When doing an "extreme rewind" import ("zpool import -XF"), we attempt
to verify all data in the pool, essentially scrubbing the entire pool.
The problem is that spa_load_verify_cb() issues an unbounded number of
concurrent scrub i/os. This can lead to all of memory being used for
these zio's, wedging the system. Like normal scrub, we need to put a
cap on the number of outstanding i/os, and have the traverse thread
block when we reach this cap.
For this purpose the cap can be very large (10,000) to optimize the
elevator algorithm. Three kernel tunables have been added:
The latter two tunables controls whether metadata and/or user data
when doing extreme rewind.
Make 'zpool import -T' imply scrub.
Make zpool import -T <txg> accept hexadecimal values for the txg when
prefixed with 0x.
Skip txg's for which there is no uberblock when doing extreme rewind.
Skip reading all user data twice by skipping prefetches when doing
extreme rewinds as we do not access via the ARC.
Illumos issues:
4970 need controls on i/o issued by zpool import -XF
4971 zpool import -T should accept hex values
4972 zpool import -T implies extreme rewind, and thus a scrub
4973 spa_load_retry retries the same txg
4974 spa_load_verify() reads all data twice
MFC r268236,268264,268524,268646,268802,269021:
This brings VHD support to mkimg(1); both dynamic and fixed file formats.
Dynamic VHD and VMDK file images are now sparsely written, meaning that
"free" sectors do not occupy space.
MFC r268608:
The tmpfs_link() must not dereference the filesystem-specific data for
a vnode until it is verified that the vnode indeed belongs to tmpfs mount.
MFC r268606:
Generalize vn_get_ino() to allow filesystems to use custom vnode
producer. Convert inline copies of vn_get_ino() in msdosfs and cd9660
into the uses of vn_get_ino_gen().
ian [Fri, 25 Jul 2014 23:29:55 +0000 (23:29 +0000)]
MFC r266565, r266651:
Map device memory using PTE_DEVICE attributes, and also ensure that the
shared flag is set on normal-memory mappings made via pmap_kenter() for SMP.
The "shared flag" part of this change isn't obvious from the diff, here's
the deal... by using the array of preformatted page table entry templates
instead of constructing the PTE from scratch, we automatically get the
right attribute bits set for both caching and shared.
ian [Fri, 25 Jul 2014 23:21:36 +0000 (23:21 +0000)]
MFC r263373, r268402
Add a way to apply CFLAGS only when building the given architecture. This
is useful primarily on a system used for cross-building, when you have a
set of flags to apply to the TARGET_ARCH being cross-built but don't want
those settings applied to building the cross-tools or other components that
run on the build host machine.
Support CXXFLAGS.${MACHINE_ARCH} as well as CFLAGS. This allows different
C++ options for toolchain versus target when cross-building.
ian [Fri, 25 Jul 2014 23:12:22 +0000 (23:12 +0000)]
MFC r261530
Set the malloc alignment to 64 bytes on platforms that use the U-Boot API
device drivers. Recent versions of u-boot run with the MMU enabled, and
require DMA-based I/O to be aligned to cache line boundaries.
r268640:
Allow multi-byte reads in the private CHELSIO_T4_GET_I2C ioctl. The
firmware allows up to 48B to be read this way but the driver limits
itself to 8B at a time to remain compatible with old cxgbetool
binaries.
dim [Thu, 24 Jul 2014 20:16:45 +0000 (20:16 +0000)]
MFC r268957:
Run mtree for BSD.tests.dist during make xdev-install, if the tests are
enabled (which they are in the default configuration). Otherwise, it
will fail because ${XDDESTDIR}/usr/include/atf-c does not exist.
MFC r268466:
Calculate the amount of resident pages by looking in the objects chain
backing the region. Add a knob to disable the residency calculation at
all.
MFC r268490:
Unconditionally initialize addr to handle the case of changed map
timestamp while the map is unlocked.
MFC r268711:
Change the calculation of the kinfo_vmentry field kve_private_resident
to reflect its name.
MFC r268712:
Followup to r268466.
- Move the code to calculate resident count into separate function.
It reduces the indent level and makes the operation of
vmmap_skip_res_cnt tunable more clear.
- Optimize the calculation of the resident page count for map entry.
Skip directly to the next lowest available index and page among the
whole shadow chain.
- Restore the use of pmap_incore(9), only to verify that current
mapping is indeed superpage.
- Note the issue with the invalid pages.
MFC r268420:
Remove IO_SYNC flag when writing extended file attributes on ZFS.
While it is possible to create and write file, modify its permissions, etc.
without ever doing sync, it looks odd that it is required for setting
extended file attributes on ZFS. UFS does not do sync there too.
Samba uses those extended attributes to store some its data, and doing it
synchronously by many times reduces file creation performance for systems
without SLOG device.
Now defaults to a 16x8 font size. The height and width can be specified
using -h and -w respectively.
r267012: Make the bold font optional
r267035: Use a hash to speed up glyph deduplication
Walking a linked list of all glyphs to look for a duplicate is very slow
for large fonts (e.g., for CJK character sets). In my test the runtime
for a sample 40000 character font went from just over 80 seconds on
average to just over 2 seconds.
r267119: -w sets the width, not height
r267123: Support "GNU Unifont" format font data
The GNU Unifont .hex format is a text file. Each line represents one
glyph and consists of a four-digit hex code point, a colon, and pairs of
hex digits representing the bitmap. By default an 8x16 font is assumed,
with 16x16 double-width glyphs, resulting in either 32 or 64 hex digits
for the bitmap.
Our version of the file format supports comments at the top of the file
to set the height and width:
Each row of bitmap data is rounded up to byte width - for example, a
10-pixel wide font uses 4 characters per row.
See http://czyborra.com/unifont/ for more background on the original
format.
r267126: Accept space after BITMAP in .bdf parser
The Unifont BDF generator incorrectly adds a space after BITMAP, and
and that error has been widely propagated.
r267173: use -h height and -w width args
r267298: Hide stats by default and improve error handling
The font stats are interesting, but rather verbose.
r267301: Speed up bold glyph map deduplication
Perform an O(n) deduplication pass over the bold maps at the end, rather
than walking the normal map list to look for a duplicate glyph each time
a bold mapping entry is added.
r267324: handle failure writing output font
r267337: move to usr.bin/vtfontcvt
vtfontcvt is useful for end users to convert arbitrary bitmap fonts
for use by vt(4). It can also be used as a build tool, allowing us
to keep the source font data in the src tree rather than uuencoded
binaries.
r268022: Rename the WITHOUT_VT_SUPPORT knob to WITHOUT_VT
The _SUPPORT knobs have a consistent meaning which differs from the
behaviour controlled by this knob. As the knob is opt-out and has not
appeared in a release the impact should be low.
r268172: correct width calculation (.hex files and commandline)
r268948: Use the standard way of printing the usage string
r268949: Remove redundant return statement after errx
Also update vtfontcvt(8), based on inclusion in FreeBSD 10.1
MFC 267883:
Expand r261243 even further and ignore any I/O port resources assigned to
PCI root bridges except for the one known-valid case on x86 where bridges
claim the I/O port registers used for PCI config space access.
MFC r263678: lldb: Invoke PT_KILL from ProcessPosix::DoDestroy
We previously sent SIGKILL to the debuggee in DoDestroy, but did not
actually detach or kill via ptrace. It seems that this somehow didn't
matter on Linux, but did on FreeBSD.
This would happen when quitting LLDB while stopped at a breakpoint, for
example. The debuggee remained stopped in ptrace (with the signal
either pending or lost). After a timeout of a second or two LLDB exits,
which caused the debuggee to resume and dump core from an unhandled
SIGTRAP.
BringProcessIntoLimbo is a poorly named wrapper for ptrace(PT_KILL)
which is the desired behaviour from DoDestroy.
Omit "too many sections" warnings if the ELF file is not dynamically
linked (and is therefore skipped anyway), and otherwise output it only
once. An errant core file would previously cause kldxref to output a
number of warnings.
Also introduce a MAXSEGS #define and replace literal 2 with it, to make
comparisons clear.
Reviewed by: kib
Sponsored by: The FreeBSD Foundation
MFC r265477: Merge -fstandalone-debug from Clang r198655:
Implement a new -fstandalone-debug option. rdar://problem/15685848
It controls everything that -flimit-debug-info used to, plus the
vtable type optimization. The old -fno-limit-debug-info option is now an
alias to -fstandalone-debug and vice versa.
Standalone is the default on Darwin until dtrace is updated to work with
non-standalone debug info (rdar://problem/15758808).
Note: I kept the LimitedDebugInfo name in CodeGenOptions::DebugInfoKind
because NoStandaloneDebugInfo sounded even more confusing.
Debug info: Support variadic functions.
Variadic functions have an unspecified parameter tag after the last
argument. In IR this is represented as an unspecified parameter in the
subroutine type.
MFC 266424,266476,266524,266573,266595,266626,266627,266633,266641,266642,
266708,266724,266934,266935,268521:
Emulation of the "ins" and "outs" instructions.
Various fixes for translating guest linear addresses to guest physical
addresses.
MFC r268642:
libc/gen: small updates to code originating at OpenBSD
arc4random.c
- CVS rev. 1.22
Change arc4random_uniform() to calculate ``2**32 % upper_bound'' as
``-upper_bound % upper_bound''. Simplifies the code and makes it the
same on both ILP32 and LP64 architectures, and also slightly faster on
LP64 architectures by using a 32-bit remainder instead of a 64-bit
remainder.
- CVS rev. 1.23
Spacing
readpassphrase.c
-CVS rev. v 1.24
most obvious unsigned char casts for ctype
MFC 264353,264509,264768,264770,264825,264846,264988,265114,265165,265365,
265941,265951,266390,266550,266910:
Various bhyve fixes:
- Don't save host's return address in 'struct vmxctx'.
- Permit non-32-bit accesses to local APIC registers.
- Factor out common ioport handler code.
- Use calloc() in favor of malloc + memset.
- Change the vlapic timer frequency to be in the ballpark of contemporary
hardware.
- Allow the guest to read the TSC via MSR 0x10.
- A VMCS is always inactive when it exits the vmx_run() loop. Remove
redundant code and the misleading comment that suggest otherwise.
- Ignore writes to microcode update MSR. This MSR is accessed by RHEL7
guest.
Add KTR tracepoints to annotate wrmsr and rdmsr VM exits.
- Provide an alias for the userboot console and name it 'comconsole'.
- Use EV_ADD to create an mevent and EV_ENABLE to enable it.
- abort(3) the process in response to a VMEXIT_ABORT.
- Don't include the guest memory segments in the bhyve(8) process core dump.
- Make the vmx asm code dtrace-fbt-friendly.
- Allow vmx_getdesc() and vmx_setdesc() to be called for a vcpu that is in
the VCPU_RUNNING state.
- Enable VMX in the IA32_FEATURE_CONTROL MSR if it not enabled and the MSR
isn't locked.
MFC 260847,264055,264867:
- Add a very simple virtio_random(4) driver for FreeBSD guests to harvest
entropy from hypervisors.
- Add support to bhyve for the virtio RNG entropy-source device to provide
entry to bhyve guests.
Use NULL instead of 0 (Patch by Sascha Wildner <saw at online.de> for Dragonfly)
Remove unnecessary semicolons (Patch by Sascha Wildner <saw at online.de> for Dragonfly)
Add support for arbitrary http requests [1]
Support EAGAIN in fetch_writev
Submitted by: Alex Hornung <alex at alexhornung.com> [1]
Reviewed by: des
MFC 263432,265366,265376:
Fixes for vcpu management in bhyve:
- Use 'cpuset_t' to represent the vcpus active in a virtual machine.
- Modify the "-p" option to be more flexible when associating a 'vcpu' with
a 'hostcpu'.
MFC 262884,263236,265407:
Various uart fixes:
- Open the uart emulation's backing tty in non-blocking mode.
- Support 16-bit register access.
- Disable the 'uart_drain()' callback when the emulated receive FIFO
is full.
MFC 259942,262274,263035,263054,263211,263744,264179,264324,264468,264631,
264648,264650,264651,266572,267558:
Flesh out the AT PIC and 8254 PIT emulations and move them into the kernel.
MFC 261904,261905,262143,262184,264921,265211,267169,267292,267294:
Various PCI fixes:
- Allow PCI devices to be configured on all valid bus numbers from 0 to 255.
- Tweak the handling of PCI capabilities in emulated devices to remove
the non-standard zero capability list terminator.
- Add a check to validate that memory BARs of passthru devices are 4KB
aligned.
- Respect and track the enable bit in the PCI configuration address word.
- Handle quad-word access to 32-bit register pairs.
MFC r268735:
Improve support for Intel Lynx Point USB 3.0 controllers by using the
USB 2.0 port mask in addition to the USB 3.0 port mask. The hardware
does not always accept when writing -1U to the port switching
registers.
dim [Sat, 19 Jul 2014 18:33:09 +0000 (18:33 +0000)]
MFC r268774:
After r261991, clang warnings about unused functions in the kernel were
completely silenced. Make sure these warnings appear again, so there is
some incentive to fix them, but do not error out the whole kernel build
for them.
projects / FreeBSD / stable / 10.git / log