commit: 6664485fa485389a7dc56f27dc52dff43bfb6bbd Author: Mike Pagano <mpagano <AT> gentoo <DOT> org> AuthorDate: Mon May 4 20:58:59 2020 +0000 Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org> CommitDate: Mon May 4 20:58:59 2020 +0000 URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=6664485f
Adding genpatches. Detail in full log Support for namespace user.pax.* on tmpfs. Enable link security restrictions by default. Bluetooth: Check key sizes only when Secure Simple Pairing is enabled. See bug #686758.This hid-apple patch enables swapping of the FN and left Control keys and some additional on some apple keyboards. See bug #622902.Add Gentoo Linux support config settings and defaults. Kernel patch enables gcc >= v9.1 optimizations for additional CPUs. Patch to tmp513 to require REGMAP_I2C for building. Add support for ZSTD-compressed kernel and initramfs (use=experimental) Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org> 0000_README | 56 ++ 1500_XATTR_USER_PREFIX.patch | 67 +++ ...ble-link-security-restrictions-by-default.patch | 20 + ...zes-only-if-Secure-Simple-Pairing-enabled.patch | 37 ++ 2600_enable-key-swapping-for-apple-mac.patch | 114 ++++ ...3-Fix-build-issue-by-selecting-CONFIG_REG.patch | 30 + ..._ZSTD-v5-1-8-prepare-zstd-for-preboot-env.patch | 82 +++ ...STD-v5-2-8-prepare-xxhash-for-preboot-env.patch | 94 +++ ...STD-v5-3-8-add-zstd-support-to-decompress.patch | 422 ++++++++++++++ ...-v5-4-8-add-support-for-zstd-compres-kern.patch | 65 +++ ...add-support-for-zstd-compressed-initramfs.patch | 50 ++ ..._ZSTD-v5-6-8-bump-ZO-z-extra-bytes-margin.patch | 20 + ...v5-7-8-support-for-ZSTD-compressed-kernel.patch | 92 +++ ...5-8-8-gitignore-add-ZSTD-compressed-files.patch | 12 + 5012_enable-cpu-optimizations-for-gcc91.patch | 632 +++++++++++++++++++++ 15 files changed, 1793 insertions(+) diff --git a/0000_README b/0000_README index 9018993..639ad9e 100644 --- a/0000_README +++ b/0000_README @@ -43,6 +43,62 @@ EXPERIMENTAL Individual Patch Descriptions: -------------------------------------------------------------------------- +Patch: 1500_XATTR_USER_PREFIX.patch +From: https://bugs.gentoo.org/show_bug.cgi?id=470644 +Desc: Support for namespace user.pax.* on tmpfs. + +Patch: 1510_fs-enable-link-security-restrictions-by-default.patch +From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/ +Desc: Enable link security restrictions by default. + +Patch: 2000_BT-Check-key-sizes-only-if-Secure-Simple-Pairing-enabled.patch +From: https://lore.kernel.org/linux-bluetooth/[email protected]/raw +Desc: Bluetooth: Check key sizes only when Secure Simple Pairing is enabled. See bug #686758 + +Patch: 2600_enable-key-swapping-for-apple-mac.patch +From: https://github.com/free5lot/hid-apple-patched +Desc: This hid-apple patch enables swapping of the FN and left Control keys and some additional on some apple keyboards. See bug #622902 + +Patch: 2900_tmp513-Fix-build-issue-by-selecting-CONFIG_REG.patch +From: https://bugs.gentoo.org/710790 +Desc: tmp513 requies REGMAP_I2C to build. Select it by default in Kconfig. See bug #710790. Thanks to Phil Stracchino + Patch: 4567_distro-Gentoo-Kconfig.patch From: Tom Wijsman <[email protected]> Desc: Add Gentoo Linux support config settings and defaults. + +Patch: 5000_ZSTD-v5-1-8-prepare-zstd-for-preboot-env.patch +From: https://lkml.org/lkml/2020/4/1/29 +Desc: lib: prepare zstd for preboot environment + +Patch: 5001_ZSTD-v5-2-8-prepare-xxhash-for-preboot-env.patch +From: https://lkml.org/lkml/2020/4/1/29 +Desc: lib: prepare xxhash for preboot environment + +Patch: 5002_ZSTD-v5-3-8-add-zstd-support-to-decompress.patch +From: https://lkml.org/lkml/2020/4/1/29 +Desc: lib: add zstd support to decompress + +Patch: 5003_ZSTD-v5-4-8-add-support-for-zstd-compres-kern.patch +From: https://lkml.org/lkml/2020/4/1/29 +Desc: init: add support for zstd compressed kernel + +Patch: 5004_ZSTD-v5-5-8-add-support-for-zstd-compressed-initramfs.patch +From: https://lkml.org/lkml/2020/4/1/29 +Desc: usr: add support for zstd compressed initramfs + +Patch: 5005_ZSTD-v5-6-8-bump-ZO-z-extra-bytes-margin.patch +From: https://lkml.org/lkml/2020/4/1/29 +Desc: x86: bump ZO_z_extra_bytes margin for zstd + +Patch: 5006_ZSTD-v5-7-8-support-for-ZSTD-compressed-kernel.patch +From: https://lkml.org/lkml/2020/4/1/29 +Desc: x86: Add support for ZSTD compressed kernel + +Patch: 5007_ZSTD-v5-8-8-gitignore-add-ZSTD-compressed-files.patch +From: https://lkml.org/lkml/2020/4/1/29 +Desc: .gitignore: add ZSTD-compressed files + +Patch: 5012_enable-cpu-optimizations-for-gcc91.patch +From: https://github.com/graysky2/kernel_gcc_patch/ +Desc: Kernel patch enables gcc >= v9.1 optimizations for additional CPUs. diff --git a/1500_XATTR_USER_PREFIX.patch b/1500_XATTR_USER_PREFIX.patch new file mode 100644 index 0000000..245dcc2 --- /dev/null +++ b/1500_XATTR_USER_PREFIX.patch @@ -0,0 +1,67 @@ +From: Anthony G. Basile <[email protected]> + +This patch adds support for a restricted user-controlled namespace on +tmpfs filesystem used to house PaX flags. The namespace must be of the +form user.pax.* and its value cannot exceed a size of 8 bytes. + +This is needed even on all Gentoo systems so that XATTR_PAX flags +are preserved for users who might build packages using portage on +a tmpfs system with a non-hardened kernel and then switch to a +hardened kernel with XATTR_PAX enabled. + +The namespace is added to any user with Extended Attribute support +enabled for tmpfs. Users who do not enable xattrs will not have +the XATTR_PAX flags preserved. + +diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h +index 1590c49..5eab462 100644 +--- a/include/uapi/linux/xattr.h ++++ b/include/uapi/linux/xattr.h +@@ -73,5 +73,9 @@ + #define XATTR_POSIX_ACL_DEFAULT "posix_acl_default" + #define XATTR_NAME_POSIX_ACL_DEFAULT XATTR_SYSTEM_PREFIX XATTR_POSIX_ACL_DEFAULT + ++/* User namespace */ ++#define XATTR_PAX_PREFIX XATTR_USER_PREFIX "pax." ++#define XATTR_PAX_FLAGS_SUFFIX "flags" ++#define XATTR_NAME_PAX_FLAGS XATTR_PAX_PREFIX XATTR_PAX_FLAGS_SUFFIX + + #endif /* _UAPI_LINUX_XATTR_H */ +--- a/mm/shmem.c 2020-05-04 15:30:27.042035334 -0400 ++++ b/mm/shmem.c 2020-05-04 15:34:57.013881725 -0400 +@@ -3238,6 +3238,14 @@ static int shmem_xattr_handler_set(const + struct shmem_inode_info *info = SHMEM_I(inode); + + name = xattr_full_name(handler, name); ++ ++ if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) { ++ if (strcmp(name, XATTR_NAME_PAX_FLAGS)) ++ return -EOPNOTSUPP; ++ if (size > 8) ++ return -EINVAL; ++ } ++ + return simple_xattr_set(&info->xattrs, name, value, size, flags, NULL); + } + +@@ -3253,6 +3261,12 @@ static const struct xattr_handler shmem_ + .set = shmem_xattr_handler_set, + }; + ++static const struct xattr_handler shmem_user_xattr_handler = { ++ .prefix = XATTR_USER_PREFIX, ++ .get = shmem_xattr_handler_get, ++ .set = shmem_xattr_handler_set, ++}; ++ + static const struct xattr_handler *shmem_xattr_handlers[] = { + #ifdef CONFIG_TMPFS_POSIX_ACL + &posix_acl_access_xattr_handler, +@@ -3260,6 +3274,7 @@ static const struct xattr_handler *shmem + #endif + &shmem_security_xattr_handler, + &shmem_trusted_xattr_handler, ++ &shmem_user_xattr_handler, + NULL + }; + diff --git a/1510_fs-enable-link-security-restrictions-by-default.patch b/1510_fs-enable-link-security-restrictions-by-default.patch new file mode 100644 index 0000000..f0ed144 --- /dev/null +++ b/1510_fs-enable-link-security-restrictions-by-default.patch @@ -0,0 +1,20 @@ +From: Ben Hutchings <[email protected]> +Subject: fs: Enable link security restrictions by default +Date: Fri, 02 Nov 2012 05:32:06 +0000 +Bug-Debian: https://bugs.debian.org/609455 +Forwarded: not-needed +This reverts commit 561ec64ae67ef25cac8d72bb9c4bfc955edfd415 +('VFS: don't do protected {sym,hard}links by default'). +--- a/fs/namei.c 2018-09-28 07:56:07.770005006 -0400 ++++ b/fs/namei.c 2018-09-28 07:56:43.370349204 -0400 +@@ -885,8 +885,8 @@ static inline void put_link(struct namei + path_put(&last->link); + } + +-int sysctl_protected_symlinks __read_mostly = 0; +-int sysctl_protected_hardlinks __read_mostly = 0; ++int sysctl_protected_symlinks __read_mostly = 1; ++int sysctl_protected_hardlinks __read_mostly = 1; + int sysctl_protected_fifos __read_mostly; + int sysctl_protected_regular __read_mostly; + diff --git a/2000_BT-Check-key-sizes-only-if-Secure-Simple-Pairing-enabled.patch b/2000_BT-Check-key-sizes-only-if-Secure-Simple-Pairing-enabled.patch new file mode 100644 index 0000000..394ad48 --- /dev/null +++ b/2000_BT-Check-key-sizes-only-if-Secure-Simple-Pairing-enabled.patch @@ -0,0 +1,37 @@ +The encryption is only mandatory to be enforced when both sides are using +Secure Simple Pairing and this means the key size check makes only sense +in that case. + +On legacy Bluetooth 2.0 and earlier devices like mice the encryption was +optional and thus causing an issue if the key size check is not bound to +using Secure Simple Pairing. + +Fixes: d5bb334a8e17 ("Bluetooth: Align minimum encryption key size for LE and BR/EDR connections") +Signed-off-by: Marcel Holtmann <[email protected]> +Cc: [email protected] +--- + net/bluetooth/hci_conn.c | 9 +++++++-- + 1 file changed, 7 insertions(+), 2 deletions(-) + +diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c +index 3cf0764d5793..7516cdde3373 100644 +--- a/net/bluetooth/hci_conn.c ++++ b/net/bluetooth/hci_conn.c +@@ -1272,8 +1272,13 @@ int hci_conn_check_link_mode(struct hci_conn *conn) + return 0; + } + +- if (hci_conn_ssp_enabled(conn) && +- !test_bit(HCI_CONN_ENCRYPT, &conn->flags)) ++ /* If Secure Simple Pairing is not enabled, then legacy connection ++ * setup is used and no encryption or key sizes can be enforced. ++ */ ++ if (!hci_conn_ssp_enabled(conn)) ++ return 1; ++ ++ if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags)) + return 0; + + /* The minimum encryption key size needs to be enforced by the +-- +2.20.1 diff --git a/2600_enable-key-swapping-for-apple-mac.patch b/2600_enable-key-swapping-for-apple-mac.patch new file mode 100644 index 0000000..ab228d3 --- /dev/null +++ b/2600_enable-key-swapping-for-apple-mac.patch @@ -0,0 +1,114 @@ +--- a/drivers/hid/hid-apple.c ++++ b/drivers/hid/hid-apple.c +@@ -52,6 +52,22 @@ + "(For people who want to keep Windows PC keyboard muscle memory. " + "[0] = as-is, Mac layout. 1 = swapped, Windows layout.)"); + ++static unsigned int swap_fn_leftctrl; ++module_param(swap_fn_leftctrl, uint, 0644); ++MODULE_PARM_DESC(swap_fn_leftctrl, "Swap the Fn and left Control keys. " ++ "(For people who want to keep PC keyboard muscle memory. " ++ "[0] = as-is, Mac layout, 1 = swapped, PC layout)"); ++ ++static unsigned int rightalt_as_rightctrl; ++module_param(rightalt_as_rightctrl, uint, 0644); ++MODULE_PARM_DESC(rightalt_as_rightctrl, "Use the right Alt key as a right Ctrl key. " ++ "[0] = as-is, Mac layout. 1 = Right Alt is right Ctrl"); ++ ++static unsigned int ejectcd_as_delete; ++module_param(ejectcd_as_delete, uint, 0644); ++MODULE_PARM_DESC(ejectcd_as_delete, "Use Eject-CD key as Delete key. " ++ "([0] = disabled, 1 = enabled)"); ++ + struct apple_sc { + unsigned long quirks; + unsigned int fn_on; +@@ -164,6 +180,21 @@ + { } + }; + ++static const struct apple_key_translation swapped_fn_leftctrl_keys[] = { ++ { KEY_FN, KEY_LEFTCTRL }, ++ { } ++}; ++ ++static const struct apple_key_translation rightalt_as_rightctrl_keys[] = { ++ { KEY_RIGHTALT, KEY_RIGHTCTRL }, ++ { } ++}; ++ ++static const struct apple_key_translation ejectcd_as_delete_keys[] = { ++ { KEY_EJECTCD, KEY_DELETE }, ++ { } ++}; ++ + static const struct apple_key_translation *apple_find_translation( + const struct apple_key_translation *table, u16 from) + { +@@ -183,9 +214,11 @@ + struct apple_sc *asc = hid_get_drvdata(hid); + const struct apple_key_translation *trans, *table; + +- if (usage->code == KEY_FN) { ++ u16 fn_keycode = (swap_fn_leftctrl) ? (KEY_LEFTCTRL) : (KEY_FN); ++ ++ if (usage->code == fn_keycode) { + asc->fn_on = !!value; +- input_event(input, usage->type, usage->code, value); ++ input_event(input, usage->type, KEY_FN, value); + return 1; + } + +@@ -264,6 +297,30 @@ + } + } + ++ if (swap_fn_leftctrl) { ++ trans = apple_find_translation(swapped_fn_leftctrl_keys, usage->code); ++ if (trans) { ++ input_event(input, usage->type, trans->to, value); ++ return 1; ++ } ++ } ++ ++ if (ejectcd_as_delete) { ++ trans = apple_find_translation(ejectcd_as_delete_keys, usage->code); ++ if (trans) { ++ input_event(input, usage->type, trans->to, value); ++ return 1; ++ } ++ } ++ ++ if (rightalt_as_rightctrl) { ++ trans = apple_find_translation(rightalt_as_rightctrl_keys, usage->code); ++ if (trans) { ++ input_event(input, usage->type, trans->to, value); ++ return 1; ++ } ++ } ++ + return 0; + } + +@@ -327,6 +384,21 @@ + + for (trans = apple_iso_keyboard; trans->from; trans++) + set_bit(trans->to, input->keybit); ++ ++ if (swap_fn_leftctrl) { ++ for (trans = swapped_fn_leftctrl_keys; trans->from; trans++) ++ set_bit(trans->to, input->keybit); ++ } ++ ++ if (ejectcd_as_delete) { ++ for (trans = ejectcd_as_delete_keys; trans->from; trans++) ++ set_bit(trans->to, input->keybit); ++ } ++ ++ if (rightalt_as_rightctrl) { ++ for (trans = rightalt_as_rightctrl_keys; trans->from; trans++) ++ set_bit(trans->to, input->keybit); ++ } + } + + static int apple_input_mapping(struct hid_device *hdev, struct hid_input *hi, diff --git a/2900_tmp513-Fix-build-issue-by-selecting-CONFIG_REG.patch b/2900_tmp513-Fix-build-issue-by-selecting-CONFIG_REG.patch new file mode 100644 index 0000000..4335685 --- /dev/null +++ b/2900_tmp513-Fix-build-issue-by-selecting-CONFIG_REG.patch @@ -0,0 +1,30 @@ +From dc328d75a6f37f4ff11a81ae16b1ec88c3197640 Mon Sep 17 00:00:00 2001 +From: Mike Pagano <[email protected]> +Date: Mon, 23 Mar 2020 08:20:06 -0400 +Subject: [PATCH 1/1] This driver requires REGMAP_I2C to build. Select it by + default in Kconfig. Reported at gentoo bugzilla: + https://bugs.gentoo.org/710790 +Cc: [email protected] + +Reported-by: Phil Stracchino <[email protected]> + +Signed-off-by: Mike Pagano <[email protected]> +--- + drivers/hwmon/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig +index 47ac20aee06f..530b4f29ba85 100644 +--- a/drivers/hwmon/Kconfig ++++ b/drivers/hwmon/Kconfig +@@ -1769,6 +1769,7 @@ config SENSORS_TMP421 + config SENSORS_TMP513 + tristate "Texas Instruments TMP513 and compatibles" + depends on I2C ++ select REGMAP_I2C + help + If you say yes here you get support for Texas Instruments TMP512, + and TMP513 temperature and power supply sensor chips. +-- +2.24.1 + diff --git a/5000_ZSTD-v5-1-8-prepare-zstd-for-preboot-env.patch b/5000_ZSTD-v5-1-8-prepare-zstd-for-preboot-env.patch new file mode 100644 index 0000000..297a8d4 --- /dev/null +++ b/5000_ZSTD-v5-1-8-prepare-zstd-for-preboot-env.patch @@ -0,0 +1,82 @@ +diff --git a/lib/zstd/decompress.c b/lib/zstd/decompress.c +index 269ee9a796c1..73ded63278cf 100644 +--- a/lib/zstd/decompress.c ++++ b/lib/zstd/decompress.c +@@ -2490,6 +2490,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB + } + } + ++#ifndef ZSTD_PREBOOT + EXPORT_SYMBOL(ZSTD_DCtxWorkspaceBound); + EXPORT_SYMBOL(ZSTD_initDCtx); + EXPORT_SYMBOL(ZSTD_decompressDCtx); +@@ -2529,3 +2530,4 @@ EXPORT_SYMBOL(ZSTD_insertBlock); + + MODULE_LICENSE("Dual BSD/GPL"); + MODULE_DESCRIPTION("Zstd Decompressor"); ++#endif +diff --git a/lib/zstd/fse_decompress.c b/lib/zstd/fse_decompress.c +index a84300e5a013..0b353530fb3f 100644 +--- a/lib/zstd/fse_decompress.c ++++ b/lib/zstd/fse_decompress.c +@@ -47,6 +47,7 @@ + ****************************************************************/ + #include "bitstream.h" + #include "fse.h" ++#include "zstd_internal.h" + #include <linux/compiler.h> + #include <linux/kernel.h> + #include <linux/string.h> /* memcpy, memset */ +@@ -60,14 +61,6 @@ + enum { FSE_static_assert = 1 / (int)(!!(c)) }; \ + } /* use only *after* variable declarations */ + +-/* check and forward error code */ +-#define CHECK_F(f) \ +- { \ +- size_t const e = f; \ +- if (FSE_isError(e)) \ +- return e; \ +- } +- + /* ************************************************************** + * Templates + ****************************************************************/ +diff --git a/lib/zstd/zstd_internal.h b/lib/zstd/zstd_internal.h +index 1a79fab9e13a..dac753397f86 100644 +--- a/lib/zstd/zstd_internal.h ++++ b/lib/zstd/zstd_internal.h +@@ -127,7 +127,14 @@ static const U32 OF_defaultNormLog = OF_DEFAULTNORMLOG; + * Shared functions to include for inlining + *********************************************/ + ZSTD_STATIC void ZSTD_copy8(void *dst, const void *src) { +- memcpy(dst, src, 8); ++ /* ++ * zstd relies heavily on gcc being able to analyze and inline this ++ * memcpy() call, since it is called in a tight loop. Preboot mode ++ * is compiled in freestanding mode, which stops gcc from analyzing ++ * memcpy(). Use __builtin_memcpy() to tell gcc to analyze this as a ++ * regular memcpy(). ++ */ ++ __builtin_memcpy(dst, src, 8); + } + /*! ZSTD_wildcopy() : + * custom version of memcpy(), can copy up to 7 bytes too many (8 bytes if length==0) */ +@@ -137,13 +144,16 @@ ZSTD_STATIC void ZSTD_wildcopy(void *dst, const void *src, ptrdiff_t length) + const BYTE* ip = (const BYTE*)src; + BYTE* op = (BYTE*)dst; + BYTE* const oend = op + length; +- /* Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388. ++#if defined(GCC_VERSION) && GCC_VERSION >= 70000 && GCC_VERSION < 70200 ++ /* ++ * Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388. + * Avoid the bad case where the loop only runs once by handling the + * special case separately. This doesn't trigger the bug because it + * doesn't involve pointer/integer overflow. + */ + if (length <= 8) + return ZSTD_copy8(dst, src); ++#endif + do { + ZSTD_copy8(op, ip); + op += 8; diff --git a/5001_ZSTD-v5-2-8-prepare-xxhash-for-preboot-env.patch b/5001_ZSTD-v5-2-8-prepare-xxhash-for-preboot-env.patch new file mode 100644 index 0000000..88e4674 --- /dev/null +++ b/5001_ZSTD-v5-2-8-prepare-xxhash-for-preboot-env.patch @@ -0,0 +1,94 @@ +diff --git a/lib/xxhash.c b/lib/xxhash.c +index aa61e2a3802f..b4364e011392 100644 +--- a/lib/xxhash.c ++++ b/lib/xxhash.c +@@ -80,13 +80,11 @@ void xxh32_copy_state(struct xxh32_state *dst, const struct xxh32_state *src) + { + memcpy(dst, src, sizeof(*dst)); + } +-EXPORT_SYMBOL(xxh32_copy_state); + + void xxh64_copy_state(struct xxh64_state *dst, const struct xxh64_state *src) + { + memcpy(dst, src, sizeof(*dst)); + } +-EXPORT_SYMBOL(xxh64_copy_state); + + /*-*************************** + * Simple Hash Functions +@@ -151,7 +149,6 @@ uint32_t xxh32(const void *input, const size_t len, const uint32_t seed) + + return h32; + } +-EXPORT_SYMBOL(xxh32); + + static uint64_t xxh64_round(uint64_t acc, const uint64_t input) + { +@@ -234,7 +231,6 @@ uint64_t xxh64(const void *input, const size_t len, const uint64_t seed) + + return h64; + } +-EXPORT_SYMBOL(xxh64); + + /*-************************************************** + * Advanced Hash Functions +@@ -251,7 +247,6 @@ void xxh32_reset(struct xxh32_state *statePtr, const uint32_t seed) + state.v4 = seed - PRIME32_1; + memcpy(statePtr, &state, sizeof(state)); + } +-EXPORT_SYMBOL(xxh32_reset); + + void xxh64_reset(struct xxh64_state *statePtr, const uint64_t seed) + { +@@ -265,7 +260,6 @@ void xxh64_reset(struct xxh64_state *statePtr, const uint64_t seed) + state.v4 = seed - PRIME64_1; + memcpy(statePtr, &state, sizeof(state)); + } +-EXPORT_SYMBOL(xxh64_reset); + + int xxh32_update(struct xxh32_state *state, const void *input, const size_t len) + { +@@ -334,7 +328,6 @@ int xxh32_update(struct xxh32_state *state, const void *input, const size_t len) + + return 0; + } +-EXPORT_SYMBOL(xxh32_update); + + uint32_t xxh32_digest(const struct xxh32_state *state) + { +@@ -372,7 +365,6 @@ uint32_t xxh32_digest(const struct xxh32_state *state) + + return h32; + } +-EXPORT_SYMBOL(xxh32_digest); + + int xxh64_update(struct xxh64_state *state, const void *input, const size_t len) + { +@@ -439,7 +431,6 @@ int xxh64_update(struct xxh64_state *state, const void *input, const size_t len) + + return 0; + } +-EXPORT_SYMBOL(xxh64_update); + + uint64_t xxh64_digest(const struct xxh64_state *state) + { +@@ -494,7 +485,19 @@ uint64_t xxh64_digest(const struct xxh64_state *state) + + return h64; + } ++ ++#ifndef XXH_PREBOOT ++EXPORT_SYMBOL(xxh32_copy_state); ++EXPORT_SYMBOL(xxh64_copy_state); ++EXPORT_SYMBOL(xxh32); ++EXPORT_SYMBOL(xxh64); ++EXPORT_SYMBOL(xxh32_reset); ++EXPORT_SYMBOL(xxh64_reset); ++EXPORT_SYMBOL(xxh32_update); ++EXPORT_SYMBOL(xxh32_digest); ++EXPORT_SYMBOL(xxh64_update); + EXPORT_SYMBOL(xxh64_digest); + + MODULE_LICENSE("Dual BSD/GPL"); + MODULE_DESCRIPTION("xxHash"); ++#endif diff --git a/5002_ZSTD-v5-3-8-add-zstd-support-to-decompress.patch b/5002_ZSTD-v5-3-8-add-zstd-support-to-decompress.patch new file mode 100644 index 0000000..1c22fa3 --- /dev/null +++ b/5002_ZSTD-v5-3-8-add-zstd-support-to-decompress.patch @@ -0,0 +1,422 @@ +diff --git a/include/linux/decompress/unzstd.h b/include/linux/decompress/unzstd.h +new file mode 100644 +index 000000000000..56d539ae880f +--- /dev/null ++++ b/include/linux/decompress/unzstd.h +@@ -0,0 +1,11 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++#ifndef LINUX_DECOMPRESS_UNZSTD_H ++#define LINUX_DECOMPRESS_UNZSTD_H ++ ++int unzstd(unsigned char *inbuf, long len, ++ long (*fill)(void*, unsigned long), ++ long (*flush)(void*, unsigned long), ++ unsigned char *output, ++ long *pos, ++ void (*error_fn)(char *x)); ++#endif +diff --git a/lib/Kconfig b/lib/Kconfig +index 5d53f9609c25..e883aecb9279 100644 +--- a/lib/Kconfig ++++ b/lib/Kconfig +@@ -336,6 +336,10 @@ config DECOMPRESS_LZ4 + select LZ4_DECOMPRESS + tristate + ++config DECOMPRESS_ZSTD ++ select ZSTD_DECOMPRESS ++ tristate ++ + # + # Generic allocator support is selected if needed + # +diff --git a/lib/Makefile b/lib/Makefile +index ab68a8674360..3ce4ac296611 100644 +--- a/lib/Makefile ++++ b/lib/Makefile +@@ -166,6 +166,7 @@ lib-$(CONFIG_DECOMPRESS_LZMA) += decompress_unlzma.o + lib-$(CONFIG_DECOMPRESS_XZ) += decompress_unxz.o + lib-$(CONFIG_DECOMPRESS_LZO) += decompress_unlzo.o + lib-$(CONFIG_DECOMPRESS_LZ4) += decompress_unlz4.o ++lib-$(CONFIG_DECOMPRESS_ZSTD) += decompress_unzstd.o + + obj-$(CONFIG_TEXTSEARCH) += textsearch.o + obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o +diff --git a/lib/decompress.c b/lib/decompress.c +index 857ab1af1ef3..ab3fc90ffc64 100644 +--- a/lib/decompress.c ++++ b/lib/decompress.c +@@ -13,6 +13,7 @@ + #include <linux/decompress/inflate.h> + #include <linux/decompress/unlzo.h> + #include <linux/decompress/unlz4.h> ++#include <linux/decompress/unzstd.h> + + #include <linux/types.h> + #include <linux/string.h> +@@ -37,6 +38,9 @@ + #ifndef CONFIG_DECOMPRESS_LZ4 + # define unlz4 NULL + #endif ++#ifndef CONFIG_DECOMPRESS_ZSTD ++# define unzstd NULL ++#endif + + struct compress_format { + unsigned char magic[2]; +@@ -52,6 +56,7 @@ static const struct compress_format compressed_formats[] __initconst = { + { {0xfd, 0x37}, "xz", unxz }, + { {0x89, 0x4c}, "lzo", unlzo }, + { {0x02, 0x21}, "lz4", unlz4 }, ++ { {0x28, 0xb5}, "zstd", unzstd }, + { {0, 0}, NULL, NULL } + }; + +diff --git a/lib/decompress_unzstd.c b/lib/decompress_unzstd.c +new file mode 100644 +index 000000000000..f317afab502f +--- /dev/null ++++ b/lib/decompress_unzstd.c +@@ -0,0 +1,342 @@ ++// SPDX-License-Identifier: GPL-2.0 ++ ++/* ++ * Important notes about in-place decompression ++ * ++ * At least on x86, the kernel is decompressed in place: the compressed data ++ * is placed to the end of the output buffer, and the decompressor overwrites ++ * most of the compressed data. There must be enough safety margin to ++ * guarantee that the write position is always behind the read position. ++ * ++ * The safety margin for ZSTD with a 128 KB block size is calculated below. ++ * Note that the margin with ZSTD is bigger than with GZIP or XZ! ++ * ++ * The worst case for in-place decompression is that the beginning of ++ * the file is compressed extremely well, and the rest of the file is ++ * uncompressible. Thus, we must look for worst-case expansion when the ++ * compressor is encoding uncompressible data. ++ * ++ * The structure of the .zst file in case of a compresed kernel is as follows. ++ * Maximum sizes (as bytes) of the fields are in parenthesis. ++ * ++ * Frame Header: (18) ++ * Blocks: (N) ++ * Checksum: (4) ++ * ++ * The frame header and checksum overhead is at most 22 bytes. ++ * ++ * ZSTD stores the data in blocks. Each block has a header whose size is ++ * a 3 bytes. After the block header, there is up to 128 KB of payload. ++ * The maximum uncompressed size of the payload is 128 KB. The minimum ++ * uncompressed size of the payload is never less than the payload size ++ * (excluding the block header). ++ * ++ * The assumption, that the uncompressed size of the payload is never ++ * smaller than the payload itself, is valid only when talking about ++ * the payload as a whole. It is possible that the payload has parts where ++ * the decompressor consumes more input than it produces output. Calculating ++ * the worst case for this would be tricky. Instead of trying to do that, ++ * let's simply make sure that the decompressor never overwrites any bytes ++ * of the payload which it is currently reading. ++ * ++ * Now we have enough information to calculate the safety margin. We need ++ * - 22 bytes for the .zst file format headers; ++ * - 3 bytes per every 128 KiB of uncompressed size (one block header per ++ * block); and ++ * - 128 KiB (biggest possible zstd block size) to make sure that the ++ * decompressor never overwrites anything from the block it is currently ++ * reading. ++ * ++ * We get the following formula: ++ * ++ * safety_margin = 22 + uncompressed_size * 3 / 131072 + 131072 ++ * <= 22 + (uncompressed_size >> 15) + 131072 ++ */ ++ ++/* ++ * Preboot environments #include "path/to/decompress_unzstd.c". ++ * All of the source files we depend on must be #included. ++ * zstd's only source dependeny is xxhash, which has no source ++ * dependencies. ++ * ++ * zstd and xxhash avoid declaring themselves as modules ++ * when ZSTD_PREBOOT and XXH_PREBOOT are defined. ++ */ ++#ifdef STATIC ++# define ZSTD_PREBOOT ++# define XXH_PREBOOT ++# include "xxhash.c" ++# include "zstd/entropy_common.c" ++# include "zstd/fse_decompress.c" ++# include "zstd/huf_decompress.c" ++# include "zstd/zstd_common.c" ++# include "zstd/decompress.c" ++#endif ++ ++#include <linux/decompress/mm.h> ++#include <linux/kernel.h> ++#include <linux/zstd.h> ++ ++/* 128MB is the maximum window size supported by zstd. */ ++#define ZSTD_WINDOWSIZE_MAX (1 << ZSTD_WINDOWLOG_MAX) ++/* Size of the input and output buffers in multi-call mode. ++ * Pick a larger size because it isn't used during kernel decompression, ++ * since that is single pass, and we have to allocate a large buffer for ++ * zstd's window anyways. The larger size speeds up initramfs decompression. ++ */ ++#define ZSTD_IOBUF_SIZE (1 << 17) ++ ++static int INIT handle_zstd_error(size_t ret, void (*error)(char *x)) ++{ ++ const int err = ZSTD_getErrorCode(ret); ++ ++ if (!ZSTD_isError(ret)) ++ return 0; ++ ++ switch (err) { ++ case ZSTD_error_memory_allocation: ++ error("ZSTD decompressor ran out of memory"); ++ break; ++ case ZSTD_error_prefix_unknown: ++ error("Input is not in the ZSTD format (wrong magic bytes)"); ++ break; ++ case ZSTD_error_dstSize_tooSmall: ++ case ZSTD_error_corruption_detected: ++ case ZSTD_error_checksum_wrong: ++ error("ZSTD-compressed data is corrupt"); ++ break; ++ default: ++ error("ZSTD-compressed data is probably corrupt"); ++ break; ++ } ++ return -1; ++} ++ ++/* ++ * Handle the case where we have the entire input and output in one segment. ++ * We can allocate less memory (no circular buffer for the sliding window), ++ * and avoid some memcpy() calls. ++ */ ++static int INIT decompress_single(const u8 *in_buf, long in_len, u8 *out_buf, ++ long out_len, long *in_pos, ++ void (*error)(char *x)) ++{ ++ const size_t wksp_size = ZSTD_DCtxWorkspaceBound(); ++ void *wksp = large_malloc(wksp_size); ++ ZSTD_DCtx *dctx = ZSTD_initDCtx(wksp, wksp_size); ++ int err; ++ size_t ret; ++ ++ if (dctx == NULL) { ++ error("Out of memory while allocating ZSTD_DCtx"); ++ err = -1; ++ goto out; ++ } ++ /* ++ * Find out how large the frame actually is, there may be junk at ++ * the end of the frame that ZSTD_decompressDCtx() can't handle. ++ */ ++ ret = ZSTD_findFrameCompressedSize(in_buf, in_len); ++ err = handle_zstd_error(ret, error); ++ if (err) ++ goto out; ++ in_len = (long)ret; ++ ++ ret = ZSTD_decompressDCtx(dctx, out_buf, out_len, in_buf, in_len); ++ err = handle_zstd_error(ret, error); ++ if (err) ++ goto out; ++ ++ if (in_pos != NULL) ++ *in_pos = in_len; ++ ++ err = 0; ++out: ++ if (wksp != NULL) ++ large_free(wksp); ++ return err; ++} ++ ++static int INIT __unzstd(unsigned char *in_buf, long in_len, ++ long (*fill)(void*, unsigned long), ++ long (*flush)(void*, unsigned long), ++ unsigned char *out_buf, long out_len, ++ long *in_pos, ++ void (*error)(char *x)) ++{ ++ ZSTD_inBuffer in; ++ ZSTD_outBuffer out; ++ ZSTD_frameParams params; ++ void *in_allocated = NULL; ++ void *out_allocated = NULL; ++ void *wksp = NULL; ++ size_t wksp_size; ++ ZSTD_DStream *dstream; ++ int err; ++ size_t ret; ++ ++ if (out_len == 0) ++ out_len = LONG_MAX; /* no limit */ ++ ++ if (fill == NULL && flush == NULL) ++ /* ++ * We can decompress faster and with less memory when we have a ++ * single chunk. ++ */ ++ return decompress_single(in_buf, in_len, out_buf, out_len, ++ in_pos, error); ++ ++ /* ++ * If in_buf is not provided, we must be using fill(), so allocate ++ * a large enough buffer. If it is provided, it must be at least ++ * ZSTD_IOBUF_SIZE large. ++ */ ++ if (in_buf == NULL) { ++ in_allocated = large_malloc(ZSTD_IOBUF_SIZE); ++ if (in_allocated == NULL) { ++ error("Out of memory while allocating input buffer"); ++ err = -1; ++ goto out; ++ } ++ in_buf = in_allocated; ++ in_len = 0; ++ } ++ /* Read the first chunk, since we need to decode the frame header. */ ++ if (fill != NULL) ++ in_len = fill(in_buf, ZSTD_IOBUF_SIZE); ++ if (in_len < 0) { ++ error("ZSTD-compressed data is truncated"); ++ err = -1; ++ goto out; ++ } ++ /* Set the first non-empty input buffer. */ ++ in.src = in_buf; ++ in.pos = 0; ++ in.size = in_len; ++ /* Allocate the output buffer if we are using flush(). */ ++ if (flush != NULL) { ++ out_allocated = large_malloc(ZSTD_IOBUF_SIZE); ++ if (out_allocated == NULL) { ++ error("Out of memory while allocating output buffer"); ++ err = -1; ++ goto out; ++ } ++ out_buf = out_allocated; ++ out_len = ZSTD_IOBUF_SIZE; ++ } ++ /* Set the output buffer. */ ++ out.dst = out_buf; ++ out.pos = 0; ++ out.size = out_len; ++ ++ /* ++ * We need to know the window size to allocate the ZSTD_DStream. ++ * Since we are streaming, we need to allocate a buffer for the sliding ++ * window. The window size varies from 1 KB to ZSTD_WINDOWSIZE_MAX ++ * (8 MB), so it is important to use the actual value so as not to ++ * waste memory when it is smaller. ++ */ ++ ret = ZSTD_getFrameParams(¶ms, in.src, in.size); ++ err = handle_zstd_error(ret, error); ++ if (err) ++ goto out; ++ if (ret != 0) { ++ error("ZSTD-compressed data has an incomplete frame header"); ++ err = -1; ++ goto out; ++ } ++ if (params.windowSize > ZSTD_WINDOWSIZE_MAX) { ++ error("ZSTD-compressed data has too large a window size"); ++ err = -1; ++ goto out; ++ } ++ ++ /* ++ * Allocate the ZSTD_DStream now that we know how much memory is ++ * required. ++ */ ++ wksp_size = ZSTD_DStreamWorkspaceBound(params.windowSize); ++ wksp = large_malloc(wksp_size); ++ dstream = ZSTD_initDStream(params.windowSize, wksp, wksp_size); ++ if (dstream == NULL) { ++ error("Out of memory while allocating ZSTD_DStream"); ++ err = -1; ++ goto out; ++ } ++ ++ /* ++ * Decompression loop: ++ * Read more data if necessary (error if no more data can be read). ++ * Call the decompression function, which returns 0 when finished. ++ * Flush any data produced if using flush(). ++ */ ++ if (in_pos != NULL) ++ *in_pos = 0; ++ do { ++ /* ++ * If we need to reload data, either we have fill() and can ++ * try to get more data, or we don't and the input is truncated. ++ */ ++ if (in.pos == in.size) { ++ if (in_pos != NULL) ++ *in_pos += in.pos; ++ in_len = fill ? fill(in_buf, ZSTD_IOBUF_SIZE) : -1; ++ if (in_len < 0) { ++ error("ZSTD-compressed data is truncated"); ++ err = -1; ++ goto out; ++ } ++ in.pos = 0; ++ in.size = in_len; ++ } ++ /* Returns zero when the frame is complete. */ ++ ret = ZSTD_decompressStream(dstream, &out, &in); ++ err = handle_zstd_error(ret, error); ++ if (err) ++ goto out; ++ /* Flush all of the data produced if using flush(). */ ++ if (flush != NULL && out.pos > 0) { ++ if (out.pos != flush(out.dst, out.pos)) { ++ error("Failed to flush()"); ++ err = -1; ++ goto out; ++ } ++ out.pos = 0; ++ } ++ } while (ret != 0); ++ ++ if (in_pos != NULL) ++ *in_pos += in.pos; ++ ++ err = 0; ++out: ++ if (in_allocated != NULL) ++ large_free(in_allocated); ++ if (out_allocated != NULL) ++ large_free(out_allocated); ++ if (wksp != NULL) ++ large_free(wksp); ++ return err; ++} ++ ++#ifndef ZSTD_PREBOOT ++STATIC int INIT unzstd(unsigned char *buf, long len, ++ long (*fill)(void*, unsigned long), ++ long (*flush)(void*, unsigned long), ++ unsigned char *out_buf, ++ long *pos, ++ void (*error)(char *x)) ++{ ++ return __unzstd(buf, len, fill, flush, out_buf, 0, pos, error); ++} ++#else ++STATIC int INIT __decompress(unsigned char *buf, long len, ++ long (*fill)(void*, unsigned long), ++ long (*flush)(void*, unsigned long), ++ unsigned char *out_buf, long out_len, ++ long *pos, ++ void (*error)(char *x)) ++{ ++ return __unzstd(buf, len, fill, flush, out_buf, out_len, pos, error); ++} ++#endif diff --git a/5003_ZSTD-v5-4-8-add-support-for-zstd-compres-kern.patch b/5003_ZSTD-v5-4-8-add-support-for-zstd-compres-kern.patch new file mode 100644 index 0000000..d9dc79e --- /dev/null +++ b/5003_ZSTD-v5-4-8-add-support-for-zstd-compres-kern.patch @@ -0,0 +1,65 @@ +diff --git a/init/Kconfig b/init/Kconfig +index 492bb7000aa4..806874fdd663 100644 +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -176,13 +176,16 @@ config HAVE_KERNEL_LZO + config HAVE_KERNEL_LZ4 + bool + ++config HAVE_KERNEL_ZSTD ++ bool ++ + config HAVE_KERNEL_UNCOMPRESSED + bool + + choice + prompt "Kernel compression mode" + default KERNEL_GZIP +- depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4 || HAVE_KERNEL_UNCOMPRESSED ++ depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4 || HAVE_KERNEL_ZSTD || HAVE_KERNEL_UNCOMPRESSED + help + The linux kernel is a kind of self-extracting executable. + Several compression algorithms are available, which differ +@@ -261,6 +264,16 @@ config KERNEL_LZ4 + is about 8% bigger than LZO. But the decompression speed is + faster than LZO. + ++config KERNEL_ZSTD ++ bool "ZSTD" ++ depends on HAVE_KERNEL_ZSTD ++ help ++ ZSTD is a compression algorithm targeting intermediate compression ++ with fast decompression speed. It will compress better than GZIP and ++ decompress around the same speed as LZO, but slower than LZ4. You ++ will need at least 192 KB RAM or more for booting. The zstd command ++ line tools is required for compression. ++ + config KERNEL_UNCOMPRESSED + bool "None" + depends on HAVE_KERNEL_UNCOMPRESSED +diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib +index b12dd5ba4896..efe69b78d455 100644 +--- a/scripts/Makefile.lib ++++ b/scripts/Makefile.lib +@@ -405,6 +405,21 @@ quiet_cmd_xzkern = XZKERN $@ + quiet_cmd_xzmisc = XZMISC $@ + cmd_xzmisc = cat $(real-prereqs) | xz --check=crc32 --lzma2=dict=1MiB > $@ + ++# ZSTD ++# --------------------------------------------------------------------------- ++# Appends the uncompressed size of the data using size_append. The .zst ++# format has the size information available at the beginning of the file too, ++# but it's in a more complex format and it's good to avoid changing the part ++# of the boot code that reads the uncompressed size. ++# Note that the bytes added by size_append will make the zstd tool think that ++# the file is corrupt. This is expected. ++ ++quiet_cmd_zstd = ZSTD $@ ++cmd_zstd = (cat $(filter-out FORCE,$^) | \ ++ zstd -19 && \ ++ $(call size_append, $(filter-out FORCE,$^))) > $@ || \ ++ (rm -f $@ ; false) ++ + # ASM offsets + # --------------------------------------------------------------------------- + diff --git a/5004_ZSTD-v5-5-8-add-support-for-zstd-compressed-initramfs.patch b/5004_ZSTD-v5-5-8-add-support-for-zstd-compressed-initramfs.patch new file mode 100644 index 0000000..0096db1 --- /dev/null +++ b/5004_ZSTD-v5-5-8-add-support-for-zstd-compressed-initramfs.patch @@ -0,0 +1,50 @@ +diff --git a/usr/Kconfig b/usr/Kconfig +index 96afb03b65f9..2599bc21c1b2 100644 +--- a/usr/Kconfig ++++ b/usr/Kconfig +@@ -100,6 +100,15 @@ config RD_LZ4 + Support loading of a LZ4 encoded initial ramdisk or cpio buffer + If unsure, say N. + ++config RD_ZSTD ++ bool "Support initial ramdisk/ramfs compressed using ZSTD" ++ default y ++ depends on BLK_DEV_INITRD ++ select DECOMPRESS_ZSTD ++ help ++ Support loading of a ZSTD encoded initial ramdisk or cpio buffer. ++ If unsure, say N. ++ + choice + prompt "Built-in initramfs compression mode" + depends on INITRAMFS_SOURCE != "" +@@ -196,6 +205,17 @@ config INITRAMFS_COMPRESSION_LZ4 + If you choose this, keep in mind that most distros don't provide lz4 + by default which could cause a build failure. + ++config INITRAMFS_COMPRESSION_ZSTD ++ bool "ZSTD" ++ depends on RD_ZSTD ++ help ++ ZSTD is a compression algorithm targeting intermediate compression ++ with fast decompression speed. It will compress better than GZIP and ++ decompress around the same speed as LZO, but slower than LZ4. ++ ++ If you choose this, keep in mind that you may need to install the zstd ++ tool to be able to compress the initram. ++ + config INITRAMFS_COMPRESSION_NONE + bool "None" + help +diff --git a/usr/Makefile b/usr/Makefile +index c12e6b15ce72..b1a81a40eab1 100644 +--- a/usr/Makefile ++++ b/usr/Makefile +@@ -15,6 +15,7 @@ compress-$(CONFIG_INITRAMFS_COMPRESSION_LZMA) := lzma + compress-$(CONFIG_INITRAMFS_COMPRESSION_XZ) := xzmisc + compress-$(CONFIG_INITRAMFS_COMPRESSION_LZO) := lzo + compress-$(CONFIG_INITRAMFS_COMPRESSION_LZ4) := lz4 ++compress-$(CONFIG_INITRAMFS_COMPRESSION_ZSTD) := zstd + + obj-$(CONFIG_BLK_DEV_INITRD) := initramfs_data.o + diff --git a/5005_ZSTD-v5-6-8-bump-ZO-z-extra-bytes-margin.patch b/5005_ZSTD-v5-6-8-bump-ZO-z-extra-bytes-margin.patch new file mode 100644 index 0000000..4e86d56 --- /dev/null +++ b/5005_ZSTD-v5-6-8-bump-ZO-z-extra-bytes-margin.patch @@ -0,0 +1,20 @@ +diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S +index 735ad7f21ab0..6dbd7e9f74c9 100644 +--- a/arch/x86/boot/header.S ++++ b/arch/x86/boot/header.S +@@ -539,8 +539,14 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr + # the size-dependent part now grows so fast. + # + # extra_bytes = (uncompressed_size >> 8) + 65536 ++# ++# ZSTD compressed data grows by at most 3 bytes per 128K, and only has a 22 ++# byte fixed overhead but has a maximum block size of 128K, so it needs a ++# larger margin. ++# ++# extra_bytes = (uncompressed_size >> 8) + 131072 + +-#define ZO_z_extra_bytes ((ZO_z_output_len >> 8) + 65536) ++#define ZO_z_extra_bytes ((ZO_z_output_len >> 8) + 131072) + #if ZO_z_output_len > ZO_z_input_len + # define ZO_z_extract_offset (ZO_z_output_len + ZO_z_extra_bytes - \ + ZO_z_input_len) diff --git a/5006_ZSTD-v5-7-8-support-for-ZSTD-compressed-kernel.patch b/5006_ZSTD-v5-7-8-support-for-ZSTD-compressed-kernel.patch new file mode 100644 index 0000000..6147136 --- /dev/null +++ b/5006_ZSTD-v5-7-8-support-for-ZSTD-compressed-kernel.patch @@ -0,0 +1,92 @@ +diff --git a/Documentation/x86/boot.rst b/Documentation/x86/boot.rst +index fa7ddc0428c8..0404e99dc1d4 100644 +--- a/Documentation/x86/boot.rst ++++ b/Documentation/x86/boot.rst +@@ -782,9 +782,9 @@ Protocol: 2.08+ + uncompressed data should be determined using the standard magic + numbers. The currently supported compression formats are gzip + (magic numbers 1F 8B or 1F 9E), bzip2 (magic number 42 5A), LZMA +- (magic number 5D 00), XZ (magic number FD 37), and LZ4 (magic number +- 02 21). The uncompressed payload is currently always ELF (magic +- number 7F 45 4C 46). ++ (magic number 5D 00), XZ (magic number FD 37), LZ4 (magic number ++ 02 21) and ZSTD (magic number 28 B5). The uncompressed payload is ++ currently always ELF (magic number 7F 45 4C 46). + + ============ ============== + Field name: payload_length +diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig +index 886fa8368256..912f783bc01a 100644 +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -185,6 +185,7 @@ config X86 + select HAVE_KERNEL_LZMA + select HAVE_KERNEL_LZO + select HAVE_KERNEL_XZ ++ select HAVE_KERNEL_ZSTD + select HAVE_KPROBES + select HAVE_KPROBES_ON_FTRACE + select HAVE_FUNCTION_ERROR_INJECTION +diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile +index 7619742f91c9..471e61400a2e 100644 +--- a/arch/x86/boot/compressed/Makefile ++++ b/arch/x86/boot/compressed/Makefile +@@ -26,7 +26,7 @@ OBJECT_FILES_NON_STANDARD := y + KCOV_INSTRUMENT := n + + targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ +- vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 ++ vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 vmlinux.bin.zst + + KBUILD_CFLAGS := -m$(BITS) -O2 + KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC) +@@ -145,6 +145,8 @@ $(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE + $(call if_changed,lzo) + $(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE + $(call if_changed,lz4) ++$(obj)/vmlinux.bin.zst: $(vmlinux.bin.all-y) FORCE ++ $(call if_changed,zstd) + + suffix-$(CONFIG_KERNEL_GZIP) := gz + suffix-$(CONFIG_KERNEL_BZIP2) := bz2 +@@ -152,6 +154,7 @@ suffix-$(CONFIG_KERNEL_LZMA) := lzma + suffix-$(CONFIG_KERNEL_XZ) := xz + suffix-$(CONFIG_KERNEL_LZO) := lzo + suffix-$(CONFIG_KERNEL_LZ4) := lz4 ++suffix-$(CONFIG_KERNEL_ZSTD) := zst + + quiet_cmd_mkpiggy = MKPIGGY $@ + cmd_mkpiggy = $(obj)/mkpiggy $< > $@ +diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c +index 9652d5c2afda..39e592d0e0b4 100644 +--- a/arch/x86/boot/compressed/misc.c ++++ b/arch/x86/boot/compressed/misc.c +@@ -77,6 +77,10 @@ static int lines, cols; + #ifdef CONFIG_KERNEL_LZ4 + #include "../../../../lib/decompress_unlz4.c" + #endif ++ ++#ifdef CONFIG_KERNEL_ZSTD ++#include "../../../../lib/decompress_unzstd.c" ++#endif + /* + * NOTE: When adding a new decompressor, please update the analysis in + * ../header.S. +diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h +index 680c320363db..d6dd43d25d9f 100644 +--- a/arch/x86/include/asm/boot.h ++++ b/arch/x86/include/asm/boot.h +@@ -24,9 +24,11 @@ + # error "Invalid value for CONFIG_PHYSICAL_ALIGN" + #endif + +-#ifdef CONFIG_KERNEL_BZIP2 ++#if defined(CONFIG_KERNEL_BZIP2) + # define BOOT_HEAP_SIZE 0x400000 +-#else /* !CONFIG_KERNEL_BZIP2 */ ++#elif defined(CONFIG_KERNEL_ZSTD) ++# define BOOT_HEAP_SIZE 0x30000 ++#else + # define BOOT_HEAP_SIZE 0x10000 + #endif + diff --git a/5007_ZSTD-v5-8-8-gitignore-add-ZSTD-compressed-files.patch b/5007_ZSTD-v5-8-8-gitignore-add-ZSTD-compressed-files.patch new file mode 100644 index 0000000..adf8578 --- /dev/null +++ b/5007_ZSTD-v5-8-8-gitignore-add-ZSTD-compressed-files.patch @@ -0,0 +1,12 @@ +diff --git a/.gitignore b/.gitignore +index 2258e906f01c..23871de69072 100644 +--- a/.gitignore ++++ b/.gitignore +@@ -44,6 +44,7 @@ + *.tab.[ch] + *.tar + *.xz ++*.zst + Module.symvers + modules.builtin + modules.order diff --git a/5012_enable-cpu-optimizations-for-gcc91.patch b/5012_enable-cpu-optimizations-for-gcc91.patch new file mode 100644 index 0000000..049ec12 --- /dev/null +++ b/5012_enable-cpu-optimizations-for-gcc91.patch @@ -0,0 +1,632 @@ +WARNING +This patch works with gcc versions 9.1+ and with kernel version 5.7+ and should +NOT be applied when compiling on older versions of gcc due to key name changes +of the march flags introduced with the version 4.9 release of gcc.[1] + +Use the older version of this patch hosted on the same github for older +versions of gcc. + +FEATURES +This patch adds additional CPU options to the Linux kernel accessible under: + Processor type and features ---> + Processor family ---> + +The expanded microarchitectures include: +* AMD Improved K8-family +* AMD K10-family +* AMD Family 10h (Barcelona) +* AMD Family 14h (Bobcat) +* AMD Family 16h (Jaguar) +* AMD Family 15h (Bulldozer) +* AMD Family 15h (Piledriver) +* AMD Family 15h (Steamroller) +* AMD Family 15h (Excavator) +* AMD Family 17h (Zen) +* AMD Family 17h (Zen 2) +* Intel Silvermont low-power processors +* Intel Goldmont low-power processors (Apollo Lake and Denverton) +* Intel Goldmont Plus low-power processors (Gemini Lake) +* Intel 1st Gen Core i3/i5/i7 (Nehalem) +* Intel 1.5 Gen Core i3/i5/i7 (Westmere) +* Intel 2nd Gen Core i3/i5/i7 (Sandybridge) +* Intel 3rd Gen Core i3/i5/i7 (Ivybridge) +* Intel 4th Gen Core i3/i5/i7 (Haswell) +* Intel 5th Gen Core i3/i5/i7 (Broadwell) +* Intel 6th Gen Core i3/i5/i7 (Skylake) +* Intel 6th Gen Core i7/i9 (Skylake X) +* Intel 8th Gen Core i3/i5/i7 (Cannon Lake) +* Intel 10th Gen Core i7/i9 (Ice Lake) +* Intel Xeon (Cascade Lake) + +It also offers to compile passing the 'native' option which, "selects the CPU +to generate code for at compilation time by determining the processor type of +the compiling machine. Using -march=native enables all instruction subsets +supported by the local machine and will produce code optimized for the local +machine under the constraints of the selected instruction set."[3] + +MINOR NOTES +This patch also changes 'atom' to 'bonnell' in accordance with the gcc v4.9 +changes. Note that upstream is using the deprecated 'match=atom' flags when I +believe it should use the newer 'march=bonnell' flag for atom processors.[2] + +It is not recommended to compile on Atom-CPUs with the 'native' option.[4] The +recommendation is to use the 'atom' option instead. + +BENEFITS +Small but real speed increases are measurable using a make endpoint comparing +a generic kernel to one built with one of the respective microarchs. + +See the following experimental evidence supporting this statement: +https://github.com/graysky2/kernel_gcc_patch + +REQUIREMENTS +linux version >=5.7 +gcc version >=9.1 + +ACKNOWLEDGMENTS +This patch builds on the seminal work by Jeroen.[5] + +REFERENCES +1. https://gcc.gnu.org/gcc-4.9/changes.html +2. https://bugzilla.kernel.org/show_bug.cgi?id=77461 +3. https://gcc.gnu.org/onlinedocs/gcc/x86-Options.html +4. https://github.com/graysky2/kernel_gcc_patch/issues/15 +5. http://www.linuxforge.net/docs/linux/linux-gcc.php + +--- a/arch/x86/include/asm/vermagic.h 2019-12-15 18:16:08.000000000 -0500 ++++ b/arch/x86/include/asm/vermagic.h 2019-12-17 14:03:55.968871551 -0500 +@@ -27,6 +27,36 @@ struct mod_arch_specific { + #define MODULE_PROC_FAMILY "586MMX " + #elif defined CONFIG_MCORE2 + #define MODULE_PROC_FAMILY "CORE2 " ++#elif defined CONFIG_MNATIVE ++#define MODULE_PROC_FAMILY "NATIVE " ++#elif defined CONFIG_MNEHALEM ++#define MODULE_PROC_FAMILY "NEHALEM " ++#elif defined CONFIG_MWESTMERE ++#define MODULE_PROC_FAMILY "WESTMERE " ++#elif defined CONFIG_MSILVERMONT ++#define MODULE_PROC_FAMILY "SILVERMONT " ++#elif defined CONFIG_MGOLDMONT ++#define MODULE_PROC_FAMILY "GOLDMONT " ++#elif defined CONFIG_MGOLDMONTPLUS ++#define MODULE_PROC_FAMILY "GOLDMONTPLUS " ++#elif defined CONFIG_MSANDYBRIDGE ++#define MODULE_PROC_FAMILY "SANDYBRIDGE " ++#elif defined CONFIG_MIVYBRIDGE ++#define MODULE_PROC_FAMILY "IVYBRIDGE " ++#elif defined CONFIG_MHASWELL ++#define MODULE_PROC_FAMILY "HASWELL " ++#elif defined CONFIG_MBROADWELL ++#define MODULE_PROC_FAMILY "BROADWELL " ++#elif defined CONFIG_MSKYLAKE ++#define MODULE_PROC_FAMILY "SKYLAKE " ++#elif defined CONFIG_MSKYLAKEX ++#define MODULE_PROC_FAMILY "SKYLAKEX " ++#elif defined CONFIG_MCANNONLAKE ++#define MODULE_PROC_FAMILY "CANNONLAKE " ++#elif defined CONFIG_MICELAKE ++#define MODULE_PROC_FAMILY "ICELAKE " ++#elif defined CONFIG_MCASCADELAKE ++#define MODULE_PROC_FAMILY "CASCADELAKE " + #elif defined CONFIG_MATOM + #define MODULE_PROC_FAMILY "ATOM " + #elif defined CONFIG_M686 +@@ -45,6 +75,28 @@ struct mod_arch_specific { + #define MODULE_PROC_FAMILY "K7 " + #elif defined CONFIG_MK8 + #define MODULE_PROC_FAMILY "K8 " ++#elif defined CONFIG_MK8SSE3 ++#define MODULE_PROC_FAMILY "K8SSE3 " ++#elif defined CONFIG_MK10 ++#define MODULE_PROC_FAMILY "K10 " ++#elif defined CONFIG_MBARCELONA ++#define MODULE_PROC_FAMILY "BARCELONA " ++#elif defined CONFIG_MBOBCAT ++#define MODULE_PROC_FAMILY "BOBCAT " ++#elif defined CONFIG_MBULLDOZER ++#define MODULE_PROC_FAMILY "BULLDOZER " ++#elif defined CONFIG_MPILEDRIVER ++#define MODULE_PROC_FAMILY "PILEDRIVER " ++#elif defined CONFIG_MSTEAMROLLER ++#define MODULE_PROC_FAMILY "STEAMROLLER " ++#elif defined CONFIG_MJAGUAR ++#define MODULE_PROC_FAMILY "JAGUAR " ++#elif defined CONFIG_MEXCAVATOR ++#define MODULE_PROC_FAMILY "EXCAVATOR " ++#elif defined CONFIG_MZEN ++#define MODULE_PROC_FAMILY "ZEN " ++#elif defined CONFIG_MZEN2 ++#define MODULE_PROC_FAMILY "ZEN2 " + #elif defined CONFIG_MELAN + #define MODULE_PROC_FAMILY "ELAN " + #elif defined CONFIG_MCRUSOE +--- a/arch/x86/Kconfig.cpu 2019-12-15 18:16:08.000000000 -0500 ++++ b/arch/x86/Kconfig.cpu 2019-12-17 14:09:03.805642284 -0500 +@@ -123,6 +123,7 @@ config MPENTIUMM + config MPENTIUM4 + bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/older Xeon" + depends on X86_32 ++ select X86_P6_NOP + ---help--- + Select this for Intel Pentium 4 chips. This includes the + Pentium 4, Pentium D, P4-based Celeron and Xeon, and +@@ -155,9 +156,8 @@ config MPENTIUM4 + -Paxville + -Dempsey + +- + config MK6 +- bool "K6/K6-II/K6-III" ++ bool "AMD K6/K6-II/K6-III" + depends on X86_32 + ---help--- + Select this for an AMD K6-family processor. Enables use of +@@ -165,7 +165,7 @@ config MK6 + flags to GCC. + + config MK7 +- bool "Athlon/Duron/K7" ++ bool "AMD Athlon/Duron/K7" + depends on X86_32 + ---help--- + Select this for an AMD Athlon K7-family processor. Enables use of +@@ -173,12 +173,90 @@ config MK7 + flags to GCC. + + config MK8 +- bool "Opteron/Athlon64/Hammer/K8" ++ bool "AMD Opteron/Athlon64/Hammer/K8" + ---help--- + Select this for an AMD Opteron or Athlon64 Hammer-family processor. + Enables use of some extended instructions, and passes appropriate + optimization flags to GCC. + ++config MK8SSE3 ++ bool "AMD Opteron/Athlon64/Hammer/K8 with SSE3" ++ ---help--- ++ Select this for improved AMD Opteron or Athlon64 Hammer-family processors. ++ Enables use of some extended instructions, and passes appropriate ++ optimization flags to GCC. ++ ++config MK10 ++ bool "AMD 61xx/7x50/PhenomX3/X4/II/K10" ++ ---help--- ++ Select this for an AMD 61xx Eight-Core Magny-Cours, Athlon X2 7x50, ++ Phenom X3/X4/II, Athlon II X2/X3/X4, or Turion II-family processor. ++ Enables use of some extended instructions, and passes appropriate ++ optimization flags to GCC. ++ ++config MBARCELONA ++ bool "AMD Barcelona" ++ ---help--- ++ Select this for AMD Family 10h Barcelona processors. ++ ++ Enables -march=barcelona ++ ++config MBOBCAT ++ bool "AMD Bobcat" ++ ---help--- ++ Select this for AMD Family 14h Bobcat processors. ++ ++ Enables -march=btver1 ++ ++config MJAGUAR ++ bool "AMD Jaguar" ++ ---help--- ++ Select this for AMD Family 16h Jaguar processors. ++ ++ Enables -march=btver2 ++ ++config MBULLDOZER ++ bool "AMD Bulldozer" ++ ---help--- ++ Select this for AMD Family 15h Bulldozer processors. ++ ++ Enables -march=bdver1 ++ ++config MPILEDRIVER ++ bool "AMD Piledriver" ++ ---help--- ++ Select this for AMD Family 15h Piledriver processors. ++ ++ Enables -march=bdver2 ++ ++config MSTEAMROLLER ++ bool "AMD Steamroller" ++ ---help--- ++ Select this for AMD Family 15h Steamroller processors. ++ ++ Enables -march=bdver3 ++ ++config MEXCAVATOR ++ bool "AMD Excavator" ++ ---help--- ++ Select this for AMD Family 15h Excavator processors. ++ ++ Enables -march=bdver4 ++ ++config MZEN ++ bool "AMD Zen" ++ ---help--- ++ Select this for AMD Family 17h Zen processors. ++ ++ Enables -march=znver1 ++ ++config MZEN2 ++ bool "AMD Zen 2" ++ ---help--- ++ Select this for AMD Family 17h Zen 2 processors. ++ ++ Enables -march=znver2 ++ + config MCRUSOE + bool "Crusoe" + depends on X86_32 +@@ -260,6 +338,7 @@ config MVIAC7 + + config MPSC + bool "Intel P4 / older Netburst based Xeon" ++ select X86_P6_NOP + depends on X86_64 + ---help--- + Optimize for Intel Pentium 4, Pentium D and older Nocona/Dempsey +@@ -269,8 +348,19 @@ config MPSC + using the cpu family field + in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one. + ++config MATOM ++ bool "Intel Atom" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for the Intel Atom platform. Intel Atom CPUs have an ++ in-order pipelining architecture and thus can benefit from ++ accordingly optimized code. Use a recent GCC with specific Atom ++ support in order to fully benefit from selecting this option. ++ + config MCORE2 +- bool "Core 2/newer Xeon" ++ bool "Intel Core 2" ++ select X86_P6_NOP + ---help--- + + Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and +@@ -278,14 +368,133 @@ config MCORE2 + family in /proc/cpuinfo. Newer ones have 6 and older ones 15 + (not a typo) + +-config MATOM +- bool "Intel Atom" ++ Enables -march=core2 ++ ++config MNEHALEM ++ bool "Intel Nehalem" ++ select X86_P6_NOP + ---help--- + +- Select this for the Intel Atom platform. Intel Atom CPUs have an +- in-order pipelining architecture and thus can benefit from +- accordingly optimized code. Use a recent GCC with specific Atom +- support in order to fully benefit from selecting this option. ++ Select this for 1st Gen Core processors in the Nehalem family. ++ ++ Enables -march=nehalem ++ ++config MWESTMERE ++ bool "Intel Westmere" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for the Intel Westmere formerly Nehalem-C family. ++ ++ Enables -march=westmere ++ ++config MSILVERMONT ++ bool "Intel Silvermont" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for the Intel Silvermont platform. ++ ++ Enables -march=silvermont ++ ++config MGOLDMONT ++ bool "Intel Goldmont" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for the Intel Goldmont platform including Apollo Lake and Denverton. ++ ++ Enables -march=goldmont ++ ++config MGOLDMONTPLUS ++ bool "Intel Goldmont Plus" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for the Intel Goldmont Plus platform including Gemini Lake. ++ ++ Enables -march=goldmont-plus ++ ++config MSANDYBRIDGE ++ bool "Intel Sandy Bridge" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for 2nd Gen Core processors in the Sandy Bridge family. ++ ++ Enables -march=sandybridge ++ ++config MIVYBRIDGE ++ bool "Intel Ivy Bridge" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for 3rd Gen Core processors in the Ivy Bridge family. ++ ++ Enables -march=ivybridge ++ ++config MHASWELL ++ bool "Intel Haswell" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for 4th Gen Core processors in the Haswell family. ++ ++ Enables -march=haswell ++ ++config MBROADWELL ++ bool "Intel Broadwell" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for 5th Gen Core processors in the Broadwell family. ++ ++ Enables -march=broadwell ++ ++config MSKYLAKE ++ bool "Intel Skylake" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for 6th Gen Core processors in the Skylake family. ++ ++ Enables -march=skylake ++ ++config MSKYLAKEX ++ bool "Intel Skylake X" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for 6th Gen Core processors in the Skylake X family. ++ ++ Enables -march=skylake-avx512 ++ ++config MCANNONLAKE ++ bool "Intel Cannon Lake" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for 8th Gen Core processors ++ ++ Enables -march=cannonlake ++ ++config MICELAKE ++ bool "Intel Ice Lake" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for 10th Gen Core processors in the Ice Lake family. ++ ++ Enables -march=icelake-client ++ ++config MCASCADELAKE ++ bool "Intel Cascade Lake" ++ select X86_P6_NOP ++ ---help--- ++ ++ Select this for Xeon processors in the Cascade Lake family. ++ ++ Enables -march=cascadelake + + config GENERIC_CPU + bool "Generic-x86-64" +@@ -294,6 +503,19 @@ config GENERIC_CPU + Generic x86-64 CPU. + Run equally well on all x86-64 CPUs. + ++config MNATIVE ++ bool "Native optimizations autodetected by GCC" ++ ---help--- ++ ++ GCC 4.2 and above support -march=native, which automatically detects ++ the optimum settings to use based on your processor. -march=native ++ also detects and applies additional settings beyond -march specific ++ to your CPU, (eg. -msse4). Unless you have a specific reason not to ++ (e.g. distcc cross-compiling), you should probably be using ++ -march=native rather than anything listed below. ++ ++ Enables -march=native ++ + endchoice + + config X86_GENERIC +@@ -318,7 +540,7 @@ config X86_INTERNODE_CACHE_SHIFT + config X86_L1_CACHE_SHIFT + int + default "7" if MPENTIUM4 || MPSC +- default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU ++ default "6" if MK7 || MK8 || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MJAGUAR || MPENTIUMM || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MNATIVE || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU + default "4" if MELAN || M486SX || M486 || MGEODEGX1 + default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX + +@@ -336,35 +558,36 @@ config X86_ALIGNMENT_16 + + config X86_INTEL_USERCOPY + def_bool y +- depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2 ++ depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK8SSE3 || MK7 || MEFFICEON || MCORE2 || MK10 || MBARCELONA || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MNATIVE + + config X86_USE_PPRO_CHECKSUM + def_bool y +- depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM ++ depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MK10 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MK8SSE3 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MATOM || MNATIVE + + config X86_USE_3DNOW + def_bool y + depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML + +-# +-# P6_NOPs are a relatively minor optimization that require a family >= +-# 6 processor, except that it is broken on certain VIA chips. +-# Furthermore, AMD chips prefer a totally different sequence of NOPs +-# (which work on all CPUs). In addition, it looks like Virtual PC +-# does not understand them. +-# +-# As a result, disallow these if we're not compiling for X86_64 (these +-# NOPs do work on all x86-64 capable chips); the list of processors in +-# the right-hand clause are the cores that benefit from this optimization. +-# + config X86_P6_NOP +- def_bool y +- depends on X86_64 +- depends on (MCORE2 || MPENTIUM4 || MPSC) ++ default n ++ bool "Support for P6_NOPs on Intel chips" ++ depends on (MCORE2 || MPENTIUM4 || MPSC || MATOM || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MNATIVE) ++ ---help--- ++ P6_NOPs are a relatively minor optimization that require a family >= ++ 6 processor, except that it is broken on certain VIA chips. ++ Furthermore, AMD chips prefer a totally different sequence of NOPs ++ (which work on all CPUs). In addition, it looks like Virtual PC ++ does not understand them. ++ ++ As a result, disallow these if we're not compiling for X86_64 (these ++ NOPs do work on all x86-64 capable chips); the list of processors in ++ the right-hand clause are the cores that benefit from this optimization. ++ ++ Say Y if you have Intel CPU newer than Pentium Pro, N otherwise. + + config X86_TSC + def_bool y +- depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64 ++ depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MK8SSE3 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MNATIVE || MATOM) || X86_64 + + config X86_CMPXCHG64 + def_bool y +@@ -374,7 +597,7 @@ config X86_CMPXCHG64 + # generates cmov. + config X86_CMOV + def_bool y +- depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX) ++ depends on (MK8 || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MJAGUAR || MK7 || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MNATIVE || MATOM || MGEODE_LX) + + config X86_MINIMUM_CPU_FAMILY + int +--- a/arch/x86/Makefile 2019-12-15 18:16:08.000000000 -0500 ++++ b/arch/x86/Makefile 2019-12-17 14:03:55.972204960 -0500 +@@ -119,13 +119,53 @@ else + KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup) + + # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu) ++ cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native) + cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) ++ cflags-$(CONFIG_MK8SSE3) += $(call cc-option,-march=k8-sse3,-mtune=k8) ++ cflags-$(CONFIG_MK10) += $(call cc-option,-march=amdfam10) ++ cflags-$(CONFIG_MBARCELONA) += $(call cc-option,-march=barcelona) ++ cflags-$(CONFIG_MBOBCAT) += $(call cc-option,-march=btver1) ++ cflags-$(CONFIG_MJAGUAR) += $(call cc-option,-march=btver2) ++ cflags-$(CONFIG_MBULLDOZER) += $(call cc-option,-march=bdver1) ++ cflags-$(CONFIG_MPILEDRIVER) += $(call cc-option,-march=bdver2) ++ cflags-$(CONFIG_MSTEAMROLLER) += $(call cc-option,-march=bdver3) ++ cflags-$(CONFIG_MEXCAVATOR) += $(call cc-option,-march=bdver4) ++ cflags-$(CONFIG_MZEN) += $(call cc-option,-march=znver1) ++ cflags-$(CONFIG_MZEN2) += $(call cc-option,-march=znver2) + cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona) + + cflags-$(CONFIG_MCORE2) += \ +- $(call cc-option,-march=core2,$(call cc-option,-mtune=generic)) +- cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \ +- $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) ++ $(call cc-option,-march=core2,$(call cc-option,-mtune=core2)) ++ cflags-$(CONFIG_MNEHALEM) += \ ++ $(call cc-option,-march=nehalem,$(call cc-option,-mtune=nehalem)) ++ cflags-$(CONFIG_MWESTMERE) += \ ++ $(call cc-option,-march=westmere,$(call cc-option,-mtune=westmere)) ++ cflags-$(CONFIG_MSILVERMONT) += \ ++ $(call cc-option,-march=silvermont,$(call cc-option,-mtune=silvermont)) ++ cflags-$(CONFIG_MGOLDMONT) += \ ++ $(call cc-option,-march=goldmont,$(call cc-option,-mtune=goldmont)) ++ cflags-$(CONFIG_MGOLDMONTPLUS) += \ ++ $(call cc-option,-march=goldmont-plus,$(call cc-option,-mtune=goldmont-plus)) ++ cflags-$(CONFIG_MSANDYBRIDGE) += \ ++ $(call cc-option,-march=sandybridge,$(call cc-option,-mtune=sandybridge)) ++ cflags-$(CONFIG_MIVYBRIDGE) += \ ++ $(call cc-option,-march=ivybridge,$(call cc-option,-mtune=ivybridge)) ++ cflags-$(CONFIG_MHASWELL) += \ ++ $(call cc-option,-march=haswell,$(call cc-option,-mtune=haswell)) ++ cflags-$(CONFIG_MBROADWELL) += \ ++ $(call cc-option,-march=broadwell,$(call cc-option,-mtune=broadwell)) ++ cflags-$(CONFIG_MSKYLAKE) += \ ++ $(call cc-option,-march=skylake,$(call cc-option,-mtune=skylake)) ++ cflags-$(CONFIG_MSKYLAKEX) += \ ++ $(call cc-option,-march=skylake-avx512,$(call cc-option,-mtune=skylake-avx512)) ++ cflags-$(CONFIG_MCANNONLAKE) += \ ++ $(call cc-option,-march=cannonlake,$(call cc-option,-mtune=cannonlake)) ++ cflags-$(CONFIG_MICELAKE) += \ ++ $(call cc-option,-march=icelake-client,$(call cc-option,-mtune=icelake-client)) ++ cflags-$(CONFIG_MCASCADELAKE) += \ ++ $(call cc-option,-march=cascadelake,$(call cc-option,-mtune=cascadelake)) ++ cflags-$(CONFIG_MATOM) += $(call cc-option,-march=bonnell) \ ++ $(call cc-option,-mtune=bonnell,$(call cc-option,-mtune=generic)) + cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic) + KBUILD_CFLAGS += $(cflags-y) + +--- a/arch/x86/Makefile_32.cpu 2019-12-15 18:16:08.000000000 -0500 ++++ b/arch/x86/Makefile_32.cpu 2019-12-17 14:03:55.972204960 -0500 +@@ -24,7 +24,19 @@ cflags-$(CONFIG_MK6) += -march=k6 + # Please note, that patches that add -march=athlon-xp and friends are pointless. + # They make zero difference whatsosever to performance at this time. + cflags-$(CONFIG_MK7) += -march=athlon ++cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native) + cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,-march=athlon) ++cflags-$(CONFIG_MK8SSE3) += $(call cc-option,-march=k8-sse3,-march=athlon) ++cflags-$(CONFIG_MK10) += $(call cc-option,-march=amdfam10,-march=athlon) ++cflags-$(CONFIG_MBARCELONA) += $(call cc-option,-march=barcelona,-march=athlon) ++cflags-$(CONFIG_MBOBCAT) += $(call cc-option,-march=btver1,-march=athlon) ++cflags-$(CONFIG_MJAGUAR) += $(call cc-option,-march=btver2,-march=athlon) ++cflags-$(CONFIG_MBULLDOZER) += $(call cc-option,-march=bdver1,-march=athlon) ++cflags-$(CONFIG_MPILEDRIVER) += $(call cc-option,-march=bdver2,-march=athlon) ++cflags-$(CONFIG_MSTEAMROLLER) += $(call cc-option,-march=bdver3,-march=athlon) ++cflags-$(CONFIG_MEXCAVATOR) += $(call cc-option,-march=bdver4,-march=athlon) ++cflags-$(CONFIG_MZEN) += $(call cc-option,-march=znver1,-march=athlon) ++cflags-$(CONFIG_MZEN2) += $(call cc-option,-march=znver2,-march=athlon) + cflags-$(CONFIG_MCRUSOE) += -march=i686 -falign-functions=0 -falign-jumps=0 -falign-loops=0 + cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) -falign-functions=0 -falign-jumps=0 -falign-loops=0 + cflags-$(CONFIG_MWINCHIPC6) += $(call cc-option,-march=winchip-c6,-march=i586) +@@ -33,8 +45,22 @@ cflags-$(CONFIG_MCYRIXIII) += $(call cc- + cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686) + cflags-$(CONFIG_MVIAC7) += -march=i686 + cflags-$(CONFIG_MCORE2) += -march=i686 $(call tune,core2) +-cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom,$(call cc-option,-march=core2,-march=i686)) \ +- $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) ++cflags-$(CONFIG_MNEHALEM) += -march=i686 $(call tune,nehalem) ++cflags-$(CONFIG_MWESTMERE) += -march=i686 $(call tune,westmere) ++cflags-$(CONFIG_MSILVERMONT) += -march=i686 $(call tune,silvermont) ++cflags-$(CONFIG_MGOLDMONT) += -march=i686 $(call tune,goldmont) ++cflags-$(CONFIG_MGOLDMONTPLUS) += -march=i686 $(call tune,goldmont-plus) ++cflags-$(CONFIG_MSANDYBRIDGE) += -march=i686 $(call tune,sandybridge) ++cflags-$(CONFIG_MIVYBRIDGE) += -march=i686 $(call tune,ivybridge) ++cflags-$(CONFIG_MHASWELL) += -march=i686 $(call tune,haswell) ++cflags-$(CONFIG_MBROADWELL) += -march=i686 $(call tune,broadwell) ++cflags-$(CONFIG_MSKYLAKE) += -march=i686 $(call tune,skylake) ++cflags-$(CONFIG_MSKYLAKEX) += -march=i686 $(call tune,skylake-avx512) ++cflags-$(CONFIG_MCANNONLAKE) += -march=i686 $(call tune,cannonlake) ++cflags-$(CONFIG_MICELAKE) += -march=i686 $(call tune,icelake-client) ++cflags-$(CONFIG_MCASCADELAKE) += -march=i686 $(call tune,cascadelake) ++cflags-$(CONFIG_MATOM) += $(call cc-option,-march=bonnell,$(call cc-option,-march=core2,-march=i686)) \ ++ $(call cc-option,-mtune=bonnell,$(call cc-option,-mtune=generic)) + + # AMD Elan support + cflags-$(CONFIG_MELAN) += -march=i486
