Merge branch 'bpf/for-next' into sched_ext-base
This commit is contained in:
@@ -337,10 +337,11 @@ Kalyan Thota <quic_kalyant@quicinc.com> <kalyan_t@codeaurora.org>
|
||||
Karthikeyan Periyasamy <quic_periyasa@quicinc.com> <periyasa@codeaurora.org>
|
||||
Kathiravan T <quic_kathirav@quicinc.com> <kathirav@codeaurora.org>
|
||||
Kay Sievers <kay.sievers@vrfy.org>
|
||||
Kees Cook <keescook@chromium.org> <kees.cook@canonical.com>
|
||||
Kees Cook <keescook@chromium.org> <keescook@google.com>
|
||||
Kees Cook <keescook@chromium.org> <kees@outflux.net>
|
||||
Kees Cook <keescook@chromium.org> <kees@ubuntu.com>
|
||||
Kees Cook <kees@kernel.org> <kees.cook@canonical.com>
|
||||
Kees Cook <kees@kernel.org> <keescook@chromium.org>
|
||||
Kees Cook <kees@kernel.org> <keescook@google.com>
|
||||
Kees Cook <kees@kernel.org> <kees@outflux.net>
|
||||
Kees Cook <kees@kernel.org> <kees@ubuntu.com>
|
||||
Keith Busch <kbusch@kernel.org> <keith.busch@intel.com>
|
||||
Keith Busch <kbusch@kernel.org> <keith.busch@linux.intel.com>
|
||||
Kenneth W Chen <kenneth.w.chen@intel.com>
|
||||
|
||||
@@ -9,8 +9,8 @@ TOMOYO is a name-based MAC extension (LSM module) for the Linux kernel.
|
||||
|
||||
LiveCD-based tutorials are available at
|
||||
|
||||
http://tomoyo.sourceforge.jp/1.8/ubuntu12.04-live.html
|
||||
http://tomoyo.sourceforge.jp/1.8/centos6-live.html
|
||||
https://tomoyo.sourceforge.net/1.8/ubuntu12.04-live.html
|
||||
https://tomoyo.sourceforge.net/1.8/centos6-live.html
|
||||
|
||||
Though these tutorials use non-LSM version of TOMOYO, they are useful for you
|
||||
to know what TOMOYO is.
|
||||
@@ -21,45 +21,32 @@ How to enable TOMOYO?
|
||||
Build the kernel with ``CONFIG_SECURITY_TOMOYO=y`` and pass ``security=tomoyo`` on
|
||||
kernel's command line.
|
||||
|
||||
Please see http://tomoyo.osdn.jp/2.5/ for details.
|
||||
Please see https://tomoyo.sourceforge.net/2.6/ for details.
|
||||
|
||||
Where is documentation?
|
||||
=======================
|
||||
|
||||
User <-> Kernel interface documentation is available at
|
||||
https://tomoyo.osdn.jp/2.5/policy-specification/index.html .
|
||||
https://tomoyo.sourceforge.net/2.6/policy-specification/index.html .
|
||||
|
||||
Materials we prepared for seminars and symposiums are available at
|
||||
https://osdn.jp/projects/tomoyo/docs/?category_id=532&language_id=1 .
|
||||
https://sourceforge.net/projects/tomoyo/files/docs/ .
|
||||
Below lists are chosen from three aspects.
|
||||
|
||||
What is TOMOYO?
|
||||
TOMOYO Linux Overview
|
||||
https://osdn.jp/projects/tomoyo/docs/lca2009-takeda.pdf
|
||||
https://sourceforge.net/projects/tomoyo/files/docs/lca2009-takeda.pdf
|
||||
TOMOYO Linux: pragmatic and manageable security for Linux
|
||||
https://osdn.jp/projects/tomoyo/docs/freedomhectaipei-tomoyo.pdf
|
||||
https://sourceforge.net/projects/tomoyo/files/docs/freedomhectaipei-tomoyo.pdf
|
||||
TOMOYO Linux: A Practical Method to Understand and Protect Your Own Linux Box
|
||||
https://osdn.jp/projects/tomoyo/docs/PacSec2007-en-no-demo.pdf
|
||||
https://sourceforge.net/projects/tomoyo/files/docs/PacSec2007-en-no-demo.pdf
|
||||
|
||||
What can TOMOYO do?
|
||||
Deep inside TOMOYO Linux
|
||||
https://osdn.jp/projects/tomoyo/docs/lca2009-kumaneko.pdf
|
||||
https://sourceforge.net/projects/tomoyo/files/docs/lca2009-kumaneko.pdf
|
||||
The role of "pathname based access control" in security.
|
||||
https://osdn.jp/projects/tomoyo/docs/lfj2008-bof.pdf
|
||||
https://sourceforge.net/projects/tomoyo/files/docs/lfj2008-bof.pdf
|
||||
|
||||
History of TOMOYO?
|
||||
Realities of Mainlining
|
||||
https://osdn.jp/projects/tomoyo/docs/lfj2008.pdf
|
||||
|
||||
What is future plan?
|
||||
====================
|
||||
|
||||
We believe that inode based security and name based security are complementary
|
||||
and both should be used together. But unfortunately, so far, we cannot enable
|
||||
multiple LSM modules at the same time. We feel sorry that you have to give up
|
||||
SELinux/SMACK/AppArmor etc. when you want to use TOMOYO.
|
||||
|
||||
We hope that LSM becomes stackable in future. Meanwhile, you can use non-LSM
|
||||
version of TOMOYO, available at http://tomoyo.osdn.jp/1.8/ .
|
||||
LSM version of TOMOYO is a subset of non-LSM version of TOMOYO. We are planning
|
||||
to port non-LSM version's functionalities to LSM versions.
|
||||
https://sourceforge.net/projects/tomoyo/files/docs/lfj2008.pdf
|
||||
|
||||
@@ -1921,6 +1921,28 @@
|
||||
Format:
|
||||
<bus_id>,<clkrate>
|
||||
|
||||
i2c_touchscreen_props= [HW,ACPI,X86]
|
||||
Set device-properties for ACPI-enumerated I2C-attached
|
||||
touchscreen, to e.g. fix coordinates of upside-down
|
||||
mounted touchscreens. If you need this option please
|
||||
submit a drivers/platform/x86/touchscreen_dmi.c patch
|
||||
adding a DMI quirk for this.
|
||||
|
||||
Format:
|
||||
<ACPI_HW_ID>:<prop_name>=<val>[:prop_name=val][:...]
|
||||
Where <val> is one of:
|
||||
Omit "=<val>" entirely Set a boolean device-property
|
||||
Unsigned number Set a u32 device-property
|
||||
Anything else Set a string device-property
|
||||
|
||||
Examples (split over multiple lines):
|
||||
i2c_touchscreen_props=GDIX1001:touchscreen-inverted-x:
|
||||
touchscreen-inverted-y
|
||||
|
||||
i2c_touchscreen_props=MSSL1680:touchscreen-size-x=1920:
|
||||
touchscreen-size-y=1080:touchscreen-inverted-y:
|
||||
firmware-name=gsl1680-vendor-model.fw:silead,home-button
|
||||
|
||||
i8042.debug [HW] Toggle i8042 debug mode
|
||||
i8042.unmask_kbd_data
|
||||
[HW] Enable printing of interrupt data from the KBD port
|
||||
|
||||
@@ -65,4 +65,6 @@ the extension, or may have deliberately removed it from the listing.
|
||||
Misaligned accesses
|
||||
-------------------
|
||||
|
||||
Misaligned accesses are supported in userspace, but they may perform poorly.
|
||||
Misaligned scalar accesses are supported in userspace, but they may perform
|
||||
poorly. Misaligned vector accesses are only supported if the Zicclsm extension
|
||||
is supported.
|
||||
|
||||
@@ -219,6 +219,14 @@ compilation and skeleton generation. Using Libbpf-rs will make building user
|
||||
space part of the BPF application easier. Note that the BPF program themselves
|
||||
must still be written in plain C.
|
||||
|
||||
libbpf logging
|
||||
==============
|
||||
|
||||
By default, libbpf logs informational and warning messages to stderr. The
|
||||
verbosity of these messages can be controlled by setting the environment
|
||||
variable LIBBPF_LOG_LEVEL to either warn, info, or debug. A custom log
|
||||
callback can be set using ``libbpf_set_print()``.
|
||||
|
||||
Additional Documentation
|
||||
========================
|
||||
|
||||
|
||||
@@ -23,3 +23,6 @@ The BPF calling convention is defined as:
|
||||
|
||||
R0 - R5 are scratch registers and BPF programs needs to spill/fill them if
|
||||
necessary across calls.
|
||||
|
||||
The BPF program needs to store the return value into register R0 before doing an
|
||||
``EXIT``.
|
||||
|
||||
@@ -14,6 +14,13 @@ set architecture (ISA).
|
||||
Documentation conventions
|
||||
=========================
|
||||
|
||||
The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
|
||||
"SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and
|
||||
"OPTIONAL" in this document are to be interpreted as described in
|
||||
BCP 14 `<https://www.rfc-editor.org/info/rfc2119>`_
|
||||
`RFC8174 <https://www.rfc-editor.org/info/rfc8174>`_
|
||||
when, and only when, they appear in all capitals, as shown here.
|
||||
|
||||
For brevity and consistency, this document refers to families
|
||||
of types using a shorthand syntax and refers to several expository,
|
||||
mnemonic functions when describing the semantics of instructions.
|
||||
@@ -25,7 +32,7 @@ Types
|
||||
This document refers to integer types with the notation `SN` to specify
|
||||
a type's signedness (`S`) and bit width (`N`), respectively.
|
||||
|
||||
.. table:: Meaning of signedness notation.
|
||||
.. table:: Meaning of signedness notation
|
||||
|
||||
==== =========
|
||||
S Meaning
|
||||
@@ -34,7 +41,7 @@ a type's signedness (`S`) and bit width (`N`), respectively.
|
||||
s signed
|
||||
==== =========
|
||||
|
||||
.. table:: Meaning of bit-width notation.
|
||||
.. table:: Meaning of bit-width notation
|
||||
|
||||
===== =========
|
||||
N Bit width
|
||||
@@ -106,9 +113,9 @@ Conformance groups
|
||||
|
||||
An implementation does not need to support all instructions specified in this
|
||||
document (e.g., deprecated instructions). Instead, a number of conformance
|
||||
groups are specified. An implementation must support the base32 conformance
|
||||
group and may support additional conformance groups, where supporting a
|
||||
conformance group means it must support all instructions in that conformance
|
||||
groups are specified. An implementation MUST support the base32 conformance
|
||||
group and MAY support additional conformance groups, where supporting a
|
||||
conformance group means it MUST support all instructions in that conformance
|
||||
group.
|
||||
|
||||
The use of named conformance groups enables interoperability between a runtime
|
||||
@@ -209,7 +216,7 @@ For example::
|
||||
07 1 0 00 00 11 22 33 44 r1 += 0x11223344 // big
|
||||
|
||||
Note that most instructions do not use all of the fields.
|
||||
Unused fields shall be cleared to zero.
|
||||
Unused fields SHALL be cleared to zero.
|
||||
|
||||
Wide instruction encoding
|
||||
--------------------------
|
||||
@@ -256,18 +263,20 @@ Instruction classes
|
||||
|
||||
The three least significant bits of the 'opcode' field store the instruction class:
|
||||
|
||||
===== ===== =============================== ===================================
|
||||
class value description reference
|
||||
===== ===== =============================== ===================================
|
||||
LD 0x0 non-standard load operations `Load and store instructions`_
|
||||
LDX 0x1 load into register operations `Load and store instructions`_
|
||||
ST 0x2 store from immediate operations `Load and store instructions`_
|
||||
STX 0x3 store from register operations `Load and store instructions`_
|
||||
ALU 0x4 32-bit arithmetic operations `Arithmetic and jump instructions`_
|
||||
JMP 0x5 64-bit jump operations `Arithmetic and jump instructions`_
|
||||
JMP32 0x6 32-bit jump operations `Arithmetic and jump instructions`_
|
||||
ALU64 0x7 64-bit arithmetic operations `Arithmetic and jump instructions`_
|
||||
===== ===== =============================== ===================================
|
||||
.. table:: Instruction class
|
||||
|
||||
===== ===== =============================== ===================================
|
||||
class value description reference
|
||||
===== ===== =============================== ===================================
|
||||
LD 0x0 non-standard load operations `Load and store instructions`_
|
||||
LDX 0x1 load into register operations `Load and store instructions`_
|
||||
ST 0x2 store from immediate operations `Load and store instructions`_
|
||||
STX 0x3 store from register operations `Load and store instructions`_
|
||||
ALU 0x4 32-bit arithmetic operations `Arithmetic and jump instructions`_
|
||||
JMP 0x5 64-bit jump operations `Arithmetic and jump instructions`_
|
||||
JMP32 0x6 32-bit jump operations `Arithmetic and jump instructions`_
|
||||
ALU64 0x7 64-bit arithmetic operations `Arithmetic and jump instructions`_
|
||||
===== ===== =============================== ===================================
|
||||
|
||||
Arithmetic and jump instructions
|
||||
================================
|
||||
@@ -285,12 +294,14 @@ For arithmetic and jump instructions (``ALU``, ``ALU64``, ``JMP`` and
|
||||
**s (source)**
|
||||
the source operand location, which unless otherwise specified is one of:
|
||||
|
||||
====== ===== ==============================================
|
||||
source value description
|
||||
====== ===== ==============================================
|
||||
K 0 use 32-bit 'imm' value as source operand
|
||||
X 1 use 'src_reg' register value as source operand
|
||||
====== ===== ==============================================
|
||||
.. table:: Source operand location
|
||||
|
||||
====== ===== ==============================================
|
||||
source value description
|
||||
====== ===== ==============================================
|
||||
K 0 use 32-bit 'imm' value as source operand
|
||||
X 1 use 'src_reg' register value as source operand
|
||||
====== ===== ==============================================
|
||||
|
||||
**instruction class**
|
||||
the instruction class (see `Instruction classes`_)
|
||||
@@ -305,27 +316,29 @@ The 'code' field encodes the operation as below, where 'src' refers to the
|
||||
the source operand and 'dst' refers to the value of the destination
|
||||
register.
|
||||
|
||||
===== ===== ======= ==========================================================
|
||||
name code offset description
|
||||
===== ===== ======= ==========================================================
|
||||
ADD 0x0 0 dst += src
|
||||
SUB 0x1 0 dst -= src
|
||||
MUL 0x2 0 dst \*= src
|
||||
DIV 0x3 0 dst = (src != 0) ? (dst / src) : 0
|
||||
SDIV 0x3 1 dst = (src != 0) ? (dst s/ src) : 0
|
||||
OR 0x4 0 dst \|= src
|
||||
AND 0x5 0 dst &= src
|
||||
LSH 0x6 0 dst <<= (src & mask)
|
||||
RSH 0x7 0 dst >>= (src & mask)
|
||||
NEG 0x8 0 dst = -dst
|
||||
MOD 0x9 0 dst = (src != 0) ? (dst % src) : dst
|
||||
SMOD 0x9 1 dst = (src != 0) ? (dst s% src) : dst
|
||||
XOR 0xa 0 dst ^= src
|
||||
MOV 0xb 0 dst = src
|
||||
MOVSX 0xb 8/16/32 dst = (s8,s16,s32)src
|
||||
ARSH 0xc 0 :term:`sign extending<Sign Extend>` dst >>= (src & mask)
|
||||
END 0xd 0 byte swap operations (see `Byte swap instructions`_ below)
|
||||
===== ===== ======= ==========================================================
|
||||
.. table:: Arithmetic instructions
|
||||
|
||||
===== ===== ======= ==========================================================
|
||||
name code offset description
|
||||
===== ===== ======= ==========================================================
|
||||
ADD 0x0 0 dst += src
|
||||
SUB 0x1 0 dst -= src
|
||||
MUL 0x2 0 dst \*= src
|
||||
DIV 0x3 0 dst = (src != 0) ? (dst / src) : 0
|
||||
SDIV 0x3 1 dst = (src != 0) ? (dst s/ src) : 0
|
||||
OR 0x4 0 dst \|= src
|
||||
AND 0x5 0 dst &= src
|
||||
LSH 0x6 0 dst <<= (src & mask)
|
||||
RSH 0x7 0 dst >>= (src & mask)
|
||||
NEG 0x8 0 dst = -dst
|
||||
MOD 0x9 0 dst = (src != 0) ? (dst % src) : dst
|
||||
SMOD 0x9 1 dst = (src != 0) ? (dst s% src) : dst
|
||||
XOR 0xa 0 dst ^= src
|
||||
MOV 0xb 0 dst = src
|
||||
MOVSX 0xb 8/16/32 dst = (s8,s16,s32)src
|
||||
ARSH 0xc 0 :term:`sign extending<Sign Extend>` dst >>= (src & mask)
|
||||
END 0xd 0 byte swap operations (see `Byte swap instructions`_ below)
|
||||
===== ===== ======= ==========================================================
|
||||
|
||||
Underflow and overflow are allowed during arithmetic operations, meaning
|
||||
the 64-bit or 32-bit value will wrap. If BPF program execution would
|
||||
@@ -374,7 +387,7 @@ interpreted as a 64-bit signed value.
|
||||
Note that there are varying definitions of the signed modulo operation
|
||||
when the dividend or divisor are negative, where implementations often
|
||||
vary by language such that Python, Ruby, etc. differ from C, Go, Java,
|
||||
etc. This specification requires that signed modulo use truncated division
|
||||
etc. This specification requires that signed modulo MUST use truncated division
|
||||
(where -13 % 3 == -1) as implemented in C, Go, etc.::
|
||||
|
||||
a % n = a - n * trunc(a / n)
|
||||
@@ -386,6 +399,19 @@ The ``MOVSX`` instruction does a move operation with sign extension.
|
||||
operands into 64-bit operands. Unlike other arithmetic instructions,
|
||||
``MOVSX`` is only defined for register source operands (``X``).
|
||||
|
||||
``{MOV, K, ALU64}`` means::
|
||||
|
||||
dst = (s64)imm
|
||||
|
||||
``{MOV, X, ALU}`` means::
|
||||
|
||||
dst = (u32)src
|
||||
|
||||
``{MOVSX, X, ALU}`` with 'offset' 8 means::
|
||||
|
||||
dst = (u32)(s32)(s8)src
|
||||
|
||||
|
||||
The ``NEG`` instruction is only defined when the source bit is clear
|
||||
(``K``).
|
||||
|
||||
@@ -404,15 +430,17 @@ only and do not use a separate source register or immediate value.
|
||||
For ``ALU``, the 1-bit source operand field in the opcode is used to
|
||||
select what byte order the operation converts from or to. For
|
||||
``ALU64``, the 1-bit source operand field in the opcode is reserved
|
||||
and must be set to 0.
|
||||
and MUST be set to 0.
|
||||
|
||||
===== ======== ===== =================================================
|
||||
class source value description
|
||||
===== ======== ===== =================================================
|
||||
ALU TO_LE 0 convert between host byte order and little endian
|
||||
ALU TO_BE 1 convert between host byte order and big endian
|
||||
ALU64 Reserved 0 do byte swap unconditionally
|
||||
===== ======== ===== =================================================
|
||||
.. table:: Byte swap instructions
|
||||
|
||||
===== ======== ===== =================================================
|
||||
class source value description
|
||||
===== ======== ===== =================================================
|
||||
ALU TO_LE 0 convert between host byte order and little endian
|
||||
ALU TO_BE 1 convert between host byte order and big endian
|
||||
ALU64 Reserved 0 do byte swap unconditionally
|
||||
===== ======== ===== =================================================
|
||||
|
||||
The 'imm' field encodes the width of the swap operations. The following widths
|
||||
are supported: 16, 32 and 64. Width 64 operations belong to the base64
|
||||
@@ -448,27 +476,29 @@ otherwise identical operations, and indicates the base64 conformance
|
||||
group unless otherwise specified.
|
||||
The 'code' field encodes the operation as below:
|
||||
|
||||
======== ===== ======= ================================= ===================================================
|
||||
code value src_reg description notes
|
||||
======== ===== ======= ================================= ===================================================
|
||||
JA 0x0 0x0 PC += offset {JA, K, JMP} only
|
||||
JA 0x0 0x0 PC += imm {JA, K, JMP32} only
|
||||
JEQ 0x1 any PC += offset if dst == src
|
||||
JGT 0x2 any PC += offset if dst > src unsigned
|
||||
JGE 0x3 any PC += offset if dst >= src unsigned
|
||||
JSET 0x4 any PC += offset if dst & src
|
||||
JNE 0x5 any PC += offset if dst != src
|
||||
JSGT 0x6 any PC += offset if dst > src signed
|
||||
JSGE 0x7 any PC += offset if dst >= src signed
|
||||
CALL 0x8 0x0 call helper function by static ID {CALL, K, JMP} only, see `Helper functions`_
|
||||
CALL 0x8 0x1 call PC += imm {CALL, K, JMP} only, see `Program-local functions`_
|
||||
CALL 0x8 0x2 call helper function by BTF ID {CALL, K, JMP} only, see `Helper functions`_
|
||||
EXIT 0x9 0x0 return {CALL, K, JMP} only
|
||||
JLT 0xa any PC += offset if dst < src unsigned
|
||||
JLE 0xb any PC += offset if dst <= src unsigned
|
||||
JSLT 0xc any PC += offset if dst < src signed
|
||||
JSLE 0xd any PC += offset if dst <= src signed
|
||||
======== ===== ======= ================================= ===================================================
|
||||
.. table:: Jump instructions
|
||||
|
||||
======== ===== ======= ================================= ===================================================
|
||||
code value src_reg description notes
|
||||
======== ===== ======= ================================= ===================================================
|
||||
JA 0x0 0x0 PC += offset {JA, K, JMP} only
|
||||
JA 0x0 0x0 PC += imm {JA, K, JMP32} only
|
||||
JEQ 0x1 any PC += offset if dst == src
|
||||
JGT 0x2 any PC += offset if dst > src unsigned
|
||||
JGE 0x3 any PC += offset if dst >= src unsigned
|
||||
JSET 0x4 any PC += offset if dst & src
|
||||
JNE 0x5 any PC += offset if dst != src
|
||||
JSGT 0x6 any PC += offset if dst > src signed
|
||||
JSGE 0x7 any PC += offset if dst >= src signed
|
||||
CALL 0x8 0x0 call helper function by static ID {CALL, K, JMP} only, see `Helper functions`_
|
||||
CALL 0x8 0x1 call PC += imm {CALL, K, JMP} only, see `Program-local functions`_
|
||||
CALL 0x8 0x2 call helper function by BTF ID {CALL, K, JMP} only, see `Helper functions`_
|
||||
EXIT 0x9 0x0 return {CALL, K, JMP} only
|
||||
JLT 0xa any PC += offset if dst < src unsigned
|
||||
JLE 0xb any PC += offset if dst <= src unsigned
|
||||
JSLT 0xc any PC += offset if dst < src signed
|
||||
JSLE 0xd any PC += offset if dst <= src signed
|
||||
======== ===== ======= ================================= ===================================================
|
||||
|
||||
where 'PC' denotes the program counter, and the offset to increment by
|
||||
is in units of 64-bit instructions relative to the instruction following
|
||||
@@ -476,9 +506,6 @@ the jump instruction. Thus 'PC += 1' skips execution of the next
|
||||
instruction if it's a basic instruction or results in undefined behavior
|
||||
if the next instruction is a 128-bit wide instruction.
|
||||
|
||||
The BPF program needs to store the return value into register R0 before doing an
|
||||
``EXIT``.
|
||||
|
||||
Example:
|
||||
|
||||
``{JSGE, X, JMP32}`` means::
|
||||
@@ -487,6 +514,10 @@ Example:
|
||||
|
||||
where 's>=' indicates a signed '>=' comparison.
|
||||
|
||||
``{JLE, K, JMP}`` means::
|
||||
|
||||
if dst <= (u64)(s64)imm goto +offset
|
||||
|
||||
``{JA, K, JMP32}`` means::
|
||||
|
||||
gotol +imm
|
||||
@@ -515,14 +546,16 @@ for each program type, but static IDs are unique across all program types.
|
||||
|
||||
Platforms that support the BPF Type Format (BTF) support identifying
|
||||
a helper function by a BTF ID encoded in the 'imm' field, where the BTF ID
|
||||
identifies the helper name and type.
|
||||
identifies the helper name and type. Further documentation of BTF
|
||||
is outside the scope of this document and is left for future work.
|
||||
|
||||
Program-local functions
|
||||
~~~~~~~~~~~~~~~~~~~~~~~
|
||||
Program-local functions are functions exposed by the same BPF program as the
|
||||
caller, and are referenced by offset from the call instruction, similar to
|
||||
``JA``. The offset is encoded in the 'imm' field of the call instruction.
|
||||
An ``EXIT`` within the program-local function will return to the caller.
|
||||
caller, and are referenced by offset from the instruction following the call
|
||||
instruction, similar to ``JA``. The offset is encoded in the 'imm' field of
|
||||
the call instruction. An ``EXIT`` within the program-local function will
|
||||
return to the caller.
|
||||
|
||||
Load and store instructions
|
||||
===========================
|
||||
@@ -537,6 +570,8 @@ For load and store instructions (``LD``, ``LDX``, ``ST``, and ``STX``), the
|
||||
**mode**
|
||||
The mode modifier is one of:
|
||||
|
||||
.. table:: Mode modifier
|
||||
|
||||
============= ===== ==================================== =============
|
||||
mode modifier value description reference
|
||||
============= ===== ==================================== =============
|
||||
@@ -551,6 +586,8 @@ For load and store instructions (``LD``, ``LDX``, ``ST``, and ``STX``), the
|
||||
**sz (size)**
|
||||
The size modifier is one of:
|
||||
|
||||
.. table:: Size modifier
|
||||
|
||||
==== ===== =====================
|
||||
size value description
|
||||
==== ===== =====================
|
||||
@@ -619,14 +656,16 @@ The 'imm' field is used to encode the actual atomic operation.
|
||||
Simple atomic operation use a subset of the values defined to encode
|
||||
arithmetic operations in the 'imm' field to encode the atomic operation:
|
||||
|
||||
======== ===== ===========
|
||||
imm value description
|
||||
======== ===== ===========
|
||||
ADD 0x00 atomic add
|
||||
OR 0x40 atomic or
|
||||
AND 0x50 atomic and
|
||||
XOR 0xa0 atomic xor
|
||||
======== ===== ===========
|
||||
.. table:: Simple atomic operations
|
||||
|
||||
======== ===== ===========
|
||||
imm value description
|
||||
======== ===== ===========
|
||||
ADD 0x00 atomic add
|
||||
OR 0x40 atomic or
|
||||
AND 0x50 atomic and
|
||||
XOR 0xa0 atomic xor
|
||||
======== ===== ===========
|
||||
|
||||
|
||||
``{ATOMIC, W, STX}`` with 'imm' = ADD means::
|
||||
@@ -640,13 +679,15 @@ XOR 0xa0 atomic xor
|
||||
In addition to the simple atomic operations, there also is a modifier and
|
||||
two complex atomic operations:
|
||||
|
||||
=========== ================ ===========================
|
||||
imm value description
|
||||
=========== ================ ===========================
|
||||
FETCH 0x01 modifier: return old value
|
||||
XCHG 0xe0 | FETCH atomic exchange
|
||||
CMPXCHG 0xf0 | FETCH atomic compare and exchange
|
||||
=========== ================ ===========================
|
||||
.. table:: Complex atomic operations
|
||||
|
||||
=========== ================ ===========================
|
||||
imm value description
|
||||
=========== ================ ===========================
|
||||
FETCH 0x01 modifier: return old value
|
||||
XCHG 0xe0 | FETCH atomic exchange
|
||||
CMPXCHG 0xf0 | FETCH atomic compare and exchange
|
||||
=========== ================ ===========================
|
||||
|
||||
The ``FETCH`` modifier is optional for simple atomic operations, and
|
||||
always set for the complex atomic operations. If the ``FETCH`` flag
|
||||
@@ -673,17 +714,19 @@ The following table defines a set of ``{IMM, DW, LD}`` instructions
|
||||
with opcode subtypes in the 'src_reg' field, using new terms such as "map"
|
||||
defined further below:
|
||||
|
||||
======= ========================================= =========== ==============
|
||||
src_reg pseudocode imm type dst type
|
||||
======= ========================================= =========== ==============
|
||||
0x0 dst = (next_imm << 32) | imm integer integer
|
||||
0x1 dst = map_by_fd(imm) map fd map
|
||||
0x2 dst = map_val(map_by_fd(imm)) + next_imm map fd data address
|
||||
0x3 dst = var_addr(imm) variable id data address
|
||||
0x4 dst = code_addr(imm) integer code address
|
||||
0x5 dst = map_by_idx(imm) map index map
|
||||
0x6 dst = map_val(map_by_idx(imm)) + next_imm map index data address
|
||||
======= ========================================= =========== ==============
|
||||
.. table:: 64-bit immediate instructions
|
||||
|
||||
======= ========================================= =========== ==============
|
||||
src_reg pseudocode imm type dst type
|
||||
======= ========================================= =========== ==============
|
||||
0x0 dst = (next_imm << 32) | imm integer integer
|
||||
0x1 dst = map_by_fd(imm) map fd map
|
||||
0x2 dst = map_val(map_by_fd(imm)) + next_imm map fd data address
|
||||
0x3 dst = var_addr(imm) variable id data address
|
||||
0x4 dst = code_addr(imm) integer code address
|
||||
0x5 dst = map_by_idx(imm) map index map
|
||||
0x6 dst = map_val(map_by_idx(imm)) + next_imm map index data address
|
||||
======= ========================================= =========== ==============
|
||||
|
||||
where
|
||||
|
||||
@@ -725,5 +768,5 @@ carried over from classic BPF. These instructions used an instruction
|
||||
class of ``LD``, a size modifier of ``W``, ``H``, or ``B``, and a
|
||||
mode modifier of ``ABS`` or ``IND``. The 'dst_reg' and 'offset' fields were
|
||||
set to zero, and 'src_reg' was set to zero for ``ABS``. However, these
|
||||
instructions are deprecated and should no longer be used. All legacy packet
|
||||
instructions are deprecated and SHOULD no longer be used. All legacy packet
|
||||
access instructions belong to the "packet" conformance group.
|
||||
|
||||
@@ -192,7 +192,7 @@ alignment larger than PAGE_SIZE.
|
||||
|
||||
Dynamic swiotlb
|
||||
---------------
|
||||
When CONFIG_DYNAMIC_SWIOTLB is enabled, swiotlb can do on-demand expansion of
|
||||
When CONFIG_SWIOTLB_DYNAMIC is enabled, swiotlb can do on-demand expansion of
|
||||
the amount of memory available for allocation as bounce buffers. If a bounce
|
||||
buffer request fails due to lack of available space, an asynchronous background
|
||||
task is kicked off to allocate memory from general system memory and turn it
|
||||
|
||||
@@ -54,11 +54,10 @@ unevaluatedProperties: false
|
||||
|
||||
examples:
|
||||
- |
|
||||
mlahb: ahb@38000000 {
|
||||
ahb {
|
||||
compatible = "st,mlahb", "simple-bus";
|
||||
#address-cells = <1>;
|
||||
#size-cells = <1>;
|
||||
reg = <0x10000000 0x40000>;
|
||||
ranges;
|
||||
dma-ranges = <0x00000000 0x38000000 0x10000>,
|
||||
<0x10000000 0x10000000 0x60000>,
|
||||
|
||||
@@ -57,17 +57,17 @@ properties:
|
||||
- const: allwinner,sun8i-v3s
|
||||
|
||||
- description: Anbernic RG35XX (2024)
|
||||
- items:
|
||||
items:
|
||||
- const: anbernic,rg35xx-2024
|
||||
- const: allwinner,sun50i-h700
|
||||
|
||||
- description: Anbernic RG35XX Plus
|
||||
- items:
|
||||
items:
|
||||
- const: anbernic,rg35xx-plus
|
||||
- const: allwinner,sun50i-h700
|
||||
|
||||
- description: Anbernic RG35XX H
|
||||
- items:
|
||||
items:
|
||||
- const: anbernic,rg35xx-h
|
||||
- const: allwinner,sun50i-h700
|
||||
|
||||
|
||||
@@ -1,129 +0,0 @@
|
||||
Vitesse VSC73xx Switches
|
||||
========================
|
||||
|
||||
This defines device tree bindings for the Vitesse VSC73xx switch chips.
|
||||
The Vitesse company has been acquired by Microsemi and Microsemi has
|
||||
been acquired Microchip but retains this vendor branding.
|
||||
|
||||
The currently supported switch chips are:
|
||||
Vitesse VSC7385 SparX-G5 5+1-port Integrated Gigabit Ethernet Switch
|
||||
Vitesse VSC7388 SparX-G8 8-port Integrated Gigabit Ethernet Switch
|
||||
Vitesse VSC7395 SparX-G5e 5+1-port Integrated Gigabit Ethernet Switch
|
||||
Vitesse VSC7398 SparX-G8e 8-port Integrated Gigabit Ethernet Switch
|
||||
|
||||
This switch could have two different management interface.
|
||||
|
||||
If SPI interface is used, the device tree node is an SPI device so it must
|
||||
reside inside a SPI bus device tree node, see spi/spi-bus.txt
|
||||
|
||||
When the chip is connected to a parallel memory bus and work in memory-mapped
|
||||
I/O mode, a platform device is used to represent the vsc73xx. In this case it
|
||||
must reside inside a platform bus device tree node.
|
||||
|
||||
Required properties:
|
||||
|
||||
- compatible: must be exactly one of:
|
||||
"vitesse,vsc7385"
|
||||
"vitesse,vsc7388"
|
||||
"vitesse,vsc7395"
|
||||
"vitesse,vsc7398"
|
||||
- gpio-controller: indicates that this switch is also a GPIO controller,
|
||||
see gpio/gpio.txt
|
||||
- #gpio-cells: this must be set to <2> and indicates that we are a twocell
|
||||
GPIO controller, see gpio/gpio.txt
|
||||
|
||||
Optional properties:
|
||||
|
||||
- reset-gpios: a handle to a GPIO line that can issue reset of the chip.
|
||||
It should be tagged as active low.
|
||||
|
||||
Required subnodes:
|
||||
|
||||
See net/dsa/dsa.txt for a list of additional required and optional properties
|
||||
and subnodes of DSA switches.
|
||||
|
||||
Examples:
|
||||
|
||||
SPI:
|
||||
switch@0 {
|
||||
compatible = "vitesse,vsc7395";
|
||||
reg = <0>;
|
||||
/* Specified for 2.5 MHz or below */
|
||||
spi-max-frequency = <2500000>;
|
||||
gpio-controller;
|
||||
#gpio-cells = <2>;
|
||||
|
||||
ports {
|
||||
#address-cells = <1>;
|
||||
#size-cells = <0>;
|
||||
|
||||
port@0 {
|
||||
reg = <0>;
|
||||
label = "lan1";
|
||||
};
|
||||
port@1 {
|
||||
reg = <1>;
|
||||
label = "lan2";
|
||||
};
|
||||
port@2 {
|
||||
reg = <2>;
|
||||
label = "lan3";
|
||||
};
|
||||
port@3 {
|
||||
reg = <3>;
|
||||
label = "lan4";
|
||||
};
|
||||
vsc: port@6 {
|
||||
reg = <6>;
|
||||
ethernet = <&gmac1>;
|
||||
phy-mode = "rgmii";
|
||||
fixed-link {
|
||||
speed = <1000>;
|
||||
full-duplex;
|
||||
pause;
|
||||
};
|
||||
};
|
||||
};
|
||||
};
|
||||
|
||||
Platform:
|
||||
switch@2,0 {
|
||||
#address-cells = <1>;
|
||||
#size-cells = <1>;
|
||||
compatible = "vitesse,vsc7385";
|
||||
reg = <0x2 0x0 0x20000>;
|
||||
reset-gpios = <&gpio0 12 GPIO_ACTIVE_LOW>;
|
||||
|
||||
ports {
|
||||
#address-cells = <1>;
|
||||
#size-cells = <0>;
|
||||
|
||||
port@0 {
|
||||
reg = <0>;
|
||||
label = "lan1";
|
||||
};
|
||||
port@1 {
|
||||
reg = <1>;
|
||||
label = "lan2";
|
||||
};
|
||||
port@2 {
|
||||
reg = <2>;
|
||||
label = "lan3";
|
||||
};
|
||||
port@3 {
|
||||
reg = <3>;
|
||||
label = "lan4";
|
||||
};
|
||||
vsc: port@6 {
|
||||
reg = <6>;
|
||||
ethernet = <&enet0>;
|
||||
phy-mode = "rgmii";
|
||||
fixed-link {
|
||||
speed = <1000>;
|
||||
full-duplex;
|
||||
pause;
|
||||
};
|
||||
};
|
||||
};
|
||||
|
||||
};
|
||||
@@ -0,0 +1,162 @@
|
||||
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
|
||||
%YAML 1.2
|
||||
---
|
||||
$id: http://devicetree.org/schemas/net/dsa/vitesse,vsc73xx.yaml#
|
||||
$schema: http://devicetree.org/meta-schemas/core.yaml#
|
||||
|
||||
title: Vitesse VSC73xx DSA Switches
|
||||
|
||||
maintainers:
|
||||
- Linus Walleij <linus.walleij@linaro.org>
|
||||
|
||||
description:
|
||||
The Vitesse DSA Switches were produced in the early-to-mid 2000s.
|
||||
|
||||
The Vitesse company has been acquired by Microsemi and Microsemi has
|
||||
been acquired Microchip but the new owner retains this vendor branding.
|
||||
|
||||
The currently supported switch chips are
|
||||
Vitesse VSC7385 SparX-G5 5+1-port Integrated Gigabit Ethernet Switch
|
||||
Vitesse VSC7388 SparX-G8 8-port Integrated Gigabit Ethernet Switch
|
||||
Vitesse VSC7395 SparX-G5e 5+1-port Integrated Gigabit Ethernet Switch
|
||||
Vitesse VSC7398 SparX-G8e 8-port Integrated Gigabit Ethernet Switch
|
||||
|
||||
This switch can use one of two different management interfaces.
|
||||
|
||||
If SPI interface is used, the device tree node is an SPI device so it must
|
||||
reside inside a SPI bus device tree node, see spi/spi-bus.txt
|
||||
|
||||
When the chip is connected to a parallel memory bus and work in memory-mapped
|
||||
I/O mode, a platform device is used to represent the vsc73xx. In this case it
|
||||
must reside inside a platform bus device tree node.
|
||||
|
||||
properties:
|
||||
compatible:
|
||||
enum:
|
||||
- vitesse,vsc7385
|
||||
- vitesse,vsc7388
|
||||
- vitesse,vsc7395
|
||||
- vitesse,vsc7398
|
||||
|
||||
reg:
|
||||
maxItems: 1
|
||||
|
||||
gpio-controller: true
|
||||
"#gpio-cells":
|
||||
const: 2
|
||||
|
||||
reset-gpios:
|
||||
description: GPIO to be used to reset the whole device
|
||||
maxItems: 1
|
||||
|
||||
allOf:
|
||||
- $ref: dsa.yaml#/$defs/ethernet-ports
|
||||
|
||||
# This checks if reg is a chipselect so the device is on an SPI
|
||||
# bus, the if-clause will fail if reg is a tuple such as for a
|
||||
# platform device.
|
||||
if:
|
||||
properties:
|
||||
reg:
|
||||
minimum: 0
|
||||
maximum: 256
|
||||
then:
|
||||
$ref: /schemas/spi/spi-peripheral-props.yaml#
|
||||
|
||||
required:
|
||||
- compatible
|
||||
- reg
|
||||
|
||||
unevaluatedProperties: false
|
||||
|
||||
examples:
|
||||
- |
|
||||
#include <dt-bindings/gpio/gpio.h>
|
||||
|
||||
spi {
|
||||
#address-cells = <1>;
|
||||
#size-cells = <0>;
|
||||
|
||||
ethernet-switch@0 {
|
||||
compatible = "vitesse,vsc7395";
|
||||
reg = <0>;
|
||||
spi-max-frequency = <2500000>;
|
||||
gpio-controller;
|
||||
#gpio-cells = <2>;
|
||||
|
||||
ethernet-ports {
|
||||
#address-cells = <1>;
|
||||
#size-cells = <0>;
|
||||
|
||||
ethernet-port@0 {
|
||||
reg = <0>;
|
||||
label = "lan1";
|
||||
};
|
||||
ethernet-port@1 {
|
||||
reg = <1>;
|
||||
label = "lan2";
|
||||
};
|
||||
ethernet-port@2 {
|
||||
reg = <2>;
|
||||
label = "lan3";
|
||||
};
|
||||
ethernet-port@3 {
|
||||
reg = <3>;
|
||||
label = "lan4";
|
||||
};
|
||||
ethernet-port@6 {
|
||||
reg = <6>;
|
||||
ethernet = <&gmac1>;
|
||||
phy-mode = "rgmii";
|
||||
fixed-link {
|
||||
speed = <1000>;
|
||||
full-duplex;
|
||||
pause;
|
||||
};
|
||||
};
|
||||
};
|
||||
};
|
||||
};
|
||||
|
||||
bus {
|
||||
#address-cells = <1>;
|
||||
#size-cells = <1>;
|
||||
|
||||
ethernet-switch@10000000 {
|
||||
compatible = "vitesse,vsc7385";
|
||||
reg = <0x10000000 0x20000>;
|
||||
reset-gpios = <&gpio0 12 GPIO_ACTIVE_LOW>;
|
||||
|
||||
ethernet-ports {
|
||||
#address-cells = <1>;
|
||||
#size-cells = <0>;
|
||||
|
||||
ethernet-port@0 {
|
||||
reg = <0>;
|
||||
label = "lan1";
|
||||
};
|
||||
ethernet-port@1 {
|
||||
reg = <1>;
|
||||
label = "lan2";
|
||||
};
|
||||
ethernet-port@2 {
|
||||
reg = <2>;
|
||||
label = "lan3";
|
||||
};
|
||||
ethernet-port@3 {
|
||||
reg = <3>;
|
||||
label = "lan4";
|
||||
};
|
||||
ethernet-port@6 {
|
||||
reg = <6>;
|
||||
ethernet = <&enet0>;
|
||||
phy-mode = "rgmii";
|
||||
fixed-link {
|
||||
speed = <1000>;
|
||||
full-duplex;
|
||||
pause;
|
||||
};
|
||||
};
|
||||
};
|
||||
};
|
||||
};
|
||||
@@ -24,6 +24,7 @@ properties:
|
||||
|
||||
managers:
|
||||
type: object
|
||||
additionalProperties: false
|
||||
description:
|
||||
List of the PD69208T4/PD69204T4/PD69208M PSE managers. Each manager
|
||||
have 4 or 8 physical ports according to the chip version. No need to
|
||||
@@ -47,8 +48,9 @@ properties:
|
||||
- "#size-cells"
|
||||
|
||||
patternProperties:
|
||||
"^manager@0[0-9a-b]$":
|
||||
"^manager@[0-9a-b]$":
|
||||
type: object
|
||||
additionalProperties: false
|
||||
description:
|
||||
PD69208T4/PD69204T4/PD69208M PSE manager exposing 4 or 8 physical
|
||||
ports.
|
||||
@@ -69,9 +71,14 @@ properties:
|
||||
patternProperties:
|
||||
'^port@[0-7]$':
|
||||
type: object
|
||||
additionalProperties: false
|
||||
|
||||
properties:
|
||||
reg:
|
||||
maxItems: 1
|
||||
|
||||
required:
|
||||
- reg
|
||||
additionalProperties: false
|
||||
|
||||
required:
|
||||
- reg
|
||||
|
||||
@@ -29,13 +29,31 @@ properties:
|
||||
of the ports conversion matrix that establishes relationship between
|
||||
the logical ports and the physical channels.
|
||||
type: object
|
||||
additionalProperties: false
|
||||
|
||||
properties:
|
||||
"#address-cells":
|
||||
const: 1
|
||||
|
||||
"#size-cells":
|
||||
const: 0
|
||||
|
||||
patternProperties:
|
||||
'^channel@[0-7]$':
|
||||
type: object
|
||||
additionalProperties: false
|
||||
|
||||
properties:
|
||||
reg:
|
||||
maxItems: 1
|
||||
|
||||
required:
|
||||
- reg
|
||||
|
||||
required:
|
||||
- "#address-cells"
|
||||
- "#size-cells"
|
||||
|
||||
unevaluatedProperties: false
|
||||
|
||||
required:
|
||||
|
||||
@@ -76,6 +76,7 @@ properties:
|
||||
- rockchip,rk3128-gmac
|
||||
- rockchip,rk3228-gmac
|
||||
- rockchip,rk3288-gmac
|
||||
- rockchip,rk3308-gmac
|
||||
- rockchip,rk3328-gmac
|
||||
- rockchip,rk3366-gmac
|
||||
- rockchip,rk3368-gmac
|
||||
|
||||
@@ -55,6 +55,14 @@ properties:
|
||||
description:
|
||||
phandle to MII_RT module's syscon regmap
|
||||
|
||||
ti,pa-stats:
|
||||
$ref: /schemas/types.yaml#/definitions/phandle
|
||||
description:
|
||||
phandle to PA_STATS module's syscon regmap. PA_STATS is a set of
|
||||
registers where different statistics related to ICSSG, are dumped by
|
||||
ICSSG firmware. PA_STATS module's syscon regmap will help the device to
|
||||
access/read/write those statistics.
|
||||
|
||||
ti,iep:
|
||||
$ref: /schemas/types.yaml#/definitions/phandle-array
|
||||
maxItems: 2
|
||||
@@ -194,6 +202,7 @@ examples:
|
||||
"tx1-0", "tx1-1", "tx1-2", "tx1-3",
|
||||
"rx0", "rx1";
|
||||
ti,mii-g-rt = <&icssg2_mii_g_rt>;
|
||||
ti,pa-stats = <&icssg2_pa_stats>;
|
||||
ti,iep = <&icssg2_iep0>, <&icssg2_iep1>;
|
||||
interrupt-parent = <&icssg2_intc>;
|
||||
interrupts = <24 0 2>, <25 1 3>;
|
||||
|
||||
@@ -128,6 +128,11 @@ properties:
|
||||
Whether to skip executing an SCM call that reassigns the memory
|
||||
region ownership.
|
||||
|
||||
qcom,no-msa-ready-indicator:
|
||||
type: boolean
|
||||
description:
|
||||
Don't wait for MSA_READY indicator to complete init.
|
||||
|
||||
qcom,smem-states:
|
||||
$ref: /schemas/types.yaml#/definitions/phandle-array
|
||||
description: State bits used by the AP to signal the WLAN Q6.
|
||||
|
||||
@@ -265,15 +265,6 @@ allOf:
|
||||
|
||||
examples:
|
||||
- |
|
||||
|
||||
q6v5_wcss: remoteproc@cd00000 {
|
||||
compatible = "qcom,ipq8074-wcss-pil";
|
||||
reg = <0xcd00000 0x4040>,
|
||||
<0x4ab000 0x20>;
|
||||
reg-names = "qdsp6",
|
||||
"rmb";
|
||||
};
|
||||
|
||||
wifi0: wifi@c000000 {
|
||||
compatible = "qcom,ipq8074-wifi";
|
||||
reg = <0xc000000 0x2000000>;
|
||||
|
||||
@@ -31,6 +31,10 @@ properties:
|
||||
phy-handle:
|
||||
$ref: ethernet-controller.yaml#/properties/phy-handle
|
||||
|
||||
clocks:
|
||||
items:
|
||||
- description: 200/375 MHz free-running clock is used as input clock.
|
||||
|
||||
required:
|
||||
- compatible
|
||||
- reg
|
||||
@@ -51,5 +55,6 @@ examples:
|
||||
compatible = "xlnx,gmii-to-rgmii-1.0";
|
||||
reg = <8>;
|
||||
phy-handle = <&phy>;
|
||||
clocks = <&dummy>;
|
||||
};
|
||||
};
|
||||
|
||||
@@ -479,6 +479,7 @@ operations:
|
||||
name: pin-get
|
||||
doc: |
|
||||
Get list of pins and its attributes.
|
||||
|
||||
- dump request without any attributes given - list all the pins in the
|
||||
system
|
||||
- dump request with target dpll - list all the pins registered with
|
||||
|
||||
@@ -349,6 +349,10 @@ attribute-sets:
|
||||
Number of packets dropped due to transient lack of resources, such as
|
||||
buffer space, host descriptors etc.
|
||||
type: uint
|
||||
-
|
||||
name: rx-csum-complete
|
||||
doc: Number of packets that were marked as CHECKSUM_COMPLETE.
|
||||
type: uint
|
||||
-
|
||||
name: rx-csum-unnecessary
|
||||
doc: Number of packets that were marked as CHECKSUM_UNNECESSARY.
|
||||
|
||||
@@ -329,24 +329,23 @@ XDP_SHARED_UMEM option and provide the initial socket's fd in the
|
||||
sxdp_shared_umem_fd field as you registered the UMEM on that
|
||||
socket. These two sockets will now share one and the same UMEM.
|
||||
|
||||
In this case, it is possible to use the NIC's packet steering
|
||||
capabilities to steer the packets to the right queue. This is not
|
||||
possible in the previous example as there is only one queue shared
|
||||
among sockets, so the NIC cannot do this steering as it can only steer
|
||||
between queues.
|
||||
There is no need to supply an XDP program like the one in the previous
|
||||
case where sockets were bound to the same queue id and
|
||||
device. Instead, use the NIC's packet steering capabilities to steer
|
||||
the packets to the right queue. In the previous example, there is only
|
||||
one queue shared among sockets, so the NIC cannot do this steering. It
|
||||
can only steer between queues.
|
||||
|
||||
In libxdp (or libbpf prior to version 1.0), you need to use the
|
||||
xsk_socket__create_shared() API as it takes a reference to a FILL ring
|
||||
and a COMPLETION ring that will be created for you and bound to the
|
||||
shared UMEM. You can use this function for all the sockets you create,
|
||||
or you can use it for the second and following ones and use
|
||||
xsk_socket__create() for the first one. Both methods yield the same
|
||||
result.
|
||||
In libbpf, you need to use the xsk_socket__create_shared() API as it
|
||||
takes a reference to a FILL ring and a COMPLETION ring that will be
|
||||
created for you and bound to the shared UMEM. You can use this
|
||||
function for all the sockets you create, or you can use it for the
|
||||
second and following ones and use xsk_socket__create() for the first
|
||||
one. Both methods yield the same result.
|
||||
|
||||
Note that a UMEM can be shared between sockets on the same queue id
|
||||
and device, as well as between queues on the same device and between
|
||||
devices at the same time. It is also possible to redirect to any
|
||||
socket as long as it is bound to the same umem with XDP_SHARED_UMEM.
|
||||
devices at the same time.
|
||||
|
||||
XDP_USE_NEED_WAKEUP bind flag
|
||||
-----------------------------
|
||||
@@ -823,10 +822,6 @@ A: The short answer is no, that is not supported at the moment. The
|
||||
switch, or other distribution mechanism, in your NIC to direct
|
||||
traffic to the correct queue id and socket.
|
||||
|
||||
Note that if you are using the XDP_SHARED_UMEM option, it is
|
||||
possible to switch traffic between any socket bound to the same
|
||||
umem.
|
||||
|
||||
Q: My packets are sometimes corrupted. What is wrong?
|
||||
|
||||
A: Care has to be taken not to feed the same buffer in the UMEM into
|
||||
|
||||
@@ -189,22 +189,19 @@ the software port.
|
||||
|
||||
* - `rx[i]_gro_packets`
|
||||
- Number of received packets processed using hardware-accelerated GRO. The
|
||||
number of hardware GRO offloaded packets received on ring i.
|
||||
number of hardware GRO offloaded packets received on ring i. Only true GRO
|
||||
packets are counted: only packets that are in an SKB with a GRO count > 1.
|
||||
- Acceleration
|
||||
|
||||
* - `rx[i]_gro_bytes`
|
||||
- Number of received bytes processed using hardware-accelerated GRO. The
|
||||
number of hardware GRO offloaded bytes received on ring i.
|
||||
number of hardware GRO offloaded bytes received on ring i. Only true GRO
|
||||
packets are counted: only packets that are in an SKB with a GRO count > 1.
|
||||
- Acceleration
|
||||
|
||||
* - `rx[i]_gro_skbs`
|
||||
- The number of receive SKBs constructed while performing
|
||||
hardware-accelerated GRO.
|
||||
- Informative
|
||||
|
||||
* - `rx[i]_gro_match_packets`
|
||||
- Number of received packets processed using hardware-accelerated GRO that
|
||||
met the flow table match criteria.
|
||||
- The number of GRO SKBs constructed from hardware-accelerated GRO. Only SKBs
|
||||
with a GRO count > 1 are counted.
|
||||
- Informative
|
||||
|
||||
* - `rx[i]_gro_large_hds`
|
||||
@@ -212,6 +209,15 @@ the software port.
|
||||
headers that require additional memory to be allocated.
|
||||
- Informative
|
||||
|
||||
* - `rx[i]_hds_nodata_packets`
|
||||
- Number of header only packets in header/data split mode [#accel]_.
|
||||
- Informative
|
||||
|
||||
* - `rx[i]_hds_nodata_bytes`
|
||||
- Number of bytes for header only packets in header/data split mode
|
||||
[#accel]_.
|
||||
- Informative
|
||||
|
||||
* - `rx[i]_lro_packets`
|
||||
- The number of LRO packets received on ring i [#accel]_.
|
||||
- Acceleration
|
||||
|
||||
@@ -72,6 +72,7 @@ Contents:
|
||||
mac80211-injection
|
||||
mctp
|
||||
mpls-sysctl
|
||||
mptcp
|
||||
mptcp-sysctl
|
||||
multiqueue
|
||||
multi-pf-netdev
|
||||
|
||||
@@ -1196,6 +1196,19 @@ tcp_pingpong_thresh - INTEGER
|
||||
|
||||
Default: 1
|
||||
|
||||
tcp_rto_min_us - INTEGER
|
||||
Minimal TCP retransmission timeout (in microseconds). Note that the
|
||||
rto_min route option has the highest precedence for configuring this
|
||||
setting, followed by the TCP_BPF_RTO_MIN socket option, followed by
|
||||
this tcp_rto_min_us sysctl.
|
||||
|
||||
The recommended practice is to use a value less or equal to 200000
|
||||
microseconds.
|
||||
|
||||
Possible Values: 1 - INT_MAX
|
||||
|
||||
Default: 200000
|
||||
|
||||
UDP variables
|
||||
=============
|
||||
|
||||
|
||||
@@ -7,14 +7,6 @@ MPTCP Sysfs variables
|
||||
/proc/sys/net/mptcp/* Variables
|
||||
===============================
|
||||
|
||||
enabled - BOOLEAN
|
||||
Control whether MPTCP sockets can be created.
|
||||
|
||||
MPTCP sockets can be created if the value is 1. This is a
|
||||
per-namespace sysctl.
|
||||
|
||||
Default: 1 (enabled)
|
||||
|
||||
add_addr_timeout - INTEGER (seconds)
|
||||
Set the timeout after which an ADD_ADDR control message will be
|
||||
resent to an MPTCP peer that has not acknowledged a previous
|
||||
@@ -25,25 +17,6 @@ add_addr_timeout - INTEGER (seconds)
|
||||
|
||||
Default: 120
|
||||
|
||||
close_timeout - INTEGER (seconds)
|
||||
Set the make-after-break timeout: in absence of any close or
|
||||
shutdown syscall, MPTCP sockets will maintain the status
|
||||
unchanged for such time, after the last subflow removal, before
|
||||
moving to TCP_CLOSE.
|
||||
|
||||
The default value matches TCP_TIMEWAIT_LEN. This is a per-namespace
|
||||
sysctl.
|
||||
|
||||
Default: 60
|
||||
|
||||
checksum_enabled - BOOLEAN
|
||||
Control whether DSS checksum can be enabled.
|
||||
|
||||
DSS checksum can be enabled if the value is nonzero. This is a
|
||||
per-namespace sysctl.
|
||||
|
||||
Default: 0
|
||||
|
||||
allow_join_initial_addr_port - BOOLEAN
|
||||
Allow peers to send join requests to the IP address and port number used
|
||||
by the initial subflow if the value is 1. This controls a flag that is
|
||||
@@ -57,6 +30,37 @@ allow_join_initial_addr_port - BOOLEAN
|
||||
|
||||
Default: 1
|
||||
|
||||
available_schedulers - STRING
|
||||
Shows the available schedulers choices that are registered. More packet
|
||||
schedulers may be available, but not loaded.
|
||||
|
||||
checksum_enabled - BOOLEAN
|
||||
Control whether DSS checksum can be enabled.
|
||||
|
||||
DSS checksum can be enabled if the value is nonzero. This is a
|
||||
per-namespace sysctl.
|
||||
|
||||
Default: 0
|
||||
|
||||
close_timeout - INTEGER (seconds)
|
||||
Set the make-after-break timeout: in absence of any close or
|
||||
shutdown syscall, MPTCP sockets will maintain the status
|
||||
unchanged for such time, after the last subflow removal, before
|
||||
moving to TCP_CLOSE.
|
||||
|
||||
The default value matches TCP_TIMEWAIT_LEN. This is a per-namespace
|
||||
sysctl.
|
||||
|
||||
Default: 60
|
||||
|
||||
enabled - BOOLEAN
|
||||
Control whether MPTCP sockets can be created.
|
||||
|
||||
MPTCP sockets can be created if the value is 1. This is a
|
||||
per-namespace sysctl.
|
||||
|
||||
Default: 1 (enabled)
|
||||
|
||||
pm_type - INTEGER
|
||||
Set the default path manager type to use for each new MPTCP
|
||||
socket. In-kernel path management will control subflow
|
||||
@@ -74,6 +78,14 @@ pm_type - INTEGER
|
||||
|
||||
Default: 0
|
||||
|
||||
scheduler - STRING
|
||||
Select the scheduler of your choice.
|
||||
|
||||
Support for selection of different schedulers. This is a per-namespace
|
||||
sysctl.
|
||||
|
||||
Default: "default"
|
||||
|
||||
stale_loss_cnt - INTEGER
|
||||
The number of MPTCP-level retransmission intervals with no traffic and
|
||||
pending outstanding data on a given subflow required to declare it stale.
|
||||
@@ -85,11 +97,3 @@ stale_loss_cnt - INTEGER
|
||||
This is a per-namespace sysctl.
|
||||
|
||||
Default: 4
|
||||
|
||||
scheduler - STRING
|
||||
Select the scheduler of your choice.
|
||||
|
||||
Support for selection of different schedulers. This is a per-namespace
|
||||
sysctl.
|
||||
|
||||
Default: "default"
|
||||
|
||||
@@ -0,0 +1,156 @@
|
||||
.. SPDX-License-Identifier: GPL-2.0
|
||||
|
||||
=====================
|
||||
Multipath TCP (MPTCP)
|
||||
=====================
|
||||
|
||||
Introduction
|
||||
============
|
||||
|
||||
Multipath TCP or MPTCP is an extension to the standard TCP and is described in
|
||||
`RFC 8684 (MPTCPv1) <https://www.rfc-editor.org/rfc/rfc8684.html>`_. It allows a
|
||||
device to make use of multiple interfaces at once to send and receive TCP
|
||||
packets over a single MPTCP connection. MPTCP can aggregate the bandwidth of
|
||||
multiple interfaces or prefer the one with the lowest latency. It also allows a
|
||||
fail-over if one path is down, and the traffic is seamlessly reinjected on other
|
||||
paths.
|
||||
|
||||
For more details about Multipath TCP in the Linux kernel, please see the
|
||||
official website: `mptcp.dev <https://www.mptcp.dev>`_.
|
||||
|
||||
|
||||
Use cases
|
||||
=========
|
||||
|
||||
Thanks to MPTCP, being able to use multiple paths in parallel or simultaneously
|
||||
brings new use-cases, compared to TCP:
|
||||
|
||||
- Seamless handovers: switching from one path to another while preserving
|
||||
established connections, e.g. to be used in mobility use-cases, like on
|
||||
smartphones.
|
||||
- Best network selection: using the "best" available path depending on some
|
||||
conditions, e.g. latency, losses, cost, bandwidth, etc.
|
||||
- Network aggregation: using multiple paths at the same time to have a higher
|
||||
throughput, e.g. to combine fixed and mobile networks to send files faster.
|
||||
|
||||
|
||||
Concepts
|
||||
========
|
||||
|
||||
Technically, when a new socket is created with the ``IPPROTO_MPTCP`` protocol
|
||||
(Linux-specific), a *subflow* (or *path*) is created. This *subflow* consists of
|
||||
a regular TCP connection that is used to transmit data through one interface.
|
||||
Additional *subflows* can be negotiated later between the hosts. For the remote
|
||||
host to be able to detect the use of MPTCP, a new field is added to the TCP
|
||||
*option* field of the underlying TCP *subflow*. This field contains, amongst
|
||||
other things, a ``MP_CAPABLE`` option that tells the other host to use MPTCP if
|
||||
it is supported. If the remote host or any middlebox in between does not support
|
||||
it, the returned ``SYN+ACK`` packet will not contain MPTCP options in the TCP
|
||||
*option* field. In that case, the connection will be "downgraded" to plain TCP,
|
||||
and it will continue with a single path.
|
||||
|
||||
This behavior is made possible by two internal components: the path manager, and
|
||||
the packet scheduler.
|
||||
|
||||
Path Manager
|
||||
------------
|
||||
|
||||
The Path Manager is in charge of *subflows*, from creation to deletion, and also
|
||||
address announcements. Typically, it is the client side that initiates subflows,
|
||||
and the server side that announces additional addresses via the ``ADD_ADDR`` and
|
||||
``REMOVE_ADDR`` options.
|
||||
|
||||
Path managers are controlled by the ``net.mptcp.pm_type`` sysctl knob -- see
|
||||
mptcp-sysctl.rst. There are two types: the in-kernel one (type ``0``) where the
|
||||
same rules are applied for all the connections (see: ``ip mptcp``) ; and the
|
||||
userspace one (type ``1``), controlled by a userspace daemon (i.e. `mptcpd
|
||||
<https://mptcpd.mptcp.dev/>`_) where different rules can be applied for each
|
||||
connection. The path managers can be controlled via a Netlink API; see
|
||||
netlink_spec/mptcp_pm.rst.
|
||||
|
||||
To be able to use multiple IP addresses on a host to create multiple *subflows*
|
||||
(paths), the default in-kernel MPTCP path-manager needs to know which IP
|
||||
addresses can be used. This can be configured with ``ip mptcp endpoint`` for
|
||||
example.
|
||||
|
||||
Packet Scheduler
|
||||
----------------
|
||||
|
||||
The Packet Scheduler is in charge of selecting which available *subflow(s)* to
|
||||
use to send the next data packet. It can decide to maximize the use of the
|
||||
available bandwidth, only to pick the path with the lower latency, or any other
|
||||
policy depending on the configuration.
|
||||
|
||||
Packet schedulers are controlled by the ``net.mptcp.scheduler`` sysctl knob --
|
||||
see mptcp-sysctl.rst.
|
||||
|
||||
|
||||
Sockets API
|
||||
===========
|
||||
|
||||
Creating MPTCP sockets
|
||||
----------------------
|
||||
|
||||
On Linux, MPTCP can be used by selecting MPTCP instead of TCP when creating the
|
||||
``socket``:
|
||||
|
||||
.. code-block:: C
|
||||
|
||||
int sd = socket(AF_INET(6), SOCK_STREAM, IPPROTO_MPTCP);
|
||||
|
||||
Note that ``IPPROTO_MPTCP`` is defined as ``262``.
|
||||
|
||||
If MPTCP is not supported, ``errno`` will be set to:
|
||||
|
||||
- ``EINVAL``: (*Invalid argument*): MPTCP is not available, on kernels < 5.6.
|
||||
- ``EPROTONOSUPPORT`` (*Protocol not supported*): MPTCP has not been compiled,
|
||||
on kernels >= v5.6.
|
||||
- ``ENOPROTOOPT`` (*Protocol not available*): MPTCP has been disabled using
|
||||
``net.mptcp.enabled`` sysctl knob; see mptcp-sysctl.rst.
|
||||
|
||||
MPTCP is then opt-in: applications need to explicitly request it. Note that
|
||||
applications can be forced to use MPTCP with different techniques, e.g.
|
||||
``LD_PRELOAD`` (see ``mptcpize``), eBPF (see ``mptcpify``), SystemTAP,
|
||||
``GODEBUG`` (``GODEBUG=multipathtcp=1``), etc.
|
||||
|
||||
Switching to ``IPPROTO_MPTCP`` instead of ``IPPROTO_TCP`` should be as
|
||||
transparent as possible for the userspace applications.
|
||||
|
||||
Socket options
|
||||
--------------
|
||||
|
||||
MPTCP supports most socket options handled by TCP. It is possible some less
|
||||
common options are not supported, but contributions are welcome.
|
||||
|
||||
Generally, the same value is propagated to all subflows, including the ones
|
||||
created after the calls to ``setsockopt()``. eBPF can be used to set different
|
||||
values per subflow.
|
||||
|
||||
There are some MPTCP specific socket options at the ``SOL_MPTCP`` (284) level to
|
||||
retrieve info. They fill the ``optval`` buffer of the ``getsockopt()`` system
|
||||
call:
|
||||
|
||||
- ``MPTCP_INFO``: Uses ``struct mptcp_info``.
|
||||
- ``MPTCP_TCPINFO``: Uses ``struct mptcp_subflow_data``, followed by an array of
|
||||
``struct tcp_info``.
|
||||
- ``MPTCP_SUBFLOW_ADDRS``: Uses ``struct mptcp_subflow_data``, followed by an
|
||||
array of ``mptcp_subflow_addrs``.
|
||||
- ``MPTCP_FULL_INFO``: Uses ``struct mptcp_full_info``, with one pointer to an
|
||||
array of ``struct mptcp_subflow_info`` (including the
|
||||
``struct mptcp_subflow_addrs``), and one pointer to an array of
|
||||
``struct tcp_info``, followed by the content of ``struct mptcp_info``.
|
||||
|
||||
Note that at the TCP level, ``TCP_IS_MPTCP`` socket option can be used to know
|
||||
if MPTCP is currently being used: the value will be set to 1 if it is.
|
||||
|
||||
|
||||
Design choices
|
||||
==============
|
||||
|
||||
A new socket type has been added for MPTCP for the userspace-facing socket. The
|
||||
kernel is in charge of creating subflow sockets: they are TCP sockets where the
|
||||
behavior is modified using TCP-ULP.
|
||||
|
||||
MPTCP listen sockets will create "plain" *accepted* TCP sockets if the
|
||||
connection request from the client didn't ask for MPTCP, making the performance
|
||||
impact minimal when MPTCP is enabled by default.
|
||||
@@ -227,7 +227,7 @@ preferably including links to previous postings, for example::
|
||||
The amount of mooing will depend on packet rate so should match
|
||||
the diurnal cycle quite well.
|
||||
|
||||
Signed-of-by: Joe Defarmer <joe@barn.org>
|
||||
Signed-off-by: Joe Defarmer <joe@barn.org>
|
||||
---
|
||||
v3:
|
||||
- add a note about time-of-day mooing fluctuation to the commit message
|
||||
|
||||
+4
-6
@@ -1107,7 +1107,6 @@ L: linux-pm@vger.kernel.org
|
||||
S: Supported
|
||||
F: Documentation/admin-guide/pm/amd-pstate.rst
|
||||
F: drivers/cpufreq/amd-pstate*
|
||||
F: include/linux/amd-pstate.h
|
||||
F: tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py
|
||||
|
||||
AMD PTDMA DRIVER
|
||||
@@ -3854,6 +3853,7 @@ BPF JIT for ARM64
|
||||
M: Daniel Borkmann <daniel@iogearbox.net>
|
||||
M: Alexei Starovoitov <ast@kernel.org>
|
||||
M: Puranjay Mohan <puranjay@kernel.org>
|
||||
R: Xu Kuohai <xukuohai@huaweicloud.com>
|
||||
L: bpf@vger.kernel.org
|
||||
S: Supported
|
||||
F: arch/arm64/net/
|
||||
@@ -5187,7 +5187,6 @@ F: Documentation/devicetree/bindings/media/i2c/chrontel,ch7322.yaml
|
||||
F: drivers/media/cec/i2c/ch7322.c
|
||||
|
||||
CIRRUS LOGIC AUDIO CODEC DRIVERS
|
||||
M: James Schulman <james.schulman@cirrus.com>
|
||||
M: David Rhodes <david.rhodes@cirrus.com>
|
||||
M: Richard Fitzgerald <rf@opensource.cirrus.com>
|
||||
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
|
||||
@@ -15238,7 +15237,6 @@ F: drivers/staging/most/
|
||||
F: include/linux/most.h
|
||||
|
||||
MOTORCOMM PHY DRIVER
|
||||
M: Peter Geis <pgwipeout@gmail.com>
|
||||
M: Frank <Frank.Sae@motor-comm.com>
|
||||
L: netdev@vger.kernel.org
|
||||
S: Maintained
|
||||
@@ -15752,7 +15750,7 @@ B: https://github.com/multipath-tcp/mptcp_net-next/issues
|
||||
T: git https://github.com/multipath-tcp/mptcp_net-next.git export-net
|
||||
T: git https://github.com/multipath-tcp/mptcp_net-next.git export
|
||||
F: Documentation/netlink/specs/mptcp_pm.yaml
|
||||
F: Documentation/networking/mptcp-sysctl.rst
|
||||
F: Documentation/networking/mptcp*.rst
|
||||
F: include/net/mptcp.h
|
||||
F: include/trace/events/mptcp.h
|
||||
F: include/uapi/linux/mptcp*.h
|
||||
@@ -21316,7 +21314,7 @@ F: arch/riscv/boot/dts/starfive/
|
||||
|
||||
STARFIVE DWMAC GLUE LAYER
|
||||
M: Emil Renner Berthing <kernel@esmil.dk>
|
||||
M: Samin Guo <samin.guo@starfivetech.com>
|
||||
M: Minda Chen <minda.chen@starfivetech.com>
|
||||
S: Maintained
|
||||
F: Documentation/devicetree/bindings/net/starfive,jh7110-dwmac.yaml
|
||||
F: drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
|
||||
@@ -22679,7 +22677,7 @@ L: tomoyo-users-en@lists.osdn.me (subscribers-only, for users in English)
|
||||
L: tomoyo-dev@lists.osdn.me (subscribers-only, for developers in Japanese)
|
||||
L: tomoyo-users@lists.osdn.me (subscribers-only, for users in Japanese)
|
||||
S: Maintained
|
||||
W: https://tomoyo.osdn.jp/
|
||||
W: https://tomoyo.sourceforge.net/
|
||||
F: security/tomoyo/
|
||||
|
||||
TOPSTAR LAPTOP EXTRAS DRIVER
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
VERSION = 6
|
||||
PATCHLEVEL = 10
|
||||
SUBLEVEL = 0
|
||||
EXTRAVERSION = -rc1
|
||||
EXTRAVERSION = -rc2
|
||||
NAME = Baby Opossum Posse
|
||||
|
||||
# *DOCUMENTATION*
|
||||
|
||||
@@ -39,7 +39,7 @@
|
||||
|
||||
/************** Functions that the back-end must provide **************/
|
||||
/* Extension for 32-bit operations. */
|
||||
inline u8 zext(u8 *buf, u8 rd);
|
||||
u8 zext(u8 *buf, u8 rd);
|
||||
/***** Moves *****/
|
||||
u8 mov_r32(u8 *buf, u8 rd, u8 rs, u8 sign_ext);
|
||||
u8 mov_r32_i32(u8 *buf, u8 reg, s32 imm);
|
||||
|
||||
@@ -62,7 +62,7 @@ enum {
|
||||
* If/when we decide to add ARCv2 instructions that do use register pairs,
|
||||
* the mapping, hopefully, doesn't need to be revisited.
|
||||
*/
|
||||
const u8 bpf2arc[][2] = {
|
||||
static const u8 bpf2arc[][2] = {
|
||||
/* Return value from in-kernel function, and exit value from eBPF */
|
||||
[BPF_REG_0] = {ARC_R_8, ARC_R_9},
|
||||
/* Arguments from eBPF program to in-kernel function */
|
||||
@@ -1302,7 +1302,7 @@ static u8 arc_b(u8 *buf, s32 offset)
|
||||
|
||||
/************* Packers (Deal with BPF_REGs) **************/
|
||||
|
||||
inline u8 zext(u8 *buf, u8 rd)
|
||||
u8 zext(u8 *buf, u8 rd)
|
||||
{
|
||||
if (rd != BPF_REG_FP)
|
||||
return arc_movi_r(buf, REG_HI(rd), 0);
|
||||
@@ -2235,6 +2235,7 @@ u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext)
|
||||
break;
|
||||
default:
|
||||
/* The caller must have handled this. */
|
||||
break;
|
||||
}
|
||||
} else {
|
||||
/*
|
||||
@@ -2253,6 +2254,7 @@ u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext)
|
||||
break;
|
||||
default:
|
||||
/* The caller must have handled this. */
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2517,7 +2519,7 @@ u8 arc_epilogue(u8 *buf, u32 usage, u16 frame_size)
|
||||
#define JCC64_NR_OF_JMPS 3 /* Number of jumps in jcc64 template. */
|
||||
#define JCC64_INSNS_TO_END 3 /* Number of insn. inclusive the 2nd jmp to end. */
|
||||
#define JCC64_SKIP_JMP 1 /* Index of the "skip" jump to "end". */
|
||||
const struct {
|
||||
static const struct {
|
||||
/*
|
||||
* "jit_off" is common between all "jmp[]" and is coupled with
|
||||
* "cond" of each "jmp[]" instance. e.g.:
|
||||
@@ -2883,7 +2885,7 @@ u8 gen_jmp_64(u8 *buf, u8 rd, u8 rs, u8 cond, u32 curr_off, u32 targ_off)
|
||||
* The "ARC_CC_SET" becomes "CC_unequal" because of the "tst"
|
||||
* instruction that precedes the conditional branch.
|
||||
*/
|
||||
const u8 arcv2_32_jmps[ARC_CC_LAST] = {
|
||||
static const u8 arcv2_32_jmps[ARC_CC_LAST] = {
|
||||
[ARC_CC_UGT] = CC_great_u,
|
||||
[ARC_CC_UGE] = CC_great_eq_u,
|
||||
[ARC_CC_ULT] = CC_less_u,
|
||||
|
||||
+11
-11
@@ -159,7 +159,7 @@ static void jit_dump(const struct jit_context *ctx)
|
||||
/* Initialise the context so there's no garbage. */
|
||||
static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog)
|
||||
{
|
||||
memset(ctx, 0, sizeof(ctx));
|
||||
memset(ctx, 0, sizeof(*ctx));
|
||||
|
||||
ctx->orig_prog = prog;
|
||||
|
||||
@@ -167,7 +167,7 @@ static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog)
|
||||
ctx->prog = bpf_jit_blind_constants(prog);
|
||||
if (IS_ERR(ctx->prog))
|
||||
return PTR_ERR(ctx->prog);
|
||||
ctx->blinded = (ctx->prog == ctx->orig_prog ? false : true);
|
||||
ctx->blinded = (ctx->prog != ctx->orig_prog);
|
||||
|
||||
/* If the verifier doesn't zero-extend, then we have to do it. */
|
||||
ctx->do_zext = !ctx->prog->aux->verifier_zext;
|
||||
@@ -1182,12 +1182,12 @@ static int jit_prepare(struct jit_context *ctx)
|
||||
}
|
||||
|
||||
/*
|
||||
* All the "handle_*()" functions have been called before by the
|
||||
* "jit_prepare()". If there was an error, we would know by now.
|
||||
* Therefore, no extra error checking at this point, other than
|
||||
* a sanity check at the end that expects the calculated length
|
||||
* (jit.len) to be equal to the length of generated instructions
|
||||
* (jit.index).
|
||||
* jit_compile() is the real compilation phase. jit_prepare() is
|
||||
* invoked before jit_compile() as a dry-run to make sure everything
|
||||
* will go OK and allocate the necessary memory.
|
||||
*
|
||||
* In the end, jit_compile() checks if it has produced the same number
|
||||
* of instructions as jit_prepare() would.
|
||||
*/
|
||||
static int jit_compile(struct jit_context *ctx)
|
||||
{
|
||||
@@ -1407,9 +1407,9 @@ static struct bpf_prog *do_extra_pass(struct bpf_prog *prog)
|
||||
|
||||
/*
|
||||
* This function may be invoked twice for the same stream of BPF
|
||||
* instructions. The "extra pass" happens, when there are "call"s
|
||||
* involved that their addresses are not known during the first
|
||||
* invocation.
|
||||
* instructions. The "extra pass" happens, when there are
|
||||
* (re)locations involved that their addresses are not known
|
||||
* during the first run.
|
||||
*/
|
||||
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
|
||||
{
|
||||
|
||||
@@ -146,7 +146,7 @@
|
||||
/* Coprocessor traps */
|
||||
.macro __init_el2_cptr
|
||||
__check_hvhe .LnVHE_\@, x1
|
||||
mov x0, #(CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN)
|
||||
mov x0, #CPACR_ELx_FPEN
|
||||
msr cpacr_el1, x0
|
||||
b .Lskip_set_cptr_\@
|
||||
.LnVHE_\@:
|
||||
@@ -277,7 +277,7 @@
|
||||
|
||||
// (h)VHE case
|
||||
mrs x0, cpacr_el1 // Disable SVE traps
|
||||
orr x0, x0, #(CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN)
|
||||
orr x0, x0, #CPACR_ELx_ZEN
|
||||
msr cpacr_el1, x0
|
||||
b .Lskip_set_cptr_\@
|
||||
|
||||
@@ -298,7 +298,7 @@
|
||||
|
||||
// (h)VHE case
|
||||
mrs x0, cpacr_el1 // Disable SME traps
|
||||
orr x0, x0, #(CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN)
|
||||
orr x0, x0, #CPACR_ELx_SMEN
|
||||
msr cpacr_el1, x0
|
||||
b .Lskip_set_cptr_sme_\@
|
||||
|
||||
|
||||
@@ -305,6 +305,12 @@
|
||||
GENMASK(19, 14) | \
|
||||
BIT(11))
|
||||
|
||||
#define CPTR_VHE_EL2_RES0 (GENMASK(63, 32) | \
|
||||
GENMASK(27, 26) | \
|
||||
GENMASK(23, 22) | \
|
||||
GENMASK(19, 18) | \
|
||||
GENMASK(15, 0))
|
||||
|
||||
/* Hyp Debug Configuration Register bits */
|
||||
#define MDCR_EL2_E2TB_MASK (UL(0x3))
|
||||
#define MDCR_EL2_E2TB_SHIFT (UL(24))
|
||||
|
||||
@@ -557,6 +557,68 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
|
||||
vcpu_set_flag((v), e); \
|
||||
} while (0)
|
||||
|
||||
#define __build_check_all_or_none(r, bits) \
|
||||
BUILD_BUG_ON(((r) & (bits)) && ((r) & (bits)) != (bits))
|
||||
|
||||
#define __cpacr_to_cptr_clr(clr, set) \
|
||||
({ \
|
||||
u64 cptr = 0; \
|
||||
\
|
||||
if ((set) & CPACR_ELx_FPEN) \
|
||||
cptr |= CPTR_EL2_TFP; \
|
||||
if ((set) & CPACR_ELx_ZEN) \
|
||||
cptr |= CPTR_EL2_TZ; \
|
||||
if ((set) & CPACR_ELx_SMEN) \
|
||||
cptr |= CPTR_EL2_TSM; \
|
||||
if ((clr) & CPACR_ELx_TTA) \
|
||||
cptr |= CPTR_EL2_TTA; \
|
||||
if ((clr) & CPTR_EL2_TAM) \
|
||||
cptr |= CPTR_EL2_TAM; \
|
||||
if ((clr) & CPTR_EL2_TCPAC) \
|
||||
cptr |= CPTR_EL2_TCPAC; \
|
||||
\
|
||||
cptr; \
|
||||
})
|
||||
|
||||
#define __cpacr_to_cptr_set(clr, set) \
|
||||
({ \
|
||||
u64 cptr = 0; \
|
||||
\
|
||||
if ((clr) & CPACR_ELx_FPEN) \
|
||||
cptr |= CPTR_EL2_TFP; \
|
||||
if ((clr) & CPACR_ELx_ZEN) \
|
||||
cptr |= CPTR_EL2_TZ; \
|
||||
if ((clr) & CPACR_ELx_SMEN) \
|
||||
cptr |= CPTR_EL2_TSM; \
|
||||
if ((set) & CPACR_ELx_TTA) \
|
||||
cptr |= CPTR_EL2_TTA; \
|
||||
if ((set) & CPTR_EL2_TAM) \
|
||||
cptr |= CPTR_EL2_TAM; \
|
||||
if ((set) & CPTR_EL2_TCPAC) \
|
||||
cptr |= CPTR_EL2_TCPAC; \
|
||||
\
|
||||
cptr; \
|
||||
})
|
||||
|
||||
#define cpacr_clear_set(clr, set) \
|
||||
do { \
|
||||
BUILD_BUG_ON((set) & CPTR_VHE_EL2_RES0); \
|
||||
BUILD_BUG_ON((clr) & CPACR_ELx_E0POE); \
|
||||
__build_check_all_or_none((clr), CPACR_ELx_FPEN); \
|
||||
__build_check_all_or_none((set), CPACR_ELx_FPEN); \
|
||||
__build_check_all_or_none((clr), CPACR_ELx_ZEN); \
|
||||
__build_check_all_or_none((set), CPACR_ELx_ZEN); \
|
||||
__build_check_all_or_none((clr), CPACR_ELx_SMEN); \
|
||||
__build_check_all_or_none((set), CPACR_ELx_SMEN); \
|
||||
\
|
||||
if (has_vhe() || has_hvhe()) \
|
||||
sysreg_clear_set(cpacr_el1, clr, set); \
|
||||
else \
|
||||
sysreg_clear_set(cptr_el2, \
|
||||
__cpacr_to_cptr_clr(clr, set), \
|
||||
__cpacr_to_cptr_set(clr, set));\
|
||||
} while (0)
|
||||
|
||||
static __always_inline void kvm_write_cptr_el2(u64 val)
|
||||
{
|
||||
if (has_vhe() || has_hvhe())
|
||||
@@ -570,17 +632,16 @@ static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu)
|
||||
u64 val;
|
||||
|
||||
if (has_vhe()) {
|
||||
val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |
|
||||
CPACR_EL1_ZEN_EL1EN);
|
||||
val = (CPACR_ELx_FPEN | CPACR_EL1_ZEN_EL1EN);
|
||||
if (cpus_have_final_cap(ARM64_SME))
|
||||
val |= CPACR_EL1_SMEN_EL1EN;
|
||||
} else if (has_hvhe()) {
|
||||
val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN);
|
||||
val = CPACR_ELx_FPEN;
|
||||
|
||||
if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs())
|
||||
val |= CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN;
|
||||
val |= CPACR_ELx_ZEN;
|
||||
if (cpus_have_final_cap(ARM64_SME))
|
||||
val |= CPACR_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN;
|
||||
val |= CPACR_ELx_SMEN;
|
||||
} else {
|
||||
val = CPTR_NVHE_EL2_RES1;
|
||||
|
||||
|
||||
@@ -76,6 +76,7 @@ static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; };
|
||||
DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
|
||||
|
||||
extern unsigned int __ro_after_init kvm_sve_max_vl;
|
||||
extern unsigned int __ro_after_init kvm_host_sve_max_vl;
|
||||
int __init kvm_arm_init_sve(void);
|
||||
|
||||
u32 __attribute_const__ kvm_target_cpu(void);
|
||||
@@ -521,6 +522,20 @@ struct kvm_cpu_context {
|
||||
u64 *vncr_array;
|
||||
};
|
||||
|
||||
struct cpu_sve_state {
|
||||
__u64 zcr_el1;
|
||||
|
||||
/*
|
||||
* Ordering is important since __sve_save_state/__sve_restore_state
|
||||
* relies on it.
|
||||
*/
|
||||
__u32 fpsr;
|
||||
__u32 fpcr;
|
||||
|
||||
/* Must be SVE_VQ_BYTES (128 bit) aligned. */
|
||||
__u8 sve_regs[];
|
||||
};
|
||||
|
||||
/*
|
||||
* This structure is instantiated on a per-CPU basis, and contains
|
||||
* data that is:
|
||||
@@ -534,7 +549,15 @@ struct kvm_cpu_context {
|
||||
*/
|
||||
struct kvm_host_data {
|
||||
struct kvm_cpu_context host_ctxt;
|
||||
struct user_fpsimd_state *fpsimd_state; /* hyp VA */
|
||||
|
||||
/*
|
||||
* All pointers in this union are hyp VA.
|
||||
* sve_state is only used in pKVM and if system_supports_sve().
|
||||
*/
|
||||
union {
|
||||
struct user_fpsimd_state *fpsimd_state;
|
||||
struct cpu_sve_state *sve_state;
|
||||
};
|
||||
|
||||
/* Ownership of the FP regs */
|
||||
enum {
|
||||
|
||||
@@ -111,7 +111,8 @@ void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu);
|
||||
|
||||
void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
|
||||
void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
|
||||
void __sve_restore_state(void *sve_pffr, u32 *fpsr);
|
||||
void __sve_save_state(void *sve_pffr, u32 *fpsr, int save_ffr);
|
||||
void __sve_restore_state(void *sve_pffr, u32 *fpsr, int restore_ffr);
|
||||
|
||||
u64 __guest_enter(struct kvm_vcpu *vcpu);
|
||||
|
||||
@@ -142,5 +143,6 @@ extern u64 kvm_nvhe_sym(id_aa64smfr0_el1_sys_val);
|
||||
|
||||
extern unsigned long kvm_nvhe_sym(__icache_flags);
|
||||
extern unsigned int kvm_nvhe_sym(kvm_arm_vmid_bits);
|
||||
extern unsigned int kvm_nvhe_sym(kvm_host_sve_max_vl);
|
||||
|
||||
#endif /* __ARM64_KVM_HYP_H__ */
|
||||
|
||||
@@ -128,4 +128,13 @@ static inline unsigned long hyp_ffa_proxy_pages(void)
|
||||
return (2 * KVM_FFA_MBOX_NR_PAGES) + DIV_ROUND_UP(desc_max, PAGE_SIZE);
|
||||
}
|
||||
|
||||
static inline size_t pkvm_host_sve_state_size(void)
|
||||
{
|
||||
if (!system_supports_sve())
|
||||
return 0;
|
||||
|
||||
return size_add(sizeof(struct cpu_sve_state),
|
||||
SVE_SIG_REGS_SIZE(sve_vq_from_vl(kvm_host_sve_max_vl)));
|
||||
}
|
||||
|
||||
#endif /* __ARM64_KVM_PKVM_H__ */
|
||||
|
||||
@@ -1931,6 +1931,11 @@ static unsigned long nvhe_percpu_order(void)
|
||||
return size ? get_order(size) : 0;
|
||||
}
|
||||
|
||||
static size_t pkvm_host_sve_state_order(void)
|
||||
{
|
||||
return get_order(pkvm_host_sve_state_size());
|
||||
}
|
||||
|
||||
/* A lookup table holding the hypervisor VA for each vector slot */
|
||||
static void *hyp_spectre_vector_selector[BP_HARDEN_EL2_SLOTS];
|
||||
|
||||
@@ -2310,12 +2315,20 @@ static void __init teardown_subsystems(void)
|
||||
|
||||
static void __init teardown_hyp_mode(void)
|
||||
{
|
||||
bool free_sve = system_supports_sve() && is_protected_kvm_enabled();
|
||||
int cpu;
|
||||
|
||||
free_hyp_pgds();
|
||||
for_each_possible_cpu(cpu) {
|
||||
free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
|
||||
free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
|
||||
|
||||
if (free_sve) {
|
||||
struct cpu_sve_state *sve_state;
|
||||
|
||||
sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
|
||||
free_pages((unsigned long) sve_state, pkvm_host_sve_state_order());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2398,6 +2411,58 @@ static int __init kvm_hyp_init_protection(u32 hyp_va_bits)
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int init_pkvm_host_sve_state(void)
|
||||
{
|
||||
int cpu;
|
||||
|
||||
if (!system_supports_sve())
|
||||
return 0;
|
||||
|
||||
/* Allocate pages for host sve state in protected mode. */
|
||||
for_each_possible_cpu(cpu) {
|
||||
struct page *page = alloc_pages(GFP_KERNEL, pkvm_host_sve_state_order());
|
||||
|
||||
if (!page)
|
||||
return -ENOMEM;
|
||||
|
||||
per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = page_address(page);
|
||||
}
|
||||
|
||||
/*
|
||||
* Don't map the pages in hyp since these are only used in protected
|
||||
* mode, which will (re)create its own mapping when initialized.
|
||||
*/
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* Finalizes the initialization of hyp mode, once everything else is initialized
|
||||
* and the initialziation process cannot fail.
|
||||
*/
|
||||
static void finalize_init_hyp_mode(void)
|
||||
{
|
||||
int cpu;
|
||||
|
||||
if (system_supports_sve() && is_protected_kvm_enabled()) {
|
||||
for_each_possible_cpu(cpu) {
|
||||
struct cpu_sve_state *sve_state;
|
||||
|
||||
sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
|
||||
per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state =
|
||||
kern_hyp_va(sve_state);
|
||||
}
|
||||
} else {
|
||||
for_each_possible_cpu(cpu) {
|
||||
struct user_fpsimd_state *fpsimd_state;
|
||||
|
||||
fpsimd_state = &per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->host_ctxt.fp_regs;
|
||||
per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->fpsimd_state =
|
||||
kern_hyp_va(fpsimd_state);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
static void pkvm_hyp_init_ptrauth(void)
|
||||
{
|
||||
struct kvm_cpu_context *hyp_ctxt;
|
||||
@@ -2566,6 +2631,10 @@ static int __init init_hyp_mode(void)
|
||||
goto out_err;
|
||||
}
|
||||
|
||||
err = init_pkvm_host_sve_state();
|
||||
if (err)
|
||||
goto out_err;
|
||||
|
||||
err = kvm_hyp_init_protection(hyp_va_bits);
|
||||
if (err) {
|
||||
kvm_err("Failed to init hyp memory protection\n");
|
||||
@@ -2730,6 +2799,13 @@ static __init int kvm_arm_init(void)
|
||||
if (err)
|
||||
goto out_subs;
|
||||
|
||||
/*
|
||||
* This should be called after initialization is done and failure isn't
|
||||
* possible anymore.
|
||||
*/
|
||||
if (!in_hyp_mode)
|
||||
finalize_init_hyp_mode();
|
||||
|
||||
kvm_arm_initialised = true;
|
||||
|
||||
return 0;
|
||||
|
||||
@@ -2181,16 +2181,23 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
|
||||
if (forward_traps(vcpu, HCR_NV))
|
||||
return;
|
||||
|
||||
spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2);
|
||||
spsr = kvm_check_illegal_exception_return(vcpu, spsr);
|
||||
|
||||
/* Check for an ERETAx */
|
||||
esr = kvm_vcpu_get_esr(vcpu);
|
||||
if (esr_iss_is_eretax(esr) && !kvm_auth_eretax(vcpu, &elr)) {
|
||||
/*
|
||||
* Oh no, ERETAx failed to authenticate. If we have
|
||||
* FPACCOMBINE, deliver an exception right away. If we
|
||||
* don't, then let the mangled ELR value trickle down the
|
||||
* Oh no, ERETAx failed to authenticate.
|
||||
*
|
||||
* If we have FPACCOMBINE and we don't have a pending
|
||||
* Illegal Execution State exception (which has priority
|
||||
* over FPAC), deliver an exception right away.
|
||||
*
|
||||
* Otherwise, let the mangled ELR value trickle down the
|
||||
* ERET handling, and the guest will have a little surprise.
|
||||
*/
|
||||
if (kvm_has_pauth(vcpu->kvm, FPACCOMBINE)) {
|
||||
if (kvm_has_pauth(vcpu->kvm, FPACCOMBINE) && !(spsr & PSR_IL_BIT)) {
|
||||
esr &= ESR_ELx_ERET_ISS_ERETA;
|
||||
esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_FPAC);
|
||||
kvm_inject_nested_sync(vcpu, esr);
|
||||
@@ -2201,17 +2208,11 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
|
||||
preempt_disable();
|
||||
kvm_arch_vcpu_put(vcpu);
|
||||
|
||||
spsr = __vcpu_sys_reg(vcpu, SPSR_EL2);
|
||||
spsr = kvm_check_illegal_exception_return(vcpu, spsr);
|
||||
if (!esr_iss_is_eretax(esr))
|
||||
elr = __vcpu_sys_reg(vcpu, ELR_EL2);
|
||||
|
||||
trace_kvm_nested_eret(vcpu, elr, spsr);
|
||||
|
||||
/*
|
||||
* Note that the current exception level is always the virtual EL2,
|
||||
* since we set HCR_EL2.NV bit only when entering the virtual EL2.
|
||||
*/
|
||||
*vcpu_pc(vcpu) = elr;
|
||||
*vcpu_cpsr(vcpu) = spsr;
|
||||
|
||||
|
||||
@@ -90,6 +90,13 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
|
||||
fpsimd_save_and_flush_cpu_state();
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* If normal guests gain SME support, maintain this behavior for pKVM
|
||||
* guests, which don't support SME.
|
||||
*/
|
||||
WARN_ON(is_protected_kvm_enabled() && system_supports_sme() &&
|
||||
read_sysreg_s(SYS_SVCR));
|
||||
}
|
||||
|
||||
/*
|
||||
@@ -161,9 +168,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
|
||||
if (has_vhe() && system_supports_sme()) {
|
||||
/* Also restore EL0 state seen on entry */
|
||||
if (vcpu_get_flag(vcpu, HOST_SME_ENABLED))
|
||||
sysreg_clear_set(CPACR_EL1, 0,
|
||||
CPACR_EL1_SMEN_EL0EN |
|
||||
CPACR_EL1_SMEN_EL1EN);
|
||||
sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_SMEN);
|
||||
else
|
||||
sysreg_clear_set(CPACR_EL1,
|
||||
CPACR_EL1_SMEN_EL0EN,
|
||||
|
||||
@@ -251,6 +251,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
|
||||
case PSR_AA32_MODE_SVC:
|
||||
case PSR_AA32_MODE_ABT:
|
||||
case PSR_AA32_MODE_UND:
|
||||
case PSR_AA32_MODE_SYS:
|
||||
if (!vcpu_el1_is_32bit(vcpu))
|
||||
return -EINVAL;
|
||||
break;
|
||||
@@ -276,7 +277,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
|
||||
if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
|
||||
int i, nr_reg;
|
||||
|
||||
switch (*vcpu_cpsr(vcpu)) {
|
||||
switch (*vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK) {
|
||||
/*
|
||||
* Either we are dealing with user mode, and only the
|
||||
* first 15 registers (+ PC) must be narrowed to 32bit.
|
||||
|
||||
@@ -50,9 +50,23 @@ bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
|
||||
u32 cpsr_cond;
|
||||
int cond;
|
||||
|
||||
/* Top two bits non-zero? Unconditional. */
|
||||
if (kvm_vcpu_get_esr(vcpu) >> 30)
|
||||
/*
|
||||
* These are the exception classes that could fire with a
|
||||
* conditional instruction.
|
||||
*/
|
||||
switch (kvm_vcpu_trap_get_class(vcpu)) {
|
||||
case ESR_ELx_EC_CP15_32:
|
||||
case ESR_ELx_EC_CP15_64:
|
||||
case ESR_ELx_EC_CP14_MR:
|
||||
case ESR_ELx_EC_CP14_LS:
|
||||
case ESR_ELx_EC_FP_ASIMD:
|
||||
case ESR_ELx_EC_CP10_ID:
|
||||
case ESR_ELx_EC_CP14_64:
|
||||
case ESR_ELx_EC_SVC32:
|
||||
break;
|
||||
default:
|
||||
return true;
|
||||
}
|
||||
|
||||
/* Is condition field valid? */
|
||||
cond = kvm_vcpu_get_condition(vcpu);
|
||||
|
||||
@@ -25,3 +25,9 @@ SYM_FUNC_START(__sve_restore_state)
|
||||
sve_load 0, x1, x2, 3
|
||||
ret
|
||||
SYM_FUNC_END(__sve_restore_state)
|
||||
|
||||
SYM_FUNC_START(__sve_save_state)
|
||||
mov x2, #1
|
||||
sve_save 0, x1, x2, 3
|
||||
ret
|
||||
SYM_FUNC_END(__sve_save_state)
|
||||
|
||||
@@ -316,10 +316,24 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
|
||||
__sve_restore_state(vcpu_sve_pffr(vcpu),
|
||||
&vcpu->arch.ctxt.fp_regs.fpsr);
|
||||
&vcpu->arch.ctxt.fp_regs.fpsr,
|
||||
true);
|
||||
write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
|
||||
}
|
||||
|
||||
static inline void __hyp_sve_save_host(void)
|
||||
{
|
||||
struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);
|
||||
|
||||
sve_state->zcr_el1 = read_sysreg_el1(SYS_ZCR);
|
||||
write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
|
||||
__sve_save_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
|
||||
&sve_state->fpsr,
|
||||
true);
|
||||
}
|
||||
|
||||
static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu);
|
||||
|
||||
/*
|
||||
* We trap the first access to the FP/SIMD to save the host context and
|
||||
* restore the guest context lazily.
|
||||
@@ -330,7 +344,6 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
|
||||
{
|
||||
bool sve_guest;
|
||||
u8 esr_ec;
|
||||
u64 reg;
|
||||
|
||||
if (!system_supports_fpsimd())
|
||||
return false;
|
||||
@@ -353,24 +366,15 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
|
||||
/* Valid trap. Switch the context: */
|
||||
|
||||
/* First disable enough traps to allow us to update the registers */
|
||||
if (has_vhe() || has_hvhe()) {
|
||||
reg = CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN;
|
||||
if (sve_guest)
|
||||
reg |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
|
||||
|
||||
sysreg_clear_set(cpacr_el1, 0, reg);
|
||||
} else {
|
||||
reg = CPTR_EL2_TFP;
|
||||
if (sve_guest)
|
||||
reg |= CPTR_EL2_TZ;
|
||||
|
||||
sysreg_clear_set(cptr_el2, reg, 0);
|
||||
}
|
||||
if (sve_guest || (is_protected_kvm_enabled() && system_supports_sve()))
|
||||
cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN);
|
||||
else
|
||||
cpacr_clear_set(0, CPACR_ELx_FPEN);
|
||||
isb();
|
||||
|
||||
/* Write out the host state if it's in the registers */
|
||||
if (host_owns_fp_regs())
|
||||
__fpsimd_save_state(*host_data_ptr(fpsimd_state));
|
||||
kvm_hyp_save_fpsimd_host(vcpu);
|
||||
|
||||
/* Restore the guest state */
|
||||
if (sve_guest)
|
||||
|
||||
@@ -59,7 +59,6 @@ static inline bool pkvm_hyp_vcpu_is_protected(struct pkvm_hyp_vcpu *hyp_vcpu)
|
||||
}
|
||||
|
||||
void pkvm_hyp_vm_table_init(void *tbl);
|
||||
void pkvm_host_fpsimd_state_init(void);
|
||||
|
||||
int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
|
||||
unsigned long pgd_hva);
|
||||
|
||||
@@ -23,20 +23,80 @@ DEFINE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
|
||||
|
||||
void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt);
|
||||
|
||||
static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);
|
||||
/*
|
||||
* On saving/restoring guest sve state, always use the maximum VL for
|
||||
* the guest. The layout of the data when saving the sve state depends
|
||||
* on the VL, so use a consistent (i.e., the maximum) guest VL.
|
||||
*/
|
||||
sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
|
||||
__sve_save_state(vcpu_sve_pffr(vcpu), &vcpu->arch.ctxt.fp_regs.fpsr, true);
|
||||
write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
|
||||
}
|
||||
|
||||
static void __hyp_sve_restore_host(void)
|
||||
{
|
||||
struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);
|
||||
|
||||
/*
|
||||
* On saving/restoring host sve state, always use the maximum VL for
|
||||
* the host. The layout of the data when saving the sve state depends
|
||||
* on the VL, so use a consistent (i.e., the maximum) host VL.
|
||||
*
|
||||
* Setting ZCR_EL2 to ZCR_ELx_LEN_MASK sets the effective length
|
||||
* supported by the system (or limited at EL3).
|
||||
*/
|
||||
write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
|
||||
__sve_restore_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
|
||||
&sve_state->fpsr,
|
||||
true);
|
||||
write_sysreg_el1(sve_state->zcr_el1, SYS_ZCR);
|
||||
}
|
||||
|
||||
static void fpsimd_sve_flush(void)
|
||||
{
|
||||
*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
|
||||
}
|
||||
|
||||
static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
if (!guest_owns_fp_regs())
|
||||
return;
|
||||
|
||||
cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN);
|
||||
isb();
|
||||
|
||||
if (vcpu_has_sve(vcpu))
|
||||
__hyp_sve_save_guest(vcpu);
|
||||
else
|
||||
__fpsimd_save_state(&vcpu->arch.ctxt.fp_regs);
|
||||
|
||||
if (system_supports_sve())
|
||||
__hyp_sve_restore_host();
|
||||
else
|
||||
__fpsimd_restore_state(*host_data_ptr(fpsimd_state));
|
||||
|
||||
*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
|
||||
}
|
||||
|
||||
static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
|
||||
{
|
||||
struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
|
||||
|
||||
fpsimd_sve_flush();
|
||||
|
||||
hyp_vcpu->vcpu.arch.ctxt = host_vcpu->arch.ctxt;
|
||||
|
||||
hyp_vcpu->vcpu.arch.sve_state = kern_hyp_va(host_vcpu->arch.sve_state);
|
||||
hyp_vcpu->vcpu.arch.sve_max_vl = host_vcpu->arch.sve_max_vl;
|
||||
/* Limit guest vector length to the maximum supported by the host. */
|
||||
hyp_vcpu->vcpu.arch.sve_max_vl = min(host_vcpu->arch.sve_max_vl, kvm_host_sve_max_vl);
|
||||
|
||||
hyp_vcpu->vcpu.arch.hw_mmu = host_vcpu->arch.hw_mmu;
|
||||
|
||||
hyp_vcpu->vcpu.arch.hcr_el2 = host_vcpu->arch.hcr_el2;
|
||||
hyp_vcpu->vcpu.arch.mdcr_el2 = host_vcpu->arch.mdcr_el2;
|
||||
hyp_vcpu->vcpu.arch.cptr_el2 = host_vcpu->arch.cptr_el2;
|
||||
|
||||
hyp_vcpu->vcpu.arch.iflags = host_vcpu->arch.iflags;
|
||||
|
||||
@@ -54,10 +114,11 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
|
||||
struct vgic_v3_cpu_if *host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3;
|
||||
unsigned int i;
|
||||
|
||||
fpsimd_sve_sync(&hyp_vcpu->vcpu);
|
||||
|
||||
host_vcpu->arch.ctxt = hyp_vcpu->vcpu.arch.ctxt;
|
||||
|
||||
host_vcpu->arch.hcr_el2 = hyp_vcpu->vcpu.arch.hcr_el2;
|
||||
host_vcpu->arch.cptr_el2 = hyp_vcpu->vcpu.arch.cptr_el2;
|
||||
|
||||
host_vcpu->arch.fault = hyp_vcpu->vcpu.arch.fault;
|
||||
|
||||
@@ -79,6 +140,17 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
|
||||
struct pkvm_hyp_vcpu *hyp_vcpu;
|
||||
struct kvm *host_kvm;
|
||||
|
||||
/*
|
||||
* KVM (and pKVM) doesn't support SME guests for now, and
|
||||
* ensures that SME features aren't enabled in pstate when
|
||||
* loading a vcpu. Therefore, if SME features enabled the host
|
||||
* is misbehaving.
|
||||
*/
|
||||
if (unlikely(system_supports_sme() && read_sysreg_s(SYS_SVCR))) {
|
||||
ret = -EINVAL;
|
||||
goto out;
|
||||
}
|
||||
|
||||
host_kvm = kern_hyp_va(host_vcpu->kvm);
|
||||
hyp_vcpu = pkvm_load_hyp_vcpu(host_kvm->arch.pkvm.handle,
|
||||
host_vcpu->vcpu_idx);
|
||||
@@ -405,11 +477,7 @@ void handle_trap(struct kvm_cpu_context *host_ctxt)
|
||||
handle_host_smc(host_ctxt);
|
||||
break;
|
||||
case ESR_ELx_EC_SVE:
|
||||
if (has_hvhe())
|
||||
sysreg_clear_set(cpacr_el1, 0, (CPACR_EL1_ZEN_EL1EN |
|
||||
CPACR_EL1_ZEN_EL0EN));
|
||||
else
|
||||
sysreg_clear_set(cptr_el2, CPTR_EL2_TZ, 0);
|
||||
cpacr_clear_set(0, CPACR_ELx_ZEN);
|
||||
isb();
|
||||
sve_cond_update_zcr_vq(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
|
||||
break;
|
||||
|
||||
@@ -18,6 +18,8 @@ unsigned long __icache_flags;
|
||||
/* Used by kvm_get_vttbr(). */
|
||||
unsigned int kvm_arm_vmid_bits;
|
||||
|
||||
unsigned int kvm_host_sve_max_vl;
|
||||
|
||||
/*
|
||||
* Set trap register values based on features in ID_AA64PFR0.
|
||||
*/
|
||||
@@ -63,7 +65,7 @@ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu)
|
||||
/* Trap SVE */
|
||||
if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), feature_ids)) {
|
||||
if (has_hvhe())
|
||||
cptr_clear |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
|
||||
cptr_clear |= CPACR_ELx_ZEN;
|
||||
else
|
||||
cptr_set |= CPTR_EL2_TZ;
|
||||
}
|
||||
@@ -247,17 +249,6 @@ void pkvm_hyp_vm_table_init(void *tbl)
|
||||
vm_table = tbl;
|
||||
}
|
||||
|
||||
void pkvm_host_fpsimd_state_init(void)
|
||||
{
|
||||
unsigned long i;
|
||||
|
||||
for (i = 0; i < hyp_nr_cpus; i++) {
|
||||
struct kvm_host_data *host_data = per_cpu_ptr(&kvm_host_data, i);
|
||||
|
||||
host_data->fpsimd_state = &host_data->host_ctxt.fp_regs;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Return the hyp vm structure corresponding to the handle.
|
||||
*/
|
||||
@@ -586,6 +577,8 @@ unlock:
|
||||
if (ret)
|
||||
unmap_donated_memory(hyp_vcpu, sizeof(*hyp_vcpu));
|
||||
|
||||
hyp_vcpu->vcpu.arch.cptr_el2 = kvm_get_reset_cptr_el2(&hyp_vcpu->vcpu);
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
|
||||
@@ -67,6 +67,28 @@ static int divide_memory_pool(void *virt, unsigned long size)
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int pkvm_create_host_sve_mappings(void)
|
||||
{
|
||||
void *start, *end;
|
||||
int ret, i;
|
||||
|
||||
if (!system_supports_sve())
|
||||
return 0;
|
||||
|
||||
for (i = 0; i < hyp_nr_cpus; i++) {
|
||||
struct kvm_host_data *host_data = per_cpu_ptr(&kvm_host_data, i);
|
||||
struct cpu_sve_state *sve_state = host_data->sve_state;
|
||||
|
||||
start = kern_hyp_va(sve_state);
|
||||
end = start + PAGE_ALIGN(pkvm_host_sve_state_size());
|
||||
ret = pkvm_create_mappings(start, end, PAGE_HYP);
|
||||
if (ret)
|
||||
return ret;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
|
||||
unsigned long *per_cpu_base,
|
||||
u32 hyp_va_bits)
|
||||
@@ -125,6 +147,8 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
|
||||
return ret;
|
||||
}
|
||||
|
||||
pkvm_create_host_sve_mappings();
|
||||
|
||||
/*
|
||||
* Map the host sections RO in the hypervisor, but transfer the
|
||||
* ownership from the host to the hypervisor itself to make sure they
|
||||
@@ -300,7 +324,6 @@ void __noreturn __pkvm_init_finalise(void)
|
||||
goto out;
|
||||
|
||||
pkvm_hyp_vm_table_init(vm_table_base);
|
||||
pkvm_host_fpsimd_state_init();
|
||||
out:
|
||||
/*
|
||||
* We tail-called to here from handle___pkvm_init() and will not return,
|
||||
|
||||
@@ -48,15 +48,14 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
|
||||
val |= has_hvhe() ? CPACR_EL1_TTA : CPTR_EL2_TTA;
|
||||
if (cpus_have_final_cap(ARM64_SME)) {
|
||||
if (has_hvhe())
|
||||
val &= ~(CPACR_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN);
|
||||
val &= ~CPACR_ELx_SMEN;
|
||||
else
|
||||
val |= CPTR_EL2_TSM;
|
||||
}
|
||||
|
||||
if (!guest_owns_fp_regs()) {
|
||||
if (has_hvhe())
|
||||
val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |
|
||||
CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN);
|
||||
val &= ~(CPACR_ELx_FPEN | CPACR_ELx_ZEN);
|
||||
else
|
||||
val |= CPTR_EL2_TFP | CPTR_EL2_TZ;
|
||||
|
||||
@@ -182,6 +181,25 @@ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code)
|
||||
kvm_handle_pvm_sysreg(vcpu, exit_code));
|
||||
}
|
||||
|
||||
static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
/*
|
||||
* Non-protected kvm relies on the host restoring its sve state.
|
||||
* Protected kvm restores the host's sve state as not to reveal that
|
||||
* fpsimd was used by a guest nor leak upper sve bits.
|
||||
*/
|
||||
if (unlikely(is_protected_kvm_enabled() && system_supports_sve())) {
|
||||
__hyp_sve_save_host();
|
||||
|
||||
/* Re-enable SVE traps if not supported for the guest vcpu. */
|
||||
if (!vcpu_has_sve(vcpu))
|
||||
cpacr_clear_set(CPACR_ELx_ZEN, 0);
|
||||
|
||||
} else {
|
||||
__fpsimd_save_state(*host_data_ptr(fpsimd_state));
|
||||
}
|
||||
}
|
||||
|
||||
static const exit_handler_fn hyp_exit_handlers[] = {
|
||||
[0 ... ESR_ELx_EC_MAX] = NULL,
|
||||
[ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32,
|
||||
|
||||
@@ -93,8 +93,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
|
||||
|
||||
val = read_sysreg(cpacr_el1);
|
||||
val |= CPACR_ELx_TTA;
|
||||
val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN |
|
||||
CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN);
|
||||
val &= ~(CPACR_ELx_ZEN | CPACR_ELx_SMEN);
|
||||
|
||||
/*
|
||||
* With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
|
||||
@@ -109,9 +108,9 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
|
||||
|
||||
if (guest_owns_fp_regs()) {
|
||||
if (vcpu_has_sve(vcpu))
|
||||
val |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
|
||||
val |= CPACR_ELx_ZEN;
|
||||
} else {
|
||||
val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN);
|
||||
val &= ~CPACR_ELx_FPEN;
|
||||
__activate_traps_fpsimd32(vcpu);
|
||||
}
|
||||
|
||||
@@ -262,6 +261,11 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
|
||||
return true;
|
||||
}
|
||||
|
||||
static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
__fpsimd_save_state(*host_data_ptr(fpsimd_state));
|
||||
}
|
||||
|
||||
static const exit_handler_fn hyp_exit_handlers[] = {
|
||||
[0 ... ESR_ELx_EC_MAX] = NULL,
|
||||
[ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32,
|
||||
|
||||
@@ -58,8 +58,10 @@ static u64 limit_nv_id_reg(u32 id, u64 val)
|
||||
break;
|
||||
|
||||
case SYS_ID_AA64PFR1_EL1:
|
||||
/* Only support SSBS */
|
||||
val &= NV_FTR(PFR1, SSBS);
|
||||
/* Only support BTI, SSBS, CSV2_frac */
|
||||
val &= (NV_FTR(PFR1, BT) |
|
||||
NV_FTR(PFR1, SSBS) |
|
||||
NV_FTR(PFR1, CSV2_frac));
|
||||
break;
|
||||
|
||||
case SYS_ID_AA64MMFR0_EL1:
|
||||
|
||||
@@ -32,6 +32,7 @@
|
||||
|
||||
/* Maximum phys_shift supported for any VM on this host */
|
||||
static u32 __ro_after_init kvm_ipa_limit;
|
||||
unsigned int __ro_after_init kvm_host_sve_max_vl;
|
||||
|
||||
/*
|
||||
* ARMv8 Reset Values
|
||||
@@ -51,6 +52,8 @@ int __init kvm_arm_init_sve(void)
|
||||
{
|
||||
if (system_supports_sve()) {
|
||||
kvm_sve_max_vl = sve_max_virtualisable_vl();
|
||||
kvm_host_sve_max_vl = sve_max_vl();
|
||||
kvm_nvhe_sym(kvm_host_sve_max_vl) = kvm_host_sve_max_vl;
|
||||
|
||||
/*
|
||||
* The get_sve_reg()/set_sve_reg() ioctl interface will need
|
||||
|
||||
@@ -44,14 +44,14 @@
|
||||
&gmac0 {
|
||||
status = "okay";
|
||||
|
||||
phy-mode = "rgmii";
|
||||
phy-mode = "rgmii-id";
|
||||
bus_id = <0x0>;
|
||||
};
|
||||
|
||||
&gmac1 {
|
||||
status = "okay";
|
||||
|
||||
phy-mode = "rgmii";
|
||||
phy-mode = "rgmii-id";
|
||||
bus_id = <0x1>;
|
||||
};
|
||||
|
||||
|
||||
@@ -43,7 +43,7 @@
|
||||
&gmac0 {
|
||||
status = "okay";
|
||||
|
||||
phy-mode = "rgmii";
|
||||
phy-mode = "rgmii-id";
|
||||
phy-handle = <&phy0>;
|
||||
mdio {
|
||||
compatible = "snps,dwmac-mdio";
|
||||
@@ -58,7 +58,7 @@
|
||||
&gmac1 {
|
||||
status = "okay";
|
||||
|
||||
phy-mode = "rgmii";
|
||||
phy-mode = "rgmii-id";
|
||||
phy-handle = <&phy1>;
|
||||
mdio {
|
||||
compatible = "snps,dwmac-mdio";
|
||||
|
||||
@@ -92,7 +92,7 @@
|
||||
&gmac2 {
|
||||
status = "okay";
|
||||
|
||||
phy-mode = "rgmii";
|
||||
phy-mode = "rgmii-id";
|
||||
phy-handle = <&phy2>;
|
||||
mdio {
|
||||
compatible = "snps,dwmac-mdio";
|
||||
|
||||
@@ -56,6 +56,7 @@ extern int early_cpu_to_node(int cpu);
|
||||
static inline void early_numa_add_cpu(int cpuid, s16 node) { }
|
||||
static inline void numa_add_cpu(unsigned int cpu) { }
|
||||
static inline void numa_remove_cpu(unsigned int cpu) { }
|
||||
static inline void set_cpuid_to_node(int cpuid, s16 node) { }
|
||||
|
||||
static inline int early_cpu_to_node(int cpu)
|
||||
{
|
||||
|
||||
@@ -42,7 +42,7 @@
|
||||
.macro JUMP_VIRT_ADDR temp1 temp2
|
||||
li.d \temp1, CACHE_BASE
|
||||
pcaddi \temp2, 0
|
||||
or \temp1, \temp1, \temp2
|
||||
bstrins.d \temp1, \temp2, (DMW_PABITS - 1), 0
|
||||
jirl zero, \temp1, 0xc
|
||||
.endm
|
||||
|
||||
|
||||
@@ -22,7 +22,7 @@
|
||||
_head:
|
||||
.word MZ_MAGIC /* "MZ", MS-DOS header */
|
||||
.org 0x8
|
||||
.dword kernel_entry /* Kernel entry point */
|
||||
.dword _kernel_entry /* Kernel entry point (physical address) */
|
||||
.dword _kernel_asize /* Kernel image effective size */
|
||||
.quad PHYS_LINK_KADDR /* Kernel image load offset from start of RAM */
|
||||
.org 0x38 /* 0x20 ~ 0x37 reserved */
|
||||
|
||||
@@ -282,7 +282,7 @@ static void __init fdt_setup(void)
|
||||
return;
|
||||
|
||||
/* Prefer to use built-in dtb, checking its legality first. */
|
||||
if (!fdt_check_header(__dtb_start))
|
||||
if (IS_ENABLED(CONFIG_BUILTIN_DTB) && !fdt_check_header(__dtb_start))
|
||||
fdt_pointer = __dtb_start;
|
||||
else
|
||||
fdt_pointer = efi_fdt_pointer(); /* Fallback to firmware dtb */
|
||||
@@ -351,10 +351,8 @@ void __init platform_init(void)
|
||||
arch_reserve_vmcore();
|
||||
arch_reserve_crashkernel();
|
||||
|
||||
#ifdef CONFIG_ACPI_TABLE_UPGRADE
|
||||
acpi_table_upgrade();
|
||||
#endif
|
||||
#ifdef CONFIG_ACPI
|
||||
acpi_table_upgrade();
|
||||
acpi_gbl_use_default_register_widths = false;
|
||||
acpi_boot_table_init();
|
||||
#endif
|
||||
|
||||
@@ -273,7 +273,6 @@ static void __init fdt_smp_setup(void)
|
||||
|
||||
if (cpuid == loongson_sysconf.boot_cpu_id) {
|
||||
cpu = 0;
|
||||
numa_add_cpu(cpu);
|
||||
} else {
|
||||
cpu = cpumask_next_zero(-1, cpu_present_mask);
|
||||
}
|
||||
@@ -283,6 +282,9 @@ static void __init fdt_smp_setup(void)
|
||||
set_cpu_present(cpu, true);
|
||||
__cpu_number_map[cpuid] = cpu;
|
||||
__cpu_logical_map[cpu] = cpuid;
|
||||
|
||||
early_numa_add_cpu(cpu, 0);
|
||||
set_cpuid_to_node(cpuid, 0);
|
||||
}
|
||||
|
||||
loongson_sysconf.nr_cpus = num_processors;
|
||||
@@ -468,6 +470,7 @@ void smp_prepare_boot_cpu(void)
|
||||
set_cpu_possible(0, true);
|
||||
set_cpu_online(0, true);
|
||||
set_my_cpu_offset(per_cpu_offset(0));
|
||||
numa_add_cpu(0);
|
||||
|
||||
rr_node = first_node(node_online_map);
|
||||
for_each_possible_cpu(cpu) {
|
||||
|
||||
@@ -6,6 +6,7 @@
|
||||
|
||||
#define PAGE_SIZE _PAGE_SIZE
|
||||
#define RO_EXCEPTION_TABLE_ALIGN 4
|
||||
#define PHYSADDR_MASK 0xffffffffffff /* 48-bit */
|
||||
|
||||
/*
|
||||
* Put .bss..swapper_pg_dir as the first thing in .bss. This will
|
||||
@@ -142,10 +143,11 @@ SECTIONS
|
||||
|
||||
#ifdef CONFIG_EFI_STUB
|
||||
/* header symbols */
|
||||
_kernel_asize = _end - _text;
|
||||
_kernel_fsize = _edata - _text;
|
||||
_kernel_vsize = _end - __initdata_begin;
|
||||
_kernel_rsize = _edata - __initdata_begin;
|
||||
_kernel_entry = ABSOLUTE(kernel_entry & PHYSADDR_MASK);
|
||||
_kernel_asize = ABSOLUTE(_end - _text);
|
||||
_kernel_fsize = ABSOLUTE(_edata - _text);
|
||||
_kernel_vsize = ABSOLUTE(_end - __initdata_begin);
|
||||
_kernel_rsize = ABSOLUTE(_edata - __initdata_begin);
|
||||
#endif
|
||||
|
||||
.gptab.sdata : {
|
||||
|
||||
@@ -137,7 +137,7 @@ config PPC
|
||||
select ARCH_HAS_GCOV_PROFILE_ALL
|
||||
select ARCH_HAS_HUGEPD if HUGETLB_PAGE
|
||||
select ARCH_HAS_KCOV
|
||||
select ARCH_HAS_KERNEL_FPU_SUPPORT if PPC_FPU
|
||||
select ARCH_HAS_KERNEL_FPU_SUPPORT if PPC64 && PPC_FPU
|
||||
select ARCH_HAS_MEMBARRIER_CALLBACKS
|
||||
select ARCH_HAS_MEMBARRIER_SYNC_CORE
|
||||
select ARCH_HAS_MEMREMAP_COMPAT_ALIGN if PPC_64S_HASH_MMU
|
||||
|
||||
@@ -92,9 +92,25 @@ __pu_failed: \
|
||||
: label)
|
||||
#endif
|
||||
|
||||
#ifdef CONFIG_CC_IS_CLANG
|
||||
#define DS_FORM_CONSTRAINT "Z<>"
|
||||
#else
|
||||
#define DS_FORM_CONSTRAINT "YZ<>"
|
||||
#endif
|
||||
|
||||
#ifdef __powerpc64__
|
||||
#ifdef CONFIG_PPC_KERNEL_PREFIXED
|
||||
#define __put_user_asm2_goto(x, ptr, label) \
|
||||
__put_user_asm_goto(x, ptr, label, "std")
|
||||
#else
|
||||
#define __put_user_asm2_goto(x, addr, label) \
|
||||
asm goto ("1: std%U1%X1 %0,%1 # put_user\n" \
|
||||
EX_TABLE(1b, %l2) \
|
||||
: \
|
||||
: "r" (x), DS_FORM_CONSTRAINT (*addr) \
|
||||
: \
|
||||
: label)
|
||||
#endif // CONFIG_PPC_KERNEL_PREFIXED
|
||||
#else /* __powerpc64__ */
|
||||
#define __put_user_asm2_goto(x, addr, label) \
|
||||
asm goto( \
|
||||
@@ -165,8 +181,19 @@ do { \
|
||||
#endif
|
||||
|
||||
#ifdef __powerpc64__
|
||||
#ifdef CONFIG_PPC_KERNEL_PREFIXED
|
||||
#define __get_user_asm2_goto(x, addr, label) \
|
||||
__get_user_asm_goto(x, addr, label, "ld")
|
||||
#else
|
||||
#define __get_user_asm2_goto(x, addr, label) \
|
||||
asm_goto_output( \
|
||||
"1: ld%U1%X1 %0, %1 # get_user\n" \
|
||||
EX_TABLE(1b, %l2) \
|
||||
: "=r" (x) \
|
||||
: DS_FORM_CONSTRAINT (*addr) \
|
||||
: \
|
||||
: label)
|
||||
#endif // CONFIG_PPC_KERNEL_PREFIXED
|
||||
#else /* __powerpc64__ */
|
||||
#define __get_user_asm2_goto(x, addr, label) \
|
||||
asm_goto_output( \
|
||||
|
||||
@@ -900,6 +900,15 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
|
||||
|
||||
/* Get offset into TMP_REG */
|
||||
EMIT(PPC_RAW_LI(tmp_reg, off));
|
||||
/*
|
||||
* Enforce full ordering for operations with BPF_FETCH by emitting a 'sync'
|
||||
* before and after the operation.
|
||||
*
|
||||
* This is a requirement in the Linux Kernel Memory Model.
|
||||
* See __cmpxchg_u32() in asm/cmpxchg.h as an example.
|
||||
*/
|
||||
if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP))
|
||||
EMIT(PPC_RAW_SYNC());
|
||||
tmp_idx = ctx->idx * 4;
|
||||
/* load value from memory into r0 */
|
||||
EMIT(PPC_RAW_LWARX(_R0, tmp_reg, dst_reg, 0));
|
||||
@@ -953,6 +962,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
|
||||
|
||||
/* For the BPF_FETCH variant, get old data into src_reg */
|
||||
if (imm & BPF_FETCH) {
|
||||
/* Emit 'sync' to enforce full ordering */
|
||||
if (IS_ENABLED(CONFIG_SMP))
|
||||
EMIT(PPC_RAW_SYNC());
|
||||
EMIT(PPC_RAW_MR(ret_reg, ax_reg));
|
||||
if (!fp->aux->verifier_zext)
|
||||
EMIT(PPC_RAW_LI(ret_reg - 1, 0)); /* higher 32-bit */
|
||||
|
||||
@@ -846,6 +846,15 @@ emit_clear:
|
||||
|
||||
/* Get offset into TMP_REG_1 */
|
||||
EMIT(PPC_RAW_LI(tmp1_reg, off));
|
||||
/*
|
||||
* Enforce full ordering for operations with BPF_FETCH by emitting a 'sync'
|
||||
* before and after the operation.
|
||||
*
|
||||
* This is a requirement in the Linux Kernel Memory Model.
|
||||
* See __cmpxchg_u64() in asm/cmpxchg.h as an example.
|
||||
*/
|
||||
if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP))
|
||||
EMIT(PPC_RAW_SYNC());
|
||||
tmp_idx = ctx->idx * 4;
|
||||
/* load value from memory into TMP_REG_2 */
|
||||
if (size == BPF_DW)
|
||||
@@ -908,6 +917,9 @@ emit_clear:
|
||||
PPC_BCC_SHORT(COND_NE, tmp_idx);
|
||||
|
||||
if (imm & BPF_FETCH) {
|
||||
/* Emit 'sync' to enforce full ordering */
|
||||
if (IS_ENABLED(CONFIG_SMP))
|
||||
EMIT(PPC_RAW_SYNC());
|
||||
EMIT(PPC_RAW_MR(ret_reg, _R0));
|
||||
/*
|
||||
* Skip unnecessary zero-extension for 32-bit cmpxchg.
|
||||
|
||||
@@ -371,8 +371,8 @@ static int read_dt_lpar_name(struct seq_file *m)
|
||||
|
||||
static void read_lpar_name(struct seq_file *m)
|
||||
{
|
||||
if (read_rtas_lpar_name(m) && read_dt_lpar_name(m))
|
||||
pr_err_once("Error can't get the LPAR name");
|
||||
if (read_rtas_lpar_name(m))
|
||||
read_dt_lpar_name(m);
|
||||
}
|
||||
|
||||
#define SPLPAR_MAXLENGTH 1026*(sizeof(char))
|
||||
|
||||
+13
-1
@@ -106,7 +106,7 @@ config RISCV
|
||||
select HAS_IOPORT if MMU
|
||||
select HAVE_ARCH_AUDITSYSCALL
|
||||
select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP
|
||||
select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT && !XIP_KERNEL
|
||||
select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT
|
||||
select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
|
||||
select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL
|
||||
select HAVE_ARCH_KASAN if MMU && 64BIT
|
||||
@@ -610,6 +610,18 @@ config TOOLCHAIN_HAS_VECTOR_CRYPTO
|
||||
def_bool $(as-instr, .option arch$(comma) +v$(comma) +zvkb)
|
||||
depends on AS_HAS_OPTION_ARCH
|
||||
|
||||
config RISCV_ISA_ZBA
|
||||
bool "Zba extension support for bit manipulation instructions"
|
||||
default y
|
||||
help
|
||||
Add support for enabling optimisations in the kernel when the Zba
|
||||
extension is detected at boot.
|
||||
|
||||
The Zba extension provides instructions to accelerate the generation
|
||||
of addresses that index into arrays of basic data types.
|
||||
|
||||
If you don't know what to do here, say Y.
|
||||
|
||||
config RISCV_ISA_ZBB
|
||||
bool "Zbb extension support for bit manipulation instructions"
|
||||
depends on TOOLCHAIN_HAS_ZBB
|
||||
|
||||
@@ -10,7 +10,7 @@
|
||||
|
||||
#include <asm/fence.h>
|
||||
|
||||
#define __arch_xchg_masked(prepend, append, r, p, n) \
|
||||
#define __arch_xchg_masked(sc_sfx, prepend, append, r, p, n) \
|
||||
({ \
|
||||
u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3); \
|
||||
ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE; \
|
||||
@@ -25,7 +25,7 @@
|
||||
"0: lr.w %0, %2\n" \
|
||||
" and %1, %0, %z4\n" \
|
||||
" or %1, %1, %z3\n" \
|
||||
" sc.w %1, %1, %2\n" \
|
||||
" sc.w" sc_sfx " %1, %1, %2\n" \
|
||||
" bnez %1, 0b\n" \
|
||||
append \
|
||||
: "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b)) \
|
||||
@@ -46,7 +46,8 @@
|
||||
: "memory"); \
|
||||
})
|
||||
|
||||
#define _arch_xchg(ptr, new, sfx, prepend, append) \
|
||||
#define _arch_xchg(ptr, new, sc_sfx, swap_sfx, prepend, \
|
||||
sc_append, swap_append) \
|
||||
({ \
|
||||
__typeof__(ptr) __ptr = (ptr); \
|
||||
__typeof__(*(__ptr)) __new = (new); \
|
||||
@@ -55,15 +56,15 @@
|
||||
switch (sizeof(*__ptr)) { \
|
||||
case 1: \
|
||||
case 2: \
|
||||
__arch_xchg_masked(prepend, append, \
|
||||
__arch_xchg_masked(sc_sfx, prepend, sc_append, \
|
||||
__ret, __ptr, __new); \
|
||||
break; \
|
||||
case 4: \
|
||||
__arch_xchg(".w" sfx, prepend, append, \
|
||||
__arch_xchg(".w" swap_sfx, prepend, swap_append, \
|
||||
__ret, __ptr, __new); \
|
||||
break; \
|
||||
case 8: \
|
||||
__arch_xchg(".d" sfx, prepend, append, \
|
||||
__arch_xchg(".d" swap_sfx, prepend, swap_append, \
|
||||
__ret, __ptr, __new); \
|
||||
break; \
|
||||
default: \
|
||||
@@ -73,16 +74,17 @@
|
||||
})
|
||||
|
||||
#define arch_xchg_relaxed(ptr, x) \
|
||||
_arch_xchg(ptr, x, "", "", "")
|
||||
_arch_xchg(ptr, x, "", "", "", "", "")
|
||||
|
||||
#define arch_xchg_acquire(ptr, x) \
|
||||
_arch_xchg(ptr, x, "", "", RISCV_ACQUIRE_BARRIER)
|
||||
_arch_xchg(ptr, x, "", "", "", \
|
||||
RISCV_ACQUIRE_BARRIER, RISCV_ACQUIRE_BARRIER)
|
||||
|
||||
#define arch_xchg_release(ptr, x) \
|
||||
_arch_xchg(ptr, x, "", RISCV_RELEASE_BARRIER, "")
|
||||
_arch_xchg(ptr, x, "", "", RISCV_RELEASE_BARRIER, "", "")
|
||||
|
||||
#define arch_xchg(ptr, x) \
|
||||
_arch_xchg(ptr, x, ".aqrl", "", "")
|
||||
_arch_xchg(ptr, x, ".rl", ".aqrl", "", RISCV_FULL_BARRIER, "")
|
||||
|
||||
#define xchg32(ptr, x) \
|
||||
({ \
|
||||
|
||||
@@ -72,7 +72,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
|
||||
/* Make sure tidle is updated */
|
||||
smp_mb();
|
||||
bdata->task_ptr = tidle;
|
||||
bdata->stack_ptr = task_stack_page(tidle) + THREAD_SIZE;
|
||||
bdata->stack_ptr = task_pt_regs(tidle);
|
||||
/* Make sure boot data is updated */
|
||||
smp_mb();
|
||||
hsm_data = __pa(bdata);
|
||||
|
||||
@@ -34,8 +34,7 @@ static void cpu_update_secondary_bootdata(unsigned int cpuid,
|
||||
|
||||
/* Make sure tidle is updated */
|
||||
smp_mb();
|
||||
WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid],
|
||||
task_stack_page(tidle) + THREAD_SIZE);
|
||||
WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid], task_pt_regs(tidle));
|
||||
WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle);
|
||||
}
|
||||
|
||||
|
||||
@@ -237,10 +237,11 @@ static gpa_t aia_imsic_ppn(struct kvm_aia *aia, gpa_t addr)
|
||||
|
||||
static u32 aia_imsic_hart_index(struct kvm_aia *aia, gpa_t addr)
|
||||
{
|
||||
u32 hart, group = 0;
|
||||
u32 hart = 0, group = 0;
|
||||
|
||||
hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) &
|
||||
GENMASK_ULL(aia->nr_hart_bits - 1, 0);
|
||||
if (aia->nr_hart_bits)
|
||||
hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) &
|
||||
GENMASK_ULL(aia->nr_hart_bits - 1, 0);
|
||||
if (aia->nr_group_bits)
|
||||
group = (addr >> aia->nr_group_shift) &
|
||||
GENMASK_ULL(aia->nr_group_bits - 1, 0);
|
||||
|
||||
@@ -724,9 +724,9 @@ static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
|
||||
switch (reg_subtype) {
|
||||
case KVM_REG_RISCV_ISA_SINGLE:
|
||||
return riscv_vcpu_set_isa_ext_single(vcpu, reg_num, reg_val);
|
||||
case KVM_REG_RISCV_SBI_MULTI_EN:
|
||||
case KVM_REG_RISCV_ISA_MULTI_EN:
|
||||
return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, true);
|
||||
case KVM_REG_RISCV_SBI_MULTI_DIS:
|
||||
case KVM_REG_RISCV_ISA_MULTI_DIS:
|
||||
return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, false);
|
||||
default:
|
||||
return -ENOENT;
|
||||
|
||||
@@ -18,6 +18,11 @@ static inline bool rvc_enabled(void)
|
||||
return IS_ENABLED(CONFIG_RISCV_ISA_C);
|
||||
}
|
||||
|
||||
static inline bool rvzba_enabled(void)
|
||||
{
|
||||
return IS_ENABLED(CONFIG_RISCV_ISA_ZBA) && riscv_has_extension_likely(RISCV_ISA_EXT_ZBA);
|
||||
}
|
||||
|
||||
static inline bool rvzbb_enabled(void)
|
||||
{
|
||||
return IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && riscv_has_extension_likely(RISCV_ISA_EXT_ZBB);
|
||||
@@ -737,6 +742,17 @@ static inline u16 rvc_swsp(u32 imm8, u8 rs2)
|
||||
return rv_css_insn(0x6, imm, rs2, 0x2);
|
||||
}
|
||||
|
||||
/* RVZBA instructions. */
|
||||
static inline u32 rvzba_sh2add(u8 rd, u8 rs1, u8 rs2)
|
||||
{
|
||||
return rv_r_insn(0x10, rs2, rs1, 0x4, rd, 0x33);
|
||||
}
|
||||
|
||||
static inline u32 rvzba_sh3add(u8 rd, u8 rs1, u8 rs2)
|
||||
{
|
||||
return rv_r_insn(0x10, rs2, rs1, 0x6, rd, 0x33);
|
||||
}
|
||||
|
||||
/* RVZBB instructions. */
|
||||
static inline u32 rvzbb_sextb(u8 rd, u8 rs1)
|
||||
{
|
||||
@@ -939,6 +955,14 @@ static inline u16 rvc_sdsp(u32 imm9, u8 rs2)
|
||||
return rv_css_insn(0x7, imm, rs2, 0x2);
|
||||
}
|
||||
|
||||
/* RV64-only ZBA instructions. */
|
||||
|
||||
static inline u32 rvzba_zextw(u8 rd, u8 rs1)
|
||||
{
|
||||
/* add.uw rd, rs1, ZERO */
|
||||
return rv_r_insn(0x04, RV_REG_ZERO, rs1, 0, rd, 0x3b);
|
||||
}
|
||||
|
||||
#endif /* __riscv_xlen == 64 */
|
||||
|
||||
/* Helper functions that emit RVC instructions when possible. */
|
||||
@@ -1082,6 +1106,28 @@ static inline void emit_sw(u8 rs1, s32 off, u8 rs2, struct rv_jit_context *ctx)
|
||||
emit(rv_sw(rs1, off, rs2), ctx);
|
||||
}
|
||||
|
||||
static inline void emit_sh2add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
|
||||
{
|
||||
if (rvzba_enabled()) {
|
||||
emit(rvzba_sh2add(rd, rs1, rs2), ctx);
|
||||
return;
|
||||
}
|
||||
|
||||
emit_slli(rd, rs1, 2, ctx);
|
||||
emit_add(rd, rd, rs2, ctx);
|
||||
}
|
||||
|
||||
static inline void emit_sh3add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
|
||||
{
|
||||
if (rvzba_enabled()) {
|
||||
emit(rvzba_sh3add(rd, rs1, rs2), ctx);
|
||||
return;
|
||||
}
|
||||
|
||||
emit_slli(rd, rs1, 3, ctx);
|
||||
emit_add(rd, rd, rs2, ctx);
|
||||
}
|
||||
|
||||
/* RV64-only helper functions. */
|
||||
#if __riscv_xlen == 64
|
||||
|
||||
@@ -1161,6 +1207,11 @@ static inline void emit_zexth(u8 rd, u8 rs, struct rv_jit_context *ctx)
|
||||
|
||||
static inline void emit_zextw(u8 rd, u8 rs, struct rv_jit_context *ctx)
|
||||
{
|
||||
if (rvzba_enabled()) {
|
||||
emit(rvzba_zextw(rd, rs), ctx);
|
||||
return;
|
||||
}
|
||||
|
||||
emit_slli(rd, rs, 32, ctx);
|
||||
emit_srli(rd, rd, 32, ctx);
|
||||
}
|
||||
|
||||
@@ -811,8 +811,7 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
|
||||
* if (!prog)
|
||||
* goto out;
|
||||
*/
|
||||
emit(rv_slli(RV_REG_T0, lo(idx_reg), 2), ctx);
|
||||
emit(rv_add(RV_REG_T0, RV_REG_T0, lo(arr_reg)), ctx);
|
||||
emit_sh2add(RV_REG_T0, lo(idx_reg), lo(arr_reg), ctx);
|
||||
off = offsetof(struct bpf_array, ptrs);
|
||||
if (is_12b_check(off, insn))
|
||||
return -1;
|
||||
|
||||
@@ -380,8 +380,7 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx)
|
||||
* if (!prog)
|
||||
* goto out;
|
||||
*/
|
||||
emit_slli(RV_REG_T2, RV_REG_A2, 3, ctx);
|
||||
emit_add(RV_REG_T2, RV_REG_T2, RV_REG_A1, ctx);
|
||||
emit_sh3add(RV_REG_T2, RV_REG_A2, RV_REG_A1, ctx);
|
||||
off = offsetof(struct bpf_array, ptrs);
|
||||
if (is_12b_check(off, insn))
|
||||
return -1;
|
||||
@@ -537,8 +536,10 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
|
||||
/* r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg); */
|
||||
case BPF_CMPXCHG:
|
||||
r0 = bpf_to_rv_reg(BPF_REG_0, ctx);
|
||||
emit(is64 ? rv_addi(RV_REG_T2, r0, 0) :
|
||||
rv_addiw(RV_REG_T2, r0, 0), ctx);
|
||||
if (is64)
|
||||
emit_mv(RV_REG_T2, r0, ctx);
|
||||
else
|
||||
emit_addiw(RV_REG_T2, r0, 0, ctx);
|
||||
emit(is64 ? rv_lr_d(r0, 0, rd, 0, 0) :
|
||||
rv_lr_w(r0, 0, rd, 0, 0), ctx);
|
||||
jmp_offset = ninsns_rvoff(8);
|
||||
@@ -868,7 +869,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
|
||||
stack_size += 8;
|
||||
sreg_off = stack_size;
|
||||
|
||||
stack_size = round_up(stack_size, 16);
|
||||
stack_size = round_up(stack_size, STACK_ALIGN);
|
||||
|
||||
if (!is_struct_ops) {
|
||||
/* For the trampoline called from function entry,
|
||||
@@ -1097,12 +1098,10 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
|
||||
/* Load current CPU number in T1 */
|
||||
emit_ld(RV_REG_T1, offsetof(struct thread_info, cpu),
|
||||
RV_REG_TP, ctx);
|
||||
/* << 3 because offsets are 8 bytes */
|
||||
emit_slli(RV_REG_T1, RV_REG_T1, 3, ctx);
|
||||
/* Load address of __per_cpu_offset array in T2 */
|
||||
emit_addr(RV_REG_T2, (u64)&__per_cpu_offset, extra_pass, ctx);
|
||||
/* Add offset of current CPU to __per_cpu_offset */
|
||||
emit_add(RV_REG_T1, RV_REG_T2, RV_REG_T1, ctx);
|
||||
/* Get address of __per_cpu_offset[cpu] in T1 */
|
||||
emit_sh3add(RV_REG_T1, RV_REG_T1, RV_REG_T2, ctx);
|
||||
/* Load __per_cpu_offset[cpu] in T1 */
|
||||
emit_ld(RV_REG_T1, 0, RV_REG_T1, ctx);
|
||||
/* Add the offset to Rd */
|
||||
@@ -1960,7 +1959,7 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog)
|
||||
{
|
||||
int i, stack_adjust = 0, store_offset, bpf_stack_adjust;
|
||||
|
||||
bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16);
|
||||
bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, STACK_ALIGN);
|
||||
if (bpf_stack_adjust)
|
||||
mark_fp(ctx);
|
||||
|
||||
@@ -1982,7 +1981,7 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog)
|
||||
if (ctx->arena_vm_start)
|
||||
stack_adjust += 8;
|
||||
|
||||
stack_adjust = round_up(stack_adjust, 16);
|
||||
stack_adjust = round_up(stack_adjust, STACK_ALIGN);
|
||||
stack_adjust += bpf_stack_adjust;
|
||||
|
||||
store_offset = stack_adjust - 8;
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
#include "../perf_event.h"
|
||||
#include "../probe.h"
|
||||
|
||||
MODULE_DESCRIPTION("Support for Intel cstate performance events");
|
||||
MODULE_LICENSE("GPL");
|
||||
|
||||
#define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \
|
||||
|
||||
@@ -34,6 +34,7 @@ static struct event_constraint uncore_constraint_fixed =
|
||||
struct event_constraint uncore_constraint_empty =
|
||||
EVENT_CONSTRAINT(0, 0, 0);
|
||||
|
||||
MODULE_DESCRIPTION("Support for Intel uncore performance events");
|
||||
MODULE_LICENSE("GPL");
|
||||
|
||||
int uncore_pcibus_to_dieid(struct pci_bus *bus)
|
||||
|
||||
@@ -64,6 +64,7 @@
|
||||
#include "perf_event.h"
|
||||
#include "probe.h"
|
||||
|
||||
MODULE_DESCRIPTION("Support Intel/AMD RAPL energy consumption counters");
|
||||
MODULE_LICENSE("GPL");
|
||||
|
||||
/*
|
||||
|
||||
@@ -2154,6 +2154,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
|
||||
|
||||
int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
|
||||
void *insn, int insn_len);
|
||||
void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg);
|
||||
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
|
||||
void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
|
||||
u64 addr, unsigned long roots);
|
||||
|
||||
@@ -77,7 +77,7 @@
|
||||
#define VMX_FEATURE_ENCLS_EXITING ( 2*32+ 15) /* "" VM-Exit on ENCLS (leaf dependent) */
|
||||
#define VMX_FEATURE_RDSEED_EXITING ( 2*32+ 16) /* "" VM-Exit on RDSEED */
|
||||
#define VMX_FEATURE_PAGE_MOD_LOGGING ( 2*32+ 17) /* "pml" Log dirty pages into buffer */
|
||||
#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* "" Conditionally reflect EPT violations as #VE exceptions */
|
||||
#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* Conditionally reflect EPT violations as #VE exceptions */
|
||||
#define VMX_FEATURE_PT_CONCEAL_VMX ( 2*32+ 19) /* "" Suppress VMX indicators in Processor Trace */
|
||||
#define VMX_FEATURE_XSAVES ( 2*32+ 20) /* "" Enable XSAVES and XRSTORS in guest */
|
||||
#define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */
|
||||
|
||||
@@ -345,6 +345,7 @@ static DECLARE_WORK(disable_freq_invariance_work,
|
||||
disable_freq_invariance_workfn);
|
||||
|
||||
DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
|
||||
EXPORT_PER_CPU_SYMBOL_GPL(arch_freq_scale);
|
||||
|
||||
static void scale_freq_tick(u64 acnt, u64 mcnt)
|
||||
{
|
||||
|
||||
@@ -1075,6 +1075,10 @@ void get_cpu_address_sizes(struct cpuinfo_x86 *c)
|
||||
|
||||
c->x86_virt_bits = (eax >> 8) & 0xff;
|
||||
c->x86_phys_bits = eax & 0xff;
|
||||
|
||||
/* Provide a sane default if not enumerated: */
|
||||
if (!c->x86_clflush_size)
|
||||
c->x86_clflush_size = 32;
|
||||
}
|
||||
|
||||
c->x86_cache_bits = c->x86_phys_bits;
|
||||
@@ -1585,6 +1589,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
|
||||
if (have_cpuid_p()) {
|
||||
cpu_detect(c);
|
||||
get_cpu_vendor(c);
|
||||
intel_unlock_cpuid_leafs(c);
|
||||
get_cpu_cap(c);
|
||||
setup_force_cpu_cap(X86_FEATURE_CPUID);
|
||||
get_cpu_address_sizes(c);
|
||||
@@ -1744,7 +1749,7 @@ static void generic_identify(struct cpuinfo_x86 *c)
|
||||
cpu_detect(c);
|
||||
|
||||
get_cpu_vendor(c);
|
||||
|
||||
intel_unlock_cpuid_leafs(c);
|
||||
get_cpu_cap(c);
|
||||
|
||||
get_cpu_address_sizes(c);
|
||||
|
||||
@@ -61,9 +61,11 @@ extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state;
|
||||
|
||||
extern void __init tsx_init(void);
|
||||
void tsx_ap_init(void);
|
||||
void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c);
|
||||
#else
|
||||
static inline void tsx_init(void) { }
|
||||
static inline void tsx_ap_init(void) { }
|
||||
static inline void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c) { }
|
||||
#endif /* CONFIG_CPU_SUP_INTEL */
|
||||
|
||||
extern void init_spectral_chicken(struct cpuinfo_x86 *c);
|
||||
|
||||
@@ -269,19 +269,26 @@ detect_keyid_bits:
|
||||
c->x86_phys_bits -= keyid_bits;
|
||||
}
|
||||
|
||||
void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c)
|
||||
{
|
||||
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
|
||||
return;
|
||||
|
||||
if (c->x86 < 6 || (c->x86 == 6 && c->x86_model < 0xd))
|
||||
return;
|
||||
|
||||
/*
|
||||
* The BIOS can have limited CPUID to leaf 2, which breaks feature
|
||||
* enumeration. Unlock it and update the maximum leaf info.
|
||||
*/
|
||||
if (msr_clear_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0)
|
||||
c->cpuid_level = cpuid_eax(0);
|
||||
}
|
||||
|
||||
static void early_init_intel(struct cpuinfo_x86 *c)
|
||||
{
|
||||
u64 misc_enable;
|
||||
|
||||
/* Unmask CPUID levels if masked: */
|
||||
if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
|
||||
if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
|
||||
MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) {
|
||||
c->cpuid_level = cpuid_eax(0);
|
||||
get_cpu_cap(c);
|
||||
}
|
||||
}
|
||||
|
||||
if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
|
||||
(c->x86 == 0x6 && c->x86_model >= 0x0e))
|
||||
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
|
||||
|
||||
@@ -84,9 +84,9 @@ static bool parse_8000_001e(struct topo_scan *tscan, bool has_topoext)
|
||||
|
||||
/*
|
||||
* If leaf 0xb is available, then the domain shifts are set
|
||||
* already and nothing to do here.
|
||||
* already and nothing to do here. Only valid for family >= 0x17.
|
||||
*/
|
||||
if (!has_topoext) {
|
||||
if (!has_topoext && tscan->c->x86 >= 0x17) {
|
||||
/*
|
||||
* Leaf 0x80000008 set the CORE domain shift already.
|
||||
* Update the SMT domain, but do not propagate it.
|
||||
|
||||
@@ -44,6 +44,7 @@ config KVM
|
||||
select KVM_VFIO
|
||||
select HAVE_KVM_PM_NOTIFIER if PM
|
||||
select KVM_GENERIC_HARDWARE_ENABLING
|
||||
select KVM_WERROR if WERROR
|
||||
help
|
||||
Support hosting fully virtualized guest machines using hardware
|
||||
virtualization extensions. You will need a fairly recent
|
||||
@@ -66,7 +67,7 @@ config KVM_WERROR
|
||||
# FRAME_WARN, i.e. KVM_WERROR=y with KASAN=y requires special tuning.
|
||||
# Building KVM with -Werror and KASAN is still doable via enabling
|
||||
# the kernel-wide WERROR=y.
|
||||
depends on KVM && EXPERT && !KASAN
|
||||
depends on KVM && ((EXPERT && !KASAN) || WERROR)
|
||||
help
|
||||
Add -Werror to the build flags for KVM.
|
||||
|
||||
@@ -97,15 +98,17 @@ config KVM_INTEL
|
||||
|
||||
config KVM_INTEL_PROVE_VE
|
||||
bool "Check that guests do not receive #VE exceptions"
|
||||
default KVM_PROVE_MMU || DEBUG_KERNEL
|
||||
depends on KVM_INTEL
|
||||
depends on KVM_INTEL && EXPERT
|
||||
help
|
||||
|
||||
Checks that KVM's page table management code will not incorrectly
|
||||
let guests receive a virtualization exception. Virtualization
|
||||
exceptions will be trapped by the hypervisor rather than injected
|
||||
in the guest.
|
||||
|
||||
Note: some CPUs appear to generate spurious EPT Violations #VEs
|
||||
that trigger KVM's WARN, in particular with eptad=0 and/or nested
|
||||
virtualization.
|
||||
|
||||
If unsure, say N.
|
||||
|
||||
config X86_SGX_KVM
|
||||
|
||||
+21
-18
@@ -59,7 +59,17 @@
|
||||
#define MAX_APIC_VECTOR 256
|
||||
#define APIC_VECTORS_PER_REG 32
|
||||
|
||||
static bool lapic_timer_advance_dynamic __read_mostly;
|
||||
/*
|
||||
* Enable local APIC timer advancement (tscdeadline mode only) with adaptive
|
||||
* tuning. When enabled, KVM programs the host timer event to fire early, i.e.
|
||||
* before the deadline expires, to account for the delay between taking the
|
||||
* VM-Exit (to inject the guest event) and the subsequent VM-Enter to resume
|
||||
* the guest, i.e. so that the interrupt arrives in the guest with minimal
|
||||
* latency relative to the deadline programmed by the guest.
|
||||
*/
|
||||
static bool lapic_timer_advance __read_mostly = true;
|
||||
module_param(lapic_timer_advance, bool, 0444);
|
||||
|
||||
#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100 /* clock cycles */
|
||||
#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 10000 /* clock cycles */
|
||||
#define LAPIC_TIMER_ADVANCE_NS_INIT 1000
|
||||
@@ -1854,16 +1864,14 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
|
||||
guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
|
||||
trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);
|
||||
|
||||
if (lapic_timer_advance_dynamic) {
|
||||
adjust_lapic_timer_advance(vcpu, guest_tsc - tsc_deadline);
|
||||
/*
|
||||
* If the timer fired early, reread the TSC to account for the
|
||||
* overhead of the above adjustment to avoid waiting longer
|
||||
* than is necessary.
|
||||
*/
|
||||
if (guest_tsc < tsc_deadline)
|
||||
guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
|
||||
}
|
||||
adjust_lapic_timer_advance(vcpu, guest_tsc - tsc_deadline);
|
||||
|
||||
/*
|
||||
* If the timer fired early, reread the TSC to account for the overhead
|
||||
* of the above adjustment to avoid waiting longer than is necessary.
|
||||
*/
|
||||
if (guest_tsc < tsc_deadline)
|
||||
guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
|
||||
|
||||
if (guest_tsc < tsc_deadline)
|
||||
__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
|
||||
@@ -2812,7 +2820,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
|
||||
return HRTIMER_NORESTART;
|
||||
}
|
||||
|
||||
int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
|
||||
int kvm_create_lapic(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
struct kvm_lapic *apic;
|
||||
|
||||
@@ -2845,13 +2853,8 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
|
||||
hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
|
||||
HRTIMER_MODE_ABS_HARD);
|
||||
apic->lapic_timer.timer.function = apic_timer_fn;
|
||||
if (timer_advance_ns == -1) {
|
||||
if (lapic_timer_advance)
|
||||
apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
|
||||
lapic_timer_advance_dynamic = true;
|
||||
} else {
|
||||
apic->lapic_timer.timer_advance_ns = timer_advance_ns;
|
||||
lapic_timer_advance_dynamic = false;
|
||||
}
|
||||
|
||||
/*
|
||||
* Stuff the APIC ENABLE bit in lieu of temporarily incrementing
|
||||
|
||||
@@ -85,7 +85,7 @@ struct kvm_lapic {
|
||||
|
||||
struct dest_map;
|
||||
|
||||
int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns);
|
||||
int kvm_create_lapic(struct kvm_vcpu *vcpu);
|
||||
void kvm_free_lapic(struct kvm_vcpu *vcpu);
|
||||
|
||||
int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
|
||||
|
||||
+36
-12
@@ -336,16 +336,19 @@ static int is_cpuid_PSE36(void)
|
||||
#ifdef CONFIG_X86_64
|
||||
static void __set_spte(u64 *sptep, u64 spte)
|
||||
{
|
||||
KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
|
||||
WRITE_ONCE(*sptep, spte);
|
||||
}
|
||||
|
||||
static void __update_clear_spte_fast(u64 *sptep, u64 spte)
|
||||
{
|
||||
KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
|
||||
WRITE_ONCE(*sptep, spte);
|
||||
}
|
||||
|
||||
static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
|
||||
{
|
||||
KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
|
||||
return xchg(sptep, spte);
|
||||
}
|
||||
|
||||
@@ -4101,6 +4104,22 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level
|
||||
return leaf;
|
||||
}
|
||||
|
||||
static int get_sptes_lockless(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
|
||||
int *root_level)
|
||||
{
|
||||
int leaf;
|
||||
|
||||
walk_shadow_page_lockless_begin(vcpu);
|
||||
|
||||
if (is_tdp_mmu_active(vcpu))
|
||||
leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, root_level);
|
||||
else
|
||||
leaf = get_walk(vcpu, addr, sptes, root_level);
|
||||
|
||||
walk_shadow_page_lockless_end(vcpu);
|
||||
return leaf;
|
||||
}
|
||||
|
||||
/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
|
||||
static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
|
||||
{
|
||||
@@ -4109,15 +4128,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
|
||||
int root, leaf, level;
|
||||
bool reserved = false;
|
||||
|
||||
walk_shadow_page_lockless_begin(vcpu);
|
||||
|
||||
if (is_tdp_mmu_active(vcpu))
|
||||
leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root);
|
||||
else
|
||||
leaf = get_walk(vcpu, addr, sptes, &root);
|
||||
|
||||
walk_shadow_page_lockless_end(vcpu);
|
||||
|
||||
leaf = get_sptes_lockless(vcpu, addr, sptes, &root);
|
||||
if (unlikely(leaf < 0)) {
|
||||
*sptep = 0ull;
|
||||
return reserved;
|
||||
@@ -4400,9 +4411,6 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
|
||||
return RET_PF_EMULATE;
|
||||
}
|
||||
|
||||
fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
|
||||
smp_rmb();
|
||||
|
||||
/*
|
||||
* Check for a relevant mmu_notifier invalidation event before getting
|
||||
* the pfn from the primary MMU, and before acquiring mmu_lock.
|
||||
@@ -5921,6 +5929,22 @@ emulate:
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
|
||||
|
||||
void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg)
|
||||
{
|
||||
u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
|
||||
int root_level, leaf, level;
|
||||
|
||||
leaf = get_sptes_lockless(vcpu, gpa, sptes, &root_level);
|
||||
if (unlikely(leaf < 0))
|
||||
return;
|
||||
|
||||
pr_err("%s %llx", msg, gpa);
|
||||
for (level = root_level; level >= leaf; level--)
|
||||
pr_cont(", spte[%d] = 0x%llx", level, sptes[level]);
|
||||
pr_cont("\n");
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(kvm_mmu_print_sptes);
|
||||
|
||||
static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
|
||||
u64 addr, hpa_t root_hpa)
|
||||
{
|
||||
|
||||
@@ -3,6 +3,8 @@
|
||||
#ifndef KVM_X86_MMU_SPTE_H
|
||||
#define KVM_X86_MMU_SPTE_H
|
||||
|
||||
#include <asm/vmx.h>
|
||||
|
||||
#include "mmu.h"
|
||||
#include "mmu_internal.h"
|
||||
|
||||
@@ -276,6 +278,13 @@ static inline bool is_shadow_present_pte(u64 pte)
|
||||
return !!(pte & SPTE_MMU_PRESENT_MASK);
|
||||
}
|
||||
|
||||
static inline bool is_ept_ve_possible(u64 spte)
|
||||
{
|
||||
return (shadow_present_mask & VMX_EPT_SUPPRESS_VE_BIT) &&
|
||||
!(spte & VMX_EPT_SUPPRESS_VE_BIT) &&
|
||||
(spte & VMX_EPT_RWX_MASK) != VMX_EPT_MISCONFIG_WX_VALUE;
|
||||
}
|
||||
|
||||
/*
|
||||
* Returns true if A/D bits are supported in hardware and are enabled by KVM.
|
||||
* When enabled, KVM uses A/D bits for all non-nested MMUs. Because L1 can
|
||||
|
||||
@@ -21,11 +21,13 @@ static inline u64 kvm_tdp_mmu_read_spte(tdp_ptep_t sptep)
|
||||
|
||||
static inline u64 kvm_tdp_mmu_write_spte_atomic(tdp_ptep_t sptep, u64 new_spte)
|
||||
{
|
||||
KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte));
|
||||
return xchg(rcu_dereference(sptep), new_spte);
|
||||
}
|
||||
|
||||
static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte)
|
||||
{
|
||||
KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte));
|
||||
WRITE_ONCE(*rcu_dereference(sptep), new_spte);
|
||||
}
|
||||
|
||||
|
||||
@@ -626,7 +626,7 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
|
||||
* SPTEs.
|
||||
*/
|
||||
handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
|
||||
0, iter->level, true);
|
||||
SHADOW_NONPRESENT_VALUE, iter->level, true);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
+14
-5
@@ -779,6 +779,14 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
|
||||
*/
|
||||
fpstate_set_confidential(&vcpu->arch.guest_fpu);
|
||||
vcpu->arch.guest_state_protected = true;
|
||||
|
||||
/*
|
||||
* SEV-ES guest mandates LBR Virtualization to be _always_ ON. Enable it
|
||||
* only after setting guest_state_protected because KVM_SET_MSRS allows
|
||||
* dynamic toggling of LBRV (for performance reason) on write access to
|
||||
* MSR_IA32_DEBUGCTLMSR when guest_state_protected is not set.
|
||||
*/
|
||||
svm_enable_lbrv(vcpu);
|
||||
return 0;
|
||||
}
|
||||
|
||||
@@ -2406,6 +2414,12 @@ void __init sev_hardware_setup(void)
|
||||
if (!boot_cpu_has(X86_FEATURE_SEV_ES))
|
||||
goto out;
|
||||
|
||||
if (!lbrv) {
|
||||
WARN_ONCE(!boot_cpu_has(X86_FEATURE_LBRV),
|
||||
"LBRV must be present for SEV-ES support");
|
||||
goto out;
|
||||
}
|
||||
|
||||
/* Has the system been allocated ASIDs for SEV-ES? */
|
||||
if (min_sev_asid == 1)
|
||||
goto out;
|
||||
@@ -3216,7 +3230,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
|
||||
struct kvm_vcpu *vcpu = &svm->vcpu;
|
||||
|
||||
svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE;
|
||||
svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
|
||||
|
||||
/*
|
||||
* An SEV-ES guest requires a VMSA area that is a separate from the
|
||||
@@ -3268,10 +3281,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
|
||||
/* Clear intercepts on selected MSRs */
|
||||
set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1);
|
||||
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1);
|
||||
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
|
||||
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
|
||||
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
|
||||
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
|
||||
}
|
||||
|
||||
void sev_init_vmcb(struct vcpu_svm *svm)
|
||||
|
||||
+51
-18
@@ -99,6 +99,7 @@ static const struct svm_direct_access_msrs {
|
||||
{ .index = MSR_IA32_SPEC_CTRL, .always = false },
|
||||
{ .index = MSR_IA32_PRED_CMD, .always = false },
|
||||
{ .index = MSR_IA32_FLUSH_CMD, .always = false },
|
||||
{ .index = MSR_IA32_DEBUGCTLMSR, .always = false },
|
||||
{ .index = MSR_IA32_LASTBRANCHFROMIP, .always = false },
|
||||
{ .index = MSR_IA32_LASTBRANCHTOIP, .always = false },
|
||||
{ .index = MSR_IA32_LASTINTFROMIP, .always = false },
|
||||
@@ -215,7 +216,7 @@ int vgif = true;
|
||||
module_param(vgif, int, 0444);
|
||||
|
||||
/* enable/disable LBR virtualization */
|
||||
static int lbrv = true;
|
||||
int lbrv = true;
|
||||
module_param(lbrv, int, 0444);
|
||||
|
||||
static int tsc_scaling = true;
|
||||
@@ -990,7 +991,7 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
|
||||
vmcb_mark_dirty(to_vmcb, VMCB_LBR);
|
||||
}
|
||||
|
||||
static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
|
||||
void svm_enable_lbrv(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
struct vcpu_svm *svm = to_svm(vcpu);
|
||||
|
||||
@@ -1000,6 +1001,9 @@ static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
|
||||
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
|
||||
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
|
||||
|
||||
if (sev_es_guest(vcpu->kvm))
|
||||
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1);
|
||||
|
||||
/* Move the LBR msrs to the vmcb02 so that the guest can see them. */
|
||||
if (is_guest_mode(vcpu))
|
||||
svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr);
|
||||
@@ -1009,6 +1013,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
struct vcpu_svm *svm = to_svm(vcpu);
|
||||
|
||||
KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm);
|
||||
|
||||
svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
|
||||
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
|
||||
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
|
||||
@@ -2822,10 +2828,24 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr)
|
||||
return 0;
|
||||
}
|
||||
|
||||
static bool
|
||||
sev_es_prevent_msr_access(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
|
||||
{
|
||||
return sev_es_guest(vcpu->kvm) &&
|
||||
vcpu->arch.guest_state_protected &&
|
||||
svm_msrpm_offset(msr_info->index) != MSR_INVALID &&
|
||||
!msr_write_intercepted(vcpu, msr_info->index);
|
||||
}
|
||||
|
||||
static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
|
||||
{
|
||||
struct vcpu_svm *svm = to_svm(vcpu);
|
||||
|
||||
if (sev_es_prevent_msr_access(vcpu, msr_info)) {
|
||||
msr_info->data = 0;
|
||||
return -EINVAL;
|
||||
}
|
||||
|
||||
switch (msr_info->index) {
|
||||
case MSR_AMD64_TSC_RATIO:
|
||||
if (!msr_info->host_initiated &&
|
||||
@@ -2976,6 +2996,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
|
||||
|
||||
u32 ecx = msr->index;
|
||||
u64 data = msr->data;
|
||||
|
||||
if (sev_es_prevent_msr_access(vcpu, msr))
|
||||
return -EINVAL;
|
||||
|
||||
switch (ecx) {
|
||||
case MSR_AMD64_TSC_RATIO:
|
||||
|
||||
@@ -3846,16 +3870,27 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu)
|
||||
struct vcpu_svm *svm = to_svm(vcpu);
|
||||
|
||||
/*
|
||||
* KVM should never request an NMI window when vNMI is enabled, as KVM
|
||||
* allows at most one to-be-injected NMI and one pending NMI, i.e. if
|
||||
* two NMIs arrive simultaneously, KVM will inject one and set
|
||||
* V_NMI_PENDING for the other. WARN, but continue with the standard
|
||||
* single-step approach to try and salvage the pending NMI.
|
||||
* If NMIs are outright masked, i.e. the vCPU is already handling an
|
||||
* NMI, and KVM has not yet intercepted an IRET, then there is nothing
|
||||
* more to do at this time as KVM has already enabled IRET intercepts.
|
||||
* If KVM has already intercepted IRET, then single-step over the IRET,
|
||||
* as NMIs aren't architecturally unmasked until the IRET completes.
|
||||
*
|
||||
* If vNMI is enabled, KVM should never request an NMI window if NMIs
|
||||
* are masked, as KVM allows at most one to-be-injected NMI and one
|
||||
* pending NMI. If two NMIs arrive simultaneously, KVM will inject one
|
||||
* NMI and set V_NMI_PENDING for the other, but if and only if NMIs are
|
||||
* unmasked. KVM _will_ request an NMI window in some situations, e.g.
|
||||
* if the vCPU is in an STI shadow or if GIF=0, KVM can't immediately
|
||||
* inject the NMI. In those situations, KVM needs to single-step over
|
||||
* the STI shadow or intercept STGI.
|
||||
*/
|
||||
WARN_ON_ONCE(is_vnmi_enabled(svm));
|
||||
if (svm_get_nmi_mask(vcpu)) {
|
||||
WARN_ON_ONCE(is_vnmi_enabled(svm));
|
||||
|
||||
if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion)
|
||||
return; /* IRET will cause a vm exit */
|
||||
if (!svm->awaiting_iret_completion)
|
||||
return; /* IRET will cause a vm exit */
|
||||
}
|
||||
|
||||
/*
|
||||
* SEV-ES guests are responsible for signaling when a vCPU is ready to
|
||||
@@ -5265,6 +5300,12 @@ static __init int svm_hardware_setup(void)
|
||||
|
||||
nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS);
|
||||
|
||||
if (lbrv) {
|
||||
if (!boot_cpu_has(X86_FEATURE_LBRV))
|
||||
lbrv = false;
|
||||
else
|
||||
pr_info("LBR virtualization supported\n");
|
||||
}
|
||||
/*
|
||||
* Note, SEV setup consumes npt_enabled and enable_mmio_caching (which
|
||||
* may be modified by svm_adjust_mmio_mask()), as well as nrips.
|
||||
@@ -5318,14 +5359,6 @@ static __init int svm_hardware_setup(void)
|
||||
svm_x86_ops.set_vnmi_pending = NULL;
|
||||
}
|
||||
|
||||
|
||||
if (lbrv) {
|
||||
if (!boot_cpu_has(X86_FEATURE_LBRV))
|
||||
lbrv = false;
|
||||
else
|
||||
pr_info("LBR virtualization supported\n");
|
||||
}
|
||||
|
||||
if (!enable_pmu)
|
||||
pr_info("PMU virtualization is disabled\n");
|
||||
|
||||
|
||||
@@ -30,7 +30,7 @@
|
||||
#define IOPM_SIZE PAGE_SIZE * 3
|
||||
#define MSRPM_SIZE PAGE_SIZE * 2
|
||||
|
||||
#define MAX_DIRECT_ACCESS_MSRS 47
|
||||
#define MAX_DIRECT_ACCESS_MSRS 48
|
||||
#define MSRPM_OFFSETS 32
|
||||
extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
|
||||
extern bool npt_enabled;
|
||||
@@ -39,6 +39,7 @@ extern int vgif;
|
||||
extern bool intercept_smi;
|
||||
extern bool x2avic_enabled;
|
||||
extern bool vnmi;
|
||||
extern int lbrv;
|
||||
|
||||
/*
|
||||
* Clean bits in VMCB.
|
||||
@@ -552,6 +553,7 @@ u32 *svm_vcpu_alloc_msrpm(void);
|
||||
void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm);
|
||||
void svm_vcpu_free_msrpm(u32 *msrpm);
|
||||
void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb);
|
||||
void svm_enable_lbrv(struct kvm_vcpu *vcpu);
|
||||
void svm_update_lbrv(struct kvm_vcpu *vcpu);
|
||||
|
||||
int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer);
|
||||
|
||||
@@ -2242,6 +2242,9 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
|
||||
vmcs_write64(EPT_POINTER,
|
||||
construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL));
|
||||
|
||||
if (vmx->ve_info)
|
||||
vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info));
|
||||
|
||||
/* All VMFUNCs are currently emulated through L0 vmexits. */
|
||||
if (cpu_has_vmx_vmfunc())
|
||||
vmcs_write64(VM_FUNCTION_CONTROL, 0);
|
||||
@@ -6230,6 +6233,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
|
||||
else if (is_alignment_check(intr_info) &&
|
||||
!vmx_guest_inject_ac(vcpu))
|
||||
return true;
|
||||
else if (is_ve_fault(intr_info))
|
||||
return true;
|
||||
return false;
|
||||
case EXIT_REASON_EXTERNAL_INTERRUPT:
|
||||
return true;
|
||||
|
||||
@@ -5218,8 +5218,15 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
|
||||
if (is_invalid_opcode(intr_info))
|
||||
return handle_ud(vcpu);
|
||||
|
||||
if (KVM_BUG_ON(is_ve_fault(intr_info), vcpu->kvm))
|
||||
return -EIO;
|
||||
if (WARN_ON_ONCE(is_ve_fault(intr_info))) {
|
||||
struct vmx_ve_information *ve_info = vmx->ve_info;
|
||||
|
||||
WARN_ONCE(ve_info->exit_reason != EXIT_REASON_EPT_VIOLATION,
|
||||
"Unexpected #VE on VM-Exit reason 0x%x", ve_info->exit_reason);
|
||||
dump_vmcs(vcpu);
|
||||
kvm_mmu_print_sptes(vcpu, ve_info->guest_physical_address, "#VE");
|
||||
return 1;
|
||||
}
|
||||
|
||||
error_code = 0;
|
||||
if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
|
||||
|
||||
+1
-10
@@ -164,15 +164,6 @@ module_param(kvmclock_periodic_sync, bool, 0444);
|
||||
static u32 __read_mostly tsc_tolerance_ppm = 250;
|
||||
module_param(tsc_tolerance_ppm, uint, 0644);
|
||||
|
||||
/*
|
||||
* lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables
|
||||
* adaptive tuning starting from default advancement of 1000ns. '0' disables
|
||||
* advancement entirely. Any other value is used as-is and disables adaptive
|
||||
* tuning, i.e. allows privileged userspace to set an exact advancement time.
|
||||
*/
|
||||
static int __read_mostly lapic_timer_advance_ns = -1;
|
||||
module_param(lapic_timer_advance_ns, int, 0644);
|
||||
|
||||
static bool __read_mostly vector_hashing = true;
|
||||
module_param(vector_hashing, bool, 0444);
|
||||
|
||||
@@ -12169,7 +12160,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
|
||||
if (r < 0)
|
||||
return r;
|
||||
|
||||
r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
|
||||
r = kvm_create_lapic(vcpu);
|
||||
if (r < 0)
|
||||
goto fail_mmu_destroy;
|
||||
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user