From 7b229b13d78d112e2c5d4a60a3c6f602289959fa Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sat, 10 Apr 2021 19:56:05 -0700 Subject: HID: hid-input: add mapping for emoji picker key HUTRR101 added a new usage code for a key that is supposed to invoke and dismiss an emoji picker widget to assist users to locate and enter emojis. This patch adds a new key definition KEY_EMOJI_PICKER and maps 0x0c/0x0d9 usage code to this new keycode. Additionally hid-debug is adjusted to recognize this new usage code as well. Signed-off-by: Dmitry Torokhov Signed-off-by: Jiri Kosina --- include/uapi/linux/input-event-codes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index ee93428ced9a..225ec87d4f22 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -611,6 +611,7 @@ #define KEY_VOICECOMMAND 0x246 /* Listening Voice Command */ #define KEY_ASSISTANT 0x247 /* AL Context-aware desktop assistant */ #define KEY_KBD_LAYOUT_NEXT 0x248 /* AC Next Keyboard Layout Select */ +#define KEY_EMOJI_PICKER 0x249 /* Show/hide emoji picker (HUTRR101) */ #define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ #define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ -- cgit v1.3-18-gd494 From 63c8af5687f6b1b70e9458cac1ffb25e86db1695 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 10 May 2021 08:48:06 +0900 Subject: block: uapi: fix comment about block device ioctl Fix the comment mentioning ioctl command range used for zoned block devices to reflect the range of commands actually implemented. Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20210509234806.3000-1-damien.lemoal@wdc.com Signed-off-by: Jens Axboe --- include/uapi/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index f44eb0a04afd..4c32e97dcdf0 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -185,7 +185,7 @@ struct fsxattr { #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) /* - * A jump here: 130-131 are reserved for zoned block devices + * A jump here: 130-136 are reserved for zoned block devices * (see uapi/linux/blkzoned.h) */ -- cgit v1.3-18-gd494 From 7ac592aa35a684ff1858fb9ec282886b9e3575ac Mon Sep 17 00:00:00 2001 From: Chris Hyser Date: Wed, 24 Mar 2021 17:40:15 -0400 Subject: sched: prctl() core-scheduling interface This patch provides support for setting and copying core scheduling 'task cookies' between threads (PID), processes (TGID), and process groups (PGID). The value of core scheduling isn't that tasks don't share a core, 'nosmt' can do that. The value lies in exploiting all the sharing opportunities that exist to recover possible lost performance and that requires a degree of flexibility in the API. From a security perspective (and there are others), the thread, process and process group distinction is an existent hierarchal categorization of tasks that reflects many of the security concerns about 'data sharing'. For example, protecting against cache-snooping by a thread that can just read the memory directly isn't all that useful. With this in mind, subcommands to CREATE/SHARE (TO/FROM) provide a mechanism to create and share cookies. CREATE/SHARE_TO specify a target pid with enum pidtype used to specify the scope of the targeted tasks. For example, PIDTYPE_TGID will share the cookie with the process and all of it's threads as typically desired in a security scenario. API: prctl(PR_SCHED_CORE, PR_SCHED_CORE_GET, tgtpid, pidtype, &cookie) prctl(PR_SCHED_CORE, PR_SCHED_CORE_CREATE, tgtpid, pidtype, NULL) prctl(PR_SCHED_CORE, PR_SCHED_CORE_SHARE_TO, tgtpid, pidtype, NULL) prctl(PR_SCHED_CORE, PR_SCHED_CORE_SHARE_FROM, srcpid, pidtype, NULL) where 'tgtpid/srcpid == 0' implies the current process and pidtype is kernel enum pid_type {PIDTYPE_PID, PIDTYPE_TGID, PIDTYPE_PGID, ...}. For return values, EINVAL, ENOMEM are what they say. ESRCH means the tgtpid/srcpid was not found. EPERM indicates lack of PTRACE permission access to tgtpid/srcpid. ENODEV indicates your machines lacks SMT. [peterz: complete rewrite] Signed-off-by: Chris Hyser Signed-off-by: Peter Zijlstra (Intel) Tested-by: Don Hiatt Tested-by: Hongyu Ning Tested-by: Vincent Guittot Link: https://lkml.kernel.org/r/20210422123309.039845339@infradead.org --- include/linux/sched.h | 2 + include/uapi/linux/prctl.h | 8 +++ kernel/sched/core_sched.c | 114 +++++++++++++++++++++++++++++++++++++++ kernel/sys.c | 5 ++ tools/include/uapi/linux/prctl.h | 8 +++ 5 files changed, 137 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index fba47e52e482..c7e7d50e2fdc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2182,6 +2182,8 @@ const struct cpumask *sched_trace_rd_span(struct root_domain *rd); #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); +extern int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, + unsigned long uaddr); #else static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 18a9f59dc067..967d9c55323d 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -259,4 +259,12 @@ struct prctl_mm_map { #define PR_PAC_SET_ENABLED_KEYS 60 #define PR_PAC_GET_ENABLED_KEYS 61 +/* Request the scheduler to share a core */ +#define PR_SCHED_CORE 62 +# define PR_SCHED_CORE_GET 0 +# define PR_SCHED_CORE_CREATE 1 /* create unique core_sched cookie */ +# define PR_SCHED_CORE_SHARE_TO 2 /* push core_sched cookie to pid */ +# define PR_SCHED_CORE_SHARE_FROM 3 /* pull core_sched cookie to pid */ +# define PR_SCHED_CORE_MAX 4 + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index dcbbeaefaaa3..9a80e9a474c0 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include #include "sched.h" /* @@ -113,3 +114,116 @@ void sched_core_free(struct task_struct *p) { sched_core_put_cookie(p->core_cookie); } + +static void __sched_core_set(struct task_struct *p, unsigned long cookie) +{ + cookie = sched_core_get_cookie(cookie); + cookie = sched_core_update_cookie(p, cookie); + sched_core_put_cookie(cookie); +} + +/* Called from prctl interface: PR_SCHED_CORE */ +int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, + unsigned long uaddr) +{ + unsigned long cookie = 0, id = 0; + struct task_struct *task, *p; + struct pid *grp; + int err = 0; + + if (!static_branch_likely(&sched_smt_present)) + return -ENODEV; + + if (type > PIDTYPE_PGID || cmd >= PR_SCHED_CORE_MAX || pid < 0 || + (cmd != PR_SCHED_CORE_GET && uaddr)) + return -EINVAL; + + rcu_read_lock(); + if (pid == 0) { + task = current; + } else { + task = find_task_by_vpid(pid); + if (!task) { + rcu_read_unlock(); + return -ESRCH; + } + } + get_task_struct(task); + rcu_read_unlock(); + + /* + * Check if this process has the right to modify the specified + * process. Use the regular "ptrace_may_access()" checks. + */ + if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { + err = -EPERM; + goto out; + } + + switch (cmd) { + case PR_SCHED_CORE_GET: + if (type != PIDTYPE_PID || uaddr & 7) { + err = -EINVAL; + goto out; + } + cookie = sched_core_clone_cookie(task); + if (cookie) { + /* XXX improve ? */ + ptr_to_hashval((void *)cookie, &id); + } + err = put_user(id, (u64 __user *)uaddr); + goto out; + + case PR_SCHED_CORE_CREATE: + cookie = sched_core_alloc_cookie(); + if (!cookie) { + err = -ENOMEM; + goto out; + } + break; + + case PR_SCHED_CORE_SHARE_TO: + cookie = sched_core_clone_cookie(current); + break; + + case PR_SCHED_CORE_SHARE_FROM: + if (type != PIDTYPE_PID) { + err = -EINVAL; + goto out; + } + cookie = sched_core_clone_cookie(task); + __sched_core_set(current, cookie); + goto out; + + default: + err = -EINVAL; + goto out; + }; + + if (type == PIDTYPE_PID) { + __sched_core_set(task, cookie); + goto out; + } + + read_lock(&tasklist_lock); + grp = task_pid_type(task, type); + + do_each_pid_thread(grp, type, p) { + if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) { + err = -EPERM; + goto out_tasklist; + } + } while_each_pid_thread(grp, type, p); + + do_each_pid_thread(grp, type, p) { + __sched_core_set(p, cookie); + } while_each_pid_thread(grp, type, p); +out_tasklist: + read_unlock(&tasklist_lock); + +out: + sched_core_put_cookie(cookie); + put_task_struct(task); + return err; +} + diff --git a/kernel/sys.c b/kernel/sys.c index 3a583a29815f..9de46a4bf492 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2550,6 +2550,11 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = set_syscall_user_dispatch(arg2, arg3, arg4, (char __user *) arg5); break; +#ifdef CONFIG_SCHED_CORE + case PR_SCHED_CORE: + error = sched_core_share_pid(arg2, arg3, arg4, arg5); + break; +#endif default: error = -EINVAL; break; diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 18a9f59dc067..967d9c55323d 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -259,4 +259,12 @@ struct prctl_mm_map { #define PR_PAC_SET_ENABLED_KEYS 60 #define PR_PAC_GET_ENABLED_KEYS 61 +/* Request the scheduler to share a core */ +#define PR_SCHED_CORE 62 +# define PR_SCHED_CORE_GET 0 +# define PR_SCHED_CORE_CREATE 1 /* create unique core_sched cookie */ +# define PR_SCHED_CORE_SHARE_TO 2 /* push core_sched cookie to pid */ +# define PR_SCHED_CORE_SHARE_FROM 3 /* pull core_sched cookie to pid */ +# define PR_SCHED_CORE_MAX 4 + #endif /* _LINUX_PRCTL_H */ -- cgit v1.3-18-gd494 From 0683b53197b55343a166f1507086823030809a19 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 2 May 2021 17:28:31 -0500 Subject: signal: Deliver all of the siginfo perf data in _perf Don't abuse si_errno and deliver all of the perf data in _perf member of siginfo_t. Note: The data field in the perf data structures in a u64 to allow a pointer to be encoded without needed to implement a 32bit and 64bit version of the same structure. There already exists a 32bit and 64bit versions siginfo_t, and the 32bit version can not include a 64bit member as it only has 32bit alignment. So unsigned long is used in siginfo_t instead of a u64 as unsigned long can encode a pointer on all architectures linux supports. v1: https://lkml.kernel.org/r/m11rarqqx2.fsf_-_@fess.ebiederm.org v2: https://lkml.kernel.org/r/20210503203814.25487-10-ebiederm@xmission.com v3: https://lkml.kernel.org/r/20210505141101.11519-11-ebiederm@xmission.com Link: https://lkml.kernel.org/r/20210517195748.8880-4-ebiederm@xmission.com Reviewed-by: Marco Elver Signed-off-by: "Eric W. Biederman" --- arch/m68k/kernel/signal.c | 3 ++- arch/x86/kernel/signal_compat.c | 6 ++++-- fs/signalfd.c | 3 ++- include/linux/compat.h | 5 ++++- include/uapi/asm-generic/siginfo.h | 8 ++++++-- include/uapi/linux/perf_event.h | 2 +- include/uapi/linux/signalfd.h | 4 ++-- kernel/signal.c | 21 +++++++++++++-------- .../testing/selftests/perf_events/sigtrap_threads.c | 14 +++++++------- 9 files changed, 41 insertions(+), 25 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index a4b7ee1df211..8f215e79e70e 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -623,7 +623,8 @@ static inline void siginfo_build_tests(void) BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x12); /* _sigfault._perf */ - BUILD_BUG_ON(offsetof(siginfo_t, si_perf) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x14); /* _sigpoll */ BUILD_BUG_ON(offsetof(siginfo_t, si_band) != 0x0c); diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index a9fcabd8a5e5..06743ec054d2 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -141,8 +141,10 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20); BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14); - BUILD_BUG_ON(offsetof(siginfo_t, si_perf) != 0x18); - BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x18); + BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x20); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_data) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_type) != 0x14); CHECK_CSI_OFFSET(_sigpoll); CHECK_CSI_SIZE (_sigpoll, 2*sizeof(int)); diff --git a/fs/signalfd.c b/fs/signalfd.c index e87e59581653..373df2f12415 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -134,7 +134,8 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, break; case SIL_PERF_EVENT: new.ssi_addr = (long) kinfo->si_addr; - new.ssi_perf = kinfo->si_perf; + new.ssi_perf_type = kinfo->si_perf_type; + new.ssi_perf_data = kinfo->si_perf_data; break; case SIL_CHLD: new.ssi_pid = kinfo->si_pid; diff --git a/include/linux/compat.h b/include/linux/compat.h index 6af7bef15e94..a27fffaae121 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -236,7 +236,10 @@ typedef struct compat_siginfo { u32 _pkey; } _addr_pkey; /* used when si_code=TRAP_PERF */ - compat_ulong_t _perf; + struct { + compat_ulong_t _data; + u32 _type; + } _perf; }; } _sigfault; diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index e663bf117b46..5a3c221f4c9d 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -91,7 +91,10 @@ union __sifields { __u32 _pkey; } _addr_pkey; /* used when si_code=TRAP_PERF */ - unsigned long _perf; + struct { + unsigned long _data; + __u32 _type; + } _perf; }; } _sigfault; @@ -154,7 +157,8 @@ typedef struct siginfo { #define si_lower _sifields._sigfault._addr_bnd._lower #define si_upper _sifields._sigfault._addr_bnd._upper #define si_pkey _sifields._sigfault._addr_pkey._pkey -#define si_perf _sifields._sigfault._perf +#define si_perf_data _sifields._sigfault._perf._data +#define si_perf_type _sifields._sigfault._perf._type #define si_band _sifields._sigpoll._band #define si_fd _sifields._sigpoll._fd #define si_call_addr _sifields._sigsys._call_addr diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index e54e639248c8..7b14753b3d38 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -464,7 +464,7 @@ struct perf_event_attr { /* * User provided data if sigtrap=1, passed back to user via - * siginfo_t::si_perf, e.g. to permit user to identify the event. + * siginfo_t::si_perf_data, e.g. to permit user to identify the event. */ __u64 sig_data; }; diff --git a/include/uapi/linux/signalfd.h b/include/uapi/linux/signalfd.h index 7e333042c7e3..e78dddf433fc 100644 --- a/include/uapi/linux/signalfd.h +++ b/include/uapi/linux/signalfd.h @@ -39,8 +39,8 @@ struct signalfd_siginfo { __s32 ssi_syscall; __u64 ssi_call_addr; __u32 ssi_arch; - __u32 __pad3; - __u64 ssi_perf; + __u32 ssi_perf_type; + __u64 ssi_perf_data; /* * Pad strcture to 128 bytes. Remember to update the diff --git a/kernel/signal.c b/kernel/signal.c index 3a18d13c39b2..dca53515ae3f 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1768,11 +1768,13 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data) struct kernel_siginfo info; clear_siginfo(&info); - info.si_signo = SIGTRAP; - info.si_errno = type; - info.si_code = TRAP_PERF; - info.si_addr = addr; - info.si_perf = sig_data; + info.si_signo = SIGTRAP; + info.si_errno = 0; + info.si_code = TRAP_PERF; + info.si_addr = addr; + info.si_perf_data = sig_data; + info.si_perf_type = type; + return force_sig_info(&info); } @@ -3356,7 +3358,8 @@ void copy_siginfo_to_external32(struct compat_siginfo *to, break; case SIL_PERF_EVENT: to->si_addr = ptr_to_compat(from->si_addr); - to->si_perf = from->si_perf; + to->si_perf_data = from->si_perf_data; + to->si_perf_type = from->si_perf_type; break; case SIL_CHLD: to->si_pid = from->si_pid; @@ -3432,7 +3435,8 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to, break; case SIL_PERF_EVENT: to->si_addr = compat_ptr(from->si_addr); - to->si_perf = from->si_perf; + to->si_perf_data = from->si_perf_data; + to->si_perf_type = from->si_perf_type; break; case SIL_CHLD: to->si_pid = from->si_pid; @@ -4615,7 +4619,8 @@ static inline void siginfo_buildtime_checks(void) CHECK_OFFSET(si_lower); CHECK_OFFSET(si_upper); CHECK_OFFSET(si_pkey); - CHECK_OFFSET(si_perf); + CHECK_OFFSET(si_perf_data); + CHECK_OFFSET(si_perf_type); /* sigpoll */ CHECK_OFFSET(si_band); diff --git a/tools/testing/selftests/perf_events/sigtrap_threads.c b/tools/testing/selftests/perf_events/sigtrap_threads.c index 78ddf5e11625..8e83cf91513a 100644 --- a/tools/testing/selftests/perf_events/sigtrap_threads.c +++ b/tools/testing/selftests/perf_events/sigtrap_threads.c @@ -43,7 +43,7 @@ static struct { siginfo_t first_siginfo; /* First observed siginfo_t. */ } ctx; -/* Unique value to check si_perf is correctly set from perf_event_attr::sig_data. */ +/* Unique value to check si_perf_data is correctly set from perf_event_attr::sig_data. */ #define TEST_SIG_DATA(addr) (~(unsigned long)(addr)) static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr) @@ -164,8 +164,8 @@ TEST_F(sigtrap_threads, enable_event) EXPECT_EQ(ctx.signal_count, NUM_THREADS); EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); - EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); /* Check enabled for parent. */ ctx.iterate_on = 0; @@ -183,8 +183,8 @@ TEST_F(sigtrap_threads, modify_and_enable_event) EXPECT_EQ(ctx.signal_count, NUM_THREADS); EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); - EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); /* Check enabled for parent. */ ctx.iterate_on = 0; @@ -203,8 +203,8 @@ TEST_F(sigtrap_threads, signal_stress) EXPECT_EQ(ctx.signal_count, NUM_THREADS * ctx.iterate_on); EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); - EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); } TEST_HARNESS_MAIN -- cgit v1.3-18-gd494 From 922e3013046b79b444c87eda5baf43afae1326a8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 3 May 2021 12:52:43 -0500 Subject: signalfd: Remove SIL_PERF_EVENT fields from signalfd_siginfo With the addition of ssi_perf_data and ssi_perf_type struct signalfd_siginfo is dangerously close to running out of space. All that remains is just enough space for two additional 64bit fields. A practice of adding all possible siginfo_t fields into struct singalfd_siginfo can not be supported as adding the missing fields ssi_lower, ssi_upper, and ssi_pkey would require two 64bit fields and one 32bit fields. In practice the fields ssi_perf_data and ssi_perf_type can never be used by signalfd as the signal that generates them always delivers them synchronously to the thread that triggers them. Therefore until someone actually needs the fields ssi_perf_data and ssi_perf_type in signalfd_siginfo remove them. This leaves a bit more room for future expansion. v1: https://lkml.kernel.org/r/20210503203814.25487-12-ebiederm@xmission.com v2: https://lkml.kernel.org/r/20210505141101.11519-12-ebiederm@xmission.com Link: https://lkml.kernel.org/r/20210517195748.8880-5-ebiederm@xmission.com Reviewed-by: Marco Elver Signed-off-by: "Eric W. Biederman" --- fs/signalfd.c | 16 ++++++---------- include/uapi/linux/signalfd.h | 4 +--- 2 files changed, 7 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/signalfd.c b/fs/signalfd.c index 373df2f12415..167b5889db4b 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -114,12 +114,13 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, break; case SIL_FAULT_BNDERR: case SIL_FAULT_PKUERR: + case SIL_PERF_EVENT: /* - * Fall through to the SIL_FAULT case. Both SIL_FAULT_BNDERR - * and SIL_FAULT_PKUERR are only generated by faults that - * deliver them synchronously to userspace. In case someone - * injects one of these signals and signalfd catches it treat - * it as SIL_FAULT. + * Fall through to the SIL_FAULT case. SIL_FAULT_BNDERR, + * SIL_FAULT_PKUERR, and SIL_PERF_EVENT are only + * generated by faults that deliver them synchronously to + * userspace. In case someone injects one of these signals + * and signalfd catches it treat it as SIL_FAULT. */ case SIL_FAULT: new.ssi_addr = (long) kinfo->si_addr; @@ -132,11 +133,6 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, new.ssi_addr = (long) kinfo->si_addr; new.ssi_addr_lsb = (short) kinfo->si_addr_lsb; break; - case SIL_PERF_EVENT: - new.ssi_addr = (long) kinfo->si_addr; - new.ssi_perf_type = kinfo->si_perf_type; - new.ssi_perf_data = kinfo->si_perf_data; - break; case SIL_CHLD: new.ssi_pid = kinfo->si_pid; new.ssi_uid = kinfo->si_uid; diff --git a/include/uapi/linux/signalfd.h b/include/uapi/linux/signalfd.h index e78dddf433fc..83429a05b698 100644 --- a/include/uapi/linux/signalfd.h +++ b/include/uapi/linux/signalfd.h @@ -39,8 +39,6 @@ struct signalfd_siginfo { __s32 ssi_syscall; __u64 ssi_call_addr; __u32 ssi_arch; - __u32 ssi_perf_type; - __u64 ssi_perf_data; /* * Pad strcture to 128 bytes. Remember to update the @@ -51,7 +49,7 @@ struct signalfd_siginfo { * comes out of a read(2) and we really don't want to have * a compat on read(2). */ - __u8 __pad[16]; + __u8 __pad[28]; }; -- cgit v1.3-18-gd494 From 12ccb76280f8c0c07794fa68f83286b934981ca5 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Tue, 13 Apr 2021 11:40:17 +0200 Subject: media: lirc: remove out of date comment This file has been updated many times since 2010. Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/lirc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/lirc.h b/include/uapi/linux/lirc.h index c45a4eaea667..9919f2062b14 100644 --- a/include/uapi/linux/lirc.h +++ b/include/uapi/linux/lirc.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * lirc.h - linux infrared remote control header file - * last modified 2010/07/13 by Jarod Wilson */ #ifndef _LINUX_LIRC_H -- cgit v1.3-18-gd494 From 2f0968827a48a3b01a0cc9185abd41978d5ce918 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Thu, 29 Apr 2021 16:48:16 +0200 Subject: media: uapi: Move the MPEG-2 stateless control type out of staging Move the MPEG-2 stateless control types out of staging, and re-number it to avoid any confusion. Signed-off-by: Ezequiel Garcia Tested-by: Jernej Skrabec Reviewed-by: Jernej Skrabec Tested-by: Daniel Almeida Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/mpeg2-ctrls.h | 4 ---- include/uapi/linux/videodev2.h | 4 ++++ 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/media/mpeg2-ctrls.h b/include/media/mpeg2-ctrls.h index a84ce088a42e..a3d19de9e53a 100644 --- a/include/media/mpeg2-ctrls.h +++ b/include/media/mpeg2-ctrls.h @@ -16,10 +16,6 @@ #define V4L2_CID_MPEG_VIDEO_MPEG2_PICTURE (V4L2_CID_CODEC_BASE+253) /* enum v4l2_ctrl_type type values */ -#define V4L2_CTRL_TYPE_MPEG2_QUANTISATION 0x0131 -#define V4L2_CTRL_TYPE_MPEG2_SEQUENCE 0x0132 -#define V4L2_CTRL_TYPE_MPEG2_PICTURE 0x0133 - #define V4L2_MPEG2_SEQ_FLAG_PROGRESSIVE 0x01 /** diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 311a01cc5775..d3bb18a3a51b 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1807,6 +1807,10 @@ enum v4l2_ctrl_type { V4L2_CTRL_TYPE_FWHT_PARAMS = 0x0220, V4L2_CTRL_TYPE_VP8_FRAME = 0x0240, + + V4L2_CTRL_TYPE_MPEG2_QUANTISATION = 0x0250, + V4L2_CTRL_TYPE_MPEG2_SEQUENCE = 0x0251, + V4L2_CTRL_TYPE_MPEG2_PICTURE = 0x0252, }; /* Used in the VIDIOC_QUERYCTRL ioctl for querying controls */ -- cgit v1.3-18-gd494 From f4815b399111d992c1118c708f464a847dfd29e2 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Thu, 29 Apr 2021 16:48:18 +0200 Subject: media: uapi: move MPEG-2 stateless controls out of staging Until now, the MPEG-2 V4L2 API was not exported as a public API, and only defined in a private media header (media/mpeg2-ctrls.h). After reviewing the MPEG-2 specification in detail, and reworking the controls so they match the MPEG-2 semantics properly, we can consider it ready. Signed-off-by: Ezequiel Garcia Tested-by: Jernej Skrabec Reviewed-by: Jernej Skrabec Tested-by: Daniel Almeida Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../media/v4l/ext-ctrls-codec-stateless.rst | 214 ++++++++++++++++++++ .../userspace-api/media/v4l/ext-ctrls-codec.rst | 216 --------------------- .../userspace-api/media/v4l/pixfmt-compressed.rst | 10 +- .../userspace-api/media/v4l/vidioc-g-ext-ctrls.rst | 12 ++ drivers/media/v4l2-core/v4l2-ctrls.c | 12 +- drivers/staging/media/hantro/hantro_drv.c | 6 +- drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c | 6 +- .../staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c | 6 +- drivers/staging/media/sunxi/cedrus/cedrus.c | 6 +- drivers/staging/media/sunxi/cedrus/cedrus_dec.c | 6 +- include/media/mpeg2-ctrls.h | 126 ------------ include/media/v4l2-ctrls.h | 1 - include/uapi/linux/v4l2-controls.h | 112 +++++++++++ include/uapi/linux/videodev2.h | 3 + 14 files changed, 367 insertions(+), 369 deletions(-) delete mode 100644 include/media/mpeg2-ctrls.h (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst index 3fc04daa9ffb..2aa508ffb6b9 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec-stateless.rst @@ -1244,3 +1244,217 @@ FWHT Flags * - __u8 - ``padding[3]`` - Applications and drivers must set this to zero. + +.. _v4l2-codec-stateless-mpeg2: + +``V4L2_CID_STATELESS_MPEG2_SEQUENCE (struct)`` + Specifies the sequence parameters (as extracted from the bitstream) for the + associated MPEG-2 slice data. This includes fields matching the syntax + elements from the sequence header and sequence extension parts of the + bitstream as specified by :ref:`mpeg2part2`. + +.. c:type:: v4l2_ctrl_mpeg2_sequence + +.. raw:: latex + + \small + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.4cm}|p{6.5cm}|p{9.4cm}| + +.. flat-table:: struct v4l2_ctrl_mpeg2_sequence + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u16 + - ``horizontal_size`` + - The width of the displayable part of the frame's luminance component. + * - __u16 + - ``vertical_size`` + - The height of the displayable part of the frame's luminance component. + * - __u32 + - ``vbv_buffer_size`` + - Used to calculate the required size of the video buffering verifier, + defined (in bits) as: 16 * 1024 * vbv_buffer_size. + * - __u16 + - ``profile_and_level_indication`` + - The current profile and level indication as extracted from the + bitstream. + * - __u8 + - ``chroma_format`` + - The chrominance sub-sampling format (1: 4:2:0, 2: 4:2:2, 3: 4:4:4). + * - __u8 + - ``flags`` + - See :ref:`MPEG-2 Sequence Flags `. + +.. _mpeg2_sequence_flags: + +``MPEG-2 Sequence Flags`` + +.. cssclass:: longtable + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_MPEG2_SEQ_FLAG_PROGRESSIVE`` + - 0x01 + - Indication that all the frames for the sequence are progressive instead + of interlaced. + +.. raw:: latex + + \normalsize + +``V4L2_CID_STATELESS_MPEG2_PICTURE (struct)`` + Specifies the picture parameters (as extracted from the bitstream) for the + associated MPEG-2 slice data. This includes fields matching the syntax + elements from the picture header and picture coding extension parts of the + bitstream as specified by :ref:`mpeg2part2`. + +.. c:type:: v4l2_ctrl_mpeg2_picture + +.. raw:: latex + + \small + +.. cssclass:: longtable + +.. tabularcolumns:: |p{1.0cm}|p{5.6cm}|p{10.7cm}| + +.. flat-table:: struct v4l2_ctrl_mpeg2_picture + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u64 + - ``backward_ref_ts`` + - Timestamp of the V4L2 capture buffer to use as backward reference, used + with B-coded and P-coded frames. The timestamp refers to the + ``timestamp`` field in struct :c:type:`v4l2_buffer`. Use the + :c:func:`v4l2_timeval_to_ns()` function to convert the struct + :c:type:`timeval` in struct :c:type:`v4l2_buffer` to a __u64. + * - __u64 + - ``forward_ref_ts`` + - Timestamp for the V4L2 capture buffer to use as forward reference, used + with B-coded frames. The timestamp refers to the ``timestamp`` field in + struct :c:type:`v4l2_buffer`. Use the :c:func:`v4l2_timeval_to_ns()` + function to convert the struct :c:type:`timeval` in struct + :c:type:`v4l2_buffer` to a __u64. + * - __u32 + - ``flags`` + - See :ref:`MPEG-2 Picture Flags `. + * - __u8 + - ``f_code[2][2]`` + - Motion vector codes. + * - __u8 + - ``picture_coding_type`` + - Picture coding type for the frame covered by the current slice + (V4L2_MPEG2_PICTURE_CODING_TYPE_I, V4L2_MPEG2_PICTURE_CODING_TYPE_P or + V4L2_MPEG2_PICTURE_CODING_TYPE_B). + * - __u8 + - ``picture_structure`` + - Picture structure (1: interlaced top field, 2: interlaced bottom field, + 3: progressive frame). + * - __u8 + - ``intra_dc_precision`` + - Precision of Discrete Cosine transform (0: 8 bits precision, + 1: 9 bits precision, 2: 10 bits precision, 3: 11 bits precision). + * - __u8 + - ``reserved[5]`` + - Applications and drivers must set this to zero. + +.. _mpeg2_picture_flags: + +``MPEG-2 Picture Flags`` + +.. cssclass:: longtable + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - ``V4L2_MPEG2_PIC_FLAG_TOP_FIELD_FIRST`` + - 0x00000001 + - If set and it's an interlaced stream, top field is output first. + * - ``V4L2_MPEG2_PIC_FLAG_FRAME_PRED_DCT`` + - 0x00000002 + - If set only frame-DCT and frame prediction are used. + * - ``V4L2_MPEG2_PIC_FLAG_CONCEALMENT_MV`` + - 0x00000004 + - If set motion vectors are coded for intra macroblocks. + * - ``V4L2_MPEG2_PIC_FLAG_Q_SCALE_TYPE`` + - 0x00000008 + - This flag affects the inverse quantization process. + * - ``V4L2_MPEG2_PIC_FLAG_INTRA_VLC`` + - 0x00000010 + - This flag affects the decoding of transform coefficient data. + * - ``V4L2_MPEG2_PIC_FLAG_ALT_SCAN`` + - 0x00000020 + - This flag affects the decoding of transform coefficient data. + * - ``V4L2_MPEG2_PIC_FLAG_REPEAT_FIRST`` + - 0x00000040 + - This flag affects the decoding process of progressive frames. + * - ``V4L2_MPEG2_PIC_FLAG_PROGRESSIVE`` + - 0x00000080 + - Indicates whether the current frame is progressive. + +.. raw:: latex + + \normalsize + +``V4L2_CID_STATELESS_MPEG2_QUANTISATION (struct)`` + Specifies quantisation matrices, in zigzag scanning order, for the + associated MPEG-2 slice data. This control is initialized by the kernel + to the matrices default values. If a bitstream transmits a user-defined + quantisation matrices load, applications are expected to use this control. + Applications are also expected to set the control loading the default + values, if the quantisation matrices need to be reset, for instance on a + sequence header. This process is specified by section 6.3.7. + "Quant matrix extension" of the specification. + +.. c:type:: v4l2_ctrl_mpeg2_quantisation + +.. tabularcolumns:: |p{0.8cm}|p{8.0cm}|p{8.5cm}| + +.. cssclass:: longtable + +.. raw:: latex + + \small + +.. flat-table:: struct v4l2_ctrl_mpeg2_quantisation + :header-rows: 0 + :stub-columns: 0 + :widths: 1 1 2 + + * - __u8 + - ``intra_quantiser_matrix[64]`` + - The quantisation matrix coefficients for intra-coded frames, in zigzag + scanning order. It is relevant for both luma and chroma components, + although it can be superseded by the chroma-specific matrix for + non-4:2:0 YUV formats. + * - __u8 + - ``non_intra_quantiser_matrix[64]`` + - The quantisation matrix coefficients for non-intra-coded frames, in + zigzag scanning order. It is relevant for both luma and chroma + components, although it can be superseded by the chroma-specific matrix + for non-4:2:0 YUV formats. + * - __u8 + - ``chroma_intra_quantiser_matrix[64]`` + - The quantisation matrix coefficients for the chominance component of + intra-coded frames, in zigzag scanning order. Only relevant for + non-4:2:0 YUV formats. + * - __u8 + - ``chroma_non_intra_quantiser_matrix[64]`` + - The quantisation matrix coefficients for the chrominance component of + non-intra-coded frames, in zigzag scanning order. Only relevant for + non-4:2:0 YUV formats. + +.. raw:: latex + + \normalsize diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst index f10b04fba229..0b8061666c57 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst @@ -1606,222 +1606,6 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type - ``V4L2_CID_MPEG_VIDEO_H264_HIER_CODING_L6_BR (integer)`` Indicates bit rate (bps) for hierarchical coding layer 6 for H264 encoder. -.. _v4l2-mpeg-mpeg2: - -``V4L2_CID_MPEG_VIDEO_MPEG2_SEQUENCE (struct)`` - Specifies the sequence parameters (as extracted from the bitstream) for the - associated MPEG-2 slice data. This includes fields matching the syntax - elements from the sequence header and sequence extension parts of the - bitstream as specified by :ref:`mpeg2part2`. - - .. note:: - - This compound control is not yet part of the public kernel API and - it is expected to change. - -.. c:type:: v4l2_ctrl_mpeg2_sequence - -.. cssclass:: longtable - -.. tabularcolumns:: |p{1.4cm}|p{6.5cm}|p{9.4cm}| - -.. flat-table:: struct v4l2_ctrl_mpeg2_sequence - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - __u16 - - ``horizontal_size`` - - The width of the displayable part of the frame's luminance component. - * - __u16 - - ``vertical_size`` - - The height of the displayable part of the frame's luminance component. - * - __u32 - - ``vbv_buffer_size`` - - Used to calculate the required size of the video buffering verifier, - defined (in bits) as: 16 * 1024 * vbv_buffer_size. - * - __u16 - - ``profile_and_level_indication`` - - The current profile and level indication as extracted from the - bitstream. - * - __u8 - - ``chroma_format`` - - The chrominance sub-sampling format (1: 4:2:0, 2: 4:2:2, 3: 4:4:4). - * - __u8 - - ``flags`` - - See :ref:`MPEG-2 Sequence Flags `. - -.. _mpeg2_sequence_flags: - -``MPEG-2 Sequence Flags`` - -.. cssclass:: longtable - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - ``V4L2_MPEG2_SEQ_FLAG_PROGRESSIVE`` - - 0x01 - - Indication that all the frames for the sequence are progressive instead - of interlaced. - -``V4L2_CID_MPEG_VIDEO_MPEG2_PICTURE (struct)`` - Specifies the picture parameters (as extracted from the bitstream) for the - associated MPEG-2 slice data. This includes fields matching the syntax - elements from the picture header and picture coding extension parts of the - bitstream as specified by :ref:`mpeg2part2`. - - .. note:: - - This compound control is not yet part of the public kernel API and - it is expected to change. - -.. c:type:: v4l2_ctrl_mpeg2_picture - -.. raw:: latex - - \small - -.. cssclass:: longtable - -.. tabularcolumns:: |p{1.0cm}|p{5.6cm}|p{10.7cm}| - -.. flat-table:: struct v4l2_ctrl_mpeg2_picture - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - __u64 - - ``backward_ref_ts`` - - Timestamp of the V4L2 capture buffer to use as backward reference, used - with B-coded and P-coded frames. The timestamp refers to the - ``timestamp`` field in struct :c:type:`v4l2_buffer`. Use the - :c:func:`v4l2_timeval_to_ns()` function to convert the struct - :c:type:`timeval` in struct :c:type:`v4l2_buffer` to a __u64. - * - __u64 - - ``forward_ref_ts`` - - Timestamp for the V4L2 capture buffer to use as forward reference, used - with B-coded frames. The timestamp refers to the ``timestamp`` field in - struct :c:type:`v4l2_buffer`. Use the :c:func:`v4l2_timeval_to_ns()` - function to convert the struct :c:type:`timeval` in struct - :c:type:`v4l2_buffer` to a __u64. - * - __u32 - - ``flags`` - - See :ref:`MPEG-2 Picture Flags `. - * - __u8 - - ``f_code[2][2]`` - - Motion vector codes. - * - __u8 - - ``picture_coding_type`` - - Picture coding type for the frame covered by the current slice - (V4L2_MPEG2_PICTURE_CODING_TYPE_I, V4L2_MPEG2_PICTURE_CODING_TYPE_P or - V4L2_MPEG2_PICTURE_CODING_TYPE_B). - * - __u8 - - ``picture_structure`` - - Picture structure (1: interlaced top field, 2: interlaced bottom field, - 3: progressive frame). - * - __u8 - - ``intra_dc_precision`` - - Precision of Discrete Cosine transform (0: 8 bits precision, - 1: 9 bits precision, 2: 10 bits precision, 3: 11 bits precision). - * - __u8 - - ``reserved[5]`` - - Applications and drivers must set this to zero. - - -.. _mpeg2_picture_flags: - -``MPEG-2 Picture Flags`` - -.. cssclass:: longtable - -.. flat-table:: - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - ``V4L2_MPEG2_PIC_FLAG_TOP_FIELD_FIRST`` - - 0x00000001 - - If set and it's an interlaced stream, top field is output first. - * - ``V4L2_MPEG2_PIC_FLAG_FRAME_PRED_DCT`` - - 0x00000002 - - If set only frame-DCT and frame prediction are used. - * - ``V4L2_MPEG2_PIC_FLAG_CONCEALMENT_MV`` - - 0x00000004 - - If set motion vectors are coded for intra macroblocks. - * - ``V4L2_MPEG2_PIC_FLAG_Q_SCALE_TYPE`` - - 0x00000008 - - This flag affects the inverse quantization process. - * - ``V4L2_MPEG2_PIC_FLAG_INTRA_VLC`` - - 0x00000010 - - This flag affects the decoding of transform coefficient data. - * - ``V4L2_MPEG2_PIC_FLAG_ALT_SCAN`` - - 0x00000020 - - This flag affects the decoding of transform coefficient data. - * - ``V4L2_MPEG2_PIC_FLAG_REPEAT_FIRST`` - - 0x00000040 - - This flag affects the decoding process of progressive frames. - * - ``V4L2_MPEG2_PIC_FLAG_PROGRESSIVE`` - - 0x00000080 - - Indicates whether the current frame is progressive. - -.. raw:: latex - - \normalsize - -``V4L2_CID_MPEG_VIDEO_MPEG2_QUANTISATION (struct)`` - Specifies quantisation matrices (as extracted from the bitstream) for the - associated MPEG-2 slice data. - - .. note:: - - This compound control is not yet part of the public kernel API and - it is expected to change. - -.. c:type:: v4l2_ctrl_mpeg2_quantisation - -.. tabularcolumns:: |p{0.8cm}|p{8.0cm}|p{8.5cm}| - -.. cssclass:: longtable - -.. raw:: latex - - \small - -.. flat-table:: struct v4l2_ctrl_mpeg2_quantisation - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - * - __u8 - - ``intra_quantiser_matrix[64]`` - - The quantisation matrix coefficients for intra-coded frames, in zigzag - scanning order. It is relevant for both luma and chroma components, - although it can be superseded by the chroma-specific matrix for - non-4:2:0 YUV formats. - * - __u8 - - ``non_intra_quantiser_matrix[64]`` - - The quantisation matrix coefficients for non-intra-coded frames, in - zigzag scanning order. It is relevant for both luma and chroma - components, although it can be superseded by the chroma-specific matrix - for non-4:2:0 YUV formats. - * - __u8 - - ``chroma_intra_quantiser_matrix[64]`` - - The quantisation matrix coefficients for the chominance component of - intra-coded frames, in zigzag scanning order. Only relevant for - non-4:2:0 YUV formats. - * - __u8 - - ``chroma_non_intra_quantiser_matrix[64]`` - - The quantisation matrix coefficients for the chrominance component of - non-intra-coded frames, in zigzag scanning order. Only relevant for - non-4:2:0 YUV formats. - -.. raw:: latex - - \normalsize - ``V4L2_CID_FWHT_I_FRAME_QP (integer)`` Quantization parameter for an I frame for FWHT. Valid range: from 1 to 31. diff --git a/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst b/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst index 6c10a062adac..0ede39907ee2 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-compressed.rst @@ -112,13 +112,13 @@ Compressed Formats - 'MG2S' - MPEG-2 parsed slice data, as extracted from the MPEG-2 bitstream. This format is adapted for stateless video decoders that implement a - MPEG-2 pipeline (using the :ref:`mem2mem` and :ref:`media-request-api`). + MPEG-2 pipeline with the :ref:`stateless_decoder`. Metadata associated with the frame to decode is required to be passed - through the ``V4L2_CID_MPEG_VIDEO_MPEG2_SEQUENCE`` and - ``V4L2_CID_MPEG_VIDEO_MPEG2_PICTURE`` controls. + through the ``V4L2_CID_STATELESS_MPEG2_SEQUENCE`` and + ``V4L2_CID_STATELESS_MPEG2_PICTURE`` controls. Quantisation matrices can optionally be specified through the - ``V4L2_CID_MPEG_VIDEO_MPEG2_QUANTISATION`` control. - See the :ref:`associated Codec Control IDs `. + ``V4L2_CID_STATELESS_MPEG2_QUANTISATION`` control. + See the :ref:`associated Codec Control IDs `. Exactly one output and one capture buffer must be provided for use with this pixel format. The output buffer must contain the appropriate number of macroblocks to decode a full corresponding frame to the matching diff --git a/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst b/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst index 3ba22983d21f..2d6bc8d94380 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst @@ -221,6 +221,18 @@ still cause this situation. - ``p_vp8_frame`` - A pointer to a struct :c:type:`v4l2_ctrl_vp8_frame`. Valid if this control is of type ``V4L2_CTRL_TYPE_VP8_FRAME``. + * - struct :c:type:`v4l2_ctrl_mpeg2_sequence` * + - ``p_mpeg2_sequence`` + - A pointer to a struct :c:type:`v4l2_ctrl_mpeg2_sequence`. Valid if this control is + of type ``V4L2_CTRL_TYPE_MPEG2_SEQUENCE``. + * - struct :c:type:`v4l2_ctrl_mpeg2_picture` * + - ``p_mpeg2_picture`` + - A pointer to a struct :c:type:`v4l2_ctrl_mpeg2_picture`. Valid if this control is + of type ``V4L2_CTRL_TYPE_MPEG2_PICTURE``. + * - struct :c:type:`v4l2_ctrl_mpeg2_quantisation` * + - ``p_mpeg2_quantisation`` + - A pointer to a struct :c:type:`v4l2_ctrl_mpeg2_quantisation`. Valid if this control is + of type ``V4L2_CTRL_TYPE_MPEG2_QUANTISATION``. * - struct :c:type:`v4l2_ctrl_hdr10_cll_info` * - ``p_hdr10_cll`` - A pointer to a struct :c:type:`v4l2_ctrl_hdr10_cll_info`. Valid if this control is diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index a693ff8dc3dc..d4e2c7318ee6 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -977,9 +977,6 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_MPEG_VIDEO_LTR_COUNT: return "LTR Count"; case V4L2_CID_MPEG_VIDEO_FRAME_LTR_INDEX: return "Frame LTR Index"; case V4L2_CID_MPEG_VIDEO_USE_LTR_FRAMES: return "Use LTR Frames"; - case V4L2_CID_MPEG_VIDEO_MPEG2_SEQUENCE: return "MPEG-2 Sequence Header"; - case V4L2_CID_MPEG_VIDEO_MPEG2_PICTURE: return "MPEG-2 Picture Header"; - case V4L2_CID_MPEG_VIDEO_MPEG2_QUANTISATION: return "MPEG-2 Quantisation Matrices"; case V4L2_CID_FWHT_I_FRAME_QP: return "FWHT I-Frame QP Value"; case V4L2_CID_FWHT_P_FRAME_QP: return "FWHT P-Frame QP Value"; @@ -1228,6 +1225,9 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_STATELESS_H264_DECODE_PARAMS: return "H264 Decode Parameters"; case V4L2_CID_STATELESS_FWHT_PARAMS: return "FWHT Stateless Parameters"; case V4L2_CID_STATELESS_VP8_FRAME: return "VP8 Frame Parameters"; + case V4L2_CID_STATELESS_MPEG2_SEQUENCE: return "MPEG-2 Sequence Header"; + case V4L2_CID_STATELESS_MPEG2_PICTURE: return "MPEG-2 Picture Header"; + case V4L2_CID_STATELESS_MPEG2_QUANTISATION: return "MPEG-2 Quantisation Matrices"; /* Colorimetry controls */ /* Keep the order of the 'case's the same as in v4l2-controls.h! */ @@ -1500,13 +1500,13 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, case V4L2_CID_RDS_TX_ALT_FREQS: *type = V4L2_CTRL_TYPE_U32; break; - case V4L2_CID_MPEG_VIDEO_MPEG2_SEQUENCE: + case V4L2_CID_STATELESS_MPEG2_SEQUENCE: *type = V4L2_CTRL_TYPE_MPEG2_SEQUENCE; break; - case V4L2_CID_MPEG_VIDEO_MPEG2_PICTURE: + case V4L2_CID_STATELESS_MPEG2_PICTURE: *type = V4L2_CTRL_TYPE_MPEG2_PICTURE; break; - case V4L2_CID_MPEG_VIDEO_MPEG2_QUANTISATION: + case V4L2_CID_STATELESS_MPEG2_QUANTISATION: *type = V4L2_CTRL_TYPE_MPEG2_QUANTISATION; break; case V4L2_CID_STATELESS_FWHT_PARAMS: diff --git a/drivers/staging/media/hantro/hantro_drv.c b/drivers/staging/media/hantro/hantro_drv.c index dc9478ac7141..2f6b01c7a6a0 100644 --- a/drivers/staging/media/hantro/hantro_drv.c +++ b/drivers/staging/media/hantro/hantro_drv.c @@ -298,17 +298,17 @@ static const struct hantro_ctrl controls[] = { }, { .codec = HANTRO_MPEG2_DECODER, .cfg = { - .id = V4L2_CID_MPEG_VIDEO_MPEG2_SEQUENCE, + .id = V4L2_CID_STATELESS_MPEG2_SEQUENCE, }, }, { .codec = HANTRO_MPEG2_DECODER, .cfg = { - .id = V4L2_CID_MPEG_VIDEO_MPEG2_PICTURE, + .id = V4L2_CID_STATELESS_MPEG2_PICTURE, }, }, { .codec = HANTRO_MPEG2_DECODER, .cfg = { - .id = V4L2_CID_MPEG_VIDEO_MPEG2_QUANTISATION, + .id = V4L2_CID_STATELESS_MPEG2_QUANTISATION, }, }, { .codec = HANTRO_VP8_DECODER, diff --git a/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c b/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c index 25d912cbe2ff..6ee1a19d189b 100644 --- a/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c +++ b/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c @@ -83,7 +83,7 @@ hantro_g1_mpeg2_dec_set_quantisation(struct hantro_dev *vpu, { struct v4l2_ctrl_mpeg2_quantisation *q; - q = hantro_get_ctrl(ctx, V4L2_CID_MPEG_VIDEO_MPEG2_QUANTISATION); + q = hantro_get_ctrl(ctx, V4L2_CID_STATELESS_MPEG2_QUANTISATION); hantro_mpeg2_dec_copy_qtable(ctx->mpeg2_dec.qtable.cpu, q); vdpu_write_relaxed(vpu, ctx->mpeg2_dec.qtable.dma, G1_REG_QTABLE_BASE); } @@ -160,9 +160,9 @@ void hantro_g1_mpeg2_dec_run(struct hantro_ctx *ctx) hantro_start_prepare_run(ctx); seq = hantro_get_ctrl(ctx, - V4L2_CID_MPEG_VIDEO_MPEG2_SEQUENCE); + V4L2_CID_STATELESS_MPEG2_SEQUENCE); pic = hantro_get_ctrl(ctx, - V4L2_CID_MPEG_VIDEO_MPEG2_PICTURE); + V4L2_CID_STATELESS_MPEG2_PICTURE); reg = G1_REG_DEC_AXI_RD_ID(0) | G1_REG_DEC_TIMEOUT_E(1) | diff --git a/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c b/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c index d16d76760278..2527dce7eb18 100644 --- a/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c +++ b/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c @@ -85,7 +85,7 @@ rk3399_vpu_mpeg2_dec_set_quantisation(struct hantro_dev *vpu, { struct v4l2_ctrl_mpeg2_quantisation *q; - q = hantro_get_ctrl(ctx, V4L2_CID_MPEG_VIDEO_MPEG2_QUANTISATION); + q = hantro_get_ctrl(ctx, V4L2_CID_STATELESS_MPEG2_QUANTISATION); hantro_mpeg2_dec_copy_qtable(ctx->mpeg2_dec.qtable.cpu, q); vdpu_write_relaxed(vpu, ctx->mpeg2_dec.qtable.dma, VDPU_REG_QTABLE_BASE); } @@ -162,9 +162,9 @@ void rk3399_vpu_mpeg2_dec_run(struct hantro_ctx *ctx) hantro_start_prepare_run(ctx); seq = hantro_get_ctrl(ctx, - V4L2_CID_MPEG_VIDEO_MPEG2_SEQUENCE); + V4L2_CID_STATELESS_MPEG2_SEQUENCE); pic = hantro_get_ctrl(ctx, - V4L2_CID_MPEG_VIDEO_MPEG2_PICTURE); + V4L2_CID_STATELESS_MPEG2_PICTURE); reg = VDPU_REG_DEC_ADV_PRE_DIS(0) | VDPU_REG_DEC_SCMD_DIS(0) | diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.c b/drivers/staging/media/sunxi/cedrus/cedrus.c index 4430c8fa2cc7..fa348c09f844 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus.c @@ -31,19 +31,19 @@ static const struct cedrus_control cedrus_controls[] = { { .cfg = { - .id = V4L2_CID_MPEG_VIDEO_MPEG2_SEQUENCE, + .id = V4L2_CID_STATELESS_MPEG2_SEQUENCE, }, .codec = CEDRUS_CODEC_MPEG2, }, { .cfg = { - .id = V4L2_CID_MPEG_VIDEO_MPEG2_PICTURE, + .id = V4L2_CID_STATELESS_MPEG2_PICTURE, }, .codec = CEDRUS_CODEC_MPEG2, }, { .cfg = { - .id = V4L2_CID_MPEG_VIDEO_MPEG2_QUANTISATION, + .id = V4L2_CID_STATELESS_MPEG2_QUANTISATION, }, .codec = CEDRUS_CODEC_MPEG2, }, diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c index e98185c1f5a7..97e410d92506 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c @@ -41,11 +41,11 @@ void cedrus_device_run(void *priv) switch (ctx->src_fmt.pixelformat) { case V4L2_PIX_FMT_MPEG2_SLICE: run.mpeg2.sequence = cedrus_find_control_data(ctx, - V4L2_CID_MPEG_VIDEO_MPEG2_SEQUENCE); + V4L2_CID_STATELESS_MPEG2_SEQUENCE); run.mpeg2.picture = cedrus_find_control_data(ctx, - V4L2_CID_MPEG_VIDEO_MPEG2_PICTURE); + V4L2_CID_STATELESS_MPEG2_PICTURE); run.mpeg2.quantisation = cedrus_find_control_data(ctx, - V4L2_CID_MPEG_VIDEO_MPEG2_QUANTISATION); + V4L2_CID_STATELESS_MPEG2_QUANTISATION); break; case V4L2_PIX_FMT_H264_SLICE: diff --git a/include/media/mpeg2-ctrls.h b/include/media/mpeg2-ctrls.h deleted file mode 100644 index a3d19de9e53a..000000000000 --- a/include/media/mpeg2-ctrls.h +++ /dev/null @@ -1,126 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * These are the MPEG2 state controls for use with stateless MPEG-2 - * codec drivers. - * - * It turns out that these structs are not stable yet and will undergo - * more changes. So keep them private until they are stable and ready to - * become part of the official public API. - */ - -#ifndef _MPEG2_CTRLS_H_ -#define _MPEG2_CTRLS_H_ - -#define V4L2_CID_MPEG_VIDEO_MPEG2_QUANTISATION (V4L2_CID_CODEC_BASE+251) -#define V4L2_CID_MPEG_VIDEO_MPEG2_SEQUENCE (V4L2_CID_CODEC_BASE+252) -#define V4L2_CID_MPEG_VIDEO_MPEG2_PICTURE (V4L2_CID_CODEC_BASE+253) - -/* enum v4l2_ctrl_type type values */ -#define V4L2_MPEG2_SEQ_FLAG_PROGRESSIVE 0x01 - -/** - * struct v4l2_ctrl_mpeg2_sequence - MPEG-2 sequence header - * - * All the members on this structure match the sequence header and sequence - * extension syntaxes as specified by the MPEG-2 specification. - * - * Fields horizontal_size, vertical_size and vbv_buffer_size are a - * combination of respective _value and extension syntax elements, - * as described in section 6.3.3 "Sequence header". - * - * @horizontal_size: combination of elements horizontal_size_value and - * horizontal_size_extension. - * @vertical_size: combination of elements vertical_size_value and - * vertical_size_extension. - * @vbv_buffer_size: combination of elements vbv_buffer_size_value and - * vbv_buffer_size_extension. - * @profile_and_level_indication: see MPEG-2 specification. - * @chroma_format: see MPEG-2 specification. - * @flags: see V4L2_MPEG2_SEQ_FLAG_{}. - */ -struct v4l2_ctrl_mpeg2_sequence { - __u16 horizontal_size; - __u16 vertical_size; - __u32 vbv_buffer_size; - __u16 profile_and_level_indication; - __u8 chroma_format; - __u8 flags; -}; - -#define V4L2_MPEG2_PIC_CODING_TYPE_I 1 -#define V4L2_MPEG2_PIC_CODING_TYPE_P 2 -#define V4L2_MPEG2_PIC_CODING_TYPE_B 3 -#define V4L2_MPEG2_PIC_CODING_TYPE_D 4 - -#define V4L2_MPEG2_PIC_TOP_FIELD 0x1 -#define V4L2_MPEG2_PIC_BOTTOM_FIELD 0x2 -#define V4L2_MPEG2_PIC_FRAME 0x3 - -#define V4L2_MPEG2_PIC_FLAG_TOP_FIELD_FIRST 0x0001 -#define V4L2_MPEG2_PIC_FLAG_FRAME_PRED_DCT 0x0002 -#define V4L2_MPEG2_PIC_FLAG_CONCEALMENT_MV 0x0004 -#define V4L2_MPEG2_PIC_FLAG_Q_SCALE_TYPE 0x0008 -#define V4L2_MPEG2_PIC_FLAG_INTRA_VLC 0x0010 -#define V4L2_MPEG2_PIC_FLAG_ALT_SCAN 0x0020 -#define V4L2_MPEG2_PIC_FLAG_REPEAT_FIRST 0x0040 -#define V4L2_MPEG2_PIC_FLAG_PROGRESSIVE 0x0080 - -/** - * struct v4l2_ctrl_mpeg2_picture - MPEG-2 picture header - * - * All the members on this structure match the picture header and picture - * coding extension syntaxes as specified by the MPEG-2 specification. - * - * @backward_ref_ts: timestamp of the V4L2 capture buffer to use as - * reference for backward prediction. - * @forward_ref_ts: timestamp of the V4L2 capture buffer to use as - * reference for forward prediction. These timestamp refers to the - * timestamp field in struct v4l2_buffer. Use v4l2_timeval_to_ns() - * to convert the struct timeval to a __u64. - * @flags: see V4L2_MPEG2_PIC_FLAG_{}. - * @f_code[2][2]: see MPEG-2 specification. - * @picture_coding_type: see MPEG-2 specification. - * @picture_structure: see V4L2_MPEG2_PIC_{}_FIELD. - * @intra_dc_precision: see MPEG-2 specification. - * @reserved: padding field. Should be zeroed by applications. - */ -struct v4l2_ctrl_mpeg2_picture { - __u64 backward_ref_ts; - __u64 forward_ref_ts; - __u32 flags; - __u8 f_code[2][2]; - __u8 picture_coding_type; - __u8 picture_structure; - __u8 intra_dc_precision; - __u8 reserved[5]; -}; - -/** - * struct v4l2_ctrl_mpeg2_quantisation - MPEG-2 quantisation - * - * Quantization matrices as specified by section 6.3.7 - * "Quant matrix extension". - * - * @intra_quantiser_matrix: The quantisation matrix coefficients - * for intra-coded frames, in zigzag scanning order. It is relevant - * for both luma and chroma components, although it can be superseded - * by the chroma-specific matrix for non-4:2:0 YUV formats. - * @non_intra_quantiser_matrix: The quantisation matrix coefficients - * for non-intra-coded frames, in zigzag scanning order. It is relevant - * for both luma and chroma components, although it can be superseded - * by the chroma-specific matrix for non-4:2:0 YUV formats. - * @chroma_intra_quantiser_matrix: The quantisation matrix coefficients - * for the chominance component of intra-coded frames, in zigzag scanning - * order. Only relevant for 4:2:2 and 4:4:4 YUV formats. - * @chroma_non_intra_quantiser_matrix: The quantisation matrix coefficients - * for the chrominance component of non-intra-coded frames, in zigzag scanning - * order. Only relevant for 4:2:2 and 4:4:4 YUV formats. - */ -struct v4l2_ctrl_mpeg2_quantisation { - __u8 intra_quantiser_matrix[64]; - __u8 non_intra_quantiser_matrix[64]; - __u8 chroma_intra_quantiser_matrix[64]; - __u8 chroma_non_intra_quantiser_matrix[64]; -}; - -#endif diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index 215e44172c66..575b59fbac77 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -17,7 +17,6 @@ * Include the stateless codec compound control definitions. * This will move to the public headers once this API is fully stable. */ -#include #include /* forward references */ diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index d43bec5f1afd..f96bea19c991 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -1862,6 +1862,118 @@ struct v4l2_ctrl_vp8_frame { __u64 flags; }; +/* Stateless MPEG-2 controls */ + +#define V4L2_MPEG2_SEQ_FLAG_PROGRESSIVE 0x01 + +#define V4L2_CID_STATELESS_MPEG2_SEQUENCE (V4L2_CID_CODEC_STATELESS_BASE+220) +/** + * struct v4l2_ctrl_mpeg2_sequence - MPEG-2 sequence header + * + * All the members on this structure match the sequence header and sequence + * extension syntaxes as specified by the MPEG-2 specification. + * + * Fields horizontal_size, vertical_size and vbv_buffer_size are a + * combination of respective _value and extension syntax elements, + * as described in section 6.3.3 "Sequence header". + * + * @horizontal_size: combination of elements horizontal_size_value and + * horizontal_size_extension. + * @vertical_size: combination of elements vertical_size_value and + * vertical_size_extension. + * @vbv_buffer_size: combination of elements vbv_buffer_size_value and + * vbv_buffer_size_extension. + * @profile_and_level_indication: see MPEG-2 specification. + * @chroma_format: see MPEG-2 specification. + * @flags: see V4L2_MPEG2_SEQ_FLAG_{}. + */ +struct v4l2_ctrl_mpeg2_sequence { + __u16 horizontal_size; + __u16 vertical_size; + __u32 vbv_buffer_size; + __u16 profile_and_level_indication; + __u8 chroma_format; + __u8 flags; +}; + +#define V4L2_MPEG2_PIC_CODING_TYPE_I 1 +#define V4L2_MPEG2_PIC_CODING_TYPE_P 2 +#define V4L2_MPEG2_PIC_CODING_TYPE_B 3 +#define V4L2_MPEG2_PIC_CODING_TYPE_D 4 + +#define V4L2_MPEG2_PIC_TOP_FIELD 0x1 +#define V4L2_MPEG2_PIC_BOTTOM_FIELD 0x2 +#define V4L2_MPEG2_PIC_FRAME 0x3 + +#define V4L2_MPEG2_PIC_FLAG_TOP_FIELD_FIRST 0x0001 +#define V4L2_MPEG2_PIC_FLAG_FRAME_PRED_DCT 0x0002 +#define V4L2_MPEG2_PIC_FLAG_CONCEALMENT_MV 0x0004 +#define V4L2_MPEG2_PIC_FLAG_Q_SCALE_TYPE 0x0008 +#define V4L2_MPEG2_PIC_FLAG_INTRA_VLC 0x0010 +#define V4L2_MPEG2_PIC_FLAG_ALT_SCAN 0x0020 +#define V4L2_MPEG2_PIC_FLAG_REPEAT_FIRST 0x0040 +#define V4L2_MPEG2_PIC_FLAG_PROGRESSIVE 0x0080 + +#define V4L2_CID_STATELESS_MPEG2_PICTURE (V4L2_CID_CODEC_STATELESS_BASE+221) +/** + * struct v4l2_ctrl_mpeg2_picture - MPEG-2 picture header + * + * All the members on this structure match the picture header and picture + * coding extension syntaxes as specified by the MPEG-2 specification. + * + * @backward_ref_ts: timestamp of the V4L2 capture buffer to use as + * reference for backward prediction. + * @forward_ref_ts: timestamp of the V4L2 capture buffer to use as + * reference for forward prediction. These timestamp refers to the + * timestamp field in struct v4l2_buffer. Use v4l2_timeval_to_ns() + * to convert the struct timeval to a __u64. + * @flags: see V4L2_MPEG2_PIC_FLAG_{}. + * @f_code: see MPEG-2 specification. + * @picture_coding_type: see MPEG-2 specification. + * @picture_structure: see V4L2_MPEG2_PIC_{}_FIELD. + * @intra_dc_precision: see MPEG-2 specification. + * @reserved: padding field. Should be zeroed by applications. + */ +struct v4l2_ctrl_mpeg2_picture { + __u64 backward_ref_ts; + __u64 forward_ref_ts; + __u32 flags; + __u8 f_code[2][2]; + __u8 picture_coding_type; + __u8 picture_structure; + __u8 intra_dc_precision; + __u8 reserved[5]; +}; + +#define V4L2_CID_STATELESS_MPEG2_QUANTISATION (V4L2_CID_CODEC_STATELESS_BASE+222) +/** + * struct v4l2_ctrl_mpeg2_quantisation - MPEG-2 quantisation + * + * Quantisation matrices as specified by section 6.3.7 + * "Quant matrix extension". + * + * @intra_quantiser_matrix: The quantisation matrix coefficients + * for intra-coded frames, in zigzag scanning order. It is relevant + * for both luma and chroma components, although it can be superseded + * by the chroma-specific matrix for non-4:2:0 YUV formats. + * @non_intra_quantiser_matrix: The quantisation matrix coefficients + * for non-intra-coded frames, in zigzag scanning order. It is relevant + * for both luma and chroma components, although it can be superseded + * by the chroma-specific matrix for non-4:2:0 YUV formats. + * @chroma_intra_quantiser_matrix: The quantisation matrix coefficients + * for the chominance component of intra-coded frames, in zigzag scanning + * order. Only relevant for 4:2:2 and 4:4:4 YUV formats. + * @chroma_non_intra_quantiser_matrix: The quantisation matrix coefficients + * for the chrominance component of non-intra-coded frames, in zigzag scanning + * order. Only relevant for 4:2:2 and 4:4:4 YUV formats. + */ +struct v4l2_ctrl_mpeg2_quantisation { + __u8 intra_quantiser_matrix[64]; + __u8 non_intra_quantiser_matrix[64]; + __u8 chroma_intra_quantiser_matrix[64]; + __u8 chroma_non_intra_quantiser_matrix[64]; +}; + #define V4L2_CID_COLORIMETRY_CLASS_BASE (V4L2_CTRL_CLASS_COLORIMETRY | 0x900) #define V4L2_CID_COLORIMETRY_CLASS (V4L2_CTRL_CLASS_COLORIMETRY | 1) diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index d3bb18a3a51b..9260791b8438 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1747,6 +1747,9 @@ struct v4l2_ext_control { struct v4l2_ctrl_h264_decode_params __user *p_h264_decode_params; struct v4l2_ctrl_fwht_params __user *p_fwht_params; struct v4l2_ctrl_vp8_frame __user *p_vp8_frame; + struct v4l2_ctrl_mpeg2_sequence __user *p_mpeg2_sequence; + struct v4l2_ctrl_mpeg2_picture __user *p_mpeg2_picture; + struct v4l2_ctrl_mpeg2_quantisation __user *p_mpeg2_quantisation; void __user *ptr; }; } __attribute__ ((packed)); -- cgit v1.3-18-gd494 From fb1070d18edb37daf3979662975bc54625a19953 Mon Sep 17 00:00:00 2001 From: Joe Richey Date: Fri, 21 May 2021 01:58:43 -0700 Subject: KVM: X86: Use _BITUL() macro in UAPI headers Replace BIT() in KVM's UPAI header with _BITUL(). BIT() is not defined in the UAPI headers and its usage may cause userspace build errors. Fixes: fb04a1eddb1a ("KVM: X86: Implement ring-based dirty memory tracking") Signed-off-by: Joe Richey Message-Id: <20210521085849.37676-3-joerichey94@gmail.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 5 +++-- tools/include/uapi/linux/kvm.h | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 3fd9a7e9d90c..79d9c44d1ad7 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -8,6 +8,7 @@ * Note: you must update KVM_API_VERSION if you change this interface. */ +#include #include #include #include @@ -1879,8 +1880,8 @@ struct kvm_hyperv_eventfd { * conversion after harvesting an entry. Also, it must not skip any * dirty bits, so that dirty bits are always harvested in sequence. */ -#define KVM_DIRTY_GFN_F_DIRTY BIT(0) -#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0) +#define KVM_DIRTY_GFN_F_RESET _BITUL(1) #define KVM_DIRTY_GFN_F_MASK 0x3 /* diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index f6afee209620..26e6d94d64ed 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -8,6 +8,7 @@ * Note: you must update KVM_API_VERSION if you change this interface. */ +#include #include #include #include @@ -1834,8 +1835,8 @@ struct kvm_hyperv_eventfd { * conversion after harvesting an entry. Also, it must not skip any * dirty bits, so that dirty bits are always harvested in sequence. */ -#define KVM_DIRTY_GFN_F_DIRTY BIT(0) -#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0) +#define KVM_DIRTY_GFN_F_RESET _BITUL(1) #define KVM_DIRTY_GFN_F_MASK 0x3 /* -- cgit v1.3-18-gd494 From d170ebb00472268410dce80ae4834c98e79315da Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 21 May 2021 10:45:44 +0200 Subject: media: uapi/linux/cec-funcs.h: set delay to 1 if unnused If the audio_out_delay value is unused, then set it to 1, not 0. The value 0 is reserved, and 1 is a much safer value since it translates to a delay of (1 - 1) * 2 = 0 ms. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/cec-funcs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h index 37590027b604..c3baaea0b8ef 100644 --- a/include/uapi/linux/cec-funcs.h +++ b/include/uapi/linux/cec-funcs.h @@ -1665,7 +1665,7 @@ static inline void cec_ops_report_current_latency(const struct cec_msg *msg, if (*audio_out_compensated == 3 && msg->len >= 7) *audio_out_delay = msg->msg[6]; else - *audio_out_delay = 0; + *audio_out_delay = 1; } static inline void cec_msg_request_current_latency(struct cec_msg *msg, -- cgit v1.3-18-gd494 From ce67eaca95f8ab5c6aae41a10adfe9a6e8efa58c Mon Sep 17 00:00:00 2001 From: Joe Richey Date: Fri, 21 May 2021 10:58:46 +0200 Subject: media: vicodec: Use _BITUL() macro in UAPI headers Replace BIT() in v4l2's UPAI header with _BITUL(). BIT() is not defined in the UAPI headers and its usage may cause userspace build errors. Fixes: 206bc0f6fb94 ("media: vicodec: mark the stateless FWHT API as stable") Signed-off-by: Joe Richey Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-controls.h | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index f96bea19c991..fdf97a6d7d18 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -50,6 +50,7 @@ #ifndef __LINUX_V4L2_CONTROLS_H #define __LINUX_V4L2_CONTROLS_H +#include #include /* Control classes */ @@ -1602,30 +1603,30 @@ struct v4l2_ctrl_h264_decode_params { #define V4L2_FWHT_VERSION 3 /* Set if this is an interlaced format */ -#define V4L2_FWHT_FL_IS_INTERLACED BIT(0) +#define V4L2_FWHT_FL_IS_INTERLACED _BITUL(0) /* Set if this is a bottom-first (NTSC) interlaced format */ -#define V4L2_FWHT_FL_IS_BOTTOM_FIRST BIT(1) +#define V4L2_FWHT_FL_IS_BOTTOM_FIRST _BITUL(1) /* Set if each 'frame' contains just one field */ -#define V4L2_FWHT_FL_IS_ALTERNATE BIT(2) +#define V4L2_FWHT_FL_IS_ALTERNATE _BITUL(2) /* * If V4L2_FWHT_FL_IS_ALTERNATE was set, then this is set if this * 'frame' is the bottom field, else it is the top field. */ -#define V4L2_FWHT_FL_IS_BOTTOM_FIELD BIT(3) +#define V4L2_FWHT_FL_IS_BOTTOM_FIELD _BITUL(3) /* Set if the Y' plane is uncompressed */ -#define V4L2_FWHT_FL_LUMA_IS_UNCOMPRESSED BIT(4) +#define V4L2_FWHT_FL_LUMA_IS_UNCOMPRESSED _BITUL(4) /* Set if the Cb plane is uncompressed */ -#define V4L2_FWHT_FL_CB_IS_UNCOMPRESSED BIT(5) +#define V4L2_FWHT_FL_CB_IS_UNCOMPRESSED _BITUL(5) /* Set if the Cr plane is uncompressed */ -#define V4L2_FWHT_FL_CR_IS_UNCOMPRESSED BIT(6) +#define V4L2_FWHT_FL_CR_IS_UNCOMPRESSED _BITUL(6) /* Set if the chroma plane is full height, if cleared it is half height */ -#define V4L2_FWHT_FL_CHROMA_FULL_HEIGHT BIT(7) +#define V4L2_FWHT_FL_CHROMA_FULL_HEIGHT _BITUL(7) /* Set if the chroma plane is full width, if cleared it is half width */ -#define V4L2_FWHT_FL_CHROMA_FULL_WIDTH BIT(8) +#define V4L2_FWHT_FL_CHROMA_FULL_WIDTH _BITUL(8) /* Set if the alpha plane is uncompressed */ -#define V4L2_FWHT_FL_ALPHA_IS_UNCOMPRESSED BIT(9) +#define V4L2_FWHT_FL_ALPHA_IS_UNCOMPRESSED _BITUL(9) /* Set if this is an I Frame */ -#define V4L2_FWHT_FL_I_FRAME BIT(10) +#define V4L2_FWHT_FL_I_FRAME _BITUL(10) /* A 4-values flag - the number of components - 1 */ #define V4L2_FWHT_FL_COMPONENTS_NUM_MSK GENMASK(18, 16) -- cgit v1.3-18-gd494 From a83d958504734f78f42b1e3392d93816297e790a Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Thu, 3 Jun 2021 21:20:26 +0200 Subject: Bluetooth: Fix VIRTIO_ID_BT assigned number It turned out that the VIRTIO_ID_* are not assigned in the virtio_ids.h file in the upstream kernel. Picking the next free one was wrong and there is a process that has been followed now. See https://github.com/oasis-tcs/virtio-spec/issues/108 for details. Fixes: afd2daa26c7a ("Bluetooth: Add support for virtio transport driver") Signed-off-by: Marcel Holtmann Signed-off-by: Luiz Augusto von Dentz --- include/uapi/linux/virtio_ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index f0c35ce8628c..4fe842c3a3a9 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -54,7 +54,7 @@ #define VIRTIO_ID_SOUND 25 /* virtio sound */ #define VIRTIO_ID_FS 26 /* virtio filesystem */ #define VIRTIO_ID_PMEM 27 /* virtio pmem */ -#define VIRTIO_ID_BT 28 /* virtio bluetooth */ #define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */ +#define VIRTIO_ID_BT 40 /* virtio bluetooth */ #endif /* _LINUX_VIRTIO_IDS_H */ -- cgit v1.3-18-gd494 From 819fbd3d8ef36c09576c2a0ffea503f5c46e9177 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 1 Jun 2021 11:31:30 +0200 Subject: media: dvb header files: move some headers to staging The audio, video and OSD APIs are used upstream only by the av7110 driver, which was moved to staging. So, move the corresponding header files to it. Signed-off-by: Mauro Carvalho Chehab --- drivers/staging/media/av7110/audio.h | 101 ++++++++++++++++ drivers/staging/media/av7110/av7110.h | 7 +- drivers/staging/media/av7110/osd.h | 181 ++++++++++++++++++++++++++++ drivers/staging/media/av7110/video.h | 220 ++++++++++++++++++++++++++++++++++ include/uapi/linux/dvb/audio.h | 101 ---------------- include/uapi/linux/dvb/osd.h | 181 ---------------------------- include/uapi/linux/dvb/video.h | 220 ---------------------------------- 7 files changed, 506 insertions(+), 505 deletions(-) create mode 100644 drivers/staging/media/av7110/audio.h create mode 100644 drivers/staging/media/av7110/osd.h create mode 100644 drivers/staging/media/av7110/video.h delete mode 100644 include/uapi/linux/dvb/audio.h delete mode 100644 include/uapi/linux/dvb/osd.h delete mode 100644 include/uapi/linux/dvb/video.h (limited to 'include/uapi/linux') diff --git a/drivers/staging/media/av7110/audio.h b/drivers/staging/media/av7110/audio.h new file mode 100644 index 000000000000..2f869da69171 --- /dev/null +++ b/drivers/staging/media/av7110/audio.h @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ +/* + * audio.h - DEPRECATED MPEG-TS audio decoder API + * + * NOTE: should not be used on future drivers + * + * Copyright (C) 2000 Ralph Metzler + * & Marcus Metzler + * for convergence integrated media GmbH + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Lesser Public License + * as published by the Free Software Foundation; either version 2.1 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ + +#ifndef _DVBAUDIO_H_ +#define _DVBAUDIO_H_ + +#include + +typedef enum { + AUDIO_SOURCE_DEMUX, /* Select the demux as the main source */ + AUDIO_SOURCE_MEMORY /* Select internal memory as the main source */ +} audio_stream_source_t; + + +typedef enum { + AUDIO_STOPPED, /* Device is stopped */ + AUDIO_PLAYING, /* Device is currently playing */ + AUDIO_PAUSED /* Device is paused */ +} audio_play_state_t; + + +typedef enum { + AUDIO_STEREO, + AUDIO_MONO_LEFT, + AUDIO_MONO_RIGHT, + AUDIO_MONO, + AUDIO_STEREO_SWAPPED +} audio_channel_select_t; + + +typedef struct audio_mixer { + unsigned int volume_left; + unsigned int volume_right; + /* what else do we need? bass, pass-through, ... */ +} audio_mixer_t; + + +typedef struct audio_status { + int AV_sync_state; /* sync audio and video? */ + int mute_state; /* audio is muted */ + audio_play_state_t play_state; /* current playback state */ + audio_stream_source_t stream_source; /* current stream source */ + audio_channel_select_t channel_select; /* currently selected channel */ + int bypass_mode; /* pass on audio data to */ + audio_mixer_t mixer_state; /* current mixer state */ +} audio_status_t; /* separate decoder hardware */ + + +/* for GET_CAPABILITIES and SET_FORMAT, the latter should only set one bit */ +#define AUDIO_CAP_DTS 1 +#define AUDIO_CAP_LPCM 2 +#define AUDIO_CAP_MP1 4 +#define AUDIO_CAP_MP2 8 +#define AUDIO_CAP_MP3 16 +#define AUDIO_CAP_AAC 32 +#define AUDIO_CAP_OGG 64 +#define AUDIO_CAP_SDDS 128 +#define AUDIO_CAP_AC3 256 + +#define AUDIO_STOP _IO('o', 1) +#define AUDIO_PLAY _IO('o', 2) +#define AUDIO_PAUSE _IO('o', 3) +#define AUDIO_CONTINUE _IO('o', 4) +#define AUDIO_SELECT_SOURCE _IO('o', 5) +#define AUDIO_SET_MUTE _IO('o', 6) +#define AUDIO_SET_AV_SYNC _IO('o', 7) +#define AUDIO_SET_BYPASS_MODE _IO('o', 8) +#define AUDIO_CHANNEL_SELECT _IO('o', 9) +#define AUDIO_GET_STATUS _IOR('o', 10, audio_status_t) + +#define AUDIO_GET_CAPABILITIES _IOR('o', 11, unsigned int) +#define AUDIO_CLEAR_BUFFER _IO('o', 12) +#define AUDIO_SET_ID _IO('o', 13) +#define AUDIO_SET_MIXER _IOW('o', 14, audio_mixer_t) +#define AUDIO_SET_STREAMTYPE _IO('o', 15) +#define AUDIO_BILINGUAL_CHANNEL_SELECT _IO('o', 20) + +#endif /* _DVBAUDIO_H_ */ diff --git a/drivers/staging/media/av7110/av7110.h b/drivers/staging/media/av7110/av7110.h index 809d938ae166..b8e8fc8ddbe9 100644 --- a/drivers/staging/media/av7110/av7110.h +++ b/drivers/staging/media/av7110/av7110.h @@ -9,11 +9,12 @@ #include #include -#include -#include +#include "video.h" +#include "audio.h" +#include "osd.h" + #include #include -#include #include #include diff --git a/drivers/staging/media/av7110/osd.h b/drivers/staging/media/av7110/osd.h new file mode 100644 index 000000000000..858997c74043 --- /dev/null +++ b/drivers/staging/media/av7110/osd.h @@ -0,0 +1,181 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ +/* + * osd.h - DEPRECATED On Screen Display API + * + * NOTE: should not be used on future drivers + * + * Copyright (C) 2001 Ralph Metzler + * & Marcus Metzler + * for convergence integrated media GmbH + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Lesser Public License + * as published by the Free Software Foundation; either version 2.1 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ + +#ifndef _DVBOSD_H_ +#define _DVBOSD_H_ + +#include + +typedef enum { + /* All functions return -2 on "not open" */ + OSD_Close = 1, /* () */ + /* + * Disables OSD and releases the buffers + * returns 0 on success + */ + OSD_Open, /* (x0,y0,x1,y1,BitPerPixel[2/4/8](color&0x0F),mix[0..15](color&0xF0)) */ + /* + * Opens OSD with this size and bit depth + * returns 0 on success, -1 on DRAM allocation error, -2 on "already open" + */ + OSD_Show, /* () */ + /* + * enables OSD mode + * returns 0 on success + */ + OSD_Hide, /* () */ + /* + * disables OSD mode + * returns 0 on success + */ + OSD_Clear, /* () */ + /* + * Sets all pixel to color 0 + * returns 0 on success + */ + OSD_Fill, /* (color) */ + /* + * Sets all pixel to color + * returns 0 on success + */ + OSD_SetColor, /* (color,R{x0},G{y0},B{x1},opacity{y1}) */ + /* + * set palette entry to , and apply + * R,G,B: 0..255 + * R=Red, G=Green, B=Blue + * opacity=0: pixel opacity 0% (only video pixel shows) + * opacity=1..254: pixel opacity as specified in header + * opacity=255: pixel opacity 100% (only OSD pixel shows) + * returns 0 on success, -1 on error + */ + OSD_SetPalette, /* (firstcolor{color},lastcolor{x0},data) */ + /* + * Set a number of entries in the palette + * sets the entries "firstcolor" through "lastcolor" from the array "data" + * data has 4 byte for each color: + * R,G,B, and a opacity value: 0->transparent, 1..254->mix, 255->pixel + */ + OSD_SetTrans, /* (transparency{color}) */ + /* + * Sets transparency of mixed pixel (0..15) + * returns 0 on success + */ + OSD_SetPixel, /* (x0,y0,color) */ + /* + * sets pixel , to color number + * returns 0 on success, -1 on error + */ + OSD_GetPixel, /* (x0,y0) */ + /* returns color number of pixel ,, or -1 */ + OSD_SetRow, /* (x0,y0,x1,data) */ + /* + * fills pixels x0,y through x1,y with the content of data[] + * returns 0 on success, -1 on clipping all pixel (no pixel drawn) + */ + OSD_SetBlock, /* (x0,y0,x1,y1,increment{color},data) */ + /* + * fills pixels x0,y0 through x1,y1 with the content of data[] + * inc contains the width of one line in the data block, + * inc<=0 uses blockwidth as linewidth + * returns 0 on success, -1 on clipping all pixel + */ + OSD_FillRow, /* (x0,y0,x1,color) */ + /* + * fills pixels x0,y through x1,y with the color + * returns 0 on success, -1 on clipping all pixel + */ + OSD_FillBlock, /* (x0,y0,x1,y1,color) */ + /* + * fills pixels x0,y0 through x1,y1 with the color + * returns 0 on success, -1 on clipping all pixel + */ + OSD_Line, /* (x0,y0,x1,y1,color) */ + /* + * draw a line from x0,y0 to x1,y1 with the color + * returns 0 on success + */ + OSD_Query, /* (x0,y0,x1,y1,xasp{color}}), yasp=11 */ + /* + * fills parameters with the picture dimensions and the pixel aspect ratio + * returns 0 on success + */ + OSD_Test, /* () */ + /* + * draws a test picture. for debugging purposes only + * returns 0 on success + * TODO: remove "test" in final version + */ + OSD_Text, /* (x0,y0,size,color,text) */ + OSD_SetWindow, /* (x0) set window with number 0 + * & Ralph Metzler + * for convergence integrated media GmbH + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public License + * as published by the Free Software Foundation; either version 2.1 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ + +#ifndef _UAPI_DVBVIDEO_H_ +#define _UAPI_DVBVIDEO_H_ + +#include +#ifndef __KERNEL__ +#include +#endif + +typedef enum { + VIDEO_FORMAT_4_3, /* Select 4:3 format */ + VIDEO_FORMAT_16_9, /* Select 16:9 format. */ + VIDEO_FORMAT_221_1 /* 2.21:1 */ +} video_format_t; + + +typedef enum { + VIDEO_PAN_SCAN, /* use pan and scan format */ + VIDEO_LETTER_BOX, /* use letterbox format */ + VIDEO_CENTER_CUT_OUT /* use center cut out format */ +} video_displayformat_t; + +typedef struct { + int w; + int h; + video_format_t aspect_ratio; +} video_size_t; + +typedef enum { + VIDEO_SOURCE_DEMUX, /* Select the demux as the main source */ + VIDEO_SOURCE_MEMORY /* If this source is selected, the stream + comes from the user through the write + system call */ +} video_stream_source_t; + + +typedef enum { + VIDEO_STOPPED, /* Video is stopped */ + VIDEO_PLAYING, /* Video is currently playing */ + VIDEO_FREEZED /* Video is freezed */ +} video_play_state_t; + + +/* Decoder commands */ +#define VIDEO_CMD_PLAY (0) +#define VIDEO_CMD_STOP (1) +#define VIDEO_CMD_FREEZE (2) +#define VIDEO_CMD_CONTINUE (3) + +/* Flags for VIDEO_CMD_FREEZE */ +#define VIDEO_CMD_FREEZE_TO_BLACK (1 << 0) + +/* Flags for VIDEO_CMD_STOP */ +#define VIDEO_CMD_STOP_TO_BLACK (1 << 0) +#define VIDEO_CMD_STOP_IMMEDIATELY (1 << 1) + +/* Play input formats: */ +/* The decoder has no special format requirements */ +#define VIDEO_PLAY_FMT_NONE (0) +/* The decoder requires full GOPs */ +#define VIDEO_PLAY_FMT_GOP (1) + +/* The structure must be zeroed before use by the application + This ensures it can be extended safely in the future. */ +struct video_command { + __u32 cmd; + __u32 flags; + union { + struct { + __u64 pts; + } stop; + + struct { + /* 0 or 1000 specifies normal speed, + 1 specifies forward single stepping, + -1 specifies backward single stepping, + >1: playback at speed/1000 of the normal speed, + <-1: reverse playback at (-speed/1000) of the normal speed. */ + __s32 speed; + __u32 format; + } play; + + struct { + __u32 data[16]; + } raw; + }; +}; + +/* FIELD_UNKNOWN can be used if the hardware does not know whether + the Vsync is for an odd, even or progressive (i.e. non-interlaced) + field. */ +#define VIDEO_VSYNC_FIELD_UNKNOWN (0) +#define VIDEO_VSYNC_FIELD_ODD (1) +#define VIDEO_VSYNC_FIELD_EVEN (2) +#define VIDEO_VSYNC_FIELD_PROGRESSIVE (3) + +struct video_event { + __s32 type; +#define VIDEO_EVENT_SIZE_CHANGED 1 +#define VIDEO_EVENT_FRAME_RATE_CHANGED 2 +#define VIDEO_EVENT_DECODER_STOPPED 3 +#define VIDEO_EVENT_VSYNC 4 + /* unused, make sure to use atomic time for y2038 if it ever gets used */ + long timestamp; + union { + video_size_t size; + unsigned int frame_rate; /* in frames per 1000sec */ + unsigned char vsync_field; /* unknown/odd/even/progressive */ + } u; +}; + + +struct video_status { + int video_blank; /* blank video on freeze? */ + video_play_state_t play_state; /* current state of playback */ + video_stream_source_t stream_source; /* current source (demux/memory) */ + video_format_t video_format; /* current aspect ratio of stream*/ + video_displayformat_t display_format;/* selected cropping mode */ +}; + + +struct video_still_picture { + char __user *iFrame; /* pointer to a single iframe in memory */ + __s32 size; +}; + + +typedef __u16 video_attributes_t; +/* bits: descr. */ +/* 15-14 Video compression mode (0=MPEG-1, 1=MPEG-2) */ +/* 13-12 TV system (0=525/60, 1=625/50) */ +/* 11-10 Aspect ratio (0=4:3, 3=16:9) */ +/* 9- 8 permitted display mode on 4:3 monitor (0=both, 1=only pan-sca */ +/* 7 line 21-1 data present in GOP (1=yes, 0=no) */ +/* 6 line 21-2 data present in GOP (1=yes, 0=no) */ +/* 5- 3 source resolution (0=720x480/576, 1=704x480/576, 2=352x480/57 */ +/* 2 source letterboxed (1=yes, 0=no) */ +/* 0 film/camera mode (0= + *camera, 1=film (625/50 only)) */ + + +/* bit definitions for capabilities: */ +/* can the hardware decode MPEG1 and/or MPEG2? */ +#define VIDEO_CAP_MPEG1 1 +#define VIDEO_CAP_MPEG2 2 +/* can you send a system and/or program stream to video device? + (you still have to open the video and the audio device but only + send the stream to the video device) */ +#define VIDEO_CAP_SYS 4 +#define VIDEO_CAP_PROG 8 +/* can the driver also handle SPU, NAVI and CSS encoded data? + (CSS API is not present yet) */ +#define VIDEO_CAP_SPU 16 +#define VIDEO_CAP_NAVI 32 +#define VIDEO_CAP_CSS 64 + + +#define VIDEO_STOP _IO('o', 21) +#define VIDEO_PLAY _IO('o', 22) +#define VIDEO_FREEZE _IO('o', 23) +#define VIDEO_CONTINUE _IO('o', 24) +#define VIDEO_SELECT_SOURCE _IO('o', 25) +#define VIDEO_SET_BLANK _IO('o', 26) +#define VIDEO_GET_STATUS _IOR('o', 27, struct video_status) +#define VIDEO_GET_EVENT _IOR('o', 28, struct video_event) +#define VIDEO_SET_DISPLAY_FORMAT _IO('o', 29) +#define VIDEO_STILLPICTURE _IOW('o', 30, struct video_still_picture) +#define VIDEO_FAST_FORWARD _IO('o', 31) +#define VIDEO_SLOWMOTION _IO('o', 32) +#define VIDEO_GET_CAPABILITIES _IOR('o', 33, unsigned int) +#define VIDEO_CLEAR_BUFFER _IO('o', 34) +#define VIDEO_SET_STREAMTYPE _IO('o', 36) +#define VIDEO_SET_FORMAT _IO('o', 37) +#define VIDEO_GET_SIZE _IOR('o', 55, video_size_t) + +/** + * VIDEO_GET_PTS + * + * Read the 33 bit presentation time stamp as defined + * in ITU T-REC-H.222.0 / ISO/IEC 13818-1. + * + * The PTS should belong to the currently played + * frame if possible, but may also be a value close to it + * like the PTS of the last decoded frame or the last PTS + * extracted by the PES parser. + */ +#define VIDEO_GET_PTS _IOR('o', 57, __u64) + +/* Read the number of displayed frames since the decoder was started */ +#define VIDEO_GET_FRAME_COUNT _IOR('o', 58, __u64) + +#define VIDEO_COMMAND _IOWR('o', 59, struct video_command) +#define VIDEO_TRY_COMMAND _IOWR('o', 60, struct video_command) + +#endif /* _UAPI_DVBVIDEO_H_ */ diff --git a/include/uapi/linux/dvb/audio.h b/include/uapi/linux/dvb/audio.h deleted file mode 100644 index 2f869da69171..000000000000 --- a/include/uapi/linux/dvb/audio.h +++ /dev/null @@ -1,101 +0,0 @@ -/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ -/* - * audio.h - DEPRECATED MPEG-TS audio decoder API - * - * NOTE: should not be used on future drivers - * - * Copyright (C) 2000 Ralph Metzler - * & Marcus Metzler - * for convergence integrated media GmbH - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Lesser Public License - * as published by the Free Software Foundation; either version 2.1 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - */ - -#ifndef _DVBAUDIO_H_ -#define _DVBAUDIO_H_ - -#include - -typedef enum { - AUDIO_SOURCE_DEMUX, /* Select the demux as the main source */ - AUDIO_SOURCE_MEMORY /* Select internal memory as the main source */ -} audio_stream_source_t; - - -typedef enum { - AUDIO_STOPPED, /* Device is stopped */ - AUDIO_PLAYING, /* Device is currently playing */ - AUDIO_PAUSED /* Device is paused */ -} audio_play_state_t; - - -typedef enum { - AUDIO_STEREO, - AUDIO_MONO_LEFT, - AUDIO_MONO_RIGHT, - AUDIO_MONO, - AUDIO_STEREO_SWAPPED -} audio_channel_select_t; - - -typedef struct audio_mixer { - unsigned int volume_left; - unsigned int volume_right; - /* what else do we need? bass, pass-through, ... */ -} audio_mixer_t; - - -typedef struct audio_status { - int AV_sync_state; /* sync audio and video? */ - int mute_state; /* audio is muted */ - audio_play_state_t play_state; /* current playback state */ - audio_stream_source_t stream_source; /* current stream source */ - audio_channel_select_t channel_select; /* currently selected channel */ - int bypass_mode; /* pass on audio data to */ - audio_mixer_t mixer_state; /* current mixer state */ -} audio_status_t; /* separate decoder hardware */ - - -/* for GET_CAPABILITIES and SET_FORMAT, the latter should only set one bit */ -#define AUDIO_CAP_DTS 1 -#define AUDIO_CAP_LPCM 2 -#define AUDIO_CAP_MP1 4 -#define AUDIO_CAP_MP2 8 -#define AUDIO_CAP_MP3 16 -#define AUDIO_CAP_AAC 32 -#define AUDIO_CAP_OGG 64 -#define AUDIO_CAP_SDDS 128 -#define AUDIO_CAP_AC3 256 - -#define AUDIO_STOP _IO('o', 1) -#define AUDIO_PLAY _IO('o', 2) -#define AUDIO_PAUSE _IO('o', 3) -#define AUDIO_CONTINUE _IO('o', 4) -#define AUDIO_SELECT_SOURCE _IO('o', 5) -#define AUDIO_SET_MUTE _IO('o', 6) -#define AUDIO_SET_AV_SYNC _IO('o', 7) -#define AUDIO_SET_BYPASS_MODE _IO('o', 8) -#define AUDIO_CHANNEL_SELECT _IO('o', 9) -#define AUDIO_GET_STATUS _IOR('o', 10, audio_status_t) - -#define AUDIO_GET_CAPABILITIES _IOR('o', 11, unsigned int) -#define AUDIO_CLEAR_BUFFER _IO('o', 12) -#define AUDIO_SET_ID _IO('o', 13) -#define AUDIO_SET_MIXER _IOW('o', 14, audio_mixer_t) -#define AUDIO_SET_STREAMTYPE _IO('o', 15) -#define AUDIO_BILINGUAL_CHANNEL_SELECT _IO('o', 20) - -#endif /* _DVBAUDIO_H_ */ diff --git a/include/uapi/linux/dvb/osd.h b/include/uapi/linux/dvb/osd.h deleted file mode 100644 index 858997c74043..000000000000 --- a/include/uapi/linux/dvb/osd.h +++ /dev/null @@ -1,181 +0,0 @@ -/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ -/* - * osd.h - DEPRECATED On Screen Display API - * - * NOTE: should not be used on future drivers - * - * Copyright (C) 2001 Ralph Metzler - * & Marcus Metzler - * for convergence integrated media GmbH - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Lesser Public License - * as published by the Free Software Foundation; either version 2.1 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - */ - -#ifndef _DVBOSD_H_ -#define _DVBOSD_H_ - -#include - -typedef enum { - /* All functions return -2 on "not open" */ - OSD_Close = 1, /* () */ - /* - * Disables OSD and releases the buffers - * returns 0 on success - */ - OSD_Open, /* (x0,y0,x1,y1,BitPerPixel[2/4/8](color&0x0F),mix[0..15](color&0xF0)) */ - /* - * Opens OSD with this size and bit depth - * returns 0 on success, -1 on DRAM allocation error, -2 on "already open" - */ - OSD_Show, /* () */ - /* - * enables OSD mode - * returns 0 on success - */ - OSD_Hide, /* () */ - /* - * disables OSD mode - * returns 0 on success - */ - OSD_Clear, /* () */ - /* - * Sets all pixel to color 0 - * returns 0 on success - */ - OSD_Fill, /* (color) */ - /* - * Sets all pixel to color - * returns 0 on success - */ - OSD_SetColor, /* (color,R{x0},G{y0},B{x1},opacity{y1}) */ - /* - * set palette entry to , and apply - * R,G,B: 0..255 - * R=Red, G=Green, B=Blue - * opacity=0: pixel opacity 0% (only video pixel shows) - * opacity=1..254: pixel opacity as specified in header - * opacity=255: pixel opacity 100% (only OSD pixel shows) - * returns 0 on success, -1 on error - */ - OSD_SetPalette, /* (firstcolor{color},lastcolor{x0},data) */ - /* - * Set a number of entries in the palette - * sets the entries "firstcolor" through "lastcolor" from the array "data" - * data has 4 byte for each color: - * R,G,B, and a opacity value: 0->transparent, 1..254->mix, 255->pixel - */ - OSD_SetTrans, /* (transparency{color}) */ - /* - * Sets transparency of mixed pixel (0..15) - * returns 0 on success - */ - OSD_SetPixel, /* (x0,y0,color) */ - /* - * sets pixel , to color number - * returns 0 on success, -1 on error - */ - OSD_GetPixel, /* (x0,y0) */ - /* returns color number of pixel ,, or -1 */ - OSD_SetRow, /* (x0,y0,x1,data) */ - /* - * fills pixels x0,y through x1,y with the content of data[] - * returns 0 on success, -1 on clipping all pixel (no pixel drawn) - */ - OSD_SetBlock, /* (x0,y0,x1,y1,increment{color},data) */ - /* - * fills pixels x0,y0 through x1,y1 with the content of data[] - * inc contains the width of one line in the data block, - * inc<=0 uses blockwidth as linewidth - * returns 0 on success, -1 on clipping all pixel - */ - OSD_FillRow, /* (x0,y0,x1,color) */ - /* - * fills pixels x0,y through x1,y with the color - * returns 0 on success, -1 on clipping all pixel - */ - OSD_FillBlock, /* (x0,y0,x1,y1,color) */ - /* - * fills pixels x0,y0 through x1,y1 with the color - * returns 0 on success, -1 on clipping all pixel - */ - OSD_Line, /* (x0,y0,x1,y1,color) */ - /* - * draw a line from x0,y0 to x1,y1 with the color - * returns 0 on success - */ - OSD_Query, /* (x0,y0,x1,y1,xasp{color}}), yasp=11 */ - /* - * fills parameters with the picture dimensions and the pixel aspect ratio - * returns 0 on success - */ - OSD_Test, /* () */ - /* - * draws a test picture. for debugging purposes only - * returns 0 on success - * TODO: remove "test" in final version - */ - OSD_Text, /* (x0,y0,size,color,text) */ - OSD_SetWindow, /* (x0) set window with number 0 - * & Ralph Metzler - * for convergence integrated media GmbH - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public License - * as published by the Free Software Foundation; either version 2.1 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - */ - -#ifndef _UAPI_DVBVIDEO_H_ -#define _UAPI_DVBVIDEO_H_ - -#include -#ifndef __KERNEL__ -#include -#endif - -typedef enum { - VIDEO_FORMAT_4_3, /* Select 4:3 format */ - VIDEO_FORMAT_16_9, /* Select 16:9 format. */ - VIDEO_FORMAT_221_1 /* 2.21:1 */ -} video_format_t; - - -typedef enum { - VIDEO_PAN_SCAN, /* use pan and scan format */ - VIDEO_LETTER_BOX, /* use letterbox format */ - VIDEO_CENTER_CUT_OUT /* use center cut out format */ -} video_displayformat_t; - -typedef struct { - int w; - int h; - video_format_t aspect_ratio; -} video_size_t; - -typedef enum { - VIDEO_SOURCE_DEMUX, /* Select the demux as the main source */ - VIDEO_SOURCE_MEMORY /* If this source is selected, the stream - comes from the user through the write - system call */ -} video_stream_source_t; - - -typedef enum { - VIDEO_STOPPED, /* Video is stopped */ - VIDEO_PLAYING, /* Video is currently playing */ - VIDEO_FREEZED /* Video is freezed */ -} video_play_state_t; - - -/* Decoder commands */ -#define VIDEO_CMD_PLAY (0) -#define VIDEO_CMD_STOP (1) -#define VIDEO_CMD_FREEZE (2) -#define VIDEO_CMD_CONTINUE (3) - -/* Flags for VIDEO_CMD_FREEZE */ -#define VIDEO_CMD_FREEZE_TO_BLACK (1 << 0) - -/* Flags for VIDEO_CMD_STOP */ -#define VIDEO_CMD_STOP_TO_BLACK (1 << 0) -#define VIDEO_CMD_STOP_IMMEDIATELY (1 << 1) - -/* Play input formats: */ -/* The decoder has no special format requirements */ -#define VIDEO_PLAY_FMT_NONE (0) -/* The decoder requires full GOPs */ -#define VIDEO_PLAY_FMT_GOP (1) - -/* The structure must be zeroed before use by the application - This ensures it can be extended safely in the future. */ -struct video_command { - __u32 cmd; - __u32 flags; - union { - struct { - __u64 pts; - } stop; - - struct { - /* 0 or 1000 specifies normal speed, - 1 specifies forward single stepping, - -1 specifies backward single stepping, - >1: playback at speed/1000 of the normal speed, - <-1: reverse playback at (-speed/1000) of the normal speed. */ - __s32 speed; - __u32 format; - } play; - - struct { - __u32 data[16]; - } raw; - }; -}; - -/* FIELD_UNKNOWN can be used if the hardware does not know whether - the Vsync is for an odd, even or progressive (i.e. non-interlaced) - field. */ -#define VIDEO_VSYNC_FIELD_UNKNOWN (0) -#define VIDEO_VSYNC_FIELD_ODD (1) -#define VIDEO_VSYNC_FIELD_EVEN (2) -#define VIDEO_VSYNC_FIELD_PROGRESSIVE (3) - -struct video_event { - __s32 type; -#define VIDEO_EVENT_SIZE_CHANGED 1 -#define VIDEO_EVENT_FRAME_RATE_CHANGED 2 -#define VIDEO_EVENT_DECODER_STOPPED 3 -#define VIDEO_EVENT_VSYNC 4 - /* unused, make sure to use atomic time for y2038 if it ever gets used */ - long timestamp; - union { - video_size_t size; - unsigned int frame_rate; /* in frames per 1000sec */ - unsigned char vsync_field; /* unknown/odd/even/progressive */ - } u; -}; - - -struct video_status { - int video_blank; /* blank video on freeze? */ - video_play_state_t play_state; /* current state of playback */ - video_stream_source_t stream_source; /* current source (demux/memory) */ - video_format_t video_format; /* current aspect ratio of stream*/ - video_displayformat_t display_format;/* selected cropping mode */ -}; - - -struct video_still_picture { - char __user *iFrame; /* pointer to a single iframe in memory */ - __s32 size; -}; - - -typedef __u16 video_attributes_t; -/* bits: descr. */ -/* 15-14 Video compression mode (0=MPEG-1, 1=MPEG-2) */ -/* 13-12 TV system (0=525/60, 1=625/50) */ -/* 11-10 Aspect ratio (0=4:3, 3=16:9) */ -/* 9- 8 permitted display mode on 4:3 monitor (0=both, 1=only pan-sca */ -/* 7 line 21-1 data present in GOP (1=yes, 0=no) */ -/* 6 line 21-2 data present in GOP (1=yes, 0=no) */ -/* 5- 3 source resolution (0=720x480/576, 1=704x480/576, 2=352x480/57 */ -/* 2 source letterboxed (1=yes, 0=no) */ -/* 0 film/camera mode (0= - *camera, 1=film (625/50 only)) */ - - -/* bit definitions for capabilities: */ -/* can the hardware decode MPEG1 and/or MPEG2? */ -#define VIDEO_CAP_MPEG1 1 -#define VIDEO_CAP_MPEG2 2 -/* can you send a system and/or program stream to video device? - (you still have to open the video and the audio device but only - send the stream to the video device) */ -#define VIDEO_CAP_SYS 4 -#define VIDEO_CAP_PROG 8 -/* can the driver also handle SPU, NAVI and CSS encoded data? - (CSS API is not present yet) */ -#define VIDEO_CAP_SPU 16 -#define VIDEO_CAP_NAVI 32 -#define VIDEO_CAP_CSS 64 - - -#define VIDEO_STOP _IO('o', 21) -#define VIDEO_PLAY _IO('o', 22) -#define VIDEO_FREEZE _IO('o', 23) -#define VIDEO_CONTINUE _IO('o', 24) -#define VIDEO_SELECT_SOURCE _IO('o', 25) -#define VIDEO_SET_BLANK _IO('o', 26) -#define VIDEO_GET_STATUS _IOR('o', 27, struct video_status) -#define VIDEO_GET_EVENT _IOR('o', 28, struct video_event) -#define VIDEO_SET_DISPLAY_FORMAT _IO('o', 29) -#define VIDEO_STILLPICTURE _IOW('o', 30, struct video_still_picture) -#define VIDEO_FAST_FORWARD _IO('o', 31) -#define VIDEO_SLOWMOTION _IO('o', 32) -#define VIDEO_GET_CAPABILITIES _IOR('o', 33, unsigned int) -#define VIDEO_CLEAR_BUFFER _IO('o', 34) -#define VIDEO_SET_STREAMTYPE _IO('o', 36) -#define VIDEO_SET_FORMAT _IO('o', 37) -#define VIDEO_GET_SIZE _IOR('o', 55, video_size_t) - -/** - * VIDEO_GET_PTS - * - * Read the 33 bit presentation time stamp as defined - * in ITU T-REC-H.222.0 / ISO/IEC 13818-1. - * - * The PTS should belong to the currently played - * frame if possible, but may also be a value close to it - * like the PTS of the last decoded frame or the last PTS - * extracted by the PES parser. - */ -#define VIDEO_GET_PTS _IOR('o', 57, __u64) - -/* Read the number of displayed frames since the decoder was started */ -#define VIDEO_GET_FRAME_COUNT _IOR('o', 58, __u64) - -#define VIDEO_COMMAND _IOWR('o', 59, struct video_command) -#define VIDEO_TRY_COMMAND _IOWR('o', 60, struct video_command) - -#endif /* _UAPI_DVBVIDEO_H_ */ -- cgit v1.3-18-gd494 From 992da01aa932b432ef8dc3885fa76415b5dbe43f Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 10 Jun 2021 16:37:37 +0100 Subject: io_uring: change registration/upd/rsrc tagging ABI There are ABI moments about recently added rsrc registration/update and tagging that might become a nuisance in the future. First, IORING_REGISTER_RSRC[_UPD] hide different types of resources under it, so breaks fine control over them by restrictions. It works for now, but once those are wanted under restrictions it would require a rework. It was also inconvenient trying to fit a new resource not supporting all the features (e.g. dynamic update) into the interface, so better to return to IORING_REGISTER_* top level dispatching. Second, register/update were considered to accept a type of resource, however that's not a good idea because there might be several ways of registration of a single resource type, e.g. we may want to add non-contig buffers or anything more exquisite as dma mapped memory. So, remove IORING_RSRC_[FILE,BUFFER] out of the ABI, and place them internally for now to limit changes. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/9b554897a7c17ad6e3becc48dfed2f7af9f423d5.1623339162.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 39 +++++++++++++++++++++++++++------------ include/uapi/linux/io_uring.h | 18 +++++++++--------- 2 files changed, 36 insertions(+), 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 42380ed563c4..663fef3d56df 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -783,6 +783,11 @@ struct io_task_work { task_work_func_t func; }; +enum { + IORING_RSRC_FILE = 0, + IORING_RSRC_BUFFER = 1, +}; + /* * NOTE! Each of the iocb union members has the file pointer * as the first entry in their struct definition. So you can @@ -9911,7 +9916,7 @@ static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, } static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, - unsigned size) + unsigned size, unsigned type) { struct io_uring_rsrc_update2 up; @@ -9919,13 +9924,13 @@ static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, return -EINVAL; if (copy_from_user(&up, arg, sizeof(up))) return -EFAULT; - if (!up.nr) + if (!up.nr || up.resv) return -EINVAL; - return __io_register_rsrc_update(ctx, up.type, &up, up.nr); + return __io_register_rsrc_update(ctx, type, &up, up.nr); } static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, - unsigned int size) + unsigned int size, unsigned int type) { struct io_uring_rsrc_register rr; @@ -9936,10 +9941,10 @@ static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, memset(&rr, 0, sizeof(rr)); if (copy_from_user(&rr, arg, size)) return -EFAULT; - if (!rr.nr) + if (!rr.nr || rr.resv || rr.resv2) return -EINVAL; - switch (rr.type) { + switch (type) { case IORING_RSRC_FILE: return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data), rr.nr, u64_to_user_ptr(rr.tags)); @@ -9961,8 +9966,10 @@ static bool io_register_op_must_quiesce(int op) case IORING_REGISTER_PROBE: case IORING_REGISTER_PERSONALITY: case IORING_UNREGISTER_PERSONALITY: - case IORING_REGISTER_RSRC: - case IORING_REGISTER_RSRC_UPDATE: + case IORING_REGISTER_FILES2: + case IORING_REGISTER_FILES_UPDATE2: + case IORING_REGISTER_BUFFERS2: + case IORING_REGISTER_BUFFERS_UPDATE: return false; default: return true; @@ -10088,11 +10095,19 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, case IORING_REGISTER_RESTRICTIONS: ret = io_register_restrictions(ctx, arg, nr_args); break; - case IORING_REGISTER_RSRC: - ret = io_register_rsrc(ctx, arg, nr_args); + case IORING_REGISTER_FILES2: + ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE); + break; + case IORING_REGISTER_FILES_UPDATE2: + ret = io_register_rsrc_update(ctx, arg, nr_args, + IORING_RSRC_FILE); + break; + case IORING_REGISTER_BUFFERS2: + ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER); break; - case IORING_REGISTER_RSRC_UPDATE: - ret = io_register_rsrc_update(ctx, arg, nr_args); + case IORING_REGISTER_BUFFERS_UPDATE: + ret = io_register_rsrc_update(ctx, arg, nr_args, + IORING_RSRC_BUFFER); break; default: ret = -EINVAL; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index e1ae46683301..48b4ddcd56ff 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -298,8 +298,12 @@ enum { IORING_UNREGISTER_PERSONALITY = 10, IORING_REGISTER_RESTRICTIONS = 11, IORING_REGISTER_ENABLE_RINGS = 12, - IORING_REGISTER_RSRC = 13, - IORING_REGISTER_RSRC_UPDATE = 14, + + /* extended with tagging */ + IORING_REGISTER_FILES2 = 13, + IORING_REGISTER_FILES_UPDATE2 = 14, + IORING_REGISTER_BUFFERS2 = 15, + IORING_REGISTER_BUFFERS_UPDATE = 16, /* this goes last */ IORING_REGISTER_LAST @@ -312,14 +316,10 @@ struct io_uring_files_update { __aligned_u64 /* __s32 * */ fds; }; -enum { - IORING_RSRC_FILE = 0, - IORING_RSRC_BUFFER = 1, -}; - struct io_uring_rsrc_register { - __u32 type; __u32 nr; + __u32 resv; + __u64 resv2; __aligned_u64 data; __aligned_u64 tags; }; @@ -335,8 +335,8 @@ struct io_uring_rsrc_update2 { __u32 resv; __aligned_u64 data; __aligned_u64 tags; - __u32 type; __u32 nr; + __u32 resv2; }; /* Skip updating fd indexes set to this value in the fd table */ -- cgit v1.3-18-gd494 From 9690557e22d63f13534fd167d293ac8ed8b104f9 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 10 Jun 2021 16:37:38 +0100 Subject: io_uring: add feature flag for rsrc tags Add IORING_FEAT_RSRC_TAGS indicating that io_uring supports a bunch of new IORING_REGISTER operations, in particular IORING_REGISTER_[FILES[,UPDATE]2,BUFFERS[2,UPDATE]] that support rsrc tagging, and also indicating implemented dynamic fixed buffer updates. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/9b995d4045b6c6b4ab7510ca124fd25ac2203af7.1623339162.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 3 ++- include/uapi/linux/io_uring.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 663fef3d56df..fa8794c61af7 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -9676,7 +9676,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | - IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS; + IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | + IORING_FEAT_RSRC_TAGS; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 48b4ddcd56ff..162ff99ed2cb 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -280,6 +280,7 @@ struct io_uring_params { #define IORING_FEAT_SQPOLL_NONFIXED (1U << 7) #define IORING_FEAT_EXT_ARG (1U << 8) #define IORING_FEAT_NATIVE_WORKERS (1U << 9) +#define IORING_FEAT_RSRC_TAGS (1U << 10) /* * io_uring_register(2) opcodes and arguments -- cgit v1.3-18-gd494 From 644f706719f0297bc5f65c8891de1c32f042eae5 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 21 May 2021 11:51:36 +0200 Subject: KVM: x86: hyper-v: Introduce KVM_CAP_HYPERV_ENFORCE_CPUID Modeled after KVM_CAP_ENFORCE_PV_FEATURE_CPUID, the new capability allows for limiting Hyper-V features to those exposed to the guest in Hyper-V CPUIDs (0x40000003, 0x40000004, ...). Signed-off-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini Message-Id: <20210521095204.2161214-3-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 11 +++++++++++ arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/hyperv.c | 21 +++++++++++++++++++++ arch/x86/kvm/hyperv.h | 1 + arch/x86/kvm/x86.c | 4 ++++ include/uapi/linux/kvm.h | 1 + 6 files changed, 39 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 7fcb2fd38f42..80154d5d98a1 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6891,3 +6891,14 @@ This capability is always enabled. This capability indicates that the KVM virtual PTP service is supported in the host. A VMM can check whether the service is available to the guest on migration. + +8.33 KVM_CAP_HYPERV_ENFORCE_CPUID +----------------------------- + +Architectures: x86 + +When enabled, KVM will disable emulated Hyper-V features provided to the +guest according to the bits Hyper-V CPUID feature leaves. Otherwise, all +currently implmented Hyper-V features are provided unconditionally when +Hyper-V identification is set in the HYPERV_CPUID_INTERFACE (0x40000001) +leaf. diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1fdb212127c4..556a8ec89451 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -543,6 +543,7 @@ struct kvm_vcpu_hv { struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); cpumask_t tlb_flush; + bool enforce_cpuid; }; /* Xen HVM per vcpu emulation context */ diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index dbd3152b1379..02b0ee189f82 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1853,6 +1853,27 @@ void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.hyperv_enabled = false; } +int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce) +{ + struct kvm_vcpu_hv *hv_vcpu; + int ret = 0; + + if (!to_hv_vcpu(vcpu)) { + if (enforce) { + ret = kvm_hv_vcpu_init(vcpu); + if (ret) + return ret; + } else { + return 0; + } + } + + hv_vcpu = to_hv_vcpu(vcpu); + hv_vcpu->enforce_cpuid = enforce; + + return ret; +} + bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu) { return vcpu->arch.hyperv_enabled && to_kvm_hv(vcpu->kvm)->hv_guest_os_id; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 60547d5cb6d7..730da8537d05 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -138,6 +138,7 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm); void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu); +int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce); int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args); int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 63e48738764e..475376a97419 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3955,6 +3955,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_TLBFLUSH: case KVM_CAP_HYPERV_SEND_IPI: case KVM_CAP_HYPERV_CPUID: + case KVM_CAP_HYPERV_ENFORCE_CPUID: case KVM_CAP_SYS_HYPERV_CPUID: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: @@ -4878,6 +4879,9 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return static_call(kvm_x86_enable_direct_tlbflush)(vcpu); + case KVM_CAP_HYPERV_ENFORCE_CPUID: + return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]); + case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; if (vcpu->arch.pv_cpuid.enforce) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 79d9c44d1ad7..792816144092 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1083,6 +1083,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_SGX_ATTRIBUTE 196 #define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197 #define KVM_CAP_PTP_KVM 198 +#define KVM_CAP_HYPERV_ENFORCE_CPUID 199 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.3-18-gd494 From 6dba940352038b56db9b591b172fb2ec76a5fd5e Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 7 Jun 2021 12:02:02 +0300 Subject: KVM: x86: Introduce KVM_GET_SREGS2 / KVM_SET_SREGS2 This is a new version of KVM_GET_SREGS / KVM_SET_SREGS. It has the following changes: * Has flags for future extensions * Has vcpu's PDPTRs, allowing to save/restore them on migration. * Lacks obsolete interrupt bitmap (done now via KVM_SET_VCPU_EVENTS) New capability, KVM_CAP_SREGS2 is added to signal the userspace of this ioctl. Signed-off-by: Maxim Levitsky Message-Id: <20210607090203.133058-8-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 48 ++++++++++++++ arch/x86/include/uapi/asm/kvm.h | 13 ++++ arch/x86/kvm/kvm_cache_regs.h | 5 ++ arch/x86/kvm/x86.c | 142 ++++++++++++++++++++++++++++++++-------- include/uapi/linux/kvm.h | 4 ++ 5 files changed, 185 insertions(+), 27 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 80154d5d98a1..cded99561adf 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5034,6 +5034,54 @@ see KVM_XEN_VCPU_SET_ATTR above. The KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST type may not be used with the KVM_XEN_VCPU_GET_ATTR ioctl. + +4.131 KVM_GET_SREGS2 +------------------ + +:Capability: KVM_CAP_SREGS2 +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_sregs2 (out) +:Returns: 0 on success, -1 on error + +Reads special registers from the vcpu. +This ioctl (when supported) replaces the KVM_GET_SREGS. + +:: + +struct kvm_sregs2 { + /* out (KVM_GET_SREGS2) / in (KVM_SET_SREGS2) */ + struct kvm_segment cs, ds, es, fs, gs, ss; + struct kvm_segment tr, ldt; + struct kvm_dtable gdt, idt; + __u64 cr0, cr2, cr3, cr4, cr8; + __u64 efer; + __u64 apic_base; + __u64 flags; + __u64 pdptrs[4]; +}; + +flags values for ``kvm_sregs2``: + +``KVM_SREGS2_FLAGS_PDPTRS_VALID`` + + Indicates thats the struct contain valid PDPTR values. + + +4.132 KVM_SET_SREGS2 +------------------ + +:Capability: KVM_CAP_SREGS2 +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_sregs2 (in) +:Returns: 0 on success, -1 on error + +Writes special registers into the vcpu. +See KVM_GET_SREGS2 for the data structures. +This ioctl (when supported) replaces the KVM_SET_SREGS. + + 5. The kvm_run structure ======================== diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 0662f644aad9..a6c327f8ad9e 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -159,6 +159,19 @@ struct kvm_sregs { __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64]; }; +struct kvm_sregs2 { + /* out (KVM_GET_SREGS2) / in (KVM_SET_SREGS2) */ + struct kvm_segment cs, ds, es, fs, gs, ss; + struct kvm_segment tr, ldt; + struct kvm_dtable gdt, idt; + __u64 cr0, cr2, cr3, cr4, cr8; + __u64 efer; + __u64 apic_base; + __u64 flags; + __u64 pdptrs[4]; +}; +#define KVM_SREGS2_FLAGS_PDPTRS_VALID 1 + /* for KVM_GET_FPU and KVM_SET_FPU */ struct kvm_fpu { __u8 fpr[8][16]; diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 296d67f689ef..90e1ffdc05b7 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -125,6 +125,11 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) return vcpu->arch.walk_mmu->pdptrs[index]; } +static inline void kvm_pdptr_write(struct kvm_vcpu *vcpu, int index, u64 value) +{ + vcpu->arch.walk_mmu->pdptrs[index] = value; +} + static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask) { ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 188c180d9f6e..8085ab830c80 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -114,6 +114,9 @@ static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); +static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); +static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); + struct kvm_x86_ops kvm_x86_ops __read_mostly; EXPORT_SYMBOL_GPL(kvm_x86_ops); @@ -817,7 +820,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); - out: return ret; @@ -3956,6 +3958,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SGX_ATTRIBUTE: #endif case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: + case KVM_CAP_SREGS2: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: @@ -4870,6 +4873,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int r; union { + struct kvm_sregs2 *sregs2; struct kvm_lapic_state *lapic; struct kvm_xsave *xsave; struct kvm_xcrs *xcrs; @@ -5242,6 +5246,28 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } #endif + case KVM_GET_SREGS2: { + u.sregs2 = kzalloc(sizeof(struct kvm_sregs2), GFP_KERNEL); + r = -ENOMEM; + if (!u.sregs2) + goto out; + __get_sregs2(vcpu, u.sregs2); + r = -EFAULT; + if (copy_to_user(argp, u.sregs2, sizeof(struct kvm_sregs2))) + goto out; + r = 0; + break; + } + case KVM_SET_SREGS2: { + u.sregs2 = memdup_user(argp, sizeof(struct kvm_sregs2)); + if (IS_ERR(u.sregs2)) { + r = PTR_ERR(u.sregs2); + u.sregs2 = NULL; + goto out; + } + r = __set_sregs2(vcpu, u.sregs2); + break; + } default: r = -EINVAL; } @@ -9937,7 +9963,7 @@ void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) } EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits); -static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static void __get_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { struct desc_ptr dt; @@ -9970,14 +9996,36 @@ skip_protected_regs: sregs->cr8 = kvm_get_cr8(vcpu); sregs->efer = vcpu->arch.efer; sregs->apic_base = kvm_get_apic_base(vcpu); +} - memset(sregs->interrupt_bitmap, 0, sizeof(sregs->interrupt_bitmap)); +static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + __get_sregs_common(vcpu, sregs); + + if (vcpu->arch.guest_state_protected) + return; if (vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft) set_bit(vcpu->arch.interrupt.nr, (unsigned long *)sregs->interrupt_bitmap); } +static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) +{ + int i; + + __get_sregs_common(vcpu, (struct kvm_sregs *)sregs2); + + if (vcpu->arch.guest_state_protected) + return; + + if (is_pae_paging(vcpu)) { + for (i = 0 ; i < 4 ; i++) + sregs2->pdptrs[i] = kvm_pdptr_read(vcpu, i); + sregs2->flags |= KVM_SREGS2_FLAGS_PDPTRS_VALID; + } +} + int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { @@ -10096,24 +10144,23 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return kvm_is_valid_cr4(vcpu, sregs->cr4); } -static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, + int *mmu_reset_needed, bool update_pdptrs) { struct msr_data apic_base_msr; - int mmu_reset_needed = 0; - int pending_vec, max_bits, idx; + int idx; struct desc_ptr dt; - int ret = -EINVAL; if (!kvm_is_valid_sregs(vcpu, sregs)) - goto out; + return -EINVAL; apic_base_msr.data = sregs->apic_base; apic_base_msr.host_initiated = true; if (kvm_set_apic_base(vcpu, &apic_base_msr)) - goto out; + return -EINVAL; if (vcpu->arch.guest_state_protected) - goto skip_protected_regs; + return 0; dt.size = sregs->idt.limit; dt.address = sregs->idt.base; @@ -10123,31 +10170,30 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) static_call(kvm_x86_set_gdt)(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; - mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; + *mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); kvm_set_cr8(vcpu, sregs->cr8); - mmu_reset_needed |= vcpu->arch.efer != sregs->efer; + *mmu_reset_needed |= vcpu->arch.efer != sregs->efer; static_call(kvm_x86_set_efer)(vcpu, sregs->efer); - mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; + *mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; static_call(kvm_x86_set_cr0)(vcpu, sregs->cr0); vcpu->arch.cr0 = sregs->cr0; - mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; + *mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; static_call(kvm_x86_set_cr4)(vcpu, sregs->cr4); - idx = srcu_read_lock(&vcpu->kvm->srcu); - if (is_pae_paging(vcpu)) { - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); - mmu_reset_needed = 1; + if (update_pdptrs) { + idx = srcu_read_lock(&vcpu->kvm->srcu); + if (is_pae_paging(vcpu)) { + load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + *mmu_reset_needed = 1; + } + srcu_read_unlock(&vcpu->kvm->srcu, idx); } - srcu_read_unlock(&vcpu->kvm->srcu, idx); - - if (mmu_reset_needed) - kvm_mmu_reset_context(vcpu); kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); @@ -10167,20 +10213,62 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) !is_protmode(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; -skip_protected_regs: + return 0; +} + +static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + int pending_vec, max_bits; + int mmu_reset_needed = 0; + int ret = __set_sregs_common(vcpu, sregs, &mmu_reset_needed, true); + + if (ret) + return ret; + + if (mmu_reset_needed) + kvm_mmu_reset_context(vcpu); + max_bits = KVM_NR_INTERRUPTS; pending_vec = find_first_bit( (const unsigned long *)sregs->interrupt_bitmap, max_bits); + if (pending_vec < max_bits) { kvm_queue_interrupt(vcpu, pending_vec, false); pr_debug("Set back pending irq %d\n", pending_vec); + kvm_make_request(KVM_REQ_EVENT, vcpu); } + return 0; +} - kvm_make_request(KVM_REQ_EVENT, vcpu); +static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) +{ + int mmu_reset_needed = 0; + bool valid_pdptrs = sregs2->flags & KVM_SREGS2_FLAGS_PDPTRS_VALID; + bool pae = (sregs2->cr0 & X86_CR0_PG) && (sregs2->cr4 & X86_CR4_PAE) && + !(sregs2->efer & EFER_LMA); + int i, ret; - ret = 0; -out: - return ret; + if (sregs2->flags & ~KVM_SREGS2_FLAGS_PDPTRS_VALID) + return -EINVAL; + + if (valid_pdptrs && (!pae || vcpu->arch.guest_state_protected)) + return -EINVAL; + + ret = __set_sregs_common(vcpu, (struct kvm_sregs *)sregs2, + &mmu_reset_needed, !valid_pdptrs); + if (ret) + return ret; + + if (valid_pdptrs) { + for (i = 0; i < 4 ; i++) + kvm_pdptr_write(vcpu, i, sregs2->pdptrs[i]); + + kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); + mmu_reset_needed = 1; + } + if (mmu_reset_needed) + kvm_mmu_reset_context(vcpu); + return 0; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 792816144092..90d44138dbfb 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1084,6 +1084,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197 #define KVM_CAP_PTP_KVM 198 #define KVM_CAP_HYPERV_ENFORCE_CPUID 199 +#define KVM_CAP_SREGS2 200 #ifdef KVM_CAP_IRQ_ROUTING @@ -1622,6 +1623,9 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) #define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) +#define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) +#define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) + struct kvm_xen_vcpu_attr { __u16 type; __u16 pad[3]; -- cgit v1.3-18-gd494 From 0dbb11230437895f7cd6fc55da61cef011e997d8 Mon Sep 17 00:00:00 2001 From: Ashish Kalra Date: Tue, 8 Jun 2021 18:05:43 +0000 Subject: KVM: X86: Introduce KVM_HC_MAP_GPA_RANGE hypercall This hypercall is used by the SEV guest to notify a change in the page encryption status to the hypervisor. The hypercall should be invoked only when the encryption attribute is changed from encrypted -> decrypted and vice versa. By default all guest pages are considered encrypted. The hypercall exits to userspace to manage the guest shared regions and integrate with the userspace VMM's migration code. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Paolo Bonzini Cc: Joerg Roedel Cc: Borislav Petkov Cc: Tom Lendacky Cc: x86@kernel.org Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Reviewed-by: Steve Rutherford Signed-off-by: Brijesh Singh Signed-off-by: Ashish Kalra Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson Co-developed-by: Paolo Bonzini Signed-off-by: Paolo Bonzini Message-Id: <90778988e1ee01926ff9cac447aacb745f954c8c.1623174621.git.ashish.kalra@amd.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 19 +++++++++++++++ Documentation/virt/kvm/cpuid.rst | 7 ++++++ Documentation/virt/kvm/hypercalls.rst | 21 ++++++++++++++++ Documentation/virt/kvm/msr.rst | 13 ++++++++++ arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/include/uapi/asm/kvm_para.h | 13 ++++++++++ arch/x86/kvm/x86.c | 46 +++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 1 + include/uapi/linux/kvm_para.h | 1 + 9 files changed, 123 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index cded99561adf..e328caa35d6c 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6950,3 +6950,22 @@ guest according to the bits Hyper-V CPUID feature leaves. Otherwise, all currently implmented Hyper-V features are provided unconditionally when Hyper-V identification is set in the HYPERV_CPUID_INTERFACE (0x40000001) leaf. + +8.34 KVM_CAP_EXIT_HYPERCALL +--------------------------- + +:Capability: KVM_CAP_EXIT_HYPERCALL +:Architectures: x86 +:Type: vm + +This capability, if enabled, will cause KVM to exit to userspace +with KVM_EXIT_HYPERCALL exit reason to process some hypercalls. + +Calling KVM_CHECK_EXTENSION for this capability will return a bitmask +of hypercalls that can be configured to exit to userspace. +Right now, the only such hypercall is KVM_HC_MAP_GPA_RANGE. + +The argument to KVM_ENABLE_CAP is also a bitmask, and must be a subset +of the result of KVM_CHECK_EXTENSION. KVM will forward to userspace +the hypercalls whose corresponding bit is in the argument, and return +ENOSYS for the others. diff --git a/Documentation/virt/kvm/cpuid.rst b/Documentation/virt/kvm/cpuid.rst index cf62162d4be2..bda3e3e737d7 100644 --- a/Documentation/virt/kvm/cpuid.rst +++ b/Documentation/virt/kvm/cpuid.rst @@ -96,6 +96,13 @@ KVM_FEATURE_MSI_EXT_DEST_ID 15 guest checks this feature bit before using extended destination ID bits in MSI address bits 11-5. +KVM_FEATURE_HC_MAP_GPA_RANGE 16 guest checks this feature bit before + using the map gpa range hypercall + to notify the page state change + +KVM_FEATURE_MIGRATION_CONTROL 17 guest checks this feature bit before + using MSR_KVM_MIGRATION_CONTROL + KVM_FEATURE_CLOCKSOURCE_STABLE_BIT 24 host will warn if no guest-side per-cpu warps are expected in kvmclock diff --git a/Documentation/virt/kvm/hypercalls.rst b/Documentation/virt/kvm/hypercalls.rst index ed4fddd364ea..e56fa8b9cfca 100644 --- a/Documentation/virt/kvm/hypercalls.rst +++ b/Documentation/virt/kvm/hypercalls.rst @@ -169,3 +169,24 @@ a0: destination APIC ID :Usage example: When sending a call-function IPI-many to vCPUs, yield if any of the IPI target vCPUs was preempted. + +8. KVM_HC_MAP_GPA_RANGE +------------------------- +:Architecture: x86 +:Status: active +:Purpose: Request KVM to map a GPA range with the specified attributes. + +a0: the guest physical address of the start page +a1: the number of (4kb) pages (must be contiguous in GPA space) +a2: attributes + + Where 'attributes' : + * bits 3:0 - preferred page size encoding 0 = 4kb, 1 = 2mb, 2 = 1gb, etc... + * bit 4 - plaintext = 0, encrypted = 1 + * bits 63:5 - reserved (must be zero) + +**Implementation note**: this hypercall is implemented in userspace via +the KVM_CAP_EXIT_HYPERCALL capability. Userspace must enable that capability +before advertising KVM_FEATURE_HC_MAP_GPA_RANGE in the guest CPUID. In +addition, if the guest supports KVM_FEATURE_MIGRATION_CONTROL, userspace +must also set up an MSR filter to process writes to MSR_KVM_MIGRATION_CONTROL. diff --git a/Documentation/virt/kvm/msr.rst b/Documentation/virt/kvm/msr.rst index e37a14c323d2..9315fc385fb0 100644 --- a/Documentation/virt/kvm/msr.rst +++ b/Documentation/virt/kvm/msr.rst @@ -376,3 +376,16 @@ data: write '1' to bit 0 of the MSR, this causes the host to re-scan its queue and check if there are more notifications pending. The MSR is available if KVM_FEATURE_ASYNC_PF_INT is present in CPUID. + +MSR_KVM_MIGRATION_CONTROL: + 0x4b564d08 + +data: + This MSR is available if KVM_FEATURE_MIGRATION_CONTROL is present in + CPUID. Bit 0 represents whether live migration of the guest is allowed. + + When a guest is started, bit 0 will be 0 if the guest has encrypted + memory and 1 if the guest does not have encrypted memory. If the + guest is communicating page encryption status to the host using the + ``KVM_HC_MAP_GPA_RANGE`` hypercall, it can set bit 0 in this MSR to + allow live migration of the guest. diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a0c29e29dd48..e11d64aa0bcd 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1087,6 +1087,8 @@ struct kvm_arch { u32 user_space_msr_mask; struct kvm_x86_msr_filter __rcu *msr_filter; + u32 hypercall_exit_enabled; + /* Guest can access the SGX PROVISIONKEY. */ bool sgx_provisioning_allowed; diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 950afebfba88..5146bbab84d4 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -33,6 +33,8 @@ #define KVM_FEATURE_PV_SCHED_YIELD 13 #define KVM_FEATURE_ASYNC_PF_INT 14 #define KVM_FEATURE_MSI_EXT_DEST_ID 15 +#define KVM_FEATURE_HC_MAP_GPA_RANGE 16 +#define KVM_FEATURE_MIGRATION_CONTROL 17 #define KVM_HINTS_REALTIME 0 @@ -54,6 +56,7 @@ #define MSR_KVM_POLL_CONTROL 0x4b564d05 #define MSR_KVM_ASYNC_PF_INT 0x4b564d06 #define MSR_KVM_ASYNC_PF_ACK 0x4b564d07 +#define MSR_KVM_MIGRATION_CONTROL 0x4b564d08 struct kvm_steal_time { __u64 steal; @@ -90,6 +93,16 @@ struct kvm_clock_pairing { /* MSR_KVM_ASYNC_PF_INT */ #define KVM_ASYNC_PF_VEC_MASK GENMASK(7, 0) +/* MSR_KVM_MIGRATION_CONTROL */ +#define KVM_MIGRATION_READY (1 << 0) + +/* KVM_HC_MAP_GPA_RANGE */ +#define KVM_MAP_GPA_RANGE_PAGE_SZ_4K 0 +#define KVM_MAP_GPA_RANGE_PAGE_SZ_2M (1 << 0) +#define KVM_MAP_GPA_RANGE_PAGE_SZ_1G (1 << 1) +#define KVM_MAP_GPA_RANGE_ENC_STAT(n) (n << 4) +#define KVM_MAP_GPA_RANGE_ENCRYPTED KVM_MAP_GPA_RANGE_ENC_STAT(1) +#define KVM_MAP_GPA_RANGE_DECRYPTED KVM_MAP_GPA_RANGE_ENC_STAT(0) /* Operations for KVM_HC_MMU_OP */ #define KVM_MMU_OP_WRITE_PTE 1 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ceb60f64085c..8b898ec8d349 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -103,6 +103,8 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; +#define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE) + #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) @@ -3996,6 +3998,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SREGS2: r = 1; break; + case KVM_CAP_EXIT_HYPERCALL: + r = KVM_EXIT_HYPERCALL_VALID_MASK; + break; case KVM_CAP_SET_GUEST_DEBUG2: return KVM_GUESTDBG_VALID_MASK; #ifdef CONFIG_KVM_XEN @@ -5622,6 +5627,14 @@ split_irqchip_unlock: if (kvm_x86_ops.vm_copy_enc_context_from) r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]); return r; + case KVM_CAP_EXIT_HYPERCALL: + if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) { + r = -EINVAL; + break; + } + kvm->arch.hypercall_exit_enabled = cap->args[0]; + r = 0; + break; default: r = -EINVAL; break; @@ -8548,6 +8561,17 @@ no_yield: return; } +static int complete_hypercall_exit(struct kvm_vcpu *vcpu) +{ + u64 ret = vcpu->run->hypercall.ret; + + if (!is_64_bit_mode(vcpu)) + ret = (u32)ret; + kvm_rax_write(vcpu, ret); + ++vcpu->stat.hypercalls; + return kvm_skip_emulated_instruction(vcpu); +} + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; @@ -8613,6 +8637,28 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) kvm_sched_yield(vcpu, a0); ret = 0; break; + case KVM_HC_MAP_GPA_RANGE: { + u64 gpa = a0, npages = a1, attrs = a2; + + ret = -KVM_ENOSYS; + if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) + break; + + if (!PAGE_ALIGNED(gpa) || !npages || + gpa_to_gfn(gpa) + npages <= gpa_to_gfn(gpa)) { + ret = -KVM_EINVAL; + break; + } + + vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; + vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + vcpu->run->hypercall.args[0] = gpa; + vcpu->run->hypercall.args[1] = npages; + vcpu->run->hypercall.args[2] = attrs; + vcpu->run->hypercall.longmode = op_64_bit; + vcpu->arch.complete_userspace_io = complete_hypercall_exit; + return 0; + } default: ret = -KVM_ENOSYS; break; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 90d44138dbfb..9febe1412f7a 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1085,6 +1085,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PTP_KVM 198 #define KVM_CAP_HYPERV_ENFORCE_CPUID 199 #define KVM_CAP_SREGS2 200 +#define KVM_CAP_EXIT_HYPERCALL 201 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h index 8b86609849b9..960c7e93d1a9 100644 --- a/include/uapi/linux/kvm_para.h +++ b/include/uapi/linux/kvm_para.h @@ -29,6 +29,7 @@ #define KVM_HC_CLOCK_PAIRING 9 #define KVM_HC_SEND_IPI 10 #define KVM_HC_SCHED_YIELD 11 +#define KVM_HC_MAP_GPA_RANGE 12 /* * hypercalls use architecture specific -- cgit v1.3-18-gd494 From 321827477360934dc040e9d3c626bf1de6c3ab3c Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Fri, 18 Jun 2021 13:04:35 +0200 Subject: icmp: don't send out ICMP messages with a source address of 0.0.0.0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When constructing ICMP response messages, the kernel will try to pick a suitable source address for the outgoing packet. However, if no IPv4 addresses are configured on the system at all, this will fail and we end up producing an ICMP message with a source address of 0.0.0.0. This can happen on a box routing IPv4 traffic via v6 nexthops, for instance. Since 0.0.0.0 is not generally routable on the internet, there's a good chance that such ICMP messages will never make it back to the sender of the original packet that the ICMP message was sent in response to. This, in turn, can create connectivity and PMTUd problems for senders. Fortunately, RFC7600 reserves a dummy address to be used as a source for ICMP messages (192.0.0.8/32), so let's teach the kernel to substitute that address as a last resort if the regular source address selection procedure fails. Below is a quick example reproducing this issue with network namespaces: ip netns add ns0 ip l add type veth peer netns ns0 ip l set dev veth0 up ip a add 10.0.0.1/24 dev veth0 ip a add fc00:dead:cafe:42::1/64 dev veth0 ip r add 10.1.0.0/24 via inet6 fc00:dead:cafe:42::2 ip -n ns0 l set dev veth0 up ip -n ns0 a add fc00:dead:cafe:42::2/64 dev veth0 ip -n ns0 r add 10.0.0.0/24 via inet6 fc00:dead:cafe:42::1 ip netns exec ns0 sysctl -w net.ipv4.icmp_ratelimit=0 ip netns exec ns0 sysctl -w net.ipv4.ip_forward=1 tcpdump -tpni veth0 -c 2 icmp & ping -w 1 10.1.0.1 > /dev/null tcpdump: verbose output suppressed, use -v[v]... for full protocol decode listening on veth0, link-type EN10MB (Ethernet), snapshot length 262144 bytes IP 10.0.0.1 > 10.1.0.1: ICMP echo request, id 29, seq 1, length 64 IP 0.0.0.0 > 10.0.0.1: ICMP net 10.1.0.1 unreachable, length 92 2 packets captured 2 packets received by filter 0 packets dropped by kernel With this patch the above capture changes to: IP 10.0.0.1 > 10.1.0.1: ICMP echo request, id 31127, seq 1, length 64 IP 192.0.0.8 > 10.0.0.1: ICMP net 10.1.0.1 unreachable, length 92 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Juliusz Chroboczek Reviewed-by: David Ahern Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- include/uapi/linux/in.h | 3 +++ net/ipv4/icmp.c | 7 +++++++ 2 files changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 7d6687618d80..d1b327036ae4 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -289,6 +289,9 @@ struct sockaddr_in { /* Address indicating an error return. */ #define INADDR_NONE ((unsigned long int) 0xffffffff) +/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */ +#define INADDR_DUMMY ((unsigned long int) 0xc0000008) + /* Network number for local host loopback. */ #define IN_LOOPBACKNET 127 diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 7b6931a4d775..752e392083e6 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -759,6 +759,13 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, icmp_param.data_len = room; icmp_param.head_len = sizeof(struct icmphdr); + /* if we don't have a source address at this point, fall back to the + * dummy address instead of sending out a packet with a source address + * of 0.0.0.0 + */ + if (!fl4.saddr) + fl4.saddr = htonl(INADDR_DUMMY); + icmp_push_reply(&icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); -- cgit v1.3-18-gd494 From 1a9fd4172d5c8ba64735b3aef7eed643d398ce05 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Fri, 21 May 2021 17:42:23 +0200 Subject: btrfs: fix typos in comments Fix typos that have snuck in since the last round. Found by codespell. Signed-off-by: David Sterba --- fs/btrfs/backref.c | 2 +- fs/btrfs/ctree.h | 6 +++--- fs/btrfs/delalloc-space.c | 2 +- fs/btrfs/dev-replace.c | 2 +- fs/btrfs/discard.c | 2 +- fs/btrfs/disk-io.c | 2 +- fs/btrfs/extent-tree.c | 2 +- fs/btrfs/file-item.c | 2 +- fs/btrfs/inode.c | 4 ++-- fs/btrfs/ioctl.c | 2 +- fs/btrfs/locking.c | 4 ++-- fs/btrfs/props.c | 2 +- fs/btrfs/qgroup.c | 2 +- fs/btrfs/scrub.c | 2 +- fs/btrfs/send.c | 2 +- fs/btrfs/space-info.c | 4 ++-- fs/btrfs/tests/extent-map-tests.c | 2 +- fs/btrfs/volumes.c | 8 ++++---- fs/btrfs/zoned.c | 4 ++-- include/uapi/linux/btrfs.h | 4 ++-- include/uapi/linux/btrfs_tree.h | 4 ++-- 21 files changed, 32 insertions(+), 32 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 117d423fdb93..7a8a2fc19533 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -2675,7 +2675,7 @@ static int handle_direct_tree_backref(struct btrfs_backref_cache *cache, * * @ref_key: The same as @ref_key in handle_direct_tree_backref() * @tree_key: The first key of this tree block. - * @path: A clean (released) path, to avoid allocating path everytime + * @path: A clean (released) path, to avoid allocating path every time * the function get called. */ static int handle_indirect_tree_backref(struct btrfs_backref_cache *cache, diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 82e58f2fbe0a..cbdabecffb05 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2757,9 +2757,9 @@ enum btrfs_reserve_flush_enum { /* * Flush space by above mentioned methods and by: * - Running delayed iputs - * - Commiting transaction + * - Committing transaction * - * Can be interruped by fatal signal. + * Can be interrupted by a fatal signal. */ BTRFS_RESERVE_FLUSH_DATA, BTRFS_RESERVE_FLUSH_FREE_SPACE_INODE, @@ -2769,7 +2769,7 @@ enum btrfs_reserve_flush_enum { * Pretty much the same as FLUSH_ALL, but can also steal space from * global rsv. * - * Can be interruped by fatal signal. + * Can be interrupted by a fatal signal. */ BTRFS_RESERVE_FLUSH_ALL_STEAL, }; diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 56642ca7af10..2059d1504149 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -89,7 +89,7 @@ * ->outstanding_extents += 1 (current value is 1) * * -> set_delalloc - * ->outstanding_extents += 1 (currrent value is 2) + * ->outstanding_extents += 1 (current value is 2) * * -> btrfs_delalloc_release_extents() * ->outstanding_extents -= 1 (current value is 1) diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index d05f73530af7..d029be40ea6f 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -37,7 +37,7 @@ * - Write duplication * * All new writes will be written to both target and source devices, so even - * if replace gets canceled, sources device still contans up-to-date data. + * if replace gets canceled, sources device still contains up-to-date data. * * Location: handle_ops_on_dev_replace() from __btrfs_map_block() * Start: btrfs_dev_replace_start() diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c index 306ff20af70f..e1b7bd927d69 100644 --- a/fs/btrfs/discard.c +++ b/fs/btrfs/discard.c @@ -624,7 +624,7 @@ void btrfs_discard_update_discardable(struct btrfs_block_group *block_group) * @fs_info: fs_info of interest * * The unused_bgs list needs to be punted to the discard lists because the - * order of operations is changed. In the normal sychronous discard path, the + * order of operations is changed. In the normal synchronous discard path, the * block groups are trimmed via a single large trim in transaction commit. This * is ultimately what we are trying to avoid with asynchronous discard. Thus, * it must be done before going down the unused_bgs path. diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index d1d5091a8385..544bb7a82e57 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3471,7 +3471,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device * At this point we know all the devices that make this filesystem, * including the seed devices but we don't know yet if the replace * target is required. So free devices that are not part of this - * filesystem but skip the replace traget device which is checked + * filesystem but skip the replace target device which is checked * below in btrfs_init_dev_replace(). */ btrfs_free_extra_devids(fs_devices); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d2f39a122d89..421120d6a14b 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1425,7 +1425,7 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, * bytenr of the parent block. Since new extents are always * created with indirect references, this will only be the case * when relocating a shared extent. In that case, root_objectid - * will be BTRFS_TREE_RELOC_OBJECTID. Otheriwse, parent must + * will be BTRFS_TREE_RELOC_OBJECTID. Otherwise, parent must * be 0 * * @root_objectid: The id of the root where this modification has originated, diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 441cee7fbb62..df6631eefc65 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -618,7 +618,7 @@ fail: * @file_start: offset in file this bio begins to describe * @contig: Boolean. If true/1 means all bio vecs in this bio are * contiguous and they begin at @file_start in the file. False/0 - * means this bio can contains potentially discontigous bio vecs + * means this bio can contain potentially discontiguous bio vecs * so the logical offset of each should be calculated separately. */ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 794d906cba6c..a2494c645681 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2784,7 +2784,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, /* * If we dropped an inline extent here, we know the range where it is * was not marked with the EXTENT_DELALLOC_NEW bit, so we update the - * number of bytes only for that range contaning the inline extent. + * number of bytes only for that range containing the inline extent. * The remaining of the range will be processed when clearning the * EXTENT_DELALLOC_BIT bit through the ordered extent completion. */ @@ -4114,7 +4114,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, * This is a placeholder inode for a subvolume we didn't have a * reference to at the time of the snapshot creation. In the meantime * we could have renamed the real subvol link into our snapshot, so - * depending on btrfs_del_root_ref to return -ENOENT here is incorret. + * depending on btrfs_del_root_ref to return -ENOENT here is incorrect. * Instead simply lookup the dir_index_item for this entry so we can * remove it. Otherwise we know we have a ref to the root and we can * call btrfs_del_root_ref, and it _shouldn't_ fail. diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index f83eb4a225cc..0ba98e08a029 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2984,7 +2984,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, err = PTR_ERR(subvol_name_ptr); goto free_parent; } - /* subvol_name_ptr is already NULL termined */ + /* subvol_name_ptr is already nul terminated */ subvol_name = (char *)kbasename(subvol_name_ptr); } } else { diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 5fafc5e89bb7..313d9d685adb 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -57,7 +57,7 @@ void btrfs_tree_read_lock(struct extent_buffer *eb) /* * Try-lock for read. * - * Retrun 1 if the rwlock has been taken, 0 otherwise + * Return 1 if the rwlock has been taken, 0 otherwise */ int btrfs_try_tree_read_lock(struct extent_buffer *eb) { @@ -72,7 +72,7 @@ int btrfs_try_tree_read_lock(struct extent_buffer *eb) /* * Try-lock for write. * - * Retrun 1 if the rwlock has been taken, 0 otherwise + * Return 1 if the rwlock has been taken, 0 otherwise */ int btrfs_try_tree_write_lock(struct extent_buffer *eb) { diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index 2dcb1cb21634..a17e53e700b1 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -348,7 +348,7 @@ static int inherit_props(struct btrfs_trans_handle *trans, /* * This is not strictly necessary as the property should be - * valid, but in case it isn't, don't propagate it futher. + * valid, but in case it isn't, don't propagate it further. */ ret = h->validate(value, strlen(value)); if (ret) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 3ded812f522c..d72885903b8c 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2521,7 +2521,7 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr, int ret = 0; /* - * If quotas get disabled meanwhile, the resouces need to be freed and + * If quotas get disabled meanwhile, the resources need to be freed and * we can't just exit here. */ if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index b60466db5654..088641ba7a8e 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2486,7 +2486,7 @@ static void drop_csum_range(struct scrub_ctx *sctx, struct btrfs_ordered_sum *su * the csum into @csum. * * The search source is sctx->csum_list, which is a pre-populated list - * storing bytenr ordered csum ranges. We're reponsible to cleanup any range + * storing bytenr ordered csum ranges. We're responsible to cleanup any range * that is before @logical. * * Return 0 if there is no csum for the range. diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 974274c7e26e..6e69302828ef 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6514,7 +6514,7 @@ static int changed_extent(struct send_ctx *sctx, * updates the inode item, but it only changes the iversion (sequence * field in the inode item) of the inode, so if a file is deduplicated * the same amount of times in both the parent and send snapshots, its - * iversion becames the same in both snapshots, whence the inode item is + * iversion becomes the same in both snapshots, whence the inode item is * the same on both snapshots. */ if (sctx->cur_ino != sctx->cmp_key->objectid) diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 42d0fa2092d4..f26fdb7a17e8 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -389,7 +389,7 @@ again: ticket = list_first_entry(head, struct reserve_ticket, list); - /* Check and see if our ticket can be satisified now. */ + /* Check and see if our ticket can be satisfied now. */ if ((used + ticket->bytes <= space_info->total_bytes) || btrfs_can_overcommit(fs_info, space_info, ticket->bytes, flush)) { @@ -961,7 +961,7 @@ static bool maybe_fail_all_tickets(struct btrfs_fs_info *fs_info, * if it doesn't feel like the space reclaimed by the commit * would result in the ticket succeeding. However if we have a * smaller ticket in the queue it may be small enough to be - * satisified by committing the transaction, so if any + * satisfied by committing the transaction, so if any * subsequent ticket is smaller than the first ticket go ahead * and send us back for another loop through the enospc flushing * code. diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c index c0aefe6dee0b..319fed82d741 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -557,7 +557,7 @@ int btrfs_test_extent_map(void) { /* * Test a chunk with 2 data stripes one of which - * interesects the physical address of the super block + * intersects the physical address of the super block * is correctly recognised. */ .raid_type = BTRFS_BLOCK_GROUP_RAID1, diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 80e962788396..582695cee9d1 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -717,7 +717,7 @@ static struct btrfs_fs_devices *find_fsid_changed( /* * Handles the case where scanned device is part of an fs that had - * multiple successful changes of FSID but curently device didn't + * multiple successful changes of FSID but currently device didn't * observe it. Meaning our fsid will be different than theirs. We need * to handle two subcases : * 1 - The fs still continues to have different METADATA/FSID uuids. @@ -1550,7 +1550,7 @@ static bool dev_extent_hole_check(struct btrfs_device *device, u64 *hole_start, * check to ensure dev extents are not double allocated. * This makes the function safe to allocate dev extents but may not report * correct usable device space, as device extent freed in current transaction - * is not reported as avaiable. + * is not reported as available. */ static int find_free_dev_extent_start(struct btrfs_device *device, u64 num_bytes, u64 search_start, u64 *start, @@ -6152,7 +6152,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *em, offset = logical - em->start; /* Len of a stripe in a chunk */ stripe_len = map->stripe_len; - /* Stripe wher this block falls in */ + /* Stripe where this block falls in */ stripe_nr = div64_u64(offset, stripe_len); /* Offset of stripe in the chunk */ stripe_offset = stripe_nr * stripe_len; @@ -7863,7 +7863,7 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info, ret = -EUCLEAN; } - /* Make sure no dev extent is beyond device bondary */ + /* Make sure no dev extent is beyond device boundary */ dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL); if (!dev) { btrfs_err(fs_info, "failed to find devid %llu", devid); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 549912120cfe..297c0b1c0634 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -81,7 +81,7 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones, * *: Special case, no superblock is written * 0: Use write pointer of zones[0] * 1: Use write pointer of zones[1] - * C: Compare super blcoks from zones[0] and zones[1], use the latest + * C: Compare super blocks from zones[0] and zones[1], use the latest * one determined by generation * x: Invalid state */ @@ -433,7 +433,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device) } /* - * If zones[0] is conventional, always use the beggining of the + * If zones[0] is conventional, always use the beginning of the * zone to record superblock. No need to validate in that case. */ if (zone_info->sb_zones[BTRFS_NR_SB_LOG_ZONES * i].type == diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 5df73001aad4..22cd037123fa 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -154,7 +154,7 @@ struct btrfs_scrub_progress { __u64 tree_bytes_scrubbed; /* # of tree bytes scrubbed */ __u64 read_errors; /* # of read errors encountered (EIO) */ __u64 csum_errors; /* # of failed csum checks */ - __u64 verify_errors; /* # of occurences, where the metadata + __u64 verify_errors; /* # of occurrences, where the metadata * of a tree block did not match the * expected values, like generation or * logical */ @@ -174,7 +174,7 @@ struct btrfs_scrub_progress { __u64 last_physical; /* last physical address scrubbed. In * case a scrub was aborted, this can * be used to restart the scrub */ - __u64 unverified_errors; /* # of occurences where a read for a + __u64 unverified_errors; /* # of occurrences where a read for a * full (64k) bio failed, but the re- * check succeeded for each 4k piece. * Intermittent error. */ diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 58d7cff9afb1..ccdb40fe40dc 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -59,7 +59,7 @@ /* for storing balance parameters in the root tree */ #define BTRFS_BALANCE_OBJECTID -4ULL -/* orhpan objectid for tracking unlinked/truncated files */ +/* orphan objectid for tracking unlinked/truncated files */ #define BTRFS_ORPHAN_OBJECTID -5ULL /* does write ahead logging to speed up fsyncs */ @@ -275,7 +275,7 @@ #define BTRFS_PERSISTENT_ITEM_KEY 249 /* - * Persistantly stores the device replace state in the device tree. + * Persistently stores the device replace state in the device tree. * The key is built like this: (0, BTRFS_DEV_REPLACE_KEY, 0). */ #define BTRFS_DEV_REPLACE_KEY 250 -- cgit v1.3-18-gd494 From ea7fc1bb1cd1b92b42b1d9273ce7e231d3dc9321 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 21 Jun 2021 12:17:12 +0100 Subject: KVM: arm64: Introduce MTE VM feature Add a new VM feature 'KVM_ARM_CAP_MTE' which enables memory tagging for a VM. This will expose the feature to the guest and automatically tag memory pages touched by the VM as PG_mte_tagged (and clear the tag storage) to ensure that the guest cannot see stale tags, and so that the tags are correctly saved/restored across swap. Actually exposing the new capability to user space happens in a later patch. Reviewed-by: Catalin Marinas Signed-off-by: Steven Price [maz: move VM_SHARED sampling into the critical section] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210621111716.37157-3-steven.price@arm.com --- arch/arm64/include/asm/kvm_emulate.h | 3 ++ arch/arm64/include/asm/kvm_host.h | 4 +++ arch/arm64/kvm/hyp/exception.c | 3 +- arch/arm64/kvm/mmu.c | 67 +++++++++++++++++++++++++++++++++++- arch/arm64/kvm/sys_regs.c | 7 ++++ include/uapi/linux/kvm.h | 1 + 6 files changed, 83 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 01b9857757f2..fd418955e31e 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -84,6 +84,9 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) || vcpu_el1_is_32bit(vcpu)) vcpu->arch.hcr_el2 |= HCR_TID2; + + if (kvm_has_mte(vcpu->kvm)) + vcpu->arch.hcr_el2 |= HCR_ATA; } static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7cd7d5c8c4bc..1c4293c46ef6 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -132,6 +132,9 @@ struct kvm_arch { u8 pfr0_csv2; u8 pfr0_csv3; + + /* Memory Tagging Extension enabled for the guest */ + bool mte_enabled; }; struct kvm_vcpu_fault_info { @@ -769,6 +772,7 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu); #define kvm_arm_vcpu_sve_finalized(vcpu) \ ((vcpu)->arch.flags & KVM_ARM64_VCPU_SVE_FINALIZED) +#define kvm_has_mte(kvm) (system_supports_mte() && (kvm)->arch.mte_enabled) #define kvm_vcpu_has_pmu(vcpu) \ (test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features)) diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index 11541b94b328..0418399e0a20 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -112,7 +112,8 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, new |= (old & PSR_C_BIT); new |= (old & PSR_V_BIT); - // TODO: TCO (if/when ARMv8.5-MemTag is exposed to guests) + if (kvm_has_mte(vcpu->kvm)) + new |= PSR_TCO_BIT; new |= (old & PSR_DIT_BIT); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index c10207fed2f3..c6a97d463892 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -822,6 +822,45 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot, return PAGE_SIZE; } +/* + * The page will be mapped in stage 2 as Normal Cacheable, so the VM will be + * able to see the page's tags and therefore they must be initialised first. If + * PG_mte_tagged is set, tags have already been initialised. + * + * The race in the test/set of the PG_mte_tagged flag is handled by: + * - preventing VM_SHARED mappings in a memslot with MTE preventing two VMs + * racing to santise the same page + * - mmap_lock protects between a VM faulting a page in and the VMM performing + * an mprotect() to add VM_MTE + */ +static int sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn, + unsigned long size) +{ + unsigned long i, nr_pages = size >> PAGE_SHIFT; + struct page *page; + + if (!kvm_has_mte(kvm)) + return 0; + + /* + * pfn_to_online_page() is used to reject ZONE_DEVICE pages + * that may not support tags. + */ + page = pfn_to_online_page(pfn); + + if (!page) + return -EFAULT; + + for (i = 0; i < nr_pages; i++, page++) { + if (!test_bit(PG_mte_tagged, &page->flags)) { + mte_clear_page_tags(page_address(page)); + set_bit(PG_mte_tagged, &page->flags); + } + } + + return 0; +} + static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_memory_slot *memslot, unsigned long hva, unsigned long fault_status) @@ -830,6 +869,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, bool write_fault, writable, force_pte = false; bool exec_fault; bool device = false; + bool shared; unsigned long mmu_seq; struct kvm *kvm = vcpu->kvm; struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; @@ -873,6 +913,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, vma_shift = PAGE_SHIFT; } + shared = (vma->vm_flags & VM_PFNMAP); + switch (vma_shift) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SHIFT: @@ -971,8 +1013,18 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (writable) prot |= KVM_PGTABLE_PROT_W; - if (fault_status != FSC_PERM && !device) + if (fault_status != FSC_PERM && !device) { + /* Check the VMM hasn't introduced a new VM_SHARED VMA */ + if (kvm_has_mte(kvm) && shared) { + ret = -EFAULT; + goto out_unlock; + } + ret = sanitise_mte_tags(kvm, pfn, vma_pagesize); + if (ret) + goto out_unlock; + clean_dcache_guest_page(pfn, vma_pagesize); + } if (exec_fault) { prot |= KVM_PGTABLE_PROT_X; @@ -1168,12 +1220,17 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { kvm_pfn_t pfn = pte_pfn(range->pte); + int ret; if (!kvm->arch.mmu.pgt) return false; WARN_ON(range->end - range->start != 1); + ret = sanitise_mte_tags(kvm, pfn, PAGE_SIZE); + if (ret) + return false; + /* * We've moved a page around, probably through CoW, so let's treat it * just like a translation fault and clean the cache to the PoC. @@ -1381,6 +1438,14 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (!vma) break; + /* + * VM_SHARED mappings are not allowed with MTE to avoid races + * when updating the PG_mte_tagged page flag, see + * sanitise_mte_tags for more details. + */ + if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED) + return -EINVAL; + /* * Take the intersection of this VMA with the memory region */ diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 1a7968ad078c..36f67f8deae1 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1047,6 +1047,13 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, break; case SYS_ID_AA64PFR1_EL1: val &= ~FEATURE(ID_AA64PFR1_MTE); + if (kvm_has_mte(vcpu->kvm)) { + u64 pfr, mte; + + pfr = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); + mte = cpuid_feature_extract_unsigned_field(pfr, ID_AA64PFR1_MTE_SHIFT); + val |= FIELD_PREP(FEATURE(ID_AA64PFR1_MTE), mte); + } break; case SYS_ID_AA64ISAR1_EL1: if (!vcpu_has_ptrauth(vcpu)) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 79d9c44d1ad7..d4da58ddcad7 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1083,6 +1083,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_SGX_ATTRIBUTE 196 #define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197 #define KVM_CAP_PTP_KVM 198 +#define KVM_CAP_ARM_MTE 199 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.3-18-gd494 From f0376edb1ddcab19a473b4bf1fbd5b6bbed3705b Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 21 Jun 2021 12:17:15 +0100 Subject: KVM: arm64: Add ioctl to fetch/store tags in a guest The VMM may not wish to have it's own mapping of guest memory mapped with PROT_MTE because this causes problems if the VMM has tag checking enabled (the guest controls the tags in physical RAM and it's unlikely the tags are correct for the VMM). Instead add a new ioctl which allows the VMM to easily read/write the tags from guest memory, allowing the VMM's mapping to be non-PROT_MTE while the VMM can still read/write the tags for the purpose of migration. Reviewed-by: Catalin Marinas Signed-off-by: Steven Price Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210621111716.37157-6-steven.price@arm.com --- arch/arm64/include/asm/kvm_host.h | 3 ++ arch/arm64/include/asm/mte-def.h | 1 + arch/arm64/include/uapi/asm/kvm.h | 11 ++++++ arch/arm64/kvm/arm.c | 7 ++++ arch/arm64/kvm/guest.c | 82 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 1 + 6 files changed, 105 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 74a7447a83a1..c93a7198c242 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -730,6 +730,9 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); +long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, + struct kvm_arm_copy_mte_tags *copy_tags); + /* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/mte-def.h b/arch/arm64/include/asm/mte-def.h index cf241b0f0a42..626d359b396e 100644 --- a/arch/arm64/include/asm/mte-def.h +++ b/arch/arm64/include/asm/mte-def.h @@ -7,6 +7,7 @@ #define MTE_GRANULE_SIZE UL(16) #define MTE_GRANULE_MASK (~(MTE_GRANULE_SIZE - 1)) +#define MTE_GRANULES_PER_PAGE (PAGE_SIZE / MTE_GRANULE_SIZE) #define MTE_TAG_SHIFT 56 #define MTE_TAG_SIZE 4 #define MTE_TAG_MASK GENMASK((MTE_TAG_SHIFT + (MTE_TAG_SIZE - 1)), MTE_TAG_SHIFT) diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 24223adae150..b3edde68bc3e 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -184,6 +184,17 @@ struct kvm_vcpu_events { __u32 reserved[12]; }; +struct kvm_arm_copy_mte_tags { + __u64 guest_ipa; + __u64 length; + void __user *addr; + __u64 flags; + __u64 reserved[2]; +}; + +#define KVM_ARM_TAGS_TO_GUEST 0 +#define KVM_ARM_TAGS_FROM_GUEST 1 + /* If you need to interpret the index values, here is the key: */ #define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 #define KVM_REG_ARM_COPROC_SHIFT 16 diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 28ce26a68f09..511f3716fe33 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1359,6 +1359,13 @@ long kvm_arch_vm_ioctl(struct file *filp, return 0; } + case KVM_ARM_MTE_COPY_TAGS: { + struct kvm_arm_copy_mte_tags copy_tags; + + if (copy_from_user(©_tags, argp, sizeof(copy_tags))) + return -EFAULT; + return kvm_vm_ioctl_mte_copy_tags(kvm, ©_tags); + } default: return -EINVAL; } diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 5cb4a1cd5603..4ddb20017b2f 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -995,3 +995,85 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, return ret; } + +long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, + struct kvm_arm_copy_mte_tags *copy_tags) +{ + gpa_t guest_ipa = copy_tags->guest_ipa; + size_t length = copy_tags->length; + void __user *tags = copy_tags->addr; + gpa_t gfn; + bool write = !(copy_tags->flags & KVM_ARM_TAGS_FROM_GUEST); + int ret = 0; + + if (!kvm_has_mte(kvm)) + return -EINVAL; + + if (copy_tags->reserved[0] || copy_tags->reserved[1]) + return -EINVAL; + + if (copy_tags->flags & ~KVM_ARM_TAGS_FROM_GUEST) + return -EINVAL; + + if (length & ~PAGE_MASK || guest_ipa & ~PAGE_MASK) + return -EINVAL; + + gfn = gpa_to_gfn(guest_ipa); + + mutex_lock(&kvm->slots_lock); + + while (length > 0) { + kvm_pfn_t pfn = gfn_to_pfn_prot(kvm, gfn, write, NULL); + void *maddr; + unsigned long num_tags; + struct page *page; + + if (is_error_noslot_pfn(pfn)) { + ret = -EFAULT; + goto out; + } + + page = pfn_to_online_page(pfn); + if (!page) { + /* Reject ZONE_DEVICE memory */ + ret = -EFAULT; + goto out; + } + maddr = page_address(page); + + if (!write) { + if (test_bit(PG_mte_tagged, &page->flags)) + num_tags = mte_copy_tags_to_user(tags, maddr, + MTE_GRANULES_PER_PAGE); + else + /* No tags in memory, so write zeros */ + num_tags = MTE_GRANULES_PER_PAGE - + clear_user(tags, MTE_GRANULES_PER_PAGE); + kvm_release_pfn_clean(pfn); + } else { + num_tags = mte_copy_tags_from_user(maddr, tags, + MTE_GRANULES_PER_PAGE); + kvm_release_pfn_dirty(pfn); + } + + if (num_tags != MTE_GRANULES_PER_PAGE) { + ret = -EFAULT; + goto out; + } + + /* Set the flag after checking the write completed fully */ + if (write) + set_bit(PG_mte_tagged, &page->flags); + + gfn++; + tags += num_tags; + length -= PAGE_SIZE; + } + +out: + mutex_unlock(&kvm->slots_lock); + /* If some data has been copied report the number of bytes copied */ + if (length != copy_tags->length) + return copy_tags->length - length; + return ret; +} diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d4da58ddcad7..da1edd2b4046 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1429,6 +1429,7 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_PMU_EVENT_FILTER */ #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) #define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) +#define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) -- cgit v1.3-18-gd494 From b87cc116c7e1bc62a84d8c46acd401db179edb11 Mon Sep 17 00:00:00 2001 From: Bharata B Rao Date: Mon, 21 Jun 2021 14:20:02 +0530 Subject: KVM: PPC: Book3S HV: Add KVM_CAP_PPC_RPT_INVALIDATE capability Now that we have H_RPT_INVALIDATE fully implemented, enable support for the same via KVM_CAP_PPC_RPT_INVALIDATE KVM capability Signed-off-by: Bharata B Rao Reviewed-by: David Gibson Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210621085003.904767-6-bharata@linux.ibm.com --- Documentation/virt/kvm/api.rst | 18 ++++++++++++++++++ arch/powerpc/kvm/powerpc.c | 3 +++ include/uapi/linux/kvm.h | 1 + 3 files changed, 22 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 7fcb2fd38f42..9977e845633f 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6362,6 +6362,24 @@ default. See Documentation/x86/sgx/2.Kernel-internals.rst for more details. +7.26 KVM_CAP_PPC_RPT_INVALIDATE +------------------------------- + +:Capability: KVM_CAP_PPC_RPT_INVALIDATE +:Architectures: ppc +:Type: vm + +This capability indicates that the kernel is capable of handling +H_RPT_INVALIDATE hcall. + +In order to enable the use of H_RPT_INVALIDATE in the guest, +user space might have to advertise it for the guest. For example, +IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is +present in the "ibm,hypertas-functions" device-tree property. + +This capability is enabled for hypervisors on platforms like POWER9 +that support radix MMU. + 8. Other capabilities. ====================== diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index a2a68a958fa0..be33b5321a76 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -682,6 +682,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = !!(hv_enabled && kvmppc_hv_ops->enable_dawr1 && !kvmppc_hv_ops->enable_dawr1(NULL)); break; + case KVM_CAP_PPC_RPT_INVALIDATE: + r = 1; + break; #endif default: r = 0; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 3fd9a7e9d90c..613198a94c43 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1082,6 +1082,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_SGX_ATTRIBUTE 196 #define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197 #define KVM_CAP_PTP_KVM 198 +#define KVM_CAP_PPC_RPT_INVALIDATE 199 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.3-18-gd494 From bf22a6976897977b0a3f1aeba6823c959fc4fdae Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 22 Apr 2021 21:44:23 +0200 Subject: futex: Provide FUTEX_LOCK_PI2 to support clock selection The FUTEX_LOCK_PI futex operand uses a CLOCK_REALTIME based absolute timeout since it was implemented, but it does not require that the FUTEX_CLOCK_REALTIME flag is set, because that was introduced later. In theory as none of the user space implementations can set the FUTEX_CLOCK_REALTIME flag on this operand, it would be possible to creatively abuse it and make the meaning invers, i.e. select CLOCK_REALTIME when not set and CLOCK_MONOTONIC when set. But that's a nasty hackery. Another option would be to have a new FUTEX_CLOCK_MONOTONIC flag only for FUTEX_LOCK_PI, but that's also awkward because it does not allow libraries to handle the timeout clock selection consistently. So provide a new FUTEX_LOCK_PI2 operand which implements the timeout semantics which the other operands use and leave FUTEX_LOCK_PI alone. Reported-by: Kurt Kanzenbach Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210422194705.440773992@linutronix.de --- include/uapi/linux/futex.h | 2 ++ kernel/futex.c | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index a89eb0accd5e..235e5b2facaa 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -21,6 +21,7 @@ #define FUTEX_WAKE_BITSET 10 #define FUTEX_WAIT_REQUEUE_PI 11 #define FUTEX_CMP_REQUEUE_PI 12 +#define FUTEX_LOCK_PI2 13 #define FUTEX_PRIVATE_FLAG 128 #define FUTEX_CLOCK_REALTIME 256 @@ -32,6 +33,7 @@ #define FUTEX_CMP_REQUEUE_PRIVATE (FUTEX_CMP_REQUEUE | FUTEX_PRIVATE_FLAG) #define FUTEX_WAKE_OP_PRIVATE (FUTEX_WAKE_OP | FUTEX_PRIVATE_FLAG) #define FUTEX_LOCK_PI_PRIVATE (FUTEX_LOCK_PI | FUTEX_PRIVATE_FLAG) +#define FUTEX_LOCK_PI2_PRIVATE (FUTEX_LOCK_PI2 | FUTEX_PRIVATE_FLAG) #define FUTEX_UNLOCK_PI_PRIVATE (FUTEX_UNLOCK_PI | FUTEX_PRIVATE_FLAG) #define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG) #define FUTEX_WAIT_BITSET_PRIVATE (FUTEX_WAIT_BITSET | FUTEX_PRIVATE_FLAG) diff --git a/kernel/futex.c b/kernel/futex.c index f820439a8aae..f832b6434625 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -3707,12 +3707,14 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, if (op & FUTEX_CLOCK_REALTIME) { flags |= FLAGS_CLOCKRT; - if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI) + if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI && + cmd != FUTEX_LOCK_PI2) return -ENOSYS; } switch (cmd) { case FUTEX_LOCK_PI: + case FUTEX_LOCK_PI2: case FUTEX_UNLOCK_PI: case FUTEX_TRYLOCK_PI: case FUTEX_WAIT_REQUEUE_PI: @@ -3740,6 +3742,8 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); case FUTEX_LOCK_PI: flags |= FLAGS_CLOCKRT; + fallthrough; + case FUTEX_LOCK_PI2: return futex_lock_pi(uaddr, flags, timeout, 0); case FUTEX_UNLOCK_PI: return futex_unlock_pi(uaddr, flags); @@ -3760,6 +3764,7 @@ static __always_inline bool futex_cmd_has_timeout(u32 cmd) switch (cmd) { case FUTEX_WAIT: case FUTEX_LOCK_PI: + case FUTEX_LOCK_PI2: case FUTEX_WAIT_BITSET: case FUTEX_WAIT_REQUEUE_PI: return true; -- cgit v1.3-18-gd494 From cb082bfab59a224a49ae803fed52cd03e8d6b5e0 Mon Sep 17 00:00:00 2001 From: Jing Zhang Date: Fri, 18 Jun 2021 22:27:04 +0000 Subject: KVM: stats: Add fd-based API to read binary stats data This commit defines the API for userspace and prepare the common functionalities to support per VM/VCPU binary stats data readings. The KVM stats now is only accessible by debugfs, which has some shortcomings this change series are supposed to fix: 1. The current debugfs stats solution in KVM could be disabled when kernel Lockdown mode is enabled, which is a potential rick for production. 2. The current debugfs stats solution in KVM is organized as "one stats per file", it is good for debugging, but not efficient for production. 3. The stats read/clear in current debugfs solution in KVM are protected by the global kvm_lock. Besides that, there are some other benefits with this change: 1. All KVM VM/VCPU stats can be read out in a bulk by one copy to userspace. 2. A schema is used to describe KVM statistics. From userspace's perspective, the KVM statistics are self-describing. 3. With the fd-based solution, a separate telemetry would be able to read KVM stats in a less privileged environment. 4. After the initial setup by reading in stats descriptors, a telemetry only needs to read the stats data itself, no more parsing or setup is needed. Reviewed-by: David Matlack Reviewed-by: Ricardo Koller Reviewed-by: Krish Sadhukhan Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba #arm64 Signed-off-by: Jing Zhang Message-Id: <20210618222709.1858088-3-jingzhangos@google.com> Signed-off-by: Paolo Bonzini --- arch/arm64/kvm/Makefile | 2 +- arch/mips/kvm/Makefile | 2 +- arch/powerpc/kvm/Makefile | 2 +- arch/s390/kvm/Makefile | 3 +- arch/x86/kvm/Makefile | 2 +- include/linux/kvm_host.h | 82 +++++++++++++++++++++++++- include/linux/kvm_types.h | 2 + include/uapi/linux/kvm.h | 73 +++++++++++++++++++++++ virt/kvm/binary_stats.c | 146 ++++++++++++++++++++++++++++++++++++++++++++++ 9 files changed, 307 insertions(+), 7 deletions(-) create mode 100644 virt/kvm/binary_stats.c (limited to 'include/uapi/linux') diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 589921392cb1..989bb5dad2c8 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -11,7 +11,7 @@ obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM) += hyp/ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ - $(KVM)/vfio.o $(KVM)/irqchip.o \ + $(KVM)/vfio.o $(KVM)/irqchip.o $(KVM)/binary_stats.o \ arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \ inject_fault.o va_layout.o handle_exit.o \ guest.o debug.o reset.o sys_regs.o \ diff --git a/arch/mips/kvm/Makefile b/arch/mips/kvm/Makefile index 30cc060857c7..c67250a956b8 100644 --- a/arch/mips/kvm/Makefile +++ b/arch/mips/kvm/Makefile @@ -2,7 +2,7 @@ # Makefile for KVM support for MIPS # -common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o eventfd.o) +common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o eventfd.o binary_stats.o) EXTRA_CFLAGS += -Ivirt/kvm -Iarch/mips/kvm diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index ab241317481c..583c14ef596e 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -6,7 +6,7 @@ ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm KVM := ../../../virt/kvm -common-objs-y = $(KVM)/kvm_main.o $(KVM)/eventfd.o +common-objs-y = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/binary_stats.o common-objs-$(CONFIG_KVM_VFIO) += $(KVM)/vfio.o common-objs-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index 12decca22e7c..b3aaadc60ead 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -4,7 +4,8 @@ # Copyright IBM Corp. 2008 KVM := ../../../virt/kvm -common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o +common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o \ + $(KVM)/irqchip.o $(KVM)/vfio.o $(KVM)/binary_stats.o ccflags-y := -Ivirt/kvm -Iarch/s390/kvm diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 83331376b779..75dfd27b6e8a 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -11,7 +11,7 @@ KVM := ../../../virt/kvm kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o \ - $(KVM)/dirty_ring.o + $(KVM)/dirty_ring.o $(KVM)/binary_stats.o kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 37cbb56ccd09..9ee7f350473b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1272,16 +1272,94 @@ struct kvm_stats_debugfs_item { int mode; }; +struct _kvm_stats_desc { + struct kvm_stats_desc desc; + char name[KVM_STATS_NAME_SIZE]; +}; + #define KVM_DBGFS_GET_MODE(dbgfs_item) \ ((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644) -#define VM_STAT(n, x, ...) \ +#define VM_STAT(n, x, ...) \ { n, offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ } -#define VCPU_STAT(n, x, ...) \ +#define VCPU_STAT(n, x, ...) \ { n, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ } +#define STATS_DESC_COMMON(type, unit, base, exp) \ + .flags = type | unit | base | \ + BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ + BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ + BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ + .exponent = exp, \ + .size = 1 + +#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp), \ + .offset = offsetof(struct kvm_vm_stat, generic.stat) \ + }, \ + .name = #stat, \ + } +#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp), \ + .offset = offsetof(struct kvm_vcpu_stat, generic.stat) \ + }, \ + .name = #stat, \ + } +#define VM_STATS_DESC(stat, type, unit, base, exp) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp), \ + .offset = offsetof(struct kvm_vm_stat, stat) \ + }, \ + .name = #stat, \ + } +#define VCPU_STATS_DESC(stat, type, unit, base, exp) \ + { \ + { \ + STATS_DESC_COMMON(type, unit, base, exp), \ + .offset = offsetof(struct kvm_vcpu_stat, stat) \ + }, \ + .name = #stat, \ + } +/* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ +#define STATS_DESC(SCOPE, stat, type, unit, base, exp) \ + SCOPE##_STATS_DESC(stat, type, unit, base, exp) + +#define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, unit, base, exponent) +#define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, unit, base, exponent) +#define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent) \ + STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, unit, base, exponent) + +/* Cumulative counter, read/write */ +#define STATS_DESC_COUNTER(SCOPE, name) \ + STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) +/* Instantaneous counter, read only */ +#define STATS_DESC_ICOUNTER(SCOPE, name) \ + STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) +/* Peak counter, read/write */ +#define STATS_DESC_PCOUNTER(SCOPE, name) \ + STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE, \ + KVM_STATS_BASE_POW10, 0) + +/* Cumulative time in nanosecond */ +#define STATS_DESC_TIME_NSEC(SCOPE, name) \ + STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ + KVM_STATS_BASE_POW10, -9) + extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; +ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, + const struct _kvm_stats_desc *desc, + void *stats, size_t size_stats, + char __user *user_buffer, size_t size, loff_t *offset); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 48db778291b7..ed6a985c5680 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -89,4 +89,6 @@ struct kvm_vcpu_stat_generic { u64 halt_poll_fail_ns; }; +#define KVM_STATS_NAME_SIZE 48 + #endif /* __KVM_TYPES_H__ */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 330835f1005b..f1ba602260f6 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1087,6 +1087,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_SREGS2 200 #define KVM_CAP_EXIT_HYPERCALL 201 #define KVM_CAP_PPC_RPT_INVALIDATE 202 +#define KVM_CAP_BINARY_STATS_FD 203 #ifdef KVM_CAP_IRQ_ROUTING @@ -1906,4 +1907,76 @@ struct kvm_dirty_gfn { #define KVM_BUS_LOCK_DETECTION_OFF (1 << 0) #define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1) +/** + * struct kvm_stats_header - Header of per vm/vcpu binary statistics data. + * @flags: Some extra information for header, always 0 for now. + * @name_size: The size in bytes of the memory which contains statistics + * name string including trailing '\0'. The memory is allocated + * at the send of statistics descriptor. + * @num_desc: The number of statistics the vm or vcpu has. + * @id_offset: The offset of the vm/vcpu stats' id string in the file pointed + * by vm/vcpu stats fd. + * @desc_offset: The offset of the vm/vcpu stats' descriptor block in the file + * pointd by vm/vcpu stats fd. + * @data_offset: The offset of the vm/vcpu stats' data block in the file + * pointed by vm/vcpu stats fd. + * + * This is the header userspace needs to read from stats fd before any other + * readings. It is used by userspace to discover all the information about the + * vm/vcpu's binary statistics. + * Userspace reads this header from the start of the vm/vcpu's stats fd. + */ +struct kvm_stats_header { + __u32 flags; + __u32 name_size; + __u32 num_desc; + __u32 id_offset; + __u32 desc_offset; + __u32 data_offset; +}; + +#define KVM_STATS_TYPE_SHIFT 0 +#define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_PEAK (0x2 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_PEAK + +#define KVM_STATS_UNIT_SHIFT 4 +#define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES + +#define KVM_STATS_BASE_SHIFT 8 +#define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) +#define KVM_STATS_BASE_POW10 (0x0 << KVM_STATS_BASE_SHIFT) +#define KVM_STATS_BASE_POW2 (0x1 << KVM_STATS_BASE_SHIFT) +#define KVM_STATS_BASE_MAX KVM_STATS_BASE_POW2 + +/** + * struct kvm_stats_desc - Descriptor of a KVM statistics. + * @flags: Annotations of the stats, like type, unit, etc. + * @exponent: Used together with @flags to determine the unit. + * @size: The number of data items for this stats. + * Every data item is of type __u64. + * @offset: The offset of the stats to the start of stat structure in + * struture kvm or kvm_vcpu. + * @unused: Unused field for future usage. Always 0 for now. + * @name: The name string for the stats. Its size is indicated by the + * &kvm_stats_header->name_size. + */ +struct kvm_stats_desc { + __u32 flags; + __s16 exponent; + __u16 size; + __u32 offset; + __u32 unused; + char name[]; +}; + +#define KVM_GET_STATS_FD _IO(KVMIO, 0xce) + #endif /* __LINUX_KVM_H */ diff --git a/virt/kvm/binary_stats.c b/virt/kvm/binary_stats.c new file mode 100644 index 000000000000..e609d428811a --- /dev/null +++ b/virt/kvm/binary_stats.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM binary statistics interface implementation + * + * Copyright 2021 Google LLC + */ + +#include +#include +#include +#include + +/** + * kvm_stats_read() - Common function to read from the binary statistics + * file descriptor. + * + * @id: identification string of the stats + * @header: stats header for a vm or a vcpu + * @desc: start address of an array of stats descriptors for a vm or a vcpu + * @stats: start address of stats data block for a vm or a vcpu + * @size_stats: the size of stats data block pointed by @stats + * @user_buffer: start address of userspace buffer + * @size: requested read size from userspace + * @offset: the start position from which the content will be read for the + * corresponding vm or vcp file descriptor + * + * The file content of a vm/vcpu file descriptor is now defined as below: + * +-------------+ + * | Header | + * +-------------+ + * | id string | + * +-------------+ + * | Descriptors | + * +-------------+ + * | Stats Data | + * +-------------+ + * Although this function allows userspace to read any amount of data (as long + * as in the limit) from any position, the typical usage would follow below + * steps: + * 1. Read header from offset 0. Get the offset of descriptors and stats data + * and some other necessary information. This is a one-time work for the + * lifecycle of the corresponding vm/vcpu stats fd. + * 2. Read id string from its offset. This is a one-time work for the lifecycle + * of the corresponding vm/vcpu stats fd. + * 3. Read descriptors from its offset and discover all the stats by parsing + * descriptors. This is a one-time work for the lifecycle of the + * corresponding vm/vcpu stats fd. + * 4. Periodically read stats data from its offset using pread. + * + * Return: the number of bytes that has been successfully read + */ +ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, + const struct _kvm_stats_desc *desc, + void *stats, size_t size_stats, + char __user *user_buffer, size_t size, loff_t *offset) +{ + ssize_t len; + ssize_t copylen; + ssize_t remain = size; + size_t size_desc; + size_t size_header; + void *src; + loff_t pos = *offset; + char __user *dest = user_buffer; + + size_header = sizeof(*header); + size_desc = header->num_desc * sizeof(*desc); + + len = KVM_STATS_NAME_SIZE + size_header + size_desc + size_stats - pos; + len = min(len, remain); + if (len <= 0) + return 0; + remain = len; + + /* + * Copy kvm stats header. + * The header is the first block of content userspace usually read out. + * The pos is 0 and the copylen and remain would be the size of header. + * The copy of the header would be skipped if offset is larger than the + * size of header. That usually happens when userspace reads stats + * descriptors and stats data. + */ + copylen = size_header - pos; + copylen = min(copylen, remain); + if (copylen > 0) { + src = (void *)header + pos; + if (copy_to_user(dest, src, copylen)) + return -EFAULT; + remain -= copylen; + pos += copylen; + dest += copylen; + } + + /* + * Copy kvm stats header id string. + * The id string is unique for every vm/vcpu, which is stored in kvm + * and kvm_vcpu structure. + * The id string is part of the stat header from the perspective of + * userspace, it is usually read out together with previous constant + * header part and could be skipped for later descriptors and stats + * data readings. + */ + copylen = header->id_offset + KVM_STATS_NAME_SIZE - pos; + copylen = min(copylen, remain); + if (copylen > 0) { + src = id + pos - header->id_offset; + if (copy_to_user(dest, src, copylen)) + return -EFAULT; + remain -= copylen; + pos += copylen; + dest += copylen; + } + + /* + * Copy kvm stats descriptors. + * The descriptors copy would be skipped in the typical case that + * userspace periodically read stats data, since the pos would be + * greater than the end address of descriptors + * (header->header.desc_offset + size_desc) causing copylen <= 0. + */ + copylen = header->desc_offset + size_desc - pos; + copylen = min(copylen, remain); + if (copylen > 0) { + src = (void *)desc + pos - header->desc_offset; + if (copy_to_user(dest, src, copylen)) + return -EFAULT; + remain -= copylen; + pos += copylen; + dest += copylen; + } + + /* Copy kvm stats values */ + copylen = header->data_offset + size_stats - pos; + copylen = min(copylen, remain); + if (copylen > 0) { + src = stats + pos - header->data_offset; + if (copy_to_user(dest, src, copylen)) + return -EFAULT; + remain -= copylen; + pos += copylen; + dest += copylen; + } + + *offset = pos; + return len; +} -- cgit v1.3-18-gd494 From 19238e75bd8ed8ffe784bf5b37586e77b2093742 Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Mon, 10 May 2021 07:48:33 -0700 Subject: kvm: x86: Allow userspace to handle emulation errors Add a fallback mechanism to the in-kernel instruction emulator that allows userspace the opportunity to process an instruction the emulator was unable to. When the in-kernel instruction emulator fails to process an instruction it will either inject a #UD into the guest or exit to userspace with exit reason KVM_INTERNAL_ERROR. This is because it does not know how to proceed in an appropriate manner. This feature lets userspace get involved to see if it can figure out a better path forward. Signed-off-by: Aaron Lewis Reviewed-by: David Edmondson Message-Id: <20210510144834.658457-2-aaronlewis@google.com> Reviewed-by: Jim Mattson Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 20 ++++++++++++++++++++ arch/x86/include/asm/kvm_host.h | 6 ++++++ arch/x86/kvm/x86.c | 40 ++++++++++++++++++++++++++++++++++++---- include/uapi/linux/kvm.h | 23 +++++++++++++++++++++++ 4 files changed, 85 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 5d8db4922df6..3b6e3b1628b4 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6546,6 +6546,7 @@ KVM_RUN_BUS_LOCK flag is used to distinguish between them. This capability can be used to check / enable 2nd DAWR feature provided by POWER10 processor. + 7.24 KVM_CAP_VM_COPY_ENC_CONTEXT_FROM ------------------------------------- @@ -6603,6 +6604,25 @@ present in the "ibm,hypertas-functions" device-tree property. This capability is enabled for hypervisors on platforms like POWER9 that support radix MMU. +7.27 KVM_CAP_EXIT_ON_EMULATION_FAILURE +-------------------------------------- + +:Architectures: x86 +:Parameters: args[0] whether the feature should be enabled or not + +When this capability is enabled, an emulation failure will result in an exit +to userspace with KVM_INTERNAL_ERROR (except when the emulator was invoked +to handle a VMware backdoor instruction). Furthermore, KVM will now provide up +to 15 instruction bytes for any exit to userspace resulting from an emulation +failure. When these exits to userspace occur use the emulation_failure struct +instead of the internal struct. They both have the same layout, but the +emulation_failure struct matches the content better. It also explicitly +defines the 'flags' field which is used to describe the fields in the struct +that are valid (ie: if KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES is +set in the 'flags' field then both 'insn_size' and 'insn_bytes' have valid data +in them.) + + 8. Other capabilities. ====================== diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3cd496c8acb8..c9ec5c76c438 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1114,6 +1114,12 @@ struct kvm_arch { bool exception_payload_enabled; bool bus_lock_detection_enabled; + /* + * If exit_on_emulation_error is set, and the in-kernel instruction + * emulator fails to emulate an instruction, allow userspace + * the opportunity to look at it. + */ + bool exit_on_emulation_error; /* Deflect RDMSR and WRMSR to user space when they trigger a #GP */ u32 user_space_msr_mask; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a7c7b2b28de7..17468d983fbd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4010,6 +4010,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) #endif case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: case KVM_CAP_SREGS2: + case KVM_CAP_EXIT_ON_EMULATION_FAILURE: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -5649,6 +5650,13 @@ split_irqchip_unlock: kvm->arch.hypercall_exit_enabled = cap->args[0]; r = 0; break; + case KVM_CAP_EXIT_ON_EMULATION_FAILURE: + r = -EINVAL; + if (cap->args[0] & ~1) + break; + kvm->arch.exit_on_emulation_error = cap->args[0]; + r = 0; + break; default: r = -EINVAL; break; @@ -7444,8 +7452,33 @@ void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) } EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt); +static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + u32 insn_size = ctxt->fetch.end - ctxt->fetch.data; + struct kvm_run *run = vcpu->run; + + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION; + run->emulation_failure.ndata = 0; + run->emulation_failure.flags = 0; + + if (insn_size) { + run->emulation_failure.ndata = 3; + run->emulation_failure.flags |= + KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES; + run->emulation_failure.insn_size = insn_size; + memset(run->emulation_failure.insn_bytes, 0x90, + sizeof(run->emulation_failure.insn_bytes)); + memcpy(run->emulation_failure.insn_bytes, + ctxt->fetch.data, insn_size); + } +} + static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { + struct kvm *kvm = vcpu->kvm; + ++vcpu->stat.insn_emulation_fail; trace_kvm_emulate_insn_failed(vcpu); @@ -7454,10 +7487,9 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) return 1; } - if (emulation_type & EMULTYPE_SKIP) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + if (kvm->arch.exit_on_emulation_error || + (emulation_type & EMULTYPE_SKIP)) { + prepare_emulation_failure_exit(vcpu); return 0; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index f1ba602260f6..68c9e6d8bbda 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -280,6 +280,9 @@ struct kvm_xen_exit { /* Encounter unexpected vm-exit reason */ #define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON 4 +/* Flags that describe what fields in emulation_failure hold valid data. */ +#define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0) + /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { /* in */ @@ -383,6 +386,25 @@ struct kvm_run { __u32 ndata; __u64 data[16]; } internal; + /* + * KVM_INTERNAL_ERROR_EMULATION + * + * "struct emulation_failure" is an overlay of "struct internal" + * that is used for the KVM_INTERNAL_ERROR_EMULATION sub-type of + * KVM_EXIT_INTERNAL_ERROR. Note, unlike other internal error + * sub-types, this struct is ABI! It also needs to be backwards + * compatible with "struct internal". Take special care that + * "ndata" is correct, that new fields are enumerated in "flags", + * and that each flag enumerates fields that are 64-bit aligned + * and sized (so that ndata+internal.data[] is valid/accurate). + */ + struct { + __u32 suberror; + __u32 ndata; + __u64 flags; + __u8 insn_size; + __u8 insn_bytes[15]; + } emulation_failure; /* KVM_EXIT_OSI */ struct { __u64 gprs[32]; @@ -1088,6 +1110,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_EXIT_HYPERCALL 201 #define KVM_CAP_PPC_RPT_INVALIDATE 202 #define KVM_CAP_BINARY_STATS_FD 203 +#define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.3-18-gd494 From 808e9df477757955a9644ca323010339be0c40ee Mon Sep 17 00:00:00 2001 From: Gleb Fotengauer-Malinovskiy Date: Fri, 25 Jun 2021 20:36:55 +0300 Subject: userfaultfd: uapi: fix UFFDIO_CONTINUE ioctl request definition This ioctl request reads from uffdio_continue structure written by userspace which justifies _IOC_WRITE flag. It also writes back to that structure which justifies _IOC_READ flag. See NOTEs in include/uapi/asm-generic/ioctl.h for more information. Fixes: f619147104c8 ("userfaultfd: add UFFDIO_CONTINUE ioctl") Signed-off-by: Gleb Fotengauer-Malinovskiy Acked-by: Peter Xu Reviewed-by: Axel Rasmussen Reviewed-by: Dmitry V. Levin Signed-off-by: Linus Torvalds --- include/uapi/linux/userfaultfd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index bafbeb1a2624..650480f41f1d 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -80,8 +80,8 @@ struct uffdio_zeropage) #define UFFDIO_WRITEPROTECT _IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \ struct uffdio_writeprotect) -#define UFFDIO_CONTINUE _IOR(UFFDIO, _UFFDIO_CONTINUE, \ - struct uffdio_continue) +#define UFFDIO_CONTINUE _IOWR(UFFDIO, _UFFDIO_CONTINUE, \ + struct uffdio_continue) /* read() structure */ struct uffd_msg { -- cgit v1.3-18-gd494 From 0ae71c7720e3ae3aabd2e8a072d27f7bd173d25c Mon Sep 17 00:00:00 2001 From: Rodrigo Campos Date: Mon, 17 May 2021 12:39:07 -0700 Subject: seccomp: Support atomic "addfd + send reply" Alban Crequy reported a race condition userspace faces when we want to add some fds and make the syscall return them[1] using seccomp notify. The problem is that currently two different ioctl() calls are needed by the process handling the syscalls (agent) for another userspace process (target): SECCOMP_IOCTL_NOTIF_ADDFD to allocate the fd and SECCOMP_IOCTL_NOTIF_SEND to return that value. Therefore, it is possible for the agent to do the first ioctl to add a file descriptor but the target is interrupted (EINTR) before the agent does the second ioctl() call. This patch adds a flag to the ADDFD ioctl() so it adds the fd and returns that value atomically to the target program, as suggested by Kees Cook[2]. This is done by simply allowing seccomp_do_user_notification() to add the fd and return it in this case. Therefore, in this case the target wakes up from the wait in seccomp_do_user_notification() either to interrupt the syscall or to add the fd and return it. This "allocate an fd and return" functionality is useful for syscalls that return a file descriptor only, like connect(2). Other syscalls that return a file descriptor but not as return value (or return more than one fd), like socketpair(), pipe(), recvmsg with SCM_RIGHTs, will not work with this flag. This effectively combines SECCOMP_IOCTL_NOTIF_ADDFD and SECCOMP_IOCTL_NOTIF_SEND into an atomic opteration. The notification's return value, nor error can be set by the user. Upon successful invocation of the SECCOMP_IOCTL_NOTIF_ADDFD ioctl with the SECCOMP_ADDFD_FLAG_SEND flag, the notifying process's errno will be 0, and the return value will be the file descriptor number that was installed. [1]: https://lore.kernel.org/lkml/CADZs7q4sw71iNHmV8EOOXhUKJMORPzF7thraxZYddTZsxta-KQ@mail.gmail.com/ [2]: https://lore.kernel.org/lkml/202012011322.26DCBC64F2@keescook/ Signed-off-by: Rodrigo Campos Signed-off-by: Sargun Dhillon Acked-by: Tycho Andersen Acked-by: Christian Brauner Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20210517193908.3113-4-sargun@sargun.me --- Documentation/userspace-api/seccomp_filter.rst | 12 ++++++ include/uapi/linux/seccomp.h | 1 + kernel/seccomp.c | 51 +++++++++++++++++++++++--- 3 files changed, 58 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index 6efb41cc8072..d61219889e49 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -259,6 +259,18 @@ and ``ioctl(SECCOMP_IOCTL_NOTIF_SEND)`` a response, indicating what should be returned to userspace. The ``id`` member of ``struct seccomp_notif_resp`` should be the same ``id`` as in ``struct seccomp_notif``. +Userspace can also add file descriptors to the notifying process via +``ioctl(SECCOMP_IOCTL_NOTIF_ADDFD)``. The ``id`` member of +``struct seccomp_notif_addfd`` should be the same ``id`` as in +``struct seccomp_notif``. The ``newfd_flags`` flag may be used to set flags +like O_EXEC on the file descriptor in the notifying process. If the supervisor +wants to inject the file descriptor with a specific number, the +``SECCOMP_ADDFD_FLAG_SETFD`` flag can be used, and set the ``newfd`` member to +the specific number to use. If that file descriptor is already open in the +notifying process it will be replaced. The supervisor can also add an FD, and +respond atomically by using the ``SECCOMP_ADDFD_FLAG_SEND`` flag and the return +value will be the injected file descriptor number. + It is worth noting that ``struct seccomp_data`` contains the values of register arguments to the syscall, but does not contain pointers to memory. The task's memory is accessible to suitably privileged traces via ``ptrace()`` or diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 6ba18b82a02e..78074254ab98 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -115,6 +115,7 @@ struct seccomp_notif_resp { /* valid flags for seccomp_notif_addfd */ #define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */ +#define SECCOMP_ADDFD_FLAG_SEND (1UL << 1) /* Addfd and return it, atomically */ /** * struct seccomp_notif_addfd diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 9f58049ac16d..057e17f3215d 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -107,6 +107,7 @@ struct seccomp_knotif { * installing process should allocate the fd as normal. * @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC * is allowed. + * @ioctl_flags: The flags used for the seccomp_addfd ioctl. * @ret: The return value of the installing process. It is set to the fd num * upon success (>= 0). * @completion: Indicates that the installing process has completed fd @@ -118,6 +119,7 @@ struct seccomp_kaddfd { struct file *file; int fd; unsigned int flags; + __u32 ioctl_flags; union { bool setfd; @@ -1065,18 +1067,37 @@ static u64 seccomp_next_notify_id(struct seccomp_filter *filter) return filter->notif->next_id++; } -static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd) +static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_knotif *n) { + int fd; + /* * Remove the notification, and reset the list pointers, indicating * that it has been handled. */ list_del_init(&addfd->list); if (!addfd->setfd) - addfd->ret = receive_fd(addfd->file, addfd->flags); + fd = receive_fd(addfd->file, addfd->flags); else - addfd->ret = receive_fd_replace(addfd->fd, addfd->file, - addfd->flags); + fd = receive_fd_replace(addfd->fd, addfd->file, addfd->flags); + addfd->ret = fd; + + if (addfd->ioctl_flags & SECCOMP_ADDFD_FLAG_SEND) { + /* If we fail reset and return an error to the notifier */ + if (fd < 0) { + n->state = SECCOMP_NOTIFY_SENT; + } else { + /* Return the FD we just added */ + n->flags = 0; + n->error = 0; + n->val = fd; + } + } + + /* + * Mark the notification as completed. From this point, addfd mem + * might be invalidated and we can't safely read it anymore. + */ complete(&addfd->completion); } @@ -1120,7 +1141,7 @@ static int seccomp_do_user_notification(int this_syscall, struct seccomp_kaddfd, list); /* Check if we were woken up by a addfd message */ if (addfd) - seccomp_handle_addfd(addfd); + seccomp_handle_addfd(addfd, &n); } while (n.state != SECCOMP_NOTIFY_REPLIED); @@ -1581,7 +1602,7 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter, if (addfd.newfd_flags & ~O_CLOEXEC) return -EINVAL; - if (addfd.flags & ~SECCOMP_ADDFD_FLAG_SETFD) + if (addfd.flags & ~(SECCOMP_ADDFD_FLAG_SETFD | SECCOMP_ADDFD_FLAG_SEND)) return -EINVAL; if (addfd.newfd && !(addfd.flags & SECCOMP_ADDFD_FLAG_SETFD)) @@ -1591,6 +1612,7 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter, if (!kaddfd.file) return -EBADF; + kaddfd.ioctl_flags = addfd.flags; kaddfd.flags = addfd.newfd_flags; kaddfd.setfd = addfd.flags & SECCOMP_ADDFD_FLAG_SETFD; kaddfd.fd = addfd.newfd; @@ -1616,6 +1638,23 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter, goto out_unlock; } + if (addfd.flags & SECCOMP_ADDFD_FLAG_SEND) { + /* + * Disallow queuing an atomic addfd + send reply while there are + * some addfd requests still to process. + * + * There is no clear reason to support it and allows us to keep + * the loop on the other side straight-forward. + */ + if (!list_empty(&knotif->addfd)) { + ret = -EBUSY; + goto out_unlock; + } + + /* Allow exactly only one reply */ + knotif->state = SECCOMP_NOTIFY_REPLIED; + } + list_add(&kaddfd.list, &knotif->addfd); complete(&knotif->ready); mutex_unlock(&filter->notify_lock); -- cgit v1.3-18-gd494