aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2018-02-06arm64: idmap: Use "awx" flags for .idmap.text .pushsection directivesWill Deacon4-7/+7
The identity map is mapped as both writeable and executable by the SWAPPER_MM_MMUFLAGS and this is relied upon by the kpti code to manage a synchronisation flag. Update the .pushsection flags to reflect the actual mapping attributes. Reported-by: Marc Zyngier <[email protected]> Signed-off-by: Will Deacon <[email protected]> Signed-off-by: Catalin Marinas <[email protected]>
2018-02-06arm64: assembler: Align phys_to_pte with pte_to_physWill Deacon2-22/+15
pte_to_phys lives in assembler.h and takes its destination register as the first argument. Move phys_to_pte out of head.S to sit with its counterpart and rejig it to follow the same calling convention. Signed-off-by: Will Deacon <[email protected]> Signed-off-by: Catalin Marinas <[email protected]>
2018-02-06arm64: entry: Reword comment about post_ttbr_update_workaroundWill Deacon1-10/+3
We don't fully understand the Cavium ThunderX erratum, but it appears that mapping the kernel as nG can lead to horrible consequences such as attempting to execute userspace from kernel context. Since kpti isn't enabled for these CPUs anyway, simplify the comment justifying the lack of post_ttbr_update_workaround in the exception trampoline. Signed-off-by: Will Deacon <[email protected]> Signed-off-by: Catalin Marinas <[email protected]>
2018-02-06arm64: assembler: Change order of macro arguments in phys_to_ttbrWill Deacon5-9/+9
Since AArch64 assembly instructions take the destination register as their first operand, do the same thing for the phys_to_ttbr macro. Acked-by: Robin Murphy <[email protected]> Signed-off-by: Will Deacon <[email protected]> Signed-off-by: Catalin Marinas <[email protected]>
2018-02-06arm64: Force KPTI to be disabled on Cavium ThunderXMarc Zyngier1-3/+14
Cavium ThunderX's erratum 27456 results in a corruption of icache entries that are loaded from memory that is mapped as non-global (i.e. ASID-tagged). As KPTI is based on memory being mapped non-global, let's prevent it from kicking in if this erratum is detected. Signed-off-by: Marc Zyngier <[email protected]> [will: Update comment] Signed-off-by: Will Deacon <[email protected]> Signed-off-by: Catalin Marinas <[email protected]>
2018-02-06arm64: kpti: Add ->enable callback to remap swapper using nG mappingsWill Deacon3-8/+231
Defaulting to global mappings for kernel space is generally good for performance and appears to be necessary for Cavium ThunderX. If we subsequently decide that we need to enable kpti, then we need to rewrite our existing page table entries to be non-global. This is fiddly, and made worse by the possible use of contiguous mappings, which require a strict break-before-make sequence. Since the enable callback runs on each online CPU from stop_machine context, we can have all CPUs enter the idmap, where secondaries can wait for the primary CPU to rewrite swapper with its MMU off. It's all fairly horrible, but at least it only runs once. Tested-by: Marc Zyngier <[email protected]> Reviewed-by: Marc Zyngier <[email protected]> Signed-off-by: Will Deacon <[email protected]> Signed-off-by: Catalin Marinas <[email protected]>
2018-02-06arm64: mm: Permit transitioning from Global to Non-Global without BBMWill Deacon1-0/+4
Break-before-make is not needed when transitioning from Global to Non-Global mappings, provided that the contiguous hint is not being used. Signed-off-by: Will Deacon <[email protected]> Signed-off-by: Catalin Marinas <[email protected]>
2018-02-06arm64: kpti: Make use of nG dependent on arm64_kernel_unmapped_at_el0()Will Deacon2-26/+16
To allow systems which do not require kpti to continue running with global kernel mappings (which appears to be a requirement for Cavium ThunderX due to a CPU erratum), make the use of nG in the kernel page tables dependent on arm64_kernel_unmapped_at_el0(), which is resolved at runtime. Signed-off-by: Will Deacon <[email protected]> Signed-off-by: Catalin Marinas <[email protected]>
2018-02-06arm64: Add software workaround for Falkor erratum 1041Shanker Donthineni8-1/+28
The ARM architecture defines the memory locations that are permitted to be accessed as the result of a speculative instruction fetch from an exception level for which all stages of translation are disabled. Specifically, the core is permitted to speculatively fetch from the 4KB region containing the current program counter 4K and next 4K. When translation is changed from enabled to disabled for the running exception level (SCTLR_ELn[M] changed from a value of 1 to 0), the Falkor core may errantly speculatively access memory locations outside of the 4KB region permitted by the architecture. The errant memory access may lead to one of the following unexpected behaviors. 1) A System Error Interrupt (SEI) being raised by the Falkor core due to the errant memory access attempting to access a region of memory that is protected by a slave-side memory protection unit. 2) Unpredictable device behavior due to a speculative read from device memory. This behavior may only occur if the instruction cache is disabled prior to or coincident with translation being changed from enabled to disabled. The conditions leading to this erratum will not occur when either of the following occur: 1) A higher exception level disables translation of a lower exception level (e.g. EL2 changing SCTLR_EL1[M] from a value of 1 to 0). 2) An exception level disabling its stage-1 translation if its stage-2 translation is enabled (e.g. EL1 changing SCTLR_EL1[M] from a value of 1 to 0 when HCR_EL2[VM] has a value of 1). To avoid the errant behavior, software must execute an ISB immediately prior to executing the MSR that will change SCTLR_ELn[M] from 1 to 0. Signed-off-by: Shanker Donthineni <[email protected]> Signed-off-by: Will Deacon <[email protected]> Signed-off-by: Catalin Marinas <[email protected]>
2018-02-06arm64: spinlock: Fix theoretical trylock() A-B-A with LSE atomicsWill Deacon1-2/+2
If the spinlock "next" ticket wraps around between the initial LDR and the cmpxchg in the LSE version of spin_trylock, then we can erroneously think that we have successfuly acquired the lock because we only check whether the next ticket return by the cmpxchg is equal to the owner ticket in our updated lock word. This patch fixes the issue by performing a full 32-bit check of the lock word when trying to determine whether or not the CASA instruction updated memory. Reported-by: Catalin Marinas <[email protected]> Signed-off-by: Will Deacon <[email protected]> Signed-off-by: Catalin Marinas <[email protected]>
2018-02-06media: videobuf2: fix up for "media: annotate ->poll() instances"Stephen Rothwell2-7/+7
Signed-off-by: Stephen Rothwell <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2018-02-06block: Add should_fail_bio() for bpf error injectionHoward McLauchlan1-1/+10
The classic error injection mechanism, should_fail_request() does not support use cases where more information is required (from the entire struct bio, for example). To that end, this patch introduces should_fail_bio(), which calls should_fail_request() under the hood but provides a convenient place for kprobes to hook into if they require the entire struct bio. This patch also replaces some existing calls to should_fail_request() with should_fail_bio() with no degradation in performance. Signed-off-by: Howard McLauchlan <[email protected]> Signed-off-by: Jens Axboe <[email protected]>
2018-02-06idr: Add documentationMatthew Wilcox4-13/+95
Move the idr kernel-doc to its own idr.rst file and add a few paragraphs about how to use it. Also add some more kernel-doc. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06idr: Make 1-based IDRs more efficientMatthew Wilcox3-40/+103
About 20% of the IDR users in the kernel want the allocated IDs to start at 1. The implementation currently searches all the way down the left hand side of the tree, finds no free ID other than ID 0, walks all the way back up, and then all the way down again. This patch 'rebases' the ID so we fill the entire radix tree, rather than leave a gap at 0. Chris Wilson says: "I did the quick hack of allocating index 0 of the idr and that eradicated idr_get_free() from being at the top of the profiles for the many-object stress tests. This improvement will be much appreciated." Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06idr: Warn if old iterators see large IDsMatthew Wilcox1-1/+8
Now that the IDR can be used to store large IDs, it is possible somebody might only partially convert their old code and use the iterators which can only handle IDs up to INT_MAX. It's probably unwise to show them a truncated ID, so settle for spewing warnings to dmesg, and terminating the iteration. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06idr: Rename idr_for_each_entry_extMatthew Wilcox3-33/+55
Most places in the kernel that we need to distinguish functions by the type of their arguments, we use '_ul' as a suffix for the unsigned long variant, not '_ext'. Also add kernel-doc. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06idr: Remove idr_alloc_extMatthew Wilcox5-111/+105
It has no more users, so remove it. Move idr_alloc() back into idr.c, move the guts of idr_alloc_cmn() into idr_alloc_u32(), remove the wrappers around idr_get_free_cmn() and rename it to idr_get_free(). While there is now no interface to allocate IDs larger than a u32, the IDR internals remain ready to handle a larger ID should a need arise. These changes make it possible to provide the guarantee that, if the nextid pointer points into the object, the object's ID will be initialised before a concurrent lookup can find the object. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06cls_u32: Convert to idr_alloc_u32Matthew Wilcox1-13/+10
No real benefit to this classifier, but since we're allocating a u32 anyway, we should use this function. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06cls_u32: Reinstate cyclic allocationMatthew Wilcox1-10/+4
Commit e7614370d6f0 ("net_sched: use idr to allocate u32 filter handles) converted htid allocation to use the IDR. The ID allocated by this scheme changes; it used to be cyclic, but now always allocates the lowest available. The IDR supports cyclic allocation, so just use the right function. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06cls_flower: Convert to idr_alloc_u32Matthew Wilcox1-16/+10
Use the new helper which saves a temporary variable and a few lines of code. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06cls_bpf: Convert to use idr_alloc_u32Matthew Wilcox1-14/+10
Use the new helper. This has a modest reduction in both lines of code and compiled code size. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06cls_basic: Convert to use idr_alloc_u32Matthew Wilcox1-15/+10
Use the new helper which saves a temporary variable and a few lines of code. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06cls_api: Convert to idr_alloc_u32Matthew Wilcox1-2/+2
Use the new helper. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06net sched actions: Convert to use idr_alloc_u32Matthew Wilcox1-35/+25
Use the new helper. Also untangle the error path, and in so doing noticed that estimator generator failure would lead to us leaking an ID. Fix that bug. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06idr: Add idr_alloc_u32 helperMatthew Wilcox2-0/+33
All current users of idr_alloc_ext() actually want to allocate a u32 and idr_alloc_u32() fits their needs better. Like idr_get_next(), it uses a 'nextid' argument which serves as both a pointer to the start ID and the assigned ID (instead of a separate minimum and pointer-to-assigned-ID argument). It uses a 'max' argument rather than 'end' because the semantics that idr_alloc has for 'end' don't work well for unsigned types. Since idr_alloc_u32() returns an errno instead of the allocated ID, mark it as __must_check to help callers use it correctly. Include copious kernel-doc. Chris Mi <[email protected]> has promised to contribute test-cases for idr_alloc_u32. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06idr: Delete idr_find_ext functionMatthew Wilcox4-9/+4
Simply changing idr_remove's 'id' argument to 'unsigned long' works for all callers. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06idr: Delete idr_replace_ext functionMatthew Wilcox7-19/+9
Changing idr_replace's 'id' argument to 'unsigned long' works for all callers. Callers which passed a negative ID now get -ENOENT instead of -EINVAL. No callers relied on this error value. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06idr: Delete idr_remove_ext functionMatthew Wilcox7-19/+14
Simply changing idr_remove's 'id' argument to 'unsigned long' suffices for all callers. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06orangefs: reverse sense of is-inode-stale test in d_revalidateMartin Brandenburg1-10/+7
If a dentry is deleted, then a dentry is recreated with the same handle but a different type (i.e. it was a file and now it's a symlink), then its a different inode. The check was backwards, so d_revalidate would not have noticed. Due to the design of the OrangeFS server, this is rather unlikely. It's also possible for the dentry to be deleted and recreated with the same type. This would be undetectable. It's a bit of a ship of Theseus. Signed-off-by: Martin Brandenburg <[email protected]> Signed-off-by: Mike Marshall <[email protected]>
2018-02-06orangefs: simplify orangefs_inode_is_staleMartin Brandenburg1-24/+30
Check whether this is a new inode at location of call. Raises the question of what to do with an unknown inode type. Old code would've marked the inode bad and returned ESTALE. Signed-off-by: Martin Brandenburg <[email protected]> Signed-off-by: Mike Marshall <[email protected]>
2018-02-06Orangefs: don't propogate whacky error codesMike Marshall1-0/+1
When we get an error return code from userspace (the client-core) we check to make sure it is a valid code. This patch maps the whacky return code to -EINVAL instead of propagating garbage back up the call chain potentially resulting in a hard-to-find train-wreck. The client-core doesn't have any business returning whacky return codes, but if it does, we don't want the kernel to crash as a result. Signed-off-by: Mike Marshall <[email protected]>
2018-02-06orangefs: use correct string lengthXiongfeng Wang3-12/+12
gcc-8 reports fs/orangefs/dcache.c: In function 'orangefs_d_revalidate': ./include/linux/string.h:245:9: warning: '__builtin_strncpy' specified bound 256 equals destination size [-Wstringop-truncation] fs/orangefs/namei.c: In function 'orangefs_rename': ./include/linux/string.h:245:9: warning: '__builtin_strncpy' specified bound 256 equals destination size [-Wstringop-truncation] fs/orangefs/super.c: In function 'orangefs_mount': ./include/linux/string.h:245:9: warning: '__builtin_strncpy' specified bound 256 equals destination size [-Wstringop-truncation] We need one less byte or call strlcpy() to make it a nul-terminated string. Signed-off-by: Xiongfeng Wang <[email protected]> Signed-off-by: Mike Marshall <[email protected]>
2018-02-06orangefs: make orangefs_make_bad_inode staticMartin Brandenburg2-21/+19
Signed-off-by: Martin Brandenburg <[email protected]> Signed-off-by: Mike Marshall <[email protected]>
2018-02-06orangefs: remove ORANGEFS_KERNEL_DEBUGMartin Brandenburg1-6/+2
It wasn't possible to enable it, and it would've had very little effect. Signed-off-by: Martin Brandenburg <[email protected]> Signed-off-by: Mike Marshall <[email protected]>
2018-02-06orangefs: remove gossip_ldebug and gossip_lerrMartin Brandenburg3-17/+2
gossip_ldebug is unused. gossip_lerr is used in two places. The messages are unique so line numbers are unnecessary. Also remove support for compiling gossip messages out. It wasn't possible to enable it anyway. Signed-off-by: Martin Brandenburg <[email protected]> Signed-off-by: Mike Marshall <[email protected]>
2018-02-06orangefs: make orangefs_client_debug_init staticMartin Brandenburg2-2/+1
Signed-off-by: Martin Brandenburg <[email protected]> Signed-off-by: Mike Marshall <[email protected]>
2018-02-06MAINTAINERS: update orangefs list and add myself as reviewerMartin Brandenburg1-1/+2
Signed-off-by: Martin Brandenburg <[email protected]> Signed-off-by: Mike Marshall <[email protected]>
2018-02-06blk-wbt: account flush requests correctlyJens Axboe1-1/+9
Mikulas reported a workload that saw bad performance, and figured out what it was due to various other types of requests being accounted as reads. Flush requests, for instance. Due to the high latency of those, we heavily throttle the writes to keep the latencies in balance. But they really should be accounted as writes. Fix this by checking the exact type of the request. If it's a read, account as a read, if it's a write or a flush, account as a write. Any other request we disregard. Previously everything would have been mistakenly accounted as reads. Reported-by: Mikulas Patocka <[email protected]> Cc: [email protected] # v4.12+ Signed-off-by: Jens Axboe <[email protected]>
2018-02-06Merge tag 'nfs-rdma-for-4.16-2' of ↵Trond Myklebust2-5/+5
git://git.linux-nfs.org/projects/anna/linux-nfs NFS-over-RDMA client fixes for Linux 4.16 #2 Stable fixes: - Fix calculating ri_max_send_sges, which can oops if max_sge is too small - Fix a BUG after device removal if freed resources haven't been allocated yet
2018-02-06Merge branch 'linus' into sched/urgent, to resolve conflictsIngo Molnar9071-253256/+389529
Conflicts: arch/arm64/kernel/entry.S arch/x86/Kconfig include/linux/sched/mm.h kernel/fork.c Signed-off-by: Ingo Molnar <[email protected]>
2018-02-06IDR test suite: Check handling negative end correctlyMatthew Wilcox1-0/+1
One of the charming quirks of the idr_alloc() interface is that you can pass a negative end and it will be interpreted as "maximum". Ensure we don't break that. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06idr test suite: Fix ida_test_random()Matthew Wilcox1-2/+2
The test was checking the wrong errno; ida_get_new_above() returns EAGAIN, not ENOMEM on memory allocation failure. Double the number of threads to increase the chance that we actually exercise this path during the test suite (it was a bit sporadic before). Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06radix tree test suite: Remove ARRAY_SIZEMatthew Wilcox1-2/+0
This is now defined in tools/include/linux/kernel.h, so our definition generates a warning. Signed-off-by: Matthew Wilcox <[email protected]>
2018-02-06drm/i915/cnp: Properly handle VBT ddc pin out of bounds.Rodrigo Vivi1-2/+3
If the table result is out of bounds on the array map there is something really wrong with VBT pin so we don't return that vbt_pin, but only return 0 instead. This basically reverts commit 'a8e6f3888b05 ("drm/i915/cnp: Ignore VBT request for know invalid DDC pin.")' Also this properly fixes commit 9c3b2689d01f ("drm/i915/cnl: Map VBT DDC Pin to BSpec DDC Pin.") v2: Do in a way that we don't break other platforms. (Jani) v3: Keep debug message (Jani) v4: Don't mess with 0 mapping was noticed by Jani and addressed with a simple solution suggested by Lucas that makes this even simpler. Fixes: a8e6f3888b05 ("drm/i915/cnp: Ignore VBT request for know invalid DDC pin.") Fixes: 9c3b2689d01f ("drm/i915/cnl: Map VBT DDC Pin to BSpec DDC Pin.") Cc: Radhakrishna Sripada <[email protected]> Cc: Jani Nikula <[email protected]> Cc: Kai Heng Feng <[email protected]> Cc: Lucas De Marchi <[email protected]> Suggested-by: Lucas De Marchi <[email protected]> Signed-off-by: Rodrigo Vivi <[email protected]> Reviewed-by: Lucas De Marchi <[email protected]> Tested-by: Kai-Heng Feng <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] (cherry picked from commit 3393ce1ed8fc43dbdb83952facaf04e644ca1d54) Signed-off-by: Rodrigo Vivi <[email protected]>
2018-02-06drm/i915/cnp: Ignore VBT request for know invalid DDC pin.Rodrigo Vivi1-3/+8
Let's ignore VBT request if the pin is clearly wrong. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104139 Cc: Kai Heng Feng <[email protected]> Signed-off-by: Rodrigo Vivi <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] Reviewed-by: Radhakrishna Sripada <[email protected]> (cherry picked from commit a8e6f3888b05c1e7b685800a3371ce050720368f) Signed-off-by: Rodrigo Vivi <[email protected]>
2018-02-06drm/i915/cmdparser: Do not check past the cmd length.Michal Srb1-0/+6
The command MEDIA_VFE_STATE checks bits at offset +2 dwords. However, it is possible to have MEDIA_VFE_STATE command with length = 0 + LENGTH_BIAS = 2. In that case check_cmd will read bits from the following command, or even past the end of the buffer. If the offset ends up outside of the command length, reject the command. Fixes: 351e3db2b363 ("drm/i915: Implement command buffer parsing logic") Signed-off-by: Michal Srb <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] Reviewed-by: Chris Wilson <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] (cherry picked from commit 3aec7f871c65eb5f76b4125fda432593c834a6f2) Signed-off-by: Rodrigo Vivi <[email protected]>
2018-02-06drm/i915/cmdparser: Check reg_table_count before derefencing.Michal Srb1-2/+2
The find_reg function was assuming that there is always at least one table in reg_tables. It is not always true. In case of VCS or VECS, the reg_tables is NULL and reg_table_count is 0, implying that no register-accessing commands are allowed. However, the command tables include commands such as MI_STORE_REGISTER_MEM. When trying to check such command, the find_reg would dereference NULL pointer. Now it will just return NULL meaning that the register was not found and the command will be rejected. Fixes: 76ff480ec963 ("drm/i915/cmdparser: Use binary search for faster register lookup") Signed-off-by: Michal Srb <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] Cc: Chris Wilson <[email protected]> Cc: Matthew Auld <[email protected]> Reviewed-by: Chris Wilson <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] register lookup") (cherry picked from commit 2f265fad9756a40c09e3f4dcc62d5d7fa73a9fb2) Signed-off-by: Rodrigo Vivi <[email protected]>
2018-02-06drm/i915/bxt, glk: Increase PCODE timeouts during CDCLK freq changingImre Deak3-9/+25
Currently we see sporadic timeouts during CDCLK changing both on BXT and GLK as reported by the Bugzilla: ticket. It's easy to reproduce this by changing the frequency in a tight loop after blanking the display. The upper bound for the completion time is 800us based on my tests, so increase it from the current 500us to 2ms; with that I couldn't trigger the problem either on BXT or GLK. Note that timeouts happened during both the change notification and the voltage level setting PCODE request. (For the latter one BSpec doesn't require us to wait for completion before further HW programming.) This issue is similar to commit 2c7d0602c815 ("drm/i915/gen9: Fix PCODE polling during CDCLK change notification") but there the PCODE request does complete (as shown by the mbox busy flag), only the reply we get from PCODE indicates a failure. So there we keep resending the request until a success reply, here we just have to increase the timeout for the one PCODE request we send. v2: - s/snb_pcode_request/sandybridge_pcode_write_timeout/ (Ville) Cc: Chris Wilson <[email protected]> Cc: Ville Syrjälä <[email protected]> Cc: <[email protected]> # v4.4+ Acked-by: Chris Wilson <[email protected]> (v1) Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103326 Reviewed-by: Ville Syrjälä <[email protected]> Signed-off-by: Imre Deak <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] (cherry picked from commit e76019a81921e87a4d9e7b3d86102bc708a6c227) Signed-off-by: Rodrigo Vivi <[email protected]>
2018-02-06drm/i915/gvt: Use KVM r/w to access guest opregionTina Zhang2-29/+70
For KVMGT, the guest opregion, which is handled by VFIO, is actually a piece of guest memory which won't be accessed by devices. So, its mfn shouldn't be obtained through VFIO interface. This patch uses KVM r/w interface to access the data in guest opregion. Fix the guest opregion accessing issue when host "intel_iommu=on". v3: - Remove mapped flag for KVM/VFIO usage, as it's useless for KVM. v2: - Set the gpa correctly when invoking KVM r/w operations. (Zhenyu) Signed-off-by: Tina Zhang <[email protected]> Cc: Yan Zhao <[email protected]> Cc: Xiong Zhang <[email protected]> Signed-off-by: Zhi Wang <[email protected]> Signed-off-by: Rodrigo Vivi <[email protected]>
2018-02-06drm/i915/gvt: Fix aperture read/write emulation when enable x-no-mmap=onChangbin Du4-59/+35
When add 'x-no-mmap=on' for vfio-pci option, aperture access in guest is emulated. But the vgpu_aperture_rw() function take wrong offset when do memcpy, since vgpu->gm.aperture_va is not the base of entire aperture. This mistake cause GPU command in guest get lost and so the seqno is not updated in engine HWSP. This patch fix this, and it also move the emulation code to kvmgt. Because only vfio need to emulate it. Put aperture rw to MMIO emulation path breaks assumptions in xengt. v2: Remove PAGE_ALIGN for size (zhenyu) Fixes: f090a00df9ec ("drm/i915/gvt: Add emulation for BAR2 (aperture) with normal file RW approach") Signed-off-by: Changbin Du <[email protected]> Signed-off-by: Zhi Wang <[email protected]> Signed-off-by: Rodrigo Vivi <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.