linux-stable.git/Documentation/admin-guide, branch v6.6.37

cpu: Ignore "mitigations" kernel parameter if CPU_MITIGATIONS=n

2024-06-12T09:11:24+00:00

[ Upstream commit ce0abef6a1d540acef85068e0e82bdf1fbeeb0e9 ]

Explicitly disallow enabling mitigations at runtime for kernels that were
built with CONFIG_CPU_MITIGATIONS=n, as some architectures may omit code
entirely if mitigations are disabled at compile time.

E.g. on x86, a large pile of Kconfigs are buried behind CPU_MITIGATIONS,
and trying to provide sane behavior for retroactively enabling mitigations
is extremely difficult, bordering on impossible.  E.g. page table isolation
and call depth tracking require build-time support, BHI mitigations will
still be off without additional kernel parameters, etc.

  [ bp: Touchups. ]

Signed-off-by: Sean Christopherson 
Signed-off-by: Borislav Petkov (AMD) 
Acked-by: Borislav Petkov (AMD) 
Link: https://lore.kernel.org/r/20240420000556.2645001-3-seanjc@google.com
Signed-off-by: Sasha Levin

Docs/admin-guide/mm/damon/usage: fix wrong example of DAMOS filter matching sysfs file

2024-05-25T14:22:55+00:00

commit da2a061888883e067e8e649d086df35c92c760a7 upstream.

The example usage of DAMOS filter sysfs files, specifically the part of
'matching' file writing for memcg type filter, is wrong.  The intention is
to exclude pages of a memcg that already getting enough care from a given
scheme, but the example is setting the filter to apply the scheme to only
the pages of the memcg.  Fix it.

Link: https://lkml.kernel.org/r/20240503180318.72798-7-sj@kernel.org
Fixes: 9b7f9322a530 ("Docs/admin-guide/mm/damon/usage: document DAMOS filters of sysfs")
Closes: https://lore.kernel.org/r/20240317191358.97578-1-sj@kernel.org
Signed-off-by: SeongJae Park 
Cc: 	[6.3.x]
Cc: Jonathan Corbet 
Cc: Shuah Khan 
Signed-off-by: Andrew Morton 
Signed-off-by: Greg Kroah-Hartman

admin-guide/hw-vuln/core-scheduling: fix return type of PR_SCHED_CORE_GET

2024-05-25T14:22:55+00:00

commit 8af2d1ab78f2342f8c4c3740ca02d86f0ebfac5a upstream.

sched_core_share_pid() copies the cookie to userspace with
put_user(id, (u64 __user *)uaddr), expecting 64 bits of space.
The "unsigned long" datatype that is documented in core-scheduling.rst
however is only 32 bits large on 32 bit architectures.

Document "unsigned long long" as the correct data type that is always
64bits large.

This matches what the selftest cs_prctl_test.c has been doing all along.

Fixes: 0159bb020ca9 ("Documentation: Add usecases, design and interface for core scheduling")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/util-linux/df7a25a0-7923-4f8b-a527-5e6f0064074d@t-8ch.de/
Signed-off-by: Thomas Weißschuh 
Reviewed-by: Chris Hyser 
Signed-off-by: Jonathan Corbet 
Link: https://lore.kernel.org/r/20240423-core-scheduling-cookie-v1-1-5753a35f8dfc@weissschuh.net
Signed-off-by: Greg Kroah-Hartman

mm, treewide: introduce NR_PAGE_ORDERS

2024-05-02T14:32:41+00:00

[ Upstream commit fd37721803c6e73619108f76ad2e12a9aa5fafaf ]

NR_PAGE_ORDERS defines the number of page orders supported by the page
allocator, ranging from 0 to MAX_ORDER, MAX_ORDER + 1 in total.

NR_PAGE_ORDERS assists in defining arrays of page orders and allows for
more natural iteration over them.

[kirill.shutemov@linux.intel.com: fixup for kerneldoc warning]
  Link: https://lkml.kernel.org/r/20240101111512.7empzyifq7kxtzk3@box
Link: https://lkml.kernel.org/r/20231228144704.14033-1-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov 
Reviewed-by: Zi Yan 
Cc: Linus Torvalds 
Signed-off-by: Andrew Morton 
Stable-dep-of: b6976f323a86 ("drm/ttm: stop pooling cached NUMA pages v2")
Signed-off-by: Sasha Levin

net: make SK_MEMORY_PCPU_RESERV tunable

2024-05-02T14:32:36+00:00

[ Upstream commit 12a686c2e761f1f1f6e6e2117a9ab9c6de2ac8a7 ]

This patch adds /proc/sys/net/core/mem_pcpu_rsv sysctl file,
to make SK_MEMORY_PCPU_RESERV tunable.

Commit 3cd3399dd7a8 ("net: implement per-cpu reserves for
memory_allocated") introduced per-cpu forward alloc cache:

"Implement a per-cpu cache of +1/-1 MB, to reduce number
of changes to sk->sk_prot->memory_allocated, which
would otherwise be cause of false sharing."

sk_prot->memory_allocated points to global atomic variable:
atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp;

If increasing the per-cpu cache size from 1MB to e.g. 16MB,
changes to sk->sk_prot->memory_allocated can be further reduced.
Performance may be improved on system with many cores.

Signed-off-by: Adam Li 
Reviewed-by: Christoph Lameter (Ampere) 
Signed-off-by: David S. Miller 
Stable-dep-of: 3584718cf2ec ("net: fix sk_memory_allocated_{add|sub} vs softirqs")
Signed-off-by: Sasha Levin

usb: new quirk to reduce the SET_ADDRESS request timeout

2024-04-27T15:11:36+00:00

[ Upstream commit 5a1ccf0c72cf917ff3ccc131d1bb8d19338ffe52 ]

This patch introduces a new USB quirk,
USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT, which modifies the timeout value
for the SET_ADDRESS request. The standard timeout for USB request/command
is 5000 ms, as recommended in the USB 3.2 specification (section 9.2.6.1).

However, certain scenarios, such as connecting devices through an APTIV
hub, can lead to timeout errors when the device enumerates as full speed
initially and later switches to high speed during chirp negotiation.

In such cases, USB analyzer logs reveal that the bus suspends for
5 seconds due to incorrect chirp parsing and resumes only after two
consecutive timeout errors trigger a hub driver reset.

Packet(54) Dir(?) Full Speed J(997.100 us) Idle(  2.850 us)
_______| Time Stamp(28 . 105 910 682)
_______|_____________________________________________________________Ch0
Packet(55) Dir(?) Full Speed J(997.118 us) Idle(  2.850 us)
_______| Time Stamp(28 . 106 910 632)
_______|_____________________________________________________________Ch0
Packet(56) Dir(?) Full Speed J(399.650 us) Idle(222.582 us)
_______| Time Stamp(28 . 107 910 600)
_______|_____________________________________________________________Ch0
Packet(57) Dir Chirp J( 23.955 ms) Idle(115.169 ms)
_______| Time Stamp(28 . 108 532 832)
_______|_____________________________________________________________Ch0
Packet(58) Dir(?) Full Speed J (Suspend)( 5.347 sec) Idle(  5.366 us)
_______| Time Stamp(28 . 247 657 600)
_______|_____________________________________________________________Ch0

This 5-second delay in device enumeration is undesirable, particularly
in automotive applications where quick enumeration is crucial
(ideally within 3 seconds).

The newly introduced quirks provide the flexibility to align with a
3-second time limit, as required in specific contexts like automotive
applications.

By reducing the SET_ADDRESS request timeout to 500 ms, the
system can respond more swiftly to errors, initiate rapid recovery, and
ensure efficient device enumeration. This change is vital for scenarios
where rapid smartphone enumeration and screen projection are essential.

To use the quirk, please write "vendor_id:product_id:p" to
/sys/bus/usb/drivers/hub/module/parameter/quirks

For example,
echo "0x2c48:0x0132:p" > /sys/bus/usb/drivers/hub/module/parameters/quirks"

Signed-off-by: Hardik Gajjar 
Reviewed-by: Alan Stern 
Link: https://lore.kernel.org/r/20231027152029.104363-2-hgajjar@de.adit-jv.com
Signed-off-by: Greg Kroah-Hartman 
Signed-off-by: Sasha Levin

x86/bugs: Remove CONFIG_BHI_MITIGATION_AUTO and spectre_bhi=auto

2024-04-17T09:19:37+00:00

commit 36d4fe147c870f6d3f6602befd7ef44393a1c87a upstream.

Unlike most other mitigations' "auto" options, spectre_bhi=auto only
mitigates newer systems, which is confusing and not particularly useful.

Remove it.

Signed-off-by: Josh Poimboeuf 
Signed-off-by: Ingo Molnar 
Reviewed-by: Nikolay Borisov 
Cc: Sean Christopherson 
Cc: Linus Torvalds 
Link: https://lore.kernel.org/r/412e9dc87971b622bbbaf64740ebc1f140bff343.1712813475.git.jpoimboe@kernel.org
Signed-off-by: Greg Kroah-Hartman

x86/bugs: Clarify that syscall hardening isn't a BHI mitigation

2024-04-17T09:19:37+00:00

commit 5f882f3b0a8bf0788d5a0ee44b1191de5319bb8a upstream.

While syscall hardening helps prevent some BHI attacks, there's still
other low-hanging fruit remaining.  Don't classify it as a mitigation
and make it clear that the system may still be vulnerable if it doesn't
have a HW or SW mitigation enabled.

Fixes: ec9404e40e8f ("x86/bhi: Add BHI mitigation knob")
Signed-off-by: Josh Poimboeuf 
Signed-off-by: Ingo Molnar 
Cc: Linus Torvalds 
Cc: Sean Christopherson 
Link: https://lore.kernel.org/r/b5951dae3fdee7f1520d5136a27be3bdfe95f88b.1712813475.git.jpoimboe@kernel.org
Signed-off-by: Greg Kroah-Hartman

x86/bugs: Fix BHI documentation

2024-04-17T09:19:36+00:00

commit dfe648903f42296866d79f10d03f8c85c9dfba30 upstream.

Fix up some inaccuracies in the BHI documentation.

Fixes: ec9404e40e8f ("x86/bhi: Add BHI mitigation knob")
Signed-off-by: Josh Poimboeuf 
Signed-off-by: Ingo Molnar 
Reviewed-by: Nikolay Borisov 
Cc: Linus Torvalds 
Cc: Sean Christopherson 
Link: https://lore.kernel.org/r/8c84f7451bfe0dd08543c6082a383f390d4aa7e2.1712813475.git.jpoimboe@kernel.org
Signed-off-by: Greg Kroah-Hartman

x86/bhi: Mitigate KVM by default

2024-04-10T14:36:08+00:00

commit 95a6ccbdc7199a14b71ad8901cb788ba7fb5167b upstream.

BHI mitigation mode spectre_bhi=auto does not deploy the software
mitigation by default. In a cloud environment, it is a likely scenario
where userspace is trusted but the guests are not trusted. Deploying
system wide mitigation in such cases is not desirable.

Update the auto mode to unconditionally mitigate against malicious
guests. Deploy the software sequence at VMexit in auto mode also, when
hardware mitigation is not available. Unlike the force =on mode,
software sequence is not deployed at syscalls in auto mode.

Suggested-by: Alexandre Chartre 
Signed-off-by: Pawan Gupta 
Signed-off-by: Daniel Sneddon 
Signed-off-by: Thomas Gleixner 
Reviewed-by: Alexandre Chartre 
Reviewed-by: Josh Poimboeuf 
Signed-off-by: Daniel Sneddon 
Signed-off-by: Greg Kroah-Hartman