kconfig | 3 +-
arch/x86/entry/entry_32.S | 12 +-
arch/x86/entry/entry_64.S | 4 +-
arch/x86/entry/vsyscall/vsyscall_64.c | 38 +++-
arch/x86/include/asm/cpu_entry_area.h | 68 +++++++
arch/x86/include/asm/desc.h | 1 +
arch/x86/include/asm/espfix.h | 7 +-
arch/x86/include/asm/fixmap.h | 71 +-------
arch/x86/include/asm/inat.h | 10 +
arch/x86/include/asm/invpcid.h | 53 ++++++
arch/x86/include/asm/mmu.h | 4 +-
arch/x86/include/asm/mmu_context.h | 54 ++----
arch/x86/include/asm/pgtable_32_types.h | 15 +-
arch/x86/include/asm/pgtable_64_types.h | 47 +++--
arch/x86/include/asm/processor.h | 6 +-
arch/x86/include/asm/stacktrace.h | 4 +-
arch/x86/include/asm/tlbflush.h | 136 +++++++-------
arch/x86/kernel/asm-offsets.c | 4 +-
arch/x86/kernel/asm-offsets_32.c | 2 +-
arch/x86/kernel/cpu/common.c | 100 +---------
arch/x86/kernel/cpu/microcode/intel.c | 13 --
arch/x86/kernel/dumpstack.c | 11 +-
arch/x86/kernel/dumpstack_32.c | 6 +-
arch/x86/kernel/dumpstack_64.c | 12 +-
arch/x86/kernel/ldt.c | 47 ++---
arch/x86/kernel/smpboot.c | 6 +-
arch/x86/kernel/traps.c | 6 +-
arch/x86/kvm/emulate.c | 32 +++-
arch/x86/kvm/mmu.c | 8 +-
arch/x86/kvm/x86.c | 2 +-
arch/x86/lib/x86-opcode-map.txt | 13 +-
arch/x86/mm/Makefile | 2 +-
arch/x86/mm/cpu_entry_area.c | 139 ++++++++++++++
arch/x86/mm/dump_pagetables.c | 98 ++++++----
arch/x86/mm/init_32.c | 6 +
arch/x86/mm/kasan_init_64.c | 29 +--
arch/x86/mm/pgtable_32.c | 1 +
arch/x86/mm/tlb.c | 10 +-
arch/x86/platform/uv/tlb_uv.c | 2 +-
arch/x86/xen/mmu_pv.c | 2 -
block/bio.c | 2 +
block/blk-throttle.c | 8 +-
crypto/af_alg.c | 6 -
crypto/algif_aead.c | 16 +-
crypto/algif_skcipher.c | 16 +-
crypto/mcryptd.c | 23 +--
crypto/skcipher.c | 10 +-
drivers/acpi/apei/erst.c | 2 +-
drivers/acpi/nfit/core.c | 9 +-
drivers/char/ipmi/ipmi_si_intf.c | 1 -
drivers/clk/sunxi/clk-sun9i-mmc.c | 12 ++
drivers/gpu/drm/i915/i915_gem.c | 9 +-
drivers/gpu/drm/sun4i/sun4i_tcon.c | 4 +-
drivers/mfd/cros_ec_spi.c | 1 +
drivers/mfd/twl4030-audio.c | 9 +-
drivers/mfd/twl6040.c | 12 +-
drivers/net/ethernet/marvell/mvneta.c | 8 +-
drivers/nvdimm/btt.c | 201 +++++++++++++++++----
drivers/nvdimm/btt.h | 45 ++++-
drivers/nvdimm/pfn_devs.c | 20 +-
drivers/parisc/lba_pci.c | 33 ++++
drivers/pci/pci-driver.c | 7 +-
drivers/pinctrl/intel/pinctrl-cherryview.c | 16 ++
drivers/spi/spi-armada-3700.c | 8 +
drivers/spi/spi-xilinx.c | 11 ++
include/asm-generic/mm_hooks.h | 5 +-
include/asm-generic/pgtable.h | 5 +
include/crypto/mcryptd.h | 1 +
include/linux/bio.h | 2 +
include/linux/blk_types.h | 9 +-
include/linux/blkdev.h | 2 +-
init/main.c | 6 +-
kernel/fork.c | 3 +-
net/ipv6/route.c | 58 +++---
sound/core/rawmidi.c | 15 +-
sound/pci/hda/patch_hdmi.c | 6 +-
sound/pci/hda/patch_realtek.c | 35 +++-
sound/usb/mixer.c | 27 +--
sound/usb/quirks.c | 7 +-
tools/objtool/.gitignore | 2 +-
tools/objtool/Makefile | 30 +--
tools/objtool/arch/x86/Build | 10 +-
tools/objtool/arch/x86/decode.c | 6 +-
.../objtool/arch/x86/{insn => include/asm}/inat.h | 12 +-
.../arch/x86/{insn => include/asm}/inat_types.h | 0
.../objtool/arch/x86/{insn => include/asm}/insn.h | 2 +-
.../objtool/{ => arch/x86/include/asm}/orc_types.h | 0
tools/objtool/arch/x86/{insn => lib}/inat.c | 2 +-
tools/objtool/arch/x86/{insn => lib}/insn.c | 4 +-
.../arch/x86/{insn => lib}/x86-opcode-map.txt | 15 +-
.../arch/x86/{insn => tools}/gen-insn-attr-x86.awk | 0
tools/objtool/orc.h | 2 +-
tools/objtool/orc_dump.c | 7 +-
tools/objtool/sync-check.sh | 29 +++
.../perf/util/intel-pt-decoder/x86-opcode-map.txt | 15 +-
tools/testing/selftests/x86/ldt_gdt.c | 9 +-
virt/kvm/arm/mmu.c | 10 +-
108 files changed, 1292 insertions(+), 693 deletions(-)
7 years, 8 months
- 4
- 78
[Linux-stable-mirror] [PATCH 1/2] Revert "Bluetooth: btusb: fix QCA Rome suspend/resume"
by Kai-Heng Feng
This reverts commit fd865802c66bc451dc515ed89360f84376ce1a56.
This commit causes a regression on some QCA ROME chips. The USB device
reset happens in btusb_open(), hence firmware loading gets interrupted.
Furthermore, this commit stops working after commit
("a0085f2510e8976614ad8f766b209448b385492f Bluetooth: btusb: driver to
enable the usb-wakeup feature"). Reset-resume quirk only gets enabled in
btusb_suspend() when it's not a wakeup source.
If we really want to reset the USB device, we need to do it before
btusb_open(). Let's handle it in drivers/usb/core/quirks.c.
Cc: stable(a)vger.kernel.org
Cc: Leif Liddy <leif.linux(a)gmail.com>
Cc: Matthias Kaehlcke <mka(a)chromium.org>
Cc: Brian Norris <briannorris(a)chromium.org>
Cc: Daniel Drake <drake(a)endlessm.com>
Signed-off-by: Kai-Heng Feng <kai.heng.feng(a)canonical.com>
---
Daniel, Cc you because this also affects your original quirk patch for
Realtek btusb.
drivers/bluetooth/btusb.c | 6 ------
1 file changed, 6 deletions(-)
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index f7120c9eb9bd..da353c4acdc7 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -3117,12 +3117,6 @@ static int btusb_probe(struct usb_interface *intf,
if (id->driver_info & BTUSB_QCA_ROME) {
data->setup_on_usb = btusb_setup_qca;
hdev->set_bdaddr = btusb_set_bdaddr_ath3012;
-
- /* QCA Rome devices lose their updated firmware over suspend,
- * but the USB hub doesn't notice any status change.
- * Explicitly request a device reset on resume.
- */
- set_bit(BTUSB_RESET_RESUME, &data->flags);
}
#ifdef CONFIG_BT_HCIBTUSB_RTL
--
2.14.1
7 years, 8 months
- 7
- 10
[Linux-stable-mirror] Patch "mm/vmstat: Make NR_TLB_REMOTE_FLUSH_RECEIVED available even on UP" has been added to the 4.9-stable tree
by gregkh＠linuxfoundation.org
This is a note to let you know that I've just added the patch titled
mm/vmstat: Make NR_TLB_REMOTE_FLUSH_RECEIVED available even on UP
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
mm-vmstat-make-nr_tlb_remote_flush_received-available-even-on-up.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From 5dd0b16cdaff9b94da06074d5888b03235c0bf17 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto(a)kernel.org>
Date: Mon, 5 Jun 2017 07:40:25 -0700
Subject: mm/vmstat: Make NR_TLB_REMOTE_FLUSH_RECEIVED available even on UP
From: Andy Lutomirski <luto(a)kernel.org>
commit 5dd0b16cdaff9b94da06074d5888b03235c0bf17 upstream.
This fixes CONFIG_SMP=n, CONFIG_DEBUG_TLBFLUSH=y without introducing
further #ifdef soup. Caught by a Kbuild bot randconfig build.
Signed-off-by: Andy Lutomirski <luto(a)kernel.org>
Cc: Borislav Petkov <bp(a)alien8.de>
Cc: Linus Torvalds <torvalds(a)linux-foundation.org>
Cc: Peter Zijlstra <peterz(a)infradead.org>
Cc: Thomas Gleixner <tglx(a)linutronix.de>
Fixes: ce4a4e565f52 ("x86/mm: Remove the UP asm/tlbflush.h code, always use the (formerly) SMP code")
Link: http://lkml.kernel.org/r/76da9a3cc4415996f2ad2c905b93414add322021.149667361…
Signed-off-by: Ingo Molnar <mingo(a)kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
include/linux/vm_event_item.h | 2 --
1 file changed, 2 deletions(-)
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -89,10 +89,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PS
#endif
#endif
#ifdef CONFIG_DEBUG_TLBFLUSH
-#ifdef CONFIG_SMP
NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */
NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
-#endif /* CONFIG_SMP */
NR_TLB_LOCAL_FLUSH_ALL,
NR_TLB_LOCAL_FLUSH_ONE,
#endif /* CONFIG_DEBUG_TLBFLUSH */
Patches currently in stable-queue which might be from luto(a)kernel.org are
queue-4.9/x86-vm86-32-switch-to-flush_tlb_mm_range-in-mark_screen_rdonly.patch
queue-4.9/x86-mm-add-the-nopcid-boot-option-to-turn-off-pcid.patch
queue-4.9/x86-mm-enable-cr4.pcide-on-supported-systems.patch
queue-4.9/mm-vmstat-make-nr_tlb_remote_flush_received-available-even-on-up.patch
queue-4.9/x86-smpboot-remove-stale-tlb-flush-invocations.patch
queue-4.9/x86-mm-remove-the-up-asm-tlbflush.h-code-always-use-the-formerly-smp-code.patch
queue-4.9/x86-mm-reimplement-flush_tlb_page-using-flush_tlb_mm_range.patch
queue-4.9/x86-mm-make-flush_tlb_mm_range-more-predictable.patch
queue-4.9/x86-mm-remove-flush_tlb-and-flush_tlb_current_task.patch
queue-4.9/x86-mm-disable-pcid-on-32-bit-kernels.patch
queue-4.9/x86-mm-64-fix-reboot-interaction-with-cr4.pcide.patch
7 years, 8 months
- 1
- 0