Merge tag 'net-6.9-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from netfilter, bluetooth and bpf.
Fairly usual collection of driver and core fixes. The large selftest
accompanying one of the fixes is also becoming a common occurrence.
Current release - regressions:
- ipv6: fix infinite recursion in fib6_dump_done()
- net/rds: fix possible null-deref in newly added error path
Current release - new code bugs:
- net: do not consume a full cacheline for system_page_pool
- bpf: fix bpf_arena-related file descriptor leaks in the verifier
- drv: ice: fix freeing uninitialized pointers, fixing misuse of the
newfangled __free() auto-cleanup
Previous releases - regressions:
- x86/bpf: fixes the BPF JIT with retbleed=stuff
- xen-netfront: add missing skb_mark_for_recycle, fix page pool
accounting leaks, revealed by recently added explicit warning
- tcp: fix bind() regression for v6-only wildcard and v4-mapped-v6
non-wildcard addresses
- Bluetooth:
- replace "hci_qca: Set BDA quirk bit if fwnode exists in DT" with
better workarounds to un-break some buggy Qualcomm devices
- set conn encrypted before conn establishes, fix re-connecting to
some headsets which use slightly unusual sequence of msgs
- mptcp:
- prevent BPF accessing lowat from a subflow socket
- don't account accept() of non-MPC client as fallback to TCP
- drv: mana: fix Rx DMA datasize and skb_over_panic
- drv: i40e: fix VF MAC filter removal
Previous releases - always broken:
- gro: various fixes related to UDP tunnels - netns crossing
problems, incorrect checksum conversions, and incorrect packet
transformations which may lead to panics
- bpf: support deferring bpf_link dealloc to after RCU grace period
- nf_tables:
- release batch on table validation from abort path
- release mutex after nft_gc_seq_end from abort path
- flush pending destroy work before exit_net release
- drv: r8169: skip DASH fw status checks when DASH is disabled"
* tag 'net-6.9-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (81 commits)
netfilter: validate user input for expected length
net/sched: act_skbmod: prevent kernel-infoleak
net: usb: ax88179_178a: avoid the interface always configured as random address
net: dsa: sja1105: Fix parameters order in sja1110_pcs_mdio_write_c45()
net: ravb: Always update error counters
net: ravb: Always process TX descriptor ring
netfilter: nf_tables: discard table flag update with pending basechain deletion
netfilter: nf_tables: Fix potential data-race in __nft_flowtable_type_get()
netfilter: nf_tables: reject new basechain after table flag update
netfilter: nf_tables: flush pending destroy work before exit_net release
netfilter: nf_tables: release mutex after nft_gc_seq_end from abort path
netfilter: nf_tables: release batch on table validation from abort path
Revert "tg3: Remove residual error handling in tg3_suspend"
tg3: Remove residual error handling in tg3_suspend
net: mana: Fix Rx DMA datasize and skb_over_panic
net/sched: fix lockdep splat in qdisc_tree_reduce_backlog()
net: phy: micrel: lan8814: Fix when enabling/disabling 1-step timestamping
net: stmmac: fix rx queue priority assignment
net: txgbe: fix i2c dev name cannot match clkdev
net: fec: Set mac_managed_pm during probe
...
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index bb884c1..623fce7 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6599,7 +6599,7 @@
To turn off having tracepoints sent to printk,
echo 0 > /proc/sys/kernel/tracepoint_printk
Note, echoing 1 into this file without the
- tracepoint_printk kernel cmdline option has no effect.
+ tp_printk kernel cmdline option has no effect.
The tp_printk_stop_on_boot (see below) can also be used
to stop the printing of events to console at
diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst
index b4213296..1363267 100644
--- a/Documentation/admin-guide/mm/zswap.rst
+++ b/Documentation/admin-guide/mm/zswap.rst
@@ -155,7 +155,7 @@
Some users cannot tolerate the swapping that comes with zswap store failures
and zswap writebacks. Swapping can be disabled entirely (without disabling
-zswap itself) on a cgroup-basis as follows:
+zswap itself) on a cgroup-basis as follows::
echo 0 > /sys/fs/cgroup/<cgroup-name>/memory.zswap.writeback
@@ -166,7 +166,7 @@
When there is a sizable amount of cold memory residing in the zswap pool, it
can be advantageous to proactively write these cold pages to swap and reclaim
the memory for other use cases. By default, the zswap shrinker is disabled.
-User can enable it as follows:
+User can enable it as follows::
echo Y > /sys/module/zswap/parameters/shrinker_enabled
diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst
index 3712d81..6c24558 100644
--- a/Documentation/arch/x86/resctrl.rst
+++ b/Documentation/arch/x86/resctrl.rst
@@ -574,7 +574,7 @@
MB:<cache_id0>=bandwidth0;<cache_id1>=bandwidth1;...
Memory bandwidth Allocation specified in MiBps
----------------------------------------------
+----------------------------------------------
Memory bandwidth domain is L3 cache.
::
diff --git a/Documentation/dev-tools/testing-overview.rst b/Documentation/dev-tools/testing-overview.rst
index 0aaf6ea..1619e5e 100644
--- a/Documentation/dev-tools/testing-overview.rst
+++ b/Documentation/dev-tools/testing-overview.rst
@@ -104,6 +104,8 @@
KASAN and can be used in production. See Documentation/dev-tools/kfence.rst
* lockdep is a locking correctness validator. See
Documentation/locking/lockdep-design.rst
+* Runtime Verification (RV) supports checking specific behaviours for a given
+ subsystem. See Documentation/trace/rv/runtime-verification.rst
* There are several other pieces of debug instrumentation in the kernel, many
of which can be found in lib/Kconfig.debug
diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst
index b1d97fa..bb5c44f8 100644
--- a/Documentation/kbuild/llvm.rst
+++ b/Documentation/kbuild/llvm.rst
@@ -178,7 +178,7 @@
- ``LLVM=1``
* - s390
- Maintained
- - ``CC=clang``
+ - ``LLVM=1`` (LLVM >= 18.1.0), ``CC=clang`` (LLVM < 18.1.0)
* - um (User Mode)
- Maintained
- ``LLVM=1``
diff --git a/Documentation/virt/kvm/x86/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst
index 9957800..84335d1 100644
--- a/Documentation/virt/kvm/x86/amd-memory-encryption.rst
+++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst
@@ -46,21 +46,16 @@
Hence, the ASID for the SEV-enabled guests must be from 1 to a maximum value
defined in the CPUID 0x8000001f[ecx] field.
-SEV Key Management
-==================
+The KVM_MEMORY_ENCRYPT_OP ioctl
+===============================
-The SEV guest key management is handled by a separate processor called the AMD
-Secure Processor (AMD-SP). Firmware running inside the AMD-SP provides a secure
-key management interface to perform common hypervisor activities such as
-encrypting bootstrap code, snapshot, migrating and debugging the guest. For more
-information, see the SEV Key Management spec [api-spec]_
-
-The main ioctl to access SEV is KVM_MEMORY_ENCRYPT_OP. If the argument
-to KVM_MEMORY_ENCRYPT_OP is NULL, the ioctl returns 0 if SEV is enabled
-and ``ENOTTY`` if it is disabled (on some older versions of Linux,
-the ioctl runs normally even with a NULL argument, and therefore will
-likely return ``EFAULT``). If non-NULL, the argument to KVM_MEMORY_ENCRYPT_OP
-must be a struct kvm_sev_cmd::
+The main ioctl to access SEV is KVM_MEMORY_ENCRYPT_OP, which operates on
+the VM file descriptor. If the argument to KVM_MEMORY_ENCRYPT_OP is NULL,
+the ioctl returns 0 if SEV is enabled and ``ENOTTY`` if it is disabled
+(on some older versions of Linux, the ioctl tries to run normally even
+with a NULL argument, and therefore will likely return ``EFAULT`` instead
+of zero if SEV is enabled). If non-NULL, the argument to
+KVM_MEMORY_ENCRYPT_OP must be a struct kvm_sev_cmd::
struct kvm_sev_cmd {
__u32 id;
@@ -87,10 +82,6 @@
The KVM_SEV_INIT command is used by the hypervisor to initialize the SEV platform
context. In a typical workflow, this command should be the first command issued.
-The firmware can be initialized either by using its own non-volatile storage or
-the OS can manage the NV storage for the firmware using the module parameter
-``init_ex_path``. If the file specified by ``init_ex_path`` does not exist or
-is invalid, the OS will create or override the file with output from PSP.
Returns: 0 on success, -negative on error
@@ -434,6 +425,21 @@
Returns: 0 on success, -negative on error
+Firmware Management
+===================
+
+The SEV guest key management is handled by a separate processor called the AMD
+Secure Processor (AMD-SP). Firmware running inside the AMD-SP provides a secure
+key management interface to perform common hypervisor activities such as
+encrypting bootstrap code, snapshot, migrating and debugging the guest. For more
+information, see the SEV Key Management spec [api-spec]_
+
+The AMD-SP firmware can be initialized either by using its own non-volatile
+storage or the OS can manage the NV storage for the firmware using
+parameter ``init_ex_path`` of the ``ccp`` module. If the file specified
+by ``init_ex_path`` does not exist or is invalid, the OS will create or
+override the file with PSP non-volatile storage.
+
References
==========
diff --git a/Documentation/virt/kvm/x86/msr.rst b/Documentation/virt/kvm/x86/msr.rst
index 9315fc38..3aecf2a 100644
--- a/Documentation/virt/kvm/x86/msr.rst
+++ b/Documentation/virt/kvm/x86/msr.rst
@@ -193,8 +193,8 @@
Asynchronous page fault (APF) control MSR.
Bits 63-6 hold 64-byte aligned physical address of a 64 byte memory area
- which must be in guest RAM and must be zeroed. This memory is expected
- to hold a copy of the following structure::
+ which must be in guest RAM. This memory is expected to hold the
+ following structure::
struct kvm_vcpu_pv_apf_data {
/* Used for 'page not present' events delivered via #PF */
@@ -204,7 +204,6 @@
__u32 token;
__u8 pad[56];
- __u32 enabled;
};
Bits 5-4 of the MSR are reserved and should be zero. Bit 0 is set to 1
@@ -232,14 +231,14 @@
as regular page fault, guest must reset 'flags' to '0' before it does
something that can generate normal page fault.
- Bytes 5-7 of 64 byte memory location ('token') will be written to by the
+ Bytes 4-7 of 64 byte memory location ('token') will be written to by the
hypervisor at the time of APF 'page ready' event injection. The content
- of these bytes is a token which was previously delivered as 'page not
- present' event. The event indicates the page in now available. Guest is
- supposed to write '0' to 'token' when it is done handling 'page ready'
- event and to write 1' to MSR_KVM_ASYNC_PF_ACK after clearing the location;
- writing to the MSR forces KVM to re-scan its queue and deliver the next
- pending notification.
+ of these bytes is a token which was previously delivered in CR2 as
+ 'page not present' event. The event indicates the page is now available.
+ Guest is supposed to write '0' to 'token' when it is done handling
+ 'page ready' event and to write '1' to MSR_KVM_ASYNC_PF_ACK after
+ clearing the location; writing to the MSR forces KVM to re-scan its
+ queue and deliver the next pending notification.
Note, MSR_KVM_ASYNC_PF_INT MSR specifying the interrupt vector for 'page
ready' APF delivery needs to be written to before enabling APF mechanism
diff --git a/MAINTAINERS b/MAINTAINERS
index de969a9..7538138 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6156,7 +6156,6 @@
M: Alasdair Kergon <agk@redhat.com>
M: Mike Snitzer <snitzer@kernel.org>
M: Mikulas Patocka <mpatocka@redhat.com>
-M: dm-devel@lists.linux.dev
L: dm-devel@lists.linux.dev
S: Maintained
Q: http://patchwork.kernel.org/project/dm-devel/list/
@@ -9652,7 +9651,9 @@
S: Maintained
F: drivers/hid/hid-logitech-hidpp.c
-HIGH-RESOLUTION TIMERS, CLOCKEVENTS
+HIGH-RESOLUTION TIMERS, TIMER WHEEL, CLOCKEVENTS
+M: Anna-Maria Behnsen <anna-maria@linutronix.de>
+M: Frederic Weisbecker <frederic@kernel.org>
M: Thomas Gleixner <tglx@linutronix.de>
L: linux-kernel@vger.kernel.org
S: Maintained
@@ -9660,9 +9661,13 @@
F: Documentation/timers/
F: include/linux/clockchips.h
F: include/linux/hrtimer.h
+F: include/linux/timer.h
F: kernel/time/clockevents.c
F: kernel/time/hrtimer.c
-F: kernel/time/timer_*.c
+F: kernel/time/timer.c
+F: kernel/time/timer_list.c
+F: kernel/time/timer_migration.*
+F: tools/testing/selftests/timers/
HIGH-SPEED SCC DRIVER FOR AX.25
L: linux-hams@vger.kernel.org
@@ -15629,9 +15634,10 @@
F: include/uapi/linux/nsm.h
NOHZ, DYNTICKS SUPPORT
+M: Anna-Maria Behnsen <anna-maria@linutronix.de>
M: Frederic Weisbecker <frederic@kernel.org>
-M: Thomas Gleixner <tglx@linutronix.de>
M: Ingo Molnar <mingo@kernel.org>
+M: Thomas Gleixner <tglx@linutronix.de>
L: linux-kernel@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/nohz
@@ -17592,15 +17598,20 @@
F: include/linux/pnp.h
POSIX CLOCKS and TIMERS
+M: Anna-Maria Behnsen <anna-maria@linutronix.de>
+M: Frederic Weisbecker <frederic@kernel.org>
M: Thomas Gleixner <tglx@linutronix.de>
L: linux-kernel@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
F: fs/timerfd.c
F: include/linux/time_namespace.h
-F: include/linux/timer*
+F: include/linux/timerfd.h
+F: include/uapi/linux/time.h
+F: include/uapi/linux/timerfd.h
F: include/trace/events/timer*
-F: kernel/time/*timer*
+F: kernel/time/itimer.c
+F: kernel/time/posix-*
F: kernel/time/namespace.c
POWER MANAGEMENT CORE
@@ -22282,13 +22293,20 @@
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
F: include/linux/clocksource.h
F: include/linux/time.h
+F: include/linux/timekeeper_internal.h
+F: include/linux/timekeeping.h
F: include/linux/timex.h
F: include/uapi/linux/time.h
F: include/uapi/linux/timex.h
F: kernel/time/alarmtimer.c
-F: kernel/time/clocksource.c
-F: kernel/time/ntp.c
-F: kernel/time/time*.c
+F: kernel/time/clocksource*
+F: kernel/time/ntp*
+F: kernel/time/time.c
+F: kernel/time/timeconst.bc
+F: kernel/time/timeconv.c
+F: kernel/time/timecounter.c
+F: kernel/time/timekeeping*
+F: kernel/time/time_test.c
F: tools/testing/selftests/timers/
TIPC NETWORK LAYER
diff --git a/Makefile b/Makefile
index 763b679..4bef632 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 9
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index ce08b74..06234c3 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -291,6 +291,21 @@
blr x2
0:
mov_q x0, HCR_HOST_NVHE_FLAGS
+
+ /*
+ * Compliant CPUs advertise their VHE-onlyness with
+ * ID_AA64MMFR4_EL1.E2H0 < 0. HCR_EL2.E2H can be
+ * RES1 in that case. Publish the E2H bit early so that
+ * it can be picked up by the init_el2_state macro.
+ *
+ * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but
+ * don't advertise it (they predate this relaxation).
+ */
+ mrs_s x1, SYS_ID_AA64MMFR4_EL1
+ tbz x1, #(ID_AA64MMFR4_EL1_E2H0_SHIFT + ID_AA64MMFR4_EL1_E2H0_WIDTH - 1), 1f
+
+ orr x0, x0, #HCR_E2H
+1:
msr hcr_el2, x0
isb
@@ -303,22 +318,10 @@
mov_q x1, INIT_SCTLR_EL1_MMU_OFF
- /*
- * Compliant CPUs advertise their VHE-onlyness with
- * ID_AA64MMFR4_EL1.E2H0 < 0. HCR_EL2.E2H can be
- * RES1 in that case.
- *
- * Fruity CPUs seem to have HCR_EL2.E2H set to RES1, but
- * don't advertise it (they predate this relaxation).
- */
- mrs_s x0, SYS_ID_AA64MMFR4_EL1
- ubfx x0, x0, #ID_AA64MMFR4_EL1_E2H0_SHIFT, #ID_AA64MMFR4_EL1_E2H0_WIDTH
- tbnz x0, #(ID_AA64MMFR4_EL1_E2H0_SHIFT + ID_AA64MMFR4_EL1_E2H0_WIDTH - 1), 1f
-
mrs x0, hcr_el2
and x0, x0, #HCR_E2H
cbz x0, 2f
-1:
+
/* Set a sane SCTLR_EL1, the VHE way */
pre_disable_mmu_workaround
msr_s SYS_SCTLR_EL12, x1
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 3dee549..c4a0a35 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2597,14 +2597,11 @@
if (err)
goto out_hyp;
- if (is_protected_kvm_enabled()) {
- kvm_info("Protected nVHE mode initialized successfully\n");
- } else if (in_hyp_mode) {
- kvm_info("VHE mode initialized successfully\n");
- } else {
- char mode = cpus_have_final_cap(ARM64_KVM_HVHE) ? 'h' : 'n';
- kvm_info("Hyp mode (%cVHE) initialized successfully\n", mode);
- }
+ kvm_info("%s%sVHE mode initialized successfully\n",
+ in_hyp_mode ? "" : (is_protected_kvm_enabled() ?
+ "Protected " : "Hyp "),
+ in_hyp_mode ? "" : (cpus_have_final_cap(ARM64_KVM_HVHE) ?
+ "h" : "n"));
/*
* FIXME: Do something reasonable if kvm_init() fails after pKVM
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index a60fb13..2fc68da 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -154,7 +154,8 @@
/* Switch to requested VMID */
__tlb_switch_to_guest(mmu, &cxt, false);
- __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0);
+ __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride,
+ TLBI_TTL_UNKNOWN);
dsb(ish);
__tlbi(vmalle1is);
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 3fae583..5a59ef8 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -528,7 +528,7 @@
kvm_clear_pte(ctx->ptep);
dsb(ishst);
- __tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), ctx->level);
+ __tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), TLBI_TTL_UNKNOWN);
} else {
if (ctx->end - ctx->addr < granule)
return -EINVAL;
@@ -843,12 +843,15 @@
* Perform the appropriate TLB invalidation based on the
* evicted pte value (if any).
*/
- if (kvm_pte_table(ctx->old, ctx->level))
- kvm_tlb_flush_vmid_range(mmu, ctx->addr,
- kvm_granule_size(ctx->level));
- else if (kvm_pte_valid(ctx->old))
+ if (kvm_pte_table(ctx->old, ctx->level)) {
+ u64 size = kvm_granule_size(ctx->level);
+ u64 addr = ALIGN_DOWN(ctx->addr, size);
+
+ kvm_tlb_flush_vmid_range(mmu, addr, size);
+ } else if (kvm_pte_valid(ctx->old)) {
kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
ctx->addr, ctx->level);
+ }
}
if (stage2_pte_is_counted(ctx->old))
@@ -896,9 +899,13 @@
if (kvm_pte_valid(ctx->old)) {
kvm_clear_pte(ctx->ptep);
- if (!stage2_unmap_defer_tlb_flush(pgt))
- kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
- ctx->addr, ctx->level);
+ if (kvm_pte_table(ctx->old, ctx->level)) {
+ kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr,
+ TLBI_TTL_UNKNOWN);
+ } else if (!stage2_unmap_defer_tlb_flush(pgt)) {
+ kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr,
+ ctx->level);
+ }
}
mm_ops->put_page(ctx->ptep);
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index b32e294..1a60b95 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -171,7 +171,8 @@
/* Switch to requested VMID */
__tlb_switch_to_guest(mmu, &cxt);
- __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0);
+ __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride,
+ TLBI_TTL_UNKNOWN);
dsb(ish);
__tlbi(vmalle1is);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 1868077..dc04bc7 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1637,7 +1637,7 @@
fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
- if (esr_fsc_is_permission_fault(esr)) {
+ if (esr_fsc_is_translation_fault(esr)) {
/* Beyond sanitised PARange (which is the IPA limit) */
if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
kvm_inject_size_fault(vcpu);
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 06ef440..516dc70 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -619,15 +619,6 @@
bool
-config FIT_IMAGE_FDT_EPM5
- bool "Include FDT for Mobileye EyeQ5 development platforms"
- depends on MACH_EYEQ5
- default n
- help
- Enable this to include the FDT for the EyeQ5 development platforms
- from Mobileye in the FIT kernel image.
- This requires u-boot on the platform.
-
config MACH_NINTENDO64
bool "Nintendo 64 console"
select CEVT_R4K
@@ -1011,6 +1002,15 @@
endchoice
+config FIT_IMAGE_FDT_EPM5
+ bool "Include FDT for Mobileye EyeQ5 development platforms"
+ depends on MACH_EYEQ5
+ default n
+ help
+ Enable this to include the FDT for the EyeQ5 development platforms
+ from Mobileye in the FIT kernel image.
+ This requires u-boot on the platform.
+
source "arch/mips/alchemy/Kconfig"
source "arch/mips/ath25/Kconfig"
source "arch/mips/ath79/Kconfig"
diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c
index 39e72aa..b467ba5 100644
--- a/arch/riscv/kvm/aia_aplic.c
+++ b/arch/riscv/kvm/aia_aplic.c
@@ -137,11 +137,21 @@
raw_spin_lock_irqsave(&irqd->lock, flags);
sm = irqd->sourcecfg & APLIC_SOURCECFG_SM_MASK;
- if (!pending &&
- ((sm == APLIC_SOURCECFG_SM_LEVEL_HIGH) ||
- (sm == APLIC_SOURCECFG_SM_LEVEL_LOW)))
+ if (sm == APLIC_SOURCECFG_SM_INACTIVE)
goto skip_write_pending;
+ if (sm == APLIC_SOURCECFG_SM_LEVEL_HIGH ||
+ sm == APLIC_SOURCECFG_SM_LEVEL_LOW) {
+ if (!pending)
+ goto skip_write_pending;
+ if ((irqd->state & APLIC_IRQ_STATE_INPUT) &&
+ sm == APLIC_SOURCECFG_SM_LEVEL_LOW)
+ goto skip_write_pending;
+ if (!(irqd->state & APLIC_IRQ_STATE_INPUT) &&
+ sm == APLIC_SOURCECFG_SM_LEVEL_HIGH)
+ goto skip_write_pending;
+ }
+
if (pending)
irqd->state |= APLIC_IRQ_STATE_PENDING;
else
@@ -187,16 +197,31 @@
static bool aplic_read_input(struct aplic *aplic, u32 irq)
{
- bool ret;
- unsigned long flags;
+ u32 sourcecfg, sm, raw_input, irq_inverted;
struct aplic_irq *irqd;
+ unsigned long flags;
+ bool ret = false;
if (!irq || aplic->nr_irqs <= irq)
return false;
irqd = &aplic->irqs[irq];
raw_spin_lock_irqsave(&irqd->lock, flags);
- ret = (irqd->state & APLIC_IRQ_STATE_INPUT) ? true : false;
+
+ sourcecfg = irqd->sourcecfg;
+ if (sourcecfg & APLIC_SOURCECFG_D)
+ goto skip;
+
+ sm = sourcecfg & APLIC_SOURCECFG_SM_MASK;
+ if (sm == APLIC_SOURCECFG_SM_INACTIVE)
+ goto skip;
+
+ raw_input = (irqd->state & APLIC_IRQ_STATE_INPUT) ? 1 : 0;
+ irq_inverted = (sm == APLIC_SOURCECFG_SM_LEVEL_LOW ||
+ sm == APLIC_SOURCECFG_SM_EDGE_FALL) ? 1 : 0;
+ ret = !!(raw_input ^ irq_inverted);
+
+skip:
raw_spin_unlock_irqrestore(&irqd->lock, flags);
return ret;
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index f4a6124..994adc2 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -986,7 +986,7 @@
static inline unsigned long num_isa_ext_regs(const struct kvm_vcpu *vcpu)
{
- return copy_isa_ext_reg_indices(vcpu, NULL);;
+ return copy_isa_ext_reg_indices(vcpu, NULL);
}
static int copy_sbi_ext_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
index 6a1f36d..cf0ad89 100644
--- a/arch/x86/Kbuild
+++ b/arch/x86/Kbuild
@@ -28,7 +28,7 @@
obj-$(CONFIG_KEXEC_FILE) += purgatory/
-obj-y += virt/svm/
+obj-y += virt/
# for cleaning
subdir- += boot tools
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 39886ba..4fff6ed 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2439,6 +2439,8 @@
# with named address spaces - see GCC PR sanitizer/111736.
#
depends on !KASAN
+ # -fsanitize=thread (KCSAN) is also incompatible.
+ depends on !KCSAN
config CC_HAS_SLS
def_bool $(cc-option,-mharden-sls=all)
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 662d9d4..5ab93fc 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -251,8 +251,6 @@
libs-y += arch/x86/lib/
-core-y += arch/x86/virt/
-
# drivers-y are linked after core-y
drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/
drivers-$(CONFIG_PCI) += arch/x86/pci/
diff --git a/arch/x86/boot/compressed/efi_mixed.S b/arch/x86/boot/compressed/efi_mixed.S
index 719e939..876fc6d 100644
--- a/arch/x86/boot/compressed/efi_mixed.S
+++ b/arch/x86/boot/compressed/efi_mixed.S
@@ -15,10 +15,12 @@
*/
#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
#include <asm/msr.h>
#include <asm/page_types.h>
#include <asm/processor-flags.h>
#include <asm/segment.h>
+#include <asm/setup.h>
.code64
.text
@@ -149,6 +151,7 @@
SYM_FUNC_START(efi32_stub_entry)
call 1f
1: popl %ecx
+ leal (efi32_boot_args - 1b)(%ecx), %ebx
/* Clear BSS */
xorl %eax, %eax
@@ -163,6 +166,7 @@
popl %ecx
popl %edx
popl %esi
+ movl %esi, 8(%ebx)
jmp efi32_entry
SYM_FUNC_END(efi32_stub_entry)
#endif
@@ -239,8 +243,6 @@
*
* Arguments: %ecx image handle
* %edx EFI system table pointer
- * %esi struct bootparams pointer (or NULL when not using
- * the EFI handover protocol)
*
* Since this is the point of no return for ordinary execution, no registers
* are considered live except for the function parameters. [Note that the EFI
@@ -266,9 +268,18 @@
leal (efi32_boot_args - 1b)(%ebx), %ebx
movl %ecx, 0(%ebx)
movl %edx, 4(%ebx)
- movl %esi, 8(%ebx)
movb $0x0, 12(%ebx) // efi_is64
+ /*
+ * Allocate some memory for a temporary struct boot_params, which only
+ * needs the minimal pieces that startup_32() relies on.
+ */
+ subl $PARAM_SIZE, %esp
+ movl %esp, %esi
+ movl $PAGE_SIZE, BP_kernel_alignment(%esi)
+ movl $_end - 1b, BP_init_size(%esi)
+ subl $startup_32 - 1b, BP_init_size(%esi)
+
/* Disable paging */
movl %cr0, %eax
btrl $X86_CR0_PG_BIT, %eax
@@ -294,8 +305,7 @@
movl 8(%ebp), %ecx // image_handle
movl 12(%ebp), %edx // sys_table
- xorl %esi, %esi
- jmp efi32_entry // pass %ecx, %edx, %esi
+ jmp efi32_entry // pass %ecx, %edx
// no other registers remain live
2: popl %edi // restore callee-save registers
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index fd63051..3d64bcc 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -41,6 +41,7 @@
obj-$(CONFIG_COMPAT_32) += vdso-image-32.o vdso32-setup.o
OBJECT_FILES_NON_STANDARD_vdso-image-32.o := n
+OBJECT_FILES_NON_STANDARD_vdso-image-x32.o := n
OBJECT_FILES_NON_STANDARD_vdso-image-64.o := n
OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index aec16e5..985ef3b 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -250,7 +250,7 @@
/*
* AMD Performance Monitor Family 17h and later:
*/
-static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
+static const u64 amd_zen1_perfmon_event_map[PERF_COUNT_HW_MAX] =
{
[PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
[PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
@@ -262,10 +262,39 @@
[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187,
};
+static const u64 amd_zen2_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x0964,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a9,
+};
+
+static const u64 amd_zen4_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x0964,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a9,
+ [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x100000120,
+};
+
static u64 amd_pmu_event_map(int hw_event)
{
- if (boot_cpu_data.x86 >= 0x17)
- return amd_f17h_perfmon_event_map[hw_event];
+ if (cpu_feature_enabled(X86_FEATURE_ZEN4) || boot_cpu_data.x86 >= 0x1a)
+ return amd_zen4_perfmon_event_map[hw_event];
+
+ if (cpu_feature_enabled(X86_FEATURE_ZEN2) || boot_cpu_data.x86 >= 0x19)
+ return amd_zen2_perfmon_event_map[hw_event];
+
+ if (cpu_feature_enabled(X86_FEATURE_ZEN1))
+ return amd_zen1_perfmon_event_map[hw_event];
return amd_perfmon_event_map[hw_event];
}
@@ -904,8 +933,8 @@
if (!status)
goto done;
- /* Read branch records before unfreezing */
- if (status & GLOBAL_STATUS_LBRS_FROZEN) {
+ /* Read branch records */
+ if (x86_pmu.lbr_nr) {
amd_pmu_lbr_read();
status &= ~GLOBAL_STATUS_LBRS_FROZEN;
}
diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c
index 4a1e600..5149830 100644
--- a/arch/x86/events/amd/lbr.c
+++ b/arch/x86/events/amd/lbr.c
@@ -402,10 +402,12 @@
wrmsrl(MSR_AMD64_LBR_SELECT, lbr_select);
}
- rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
- rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
+ if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
+ rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
+ wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+ }
- wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+ rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg | DBG_EXTN_CFG_LBRV2EN);
}
@@ -418,10 +420,12 @@
return;
rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
- rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
-
wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN);
- wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+
+ if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
+ rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
+ wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+ }
}
__init int amd_pmu_lbr_init(void)
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 076bf8d..25466c4 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -14,6 +14,7 @@
#include <asm/asm.h>
#include <asm/fred.h>
#include <asm/gsseg.h>
+#include <asm/nospec-branch.h>
#ifndef CONFIG_X86_CMPXCHG64
extern void cmpxchg8b_emu(void);
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index a127369..42157dd 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -91,8 +91,9 @@
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \
REQUIRED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 21))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 22))
#define DISABLED_MASK_BIT_SET(feature_bit) \
( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \
@@ -116,8 +117,9 @@
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \
DISABLED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 21))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 22))
#define cpu_has(c, bit) \
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index f0337f7..a38f8f9 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
/*
* Defines x86 CPU feature bits
*/
-#define NCAPINTS 21 /* N 32-bit words worth of info */
+#define NCAPINTS 22 /* N 32-bit words worth of info */
#define NBUGINTS 2 /* N 32-bit bug flags */
/*
@@ -460,6 +460,14 @@
#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */
/*
+ * Extended auxiliary flags: Linux defined - for features scattered in various
+ * CPUID levels like 0x80000022, etc.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */
+
+/*
* BUG word(s)
*/
#define X86_BUG(x) (NCAPINTS*32 + (x))
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index da4054f..c492bdc 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -155,6 +155,7 @@
#define DISABLED_MASK18 (DISABLE_IBT)
#define DISABLED_MASK19 (DISABLE_SEV_SNP)
#define DISABLED_MASK20 0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define DISABLED_MASK21 0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index fc3a8a3..170c89e 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -262,11 +262,20 @@
.Lskip_rsb_\@:
.endm
+/*
+ * The CALL to srso_alias_untrain_ret() must be patched in directly at
+ * the spot where untraining must be done, ie., srso_alias_untrain_ret()
+ * must be the target of a CALL instruction instead of indirectly
+ * jumping to a wrapper which then calls it. Therefore, this macro is
+ * called outside of __UNTRAIN_RET below, for the time being, before the
+ * kernel can support nested alternatives with arbitrary nesting.
+ */
+.macro CALL_UNTRAIN_RET
#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
-#define CALL_UNTRAIN_RET "call entry_untrain_ret"
-#else
-#define CALL_UNTRAIN_RET ""
+ ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \
+ "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS
#endif
+.endm
/*
* Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the
@@ -282,8 +291,8 @@
.macro __UNTRAIN_RET ibpb_feature, call_depth_insns
#if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY)
VALIDATE_UNRET_END
- ALTERNATIVE_3 "", \
- CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
+ CALL_UNTRAIN_RET
+ ALTERNATIVE_2 "", \
"call entry_ibpb", \ibpb_feature, \
__stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH
#endif
@@ -342,6 +351,8 @@
static inline void retbleed_return_thunk(void) {}
#endif
+extern void srso_alias_untrain_ret(void);
+
#ifdef CONFIG_MITIGATION_SRSO
extern void srso_return_thunk(void);
extern void srso_alias_return_thunk(void);
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index 7ba1726..e9187dd 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -99,6 +99,7 @@
#define REQUIRED_MASK18 0
#define REQUIRED_MASK19 0
#define REQUIRED_MASK20 0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define REQUIRED_MASK21 0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 9477b40..07e125f 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -218,12 +218,12 @@
unsigned long npages);
void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
unsigned long npages);
-void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op);
void snp_set_memory_shared(unsigned long vaddr, unsigned long npages);
void snp_set_memory_private(unsigned long vaddr, unsigned long npages);
void snp_set_wakeup_secondary_cpu(void);
bool snp_init(struct boot_params *bp);
void __noreturn snp_abort(void);
+void snp_dmi_setup(void);
int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio);
void snp_accept_memory(phys_addr_t start, phys_addr_t end);
u64 snp_get_unsupported_features(u64 status);
@@ -244,12 +244,12 @@
early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { }
static inline void __init
early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned long npages) { }
-static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { }
static inline void snp_set_memory_shared(unsigned long vaddr, unsigned long npages) { }
static inline void snp_set_memory_private(unsigned long vaddr, unsigned long npages) { }
static inline void snp_set_wakeup_secondary_cpu(void) { }
static inline bool snp_init(struct boot_params *bp) { return false; }
static inline void snp_abort(void) { }
+static inline void snp_dmi_setup(void) { }
static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio)
{
return -ENOTTY;
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index b89b40f..6149eab 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -30,12 +30,13 @@
* @reserve_resources: reserve the standard resources for the
* platform
* @memory_setup: platform specific memory setup
- *
+ * @dmi_setup: platform specific DMI setup
*/
struct x86_init_resources {
void (*probe_roms)(void);
void (*reserve_resources)(void);
char *(*memory_setup)(void);
+ void (*dmi_setup)(void);
};
/**
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index ad29984..ef11aa4 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -694,6 +694,7 @@
struct kvm_sev_cmd {
__u32 id;
+ __u32 pad0;
__u64 data;
__u32 error;
__u32 sev_fd;
@@ -704,28 +705,35 @@
__u32 policy;
__u64 dh_uaddr;
__u32 dh_len;
+ __u32 pad0;
__u64 session_uaddr;
__u32 session_len;
+ __u32 pad1;
};
struct kvm_sev_launch_update_data {
__u64 uaddr;
__u32 len;
+ __u32 pad0;
};
struct kvm_sev_launch_secret {
__u64 hdr_uaddr;
__u32 hdr_len;
+ __u32 pad0;
__u64 guest_uaddr;
__u32 guest_len;
+ __u32 pad1;
__u64 trans_uaddr;
__u32 trans_len;
+ __u32 pad2;
};
struct kvm_sev_launch_measure {
__u64 uaddr;
__u32 len;
+ __u32 pad0;
};
struct kvm_sev_guest_status {
@@ -738,33 +746,43 @@
__u64 src_uaddr;
__u64 dst_uaddr;
__u32 len;
+ __u32 pad0;
};
struct kvm_sev_attestation_report {
__u8 mnonce[16];
__u64 uaddr;
__u32 len;
+ __u32 pad0;
};
struct kvm_sev_send_start {
__u32 policy;
+ __u32 pad0;
__u64 pdh_cert_uaddr;
__u32 pdh_cert_len;
+ __u32 pad1;
__u64 plat_certs_uaddr;
__u32 plat_certs_len;
+ __u32 pad2;
__u64 amd_certs_uaddr;
__u32 amd_certs_len;
+ __u32 pad3;
__u64 session_uaddr;
__u32 session_len;
+ __u32 pad4;
};
struct kvm_sev_send_update_data {
__u64 hdr_uaddr;
__u32 hdr_len;
+ __u32 pad0;
__u64 guest_uaddr;
__u32 guest_len;
+ __u32 pad1;
__u64 trans_uaddr;
__u32 trans_len;
+ __u32 pad2;
};
struct kvm_sev_receive_start {
@@ -772,17 +790,22 @@
__u32 policy;
__u64 pdh_uaddr;
__u32 pdh_len;
+ __u32 pad0;
__u64 session_uaddr;
__u32 session_len;
+ __u32 pad1;
};
struct kvm_sev_receive_update_data {
__u64 hdr_uaddr;
__u32 hdr_len;
+ __u32 pad0;
__u64 guest_uaddr;
__u32 guest_len;
+ __u32 pad1;
__u64 trans_uaddr;
__u32 trans_len;
+ __u32 pad2;
};
#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 6bc3456..a1efa79 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -142,7 +142,6 @@
__u32 token;
__u8 pad[56];
- __u32 enabled;
};
#define KVM_PV_EOI_BIT 0
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 0dad49a..a515328 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -49,6 +49,7 @@
{ X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 },
{ X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 },
{ X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 },
+ { X86_FEATURE_AMD_LBR_PMC_FREEZE, CPUID_EAX, 2, 0x80000022, 0 },
{ 0, 0, 0, 0, 0 }
};
diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c
index e963344..53935b4 100644
--- a/arch/x86/kernel/eisa.c
+++ b/arch/x86/kernel/eisa.c
@@ -2,6 +2,7 @@
/*
* EISA specific code
*/
+#include <linux/cc_platform.h>
#include <linux/ioport.h>
#include <linux/eisa.h>
#include <linux/io.h>
@@ -12,7 +13,7 @@
{
void __iomem *p;
- if (xen_pv_domain() && !xen_initial_domain())
+ if ((xen_pv_domain() && !xen_initial_domain()) || cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
return 0;
p = ioremap(0x0FFFD9, 4);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 4cadfd6..7f0732b 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -65,6 +65,7 @@
early_param("no-steal-acc", parse_no_stealacc);
+static DEFINE_PER_CPU_READ_MOSTLY(bool, async_pf_enabled);
static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
static int has_steal_clock = 0;
@@ -244,7 +245,7 @@
{
u32 flags = 0;
- if (__this_cpu_read(apf_reason.enabled)) {
+ if (__this_cpu_read(async_pf_enabled)) {
flags = __this_cpu_read(apf_reason.flags);
__this_cpu_write(apf_reason.flags, 0);
}
@@ -295,7 +296,7 @@
inc_irq_stat(irq_hv_callback_count);
- if (__this_cpu_read(apf_reason.enabled)) {
+ if (__this_cpu_read(async_pf_enabled)) {
token = __this_cpu_read(apf_reason.token);
kvm_async_pf_task_wake(token);
__this_cpu_write(apf_reason.token, 0);
@@ -362,7 +363,7 @@
wrmsrl(MSR_KVM_ASYNC_PF_INT, HYPERVISOR_CALLBACK_VECTOR);
wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
- __this_cpu_write(apf_reason.enabled, 1);
+ __this_cpu_write(async_pf_enabled, true);
pr_debug("setup async PF for cpu %d\n", smp_processor_id());
}
@@ -383,11 +384,11 @@
static void kvm_pv_disable_apf(void)
{
- if (!__this_cpu_read(apf_reason.enabled))
+ if (!__this_cpu_read(async_pf_enabled))
return;
wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
- __this_cpu_write(apf_reason.enabled, 0);
+ __this_cpu_write(async_pf_enabled, false);
pr_debug("disable async PF for cpu %d\n", smp_processor_id());
}
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 9a5b372..ed163c8 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -580,7 +580,7 @@
static char *nmi_check_stall_msg[] = {
/* */
-/* +--------- nsp->idt_seq_snap & 0x1: CPU is in NMI handler. */
+/* +--------- nmi_seq & 0x1: CPU is currently in NMI handler. */
/* | +------ cpu_is_offline(cpu) */
/* | | +--- nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls): */
/* | | | NMI handler has been invoked. */
@@ -628,22 +628,26 @@
nmi_seq = READ_ONCE(nsp->idt_nmi_seq);
if (nsp->idt_nmi_seq_snap + 1 == nmi_seq && (nmi_seq & 0x1)) {
msgp = "CPU entered NMI handler function, but has not exited";
- } else if ((nsp->idt_nmi_seq_snap & 0x1) != (nmi_seq & 0x1)) {
- msgp = "CPU is handling NMIs";
- } else {
- idx = ((nsp->idt_seq_snap & 0x1) << 2) |
+ } else if (nsp->idt_nmi_seq_snap == nmi_seq ||
+ nsp->idt_nmi_seq_snap + 1 == nmi_seq) {
+ idx = ((nmi_seq & 0x1) << 2) |
(cpu_is_offline(cpu) << 1) |
(nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls));
msgp = nmi_check_stall_msg[idx];
if (nsp->idt_ignored_snap != READ_ONCE(nsp->idt_ignored) && (idx & 0x1))
modp = ", but OK because ignore_nmis was set";
- if (nmi_seq & 0x1)
- msghp = " (CPU currently in NMI handler function)";
- else if (nsp->idt_nmi_seq_snap + 1 == nmi_seq)
+ if (nsp->idt_nmi_seq_snap + 1 == nmi_seq)
msghp = " (CPU exited one NMI handler function)";
+ else if (nmi_seq & 0x1)
+ msghp = " (CPU currently in NMI handler function)";
+ else
+ msghp = " (CPU was never in an NMI handler function)";
+ } else {
+ msgp = "CPU is handling NMIs";
}
- pr_alert("%s: CPU %d: %s%s%s, last activity: %lu jiffies ago.\n",
- __func__, cpu, msgp, modp, msghp, j - READ_ONCE(nsp->recv_jiffies));
+ pr_alert("%s: CPU %d: %s%s%s\n", __func__, cpu, msgp, modp, msghp);
+ pr_alert("%s: last activity: %lu jiffies ago.\n",
+ __func__, j - READ_ONCE(nsp->recv_jiffies));
}
}
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
index 319fef3..cc2c34b 100644
--- a/arch/x86/kernel/probe_roms.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -203,16 +203,6 @@
unsigned char c;
int i;
- /*
- * The ROM memory range is not part of the e820 table and is therefore not
- * pre-validated by BIOS. The kernel page table maps the ROM region as encrypted
- * memory, and SNP requires encrypted memory to be validated before access.
- * Do that here.
- */
- snp_prep_memory(video_rom_resource.start,
- ((system_rom_resource.end + 1) - video_rom_resource.start),
- SNP_PAGE_STATE_PRIVATE);
-
/* video rom */
upper = adapter_rom_resources[0].start;
for (start = video_rom_resource.start; start < upper; start += 2048) {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ef20650..0109e6c 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -9,7 +9,6 @@
#include <linux/console.h>
#include <linux/crash_dump.h>
#include <linux/dma-map-ops.h>
-#include <linux/dmi.h>
#include <linux/efi.h>
#include <linux/ima.h>
#include <linux/init_ohci1394_dma.h>
@@ -902,7 +901,7 @@
efi_init();
reserve_ibft_region();
- dmi_setup();
+ x86_init.resources.dmi_setup();
/*
* VMware detection requires dmi to be available, so this
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index b59b09c..7e1e63cc 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -23,6 +23,7 @@
#include <linux/platform_device.h>
#include <linux/io.h>
#include <linux/psp-sev.h>
+#include <linux/dmi.h>
#include <uapi/linux/sev-guest.h>
#include <asm/init.h>
@@ -795,21 +796,6 @@
early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED);
}
-void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op)
-{
- unsigned long vaddr, npages;
-
- vaddr = (unsigned long)__va(paddr);
- npages = PAGE_ALIGN(sz) >> PAGE_SHIFT;
-
- if (op == SNP_PAGE_STATE_PRIVATE)
- early_snp_set_memory_private(vaddr, paddr, npages);
- else if (op == SNP_PAGE_STATE_SHARED)
- early_snp_set_memory_shared(vaddr, paddr, npages);
- else
- WARN(1, "invalid memory op %d\n", op);
-}
-
static unsigned long __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,
unsigned long vaddr_end, int op)
{
@@ -2136,6 +2122,17 @@
sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
}
+/*
+ * SEV-SNP guests should only execute dmi_setup() if EFI_CONFIG_TABLES are
+ * enabled, as the alternative (fallback) logic for DMI probing in the legacy
+ * ROM region can cause a crash since this region is not pre-validated.
+ */
+void __init snp_dmi_setup(void)
+{
+ if (efi_enabled(EFI_CONFIG_TABLES))
+ dmi_setup();
+}
+
static void dump_cpuid_table(void)
{
const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index a42830d..d5dc5a9 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -3,6 +3,7 @@
*
* For licencing details see kernel-base/COPYING
*/
+#include <linux/dmi.h>
#include <linux/init.h>
#include <linux/ioport.h>
#include <linux/export.h>
@@ -66,6 +67,7 @@
.probe_roms = probe_roms,
.reserve_resources = reserve_standard_io_resources,
.memory_setup = e820__memory_setup_default,
+ .dmi_setup = dmi_setup,
},
.mpparse = {
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index adba49a..bfc0bfc 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -189,15 +189,15 @@
return 0;
}
-static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu,
- const char *sig)
+static struct kvm_hypervisor_cpuid __kvm_get_hypervisor_cpuid(struct kvm_cpuid_entry2 *entries,
+ int nent, const char *sig)
{
struct kvm_hypervisor_cpuid cpuid = {};
struct kvm_cpuid_entry2 *entry;
u32 base;
for_each_possible_hypervisor_cpuid_base(base) {
- entry = kvm_find_cpuid_entry(vcpu, base);
+ entry = cpuid_entry2_find(entries, nent, base, KVM_CPUID_INDEX_NOT_SIGNIFICANT);
if (entry) {
u32 signature[3];
@@ -217,22 +217,29 @@
return cpuid;
}
-static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu,
- struct kvm_cpuid_entry2 *entries, int nent)
+static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu,
+ const char *sig)
+{
+ return __kvm_get_hypervisor_cpuid(vcpu->arch.cpuid_entries,
+ vcpu->arch.cpuid_nent, sig);
+}
+
+static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_cpuid_entry2 *entries,
+ int nent, u32 kvm_cpuid_base)
+{
+ return cpuid_entry2_find(entries, nent, kvm_cpuid_base | KVM_CPUID_FEATURES,
+ KVM_CPUID_INDEX_NOT_SIGNIFICANT);
+}
+
+static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
{
u32 base = vcpu->arch.kvm_cpuid.base;
if (!base)
return NULL;
- return cpuid_entry2_find(entries, nent, base | KVM_CPUID_FEATURES,
- KVM_CPUID_INDEX_NOT_SIGNIFICANT);
-}
-
-static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
-{
- return __kvm_find_kvm_cpuid_features(vcpu, vcpu->arch.cpuid_entries,
- vcpu->arch.cpuid_nent);
+ return __kvm_find_kvm_cpuid_features(vcpu->arch.cpuid_entries,
+ vcpu->arch.cpuid_nent, base);
}
void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
@@ -266,6 +273,7 @@
int nent)
{
struct kvm_cpuid_entry2 *best;
+ struct kvm_hypervisor_cpuid kvm_cpuid;
best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT);
if (best) {
@@ -292,10 +300,12 @@
cpuid_entry_has(best, X86_FEATURE_XSAVEC)))
best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
- best = __kvm_find_kvm_cpuid_features(vcpu, entries, nent);
- if (kvm_hlt_in_guest(vcpu->kvm) && best &&
- (best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
- best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
+ kvm_cpuid = __kvm_get_hypervisor_cpuid(entries, nent, KVM_SIGNATURE);
+ if (kvm_cpuid.base) {
+ best = __kvm_find_kvm_cpuid_features(entries, nent, kvm_cpuid.base);
+ if (kvm_hlt_in_guest(vcpu->kvm) && best)
+ best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
+ }
if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
best = cpuid_entry2_find(entries, nent, 0x1, KVM_CPUID_INDEX_NOT_SIGNIFICANT);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index ae0ac12..e5a4d9b 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -84,9 +84,10 @@
};
/* Called with the sev_bitmap_lock held, or on shutdown */
-static int sev_flush_asids(int min_asid, int max_asid)
+static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid)
{
- int ret, asid, error = 0;
+ int ret, error = 0;
+ unsigned int asid;
/* Check if there are any ASIDs to reclaim before performing a flush */
asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid);
@@ -116,7 +117,7 @@
}
/* Must be called with the sev_bitmap_lock held */
-static bool __sev_recycle_asids(int min_asid, int max_asid)
+static bool __sev_recycle_asids(unsigned int min_asid, unsigned int max_asid)
{
if (sev_flush_asids(min_asid, max_asid))
return false;
@@ -143,8 +144,20 @@
static int sev_asid_new(struct kvm_sev_info *sev)
{
- int asid, min_asid, max_asid, ret;
+ /*
+ * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
+ * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
+ * Note: min ASID can end up larger than the max if basic SEV support is
+ * effectively disabled by disallowing use of ASIDs for SEV guests.
+ */
+ unsigned int min_asid = sev->es_active ? 1 : min_sev_asid;
+ unsigned int max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
+ unsigned int asid;
bool retry = true;
+ int ret;
+
+ if (min_asid > max_asid)
+ return -ENOTTY;
WARN_ON(sev->misc_cg);
sev->misc_cg = get_current_misc_cg();
@@ -157,12 +170,6 @@
mutex_lock(&sev_bitmap_lock);
- /*
- * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
- * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
- */
- min_asid = sev->es_active ? 1 : min_sev_asid;
- max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
again:
asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid);
if (asid > max_asid) {
@@ -179,7 +186,8 @@
mutex_unlock(&sev_bitmap_lock);
- return asid;
+ sev->asid = asid;
+ return 0;
e_uncharge:
sev_misc_cg_uncharge(sev);
put_misc_cg(sev->misc_cg);
@@ -187,7 +195,7 @@
return ret;
}
-static int sev_get_asid(struct kvm *kvm)
+static unsigned int sev_get_asid(struct kvm *kvm)
{
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
@@ -247,21 +255,19 @@
{
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
struct sev_platform_init_args init_args = {0};
- int asid, ret;
+ int ret;
if (kvm->created_vcpus)
return -EINVAL;
- ret = -EBUSY;
if (unlikely(sev->active))
- return ret;
+ return -EINVAL;
sev->active = true;
sev->es_active = argp->id == KVM_SEV_ES_INIT;
- asid = sev_asid_new(sev);
- if (asid < 0)
+ ret = sev_asid_new(sev);
+ if (ret)
goto e_no_asid;
- sev->asid = asid;
init_args.probe = false;
ret = sev_platform_init(&init_args);
@@ -287,8 +293,8 @@
static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
{
+ unsigned int asid = sev_get_asid(kvm);
struct sev_data_activate activate;
- int asid = sev_get_asid(kvm);
int ret;
/* activate ASID on the given handle */
@@ -2240,8 +2246,10 @@
goto out;
}
- sev_asid_count = max_sev_asid - min_sev_asid + 1;
- WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count));
+ if (min_sev_asid <= max_sev_asid) {
+ sev_asid_count = max_sev_asid - min_sev_asid + 1;
+ WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count));
+ }
sev_supported = true;
/* SEV-ES support requested? */
@@ -2272,7 +2280,9 @@
out:
if (boot_cpu_has(X86_FEATURE_SEV))
pr_info("SEV %s (ASIDs %u - %u)\n",
- sev_supported ? "enabled" : "disabled",
+ sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" :
+ "unusable" :
+ "disabled",
min_sev_asid, max_sev_asid);
if (boot_cpu_has(X86_FEATURE_SEV_ES))
pr_info("SEV-ES %s (ASIDs %u - %u)\n",
@@ -2320,7 +2330,7 @@
*/
static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va)
{
- int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid;
+ unsigned int asid = sev_get_asid(vcpu->kvm);
/*
* Note! The address must be a kernel address, as regular page walk
@@ -2638,7 +2648,7 @@
void pre_sev_run(struct vcpu_svm *svm, int cpu)
{
struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
- int asid = sev_get_asid(svm->vcpu.kvm);
+ unsigned int asid = sev_get_asid(svm->vcpu.kvm);
/* Assign the asid allocated with this SEV guest */
svm->asid = asid;
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 88659de..c6b4b17 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -735,13 +735,13 @@
* Tracepoint for nested #vmexit because of interrupt pending
*/
TRACE_EVENT(kvm_invlpga,
- TP_PROTO(__u64 rip, int asid, u64 address),
+ TP_PROTO(__u64 rip, unsigned int asid, u64 address),
TP_ARGS(rip, asid, address),
TP_STRUCT__entry(
- __field( __u64, rip )
- __field( int, asid )
- __field( __u64, address )
+ __field( __u64, rip )
+ __field( unsigned int, asid )
+ __field( __u64, address )
),
TP_fast_assign(
@@ -750,7 +750,7 @@
__entry->address = address;
),
- TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx",
+ TP_printk("rip: 0x%016llx asid: %u address: 0x%016llx",
__entry->rip, __entry->asid, __entry->address)
);
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 721b528..0795b34 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -163,6 +163,7 @@
lfence
jmp srso_alias_return_thunk
SYM_FUNC_END(srso_alias_untrain_ret)
+__EXPORT_THUNK(srso_alias_untrain_ret)
.popsection
.pushsection .text..__x86.rethunk_safe
@@ -224,10 +225,15 @@
SYM_CODE_END(srso_return_thunk)
#define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret"
-#define JMP_SRSO_ALIAS_UNTRAIN_RET "jmp srso_alias_untrain_ret"
#else /* !CONFIG_MITIGATION_SRSO */
+/* Dummy for the alternative in CALL_UNTRAIN_RET. */
+SYM_CODE_START(srso_alias_untrain_ret)
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+SYM_FUNC_END(srso_alias_untrain_ret)
+__EXPORT_THUNK(srso_alias_untrain_ret)
#define JMP_SRSO_UNTRAIN_RET "ud2"
-#define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2"
#endif /* CONFIG_MITIGATION_SRSO */
#ifdef CONFIG_MITIGATION_UNRET_ENTRY
@@ -319,9 +325,7 @@
#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
SYM_FUNC_START(entry_untrain_ret)
- ALTERNATIVE_2 JMP_RETBLEED_UNTRAIN_RET, \
- JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO, \
- JMP_SRSO_ALIAS_UNTRAIN_RET, X86_FEATURE_SRSO_ALIAS
+ ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO
SYM_FUNC_END(entry_untrain_ret)
__EXPORT_THUNK(entry_untrain_ret)
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index a204a33..968d700 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -26,31 +26,18 @@
for (; addr < end; addr = next) {
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
- bool use_gbpage;
next = (addr & PUD_MASK) + PUD_SIZE;
if (next > end)
next = end;
- /* if this is already a gbpage, this portion is already mapped */
- if (pud_leaf(*pud))
- continue;
-
- /* Is using a gbpage allowed? */
- use_gbpage = info->direct_gbpages;
-
- /* Don't use gbpage if it maps more than the requested region. */
- /* at the begining: */
- use_gbpage &= ((addr & ~PUD_MASK) == 0);
- /* ... or at the end: */
- use_gbpage &= ((next & ~PUD_MASK) == 0);
-
- /* Never overwrite existing mappings */
- use_gbpage &= !pud_present(*pud);
-
- if (use_gbpage) {
+ if (info->direct_gbpages) {
pud_t pudval;
+ if (pud_present(*pud))
+ continue;
+
+ addr &= PUD_MASK;
pudval = __pud((addr - info->offset) | info->page_flag);
set_pud(pud, pudval);
continue;
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 70b91de..422602f 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -492,6 +492,24 @@
*/
if (sev_status & MSR_AMD64_SEV_ENABLED)
ia32_disable();
+
+ /*
+ * Override init functions that scan the ROM region in SEV-SNP guests,
+ * as this memory is not pre-validated and would thus cause a crash.
+ */
+ if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) {
+ x86_init.mpparse.find_mptable = x86_init_noop;
+ x86_init.pci.init_irq = x86_init_noop;
+ x86_init.resources.probe_roms = x86_init_noop;
+
+ /*
+ * DMI setup behavior for SEV-SNP guests depends on
+ * efi_enabled(EFI_CONFIG_TABLES), which hasn't been
+ * parsed yet. snp_dmi_setup() will run after that
+ * parsing has happened.
+ */
+ x86_init.resources.dmi_setup = snp_dmi_setup;
+ }
}
void __init mem_encrypt_free_decrypted_mem(void)
diff --git a/arch/x86/virt/Makefile b/arch/x86/virt/Makefile
index 1e36502..ea343fc 100644
--- a/arch/x86/virt/Makefile
+++ b/arch/x86/virt/Makefile
@@ -1,2 +1,2 @@
# SPDX-License-Identifier: GPL-2.0-only
-obj-y += vmx/
+obj-y += svm/ vmx/
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 2a06fd3..4e3483a 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -726,7 +726,7 @@
* which can be mixed are set in each bio and mark @rq as mixed
* merged.
*/
-void blk_rq_set_mixed_merge(struct request *rq)
+static void blk_rq_set_mixed_merge(struct request *rq)
{
blk_opf_t ff = rq->cmd_flags & REQ_FAILFAST_MASK;
struct bio *bio;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 555ada92..32afb87 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -770,16 +770,11 @@
/*
* Partial zone append completions cannot be supported as the
* BIO fragments may end up not being written sequentially.
- * For such case, force the completed nbytes to be equal to
- * the BIO size so that bio_advance() sets the BIO remaining
- * size to 0 and we end up calling bio_endio() before returning.
*/
- if (bio->bi_iter.bi_size != nbytes) {
+ if (bio->bi_iter.bi_size != nbytes)
bio->bi_status = BLK_STS_IOERR;
- nbytes = bio->bi_iter.bi_size;
- } else {
+ else
bio->bi_iter.bi_sector = rq->__sector;
- }
}
bio_advance(bio, nbytes);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 3c7d8d6..cdbaef1 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -146,8 +146,7 @@
max_hw_sectors = min_not_zero(lim->max_hw_sectors,
lim->max_dev_sectors);
if (lim->max_user_sectors) {
- if (lim->max_user_sectors > max_hw_sectors ||
- lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
+ if (lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
return -EINVAL;
lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
} else {
diff --git a/block/blk.h b/block/blk.h
index 5cac4e2..d9f5849 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -339,7 +339,6 @@
bool blk_attempt_req_merge(struct request_queue *q, struct request *rq,
struct request *next);
unsigned int blk_recalc_rq_segments(struct request *rq);
-void blk_rq_set_mixed_merge(struct request *rq);
bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c
index b91155e..c9131259 100644
--- a/drivers/acpi/acpica/dbnames.c
+++ b/drivers/acpi/acpica/dbnames.c
@@ -550,8 +550,12 @@
ACPI_FREE(buffer.pointer);
buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER;
- acpi_evaluate_object(obj_handle, NULL, NULL, &buffer);
-
+ status = acpi_evaluate_object(obj_handle, NULL, NULL, &buffer);
+ if (ACPI_FAILURE(status)) {
+ acpi_os_printf("Could Not evaluate object %p\n",
+ obj_handle);
+ return (AE_OK);
+ }
/*
* Since this is a field unit, surround the output in braces
*/
diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c
index 66e7f52..01faca3 100644
--- a/drivers/acpi/apei/einj-core.c
+++ b/drivers/acpi/apei/einj-core.c
@@ -851,7 +851,7 @@
return rc;
}
-static void __exit einj_remove(struct platform_device *pdev)
+static void einj_remove(struct platform_device *pdev)
{
struct apei_exec_context ctx;
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index b0d6e69..214b935 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -712,8 +712,10 @@
ehc->saved_ncq_enabled |= 1 << devno;
/* If we are resuming, wake up the device */
- if (ap->pflags & ATA_PFLAG_RESUMING)
+ if (ap->pflags & ATA_PFLAG_RESUMING) {
+ dev->flags |= ATA_DFLAG_RESUMING;
ehc->i.dev_action[devno] |= ATA_EH_SET_ACTIVE;
+ }
}
}
@@ -3169,6 +3171,7 @@
return 0;
err:
+ dev->flags &= ~ATA_DFLAG_RESUMING;
*r_failed_dev = dev;
return rc;
}
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 0a0f483..2f4c588 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -4730,6 +4730,7 @@
struct ata_link *link;
struct ata_device *dev;
unsigned long flags;
+ bool do_resume;
int ret = 0;
mutex_lock(&ap->scsi_scan_mutex);
@@ -4751,7 +4752,15 @@
if (scsi_device_get(sdev))
continue;
+ do_resume = dev->flags & ATA_DFLAG_RESUMING;
+
spin_unlock_irqrestore(ap->lock, flags);
+ if (do_resume) {
+ ret = scsi_resume_device(sdev);
+ if (ret == -EWOULDBLOCK)
+ goto unlock;
+ dev->flags &= ~ATA_DFLAG_RESUMING;
+ }
ret = scsi_rescan_device(sdev);
scsi_device_put(sdev);
spin_lock_irqsave(ap->lock, flags);
diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig
index 67998db..5f3c9c5 100644
--- a/drivers/cxl/Kconfig
+++ b/drivers/cxl/Kconfig
@@ -144,17 +144,4 @@
If unsure, or if this kernel is meant for production environments,
say N.
-config CXL_PMU
- tristate "CXL Performance Monitoring Unit"
- default CXL_BUS
- depends on PERF_EVENTS
- help
- Support performance monitoring as defined in CXL rev 3.0
- section 13.2: Performance Monitoring. CXL components may have
- one or more CXL Performance Monitoring Units (CPMUs).
-
- Say 'y/m' to enable a driver that will attach to performance
- monitoring units and provide standard perf based interfaces.
-
- If unsure say 'm'.
endif
diff --git a/drivers/dma-buf/st-dma-fence-chain.c b/drivers/dma-buf/st-dma-fence-chain.c
index 9c2a0c0..ed4b323 100644
--- a/drivers/dma-buf/st-dma-fence-chain.c
+++ b/drivers/dma-buf/st-dma-fence-chain.c
@@ -84,11 +84,11 @@
return -ENOMEM;
chain = mock_chain(NULL, f, 1);
- if (!chain)
+ if (chain)
+ dma_fence_enable_sw_signaling(chain);
+ else
err = -ENOMEM;
- dma_fence_enable_sw_signaling(chain);
-
dma_fence_signal(f);
dma_fence_put(f);
diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c
index 7e18528..c41e7b2 100644
--- a/drivers/firmware/efi/libstub/randomalloc.c
+++ b/drivers/firmware/efi/libstub/randomalloc.c
@@ -120,7 +120,7 @@
continue;
}
- target = round_up(max(md->phys_addr, alloc_min), align) + target_slot * align;
+ target = round_up(max_t(u64, md->phys_addr, alloc_min), align) + target_slot * align;
pages = size / EFI_PAGE_SIZE;
status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS,
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 6a6ffc6..d5a8182 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -496,6 +496,7 @@
hdr->vid_mode = 0xffff;
hdr->type_of_loader = 0x21;
+ hdr->initrd_addr_max = INT_MAX;
/* Convert unicode cmdline to ascii */
cmdline_ptr = efi_convert_cmdline(image, &options_size);
diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c
index f384fa2..fa96356 100644
--- a/drivers/gpio/gpiolib-cdev.c
+++ b/drivers/gpio/gpiolib-cdev.c
@@ -1083,10 +1083,20 @@
return 0;
}
+static inline char *make_irq_label(const char *orig)
+{
+ return kstrdup_and_replace(orig, '/', ':', GFP_KERNEL);
+}
+
+static inline void free_irq_label(const char *label)
+{
+ kfree(label);
+}
+
static void edge_detector_stop(struct line *line)
{
if (line->irq) {
- free_irq(line->irq, line);
+ free_irq_label(free_irq(line->irq, line));
line->irq = 0;
}
@@ -1110,6 +1120,7 @@
unsigned long irqflags = 0;
u64 eflags;
int irq, ret;
+ char *label;
eflags = edflags & GPIO_V2_LINE_EDGE_FLAGS;
if (eflags && !kfifo_initialized(&line->req->events)) {
@@ -1146,11 +1157,17 @@
IRQF_TRIGGER_RISING : IRQF_TRIGGER_FALLING;
irqflags |= IRQF_ONESHOT;
+ label = make_irq_label(line->req->label);
+ if (!label)
+ return -ENOMEM;
+
/* Request a thread to read the events */
ret = request_threaded_irq(irq, edge_irq_handler, edge_irq_thread,
- irqflags, line->req->label, line);
- if (ret)
+ irqflags, label, line);
+ if (ret) {
+ free_irq_label(label);
return ret;
+ }
line->irq = irq;
return 0;
@@ -1973,7 +1990,7 @@
blocking_notifier_chain_unregister(&le->gdev->device_notifier,
&le->device_unregistered_nb);
if (le->irq)
- free_irq(le->irq, le);
+ free_irq_label(free_irq(le->irq, le));
if (le->desc)
gpiod_free(le->desc);
kfree(le->label);
@@ -2114,6 +2131,7 @@
int fd;
int ret;
int irq, irqflags = 0;
+ char *label;
if (copy_from_user(&eventreq, ip, sizeof(eventreq)))
return -EFAULT;
@@ -2198,15 +2216,23 @@
if (ret)
goto out_free_le;
+ label = make_irq_label(le->label);
+ if (!label) {
+ ret = -ENOMEM;
+ goto out_free_le;
+ }
+
/* Request a thread to read the events */
ret = request_threaded_irq(irq,
lineevent_irq_handler,
lineevent_irq_thread,
irqflags,
- le->label,
+ label,
le);
- if (ret)
+ if (ret) {
+ free_irq_label(label);
goto out_free_le;
+ }
le->irq = irq;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index ce94e37..59ccf9a 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2397,6 +2397,11 @@
}
EXPORT_SYMBOL_GPL(gpiochip_dup_line_label);
+static inline const char *function_name_or_default(const char *con_id)
+{
+ return con_id ?: "(default)";
+}
+
/**
* gpiochip_request_own_desc - Allow GPIO chip to request its own descriptor
* @gc: GPIO chip
@@ -2425,10 +2430,11 @@
enum gpiod_flags dflags)
{
struct gpio_desc *desc = gpiochip_get_desc(gc, hwnum);
+ const char *name = function_name_or_default(label);
int ret;
if (IS_ERR(desc)) {
- chip_err(gc, "failed to get GPIO descriptor\n");
+ chip_err(gc, "failed to get GPIO %s descriptor\n", name);
return desc;
}
@@ -2438,8 +2444,8 @@
ret = gpiod_configure_flags(desc, label, lflags, dflags);
if (ret) {
- chip_err(gc, "setup of own GPIO %s failed\n", label);
gpiod_free_commit(desc);
+ chip_err(gc, "setup of own GPIO %s failed\n", name);
return ERR_PTR(ret);
}
@@ -4153,19 +4159,17 @@
enum gpiod_flags *flags,
unsigned long *lookupflags)
{
+ const char *name = function_name_or_default(con_id);
struct gpio_desc *desc = ERR_PTR(-ENOENT);
if (is_of_node(fwnode)) {
- dev_dbg(consumer, "using DT '%pfw' for '%s' GPIO lookup\n",
- fwnode, con_id);
+ dev_dbg(consumer, "using DT '%pfw' for '%s' GPIO lookup\n", fwnode, name);
desc = of_find_gpio(to_of_node(fwnode), con_id, idx, lookupflags);
} else if (is_acpi_node(fwnode)) {
- dev_dbg(consumer, "using ACPI '%pfw' for '%s' GPIO lookup\n",
- fwnode, con_id);
+ dev_dbg(consumer, "using ACPI '%pfw' for '%s' GPIO lookup\n", fwnode, name);
desc = acpi_find_gpio(fwnode, con_id, idx, flags, lookupflags);
} else if (is_software_node(fwnode)) {
- dev_dbg(consumer, "using swnode '%pfw' for '%s' GPIO lookup\n",
- fwnode, con_id);
+ dev_dbg(consumer, "using swnode '%pfw' for '%s' GPIO lookup\n", fwnode, name);
desc = swnode_find_gpio(fwnode, con_id, idx, lookupflags);
}
@@ -4181,6 +4185,7 @@
bool platform_lookup_allowed)
{
unsigned long lookupflags = GPIO_LOOKUP_FLAGS_DEFAULT;
+ const char *name = function_name_or_default(con_id);
/*
* scoped_guard() is implemented as a for loop, meaning static
* analyzers will complain about these two not being initialized.
@@ -4203,8 +4208,7 @@
}
if (IS_ERR(desc)) {
- dev_dbg(consumer, "No GPIO consumer %s found\n",
- con_id);
+ dev_dbg(consumer, "No GPIO consumer %s found\n", name);
return desc;
}
@@ -4226,15 +4230,14 @@
*
* FIXME: Make this more sane and safe.
*/
- dev_info(consumer,
- "nonexclusive access to GPIO for %s\n", con_id);
+ dev_info(consumer, "nonexclusive access to GPIO for %s\n", name);
return desc;
}
ret = gpiod_configure_flags(desc, con_id, lookupflags, flags);
if (ret < 0) {
- dev_dbg(consumer, "setup of GPIO %s failed\n", con_id);
gpiod_put(desc);
+ dev_dbg(consumer, "setup of GPIO %s failed\n", name);
return ERR_PTR(ret);
}
@@ -4350,6 +4353,7 @@
int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id,
unsigned long lflags, enum gpiod_flags dflags)
{
+ const char *name = function_name_or_default(con_id);
int ret;
if (lflags & GPIO_ACTIVE_LOW)
@@ -4393,7 +4397,7 @@
/* No particular flag request, return here... */
if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) {
- gpiod_dbg(desc, "no flags found for %s\n", con_id);
+ gpiod_dbg(desc, "no flags found for GPIO %s\n", name);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5dc24c9..aa16d51 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4539,6 +4539,8 @@
if (r)
goto unprepare;
+ flush_delayed_work(&adev->gfx.gfx_off_delay_work);
+
for (i = 0; i < adev->num_ip_blocks; i++) {
if (!adev->ip_blocks[i].status.valid)
continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index a07e4b8..fdd36fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -2237,6 +2237,7 @@
{
switch (amdgpu_ip_version(adev, VCN_HWIP, 0)) {
case IP_VERSION(4, 0, 5):
+ case IP_VERSION(4, 0, 6):
if (amdgpu_umsch_mm & 0x1) {
amdgpu_device_ip_block_add(adev, &umsch_mm_v4_0_ip_block);
adev->enable_umsch_mm = true;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 5505d64..06f0a65 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -524,46 +524,58 @@
{
struct amdgpu_ring *ring = file_inode(f)->i_private;
volatile u32 *mqd;
- int r;
+ u32 *kbuf;
+ int r, i;
uint32_t value, result;
if (*pos & 3 || size & 3)
return -EINVAL;
- result = 0;
+ kbuf = kmalloc(ring->mqd_size, GFP_KERNEL);
+ if (!kbuf)
+ return -ENOMEM;
r = amdgpu_bo_reserve(ring->mqd_obj, false);
if (unlikely(r != 0))
- return r;
+ goto err_free;
r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&mqd);
- if (r) {
- amdgpu_bo_unreserve(ring->mqd_obj);
- return r;
- }
+ if (r)
+ goto err_unreserve;
+ /*
+ * Copy to local buffer to avoid put_user(), which might fault
+ * and acquire mmap_sem, under reservation_ww_class_mutex.
+ */
+ for (i = 0; i < ring->mqd_size/sizeof(u32); i++)
+ kbuf[i] = mqd[i];
+
+ amdgpu_bo_kunmap(ring->mqd_obj);
+ amdgpu_bo_unreserve(ring->mqd_obj);
+
+ result = 0;
while (size) {
if (*pos >= ring->mqd_size)
- goto done;
+ break;
- value = mqd[*pos/4];
+ value = kbuf[*pos/4];
r = put_user(value, (uint32_t *)buf);
if (r)
- goto done;
+ goto err_free;
buf += 4;
result += 4;
size -= 4;
*pos += 4;
}
-done:
- amdgpu_bo_kunmap(ring->mqd_obj);
- mqd = NULL;
- amdgpu_bo_unreserve(ring->mqd_obj);
- if (r)
- return r;
-
+ kfree(kbuf);
return result;
+
+err_unreserve:
+ amdgpu_bo_unreserve(ring->mqd_obj);
+err_free:
+ kfree(kbuf);
+ return r;
}
static const struct file_operations amdgpu_debugfs_mqd_fops = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
index ab820cf..0df97c3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
@@ -189,10 +189,13 @@
mqd->rptr_val = 0;
mqd->unmapped = 1;
+ if (adev->vpe.collaborate_mode)
+ memcpy(++mqd, test->mqd_data_cpu_addr, sizeof(struct MQD_INFO));
+
qinfo->mqd_addr = test->mqd_data_gpu_addr;
qinfo->csa_addr = test->ctx_data_gpu_addr +
offsetof(struct umsch_mm_test_ctx_data, vpe_ctx_csa);
- qinfo->doorbell_offset_0 = (adev->doorbell_index.vpe_ring + 1) << 1;
+ qinfo->doorbell_offset_0 = 0;
qinfo->doorbell_offset_1 = 0;
}
@@ -287,7 +290,10 @@
ring[5] = 0;
mqd->wptr_val = (6 << 2);
- // WDOORBELL32(adev->umsch_mm.agdb_index[CONTEXT_PRIORITY_LEVEL_NORMAL], mqd->wptr_val);
+ if (adev->vpe.collaborate_mode)
+ (++mqd)->wptr_val = (6 << 2);
+
+ WDOORBELL32(adev->umsch_mm.agdb_index[CONTEXT_PRIORITY_LEVEL_NORMAL], mqd->wptr_val);
for (i = 0; i < adev->usec_timeout; i++) {
if (*fence == test_pattern)
@@ -571,6 +577,7 @@
switch (amdgpu_ip_version(adev, VCN_HWIP, 0)) {
case IP_VERSION(4, 0, 5):
+ case IP_VERSION(4, 0, 6):
fw_name = "amdgpu/umsch_mm_4_0_0.bin";
break;
default:
@@ -750,6 +757,7 @@
switch (amdgpu_ip_version(adev, VCN_HWIP, 0)) {
case IP_VERSION(4, 0, 5):
+ case IP_VERSION(4, 0, 6):
umsch_mm_v4_0_set_funcs(&adev->umsch_mm);
break;
default:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h
index 8258a43..5014b5a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h
@@ -33,13 +33,6 @@
UMSCH_SWIP_ENGINE_TYPE_MAX
};
-enum UMSCH_SWIP_AFFINITY_TYPE {
- UMSCH_SWIP_AFFINITY_TYPE_ANY = 0,
- UMSCH_SWIP_AFFINITY_TYPE_VCN0 = 1,
- UMSCH_SWIP_AFFINITY_TYPE_VCN1 = 2,
- UMSCH_SWIP_AFFINITY_TYPE_MAX
-};
-
enum UMSCH_CONTEXT_PRIORITY_LEVEL {
CONTEXT_PRIORITY_LEVEL_IDLE = 0,
CONTEXT_PRIORITY_LEVEL_NORMAL = 1,
@@ -51,13 +44,15 @@
struct umsch_mm_set_resource_input {
uint32_t vmid_mask_mm_vcn;
uint32_t vmid_mask_mm_vpe;
+ uint32_t collaboration_mask_vpe;
uint32_t logging_vmid;
uint32_t engine_mask;
union {
struct {
uint32_t disable_reset : 1;
uint32_t disable_umsch_mm_log : 1;
- uint32_t reserved : 30;
+ uint32_t use_rs64mem_for_proc_ctx_csa : 1;
+ uint32_t reserved : 29;
};
uint32_t uint32_all;
};
@@ -78,15 +73,18 @@
uint32_t doorbell_offset_1;
enum UMSCH_SWIP_ENGINE_TYPE engine_type;
uint32_t affinity;
- enum UMSCH_SWIP_AFFINITY_TYPE affinity_type;
uint64_t mqd_addr;
uint64_t h_context;
uint64_t h_queue;
uint32_t vm_context_cntl;
+ uint32_t process_csa_array_index;
+ uint32_t context_csa_array_index;
+
struct {
uint32_t is_context_suspended : 1;
- uint32_t reserved : 31;
+ uint32_t collaboration_mode : 1;
+ uint32_t reserved : 30;
};
};
@@ -94,6 +92,7 @@
uint32_t doorbell_offset_0;
uint32_t doorbell_offset_1;
uint64_t context_csa_addr;
+ uint32_t context_csa_array_index;
};
struct MQD_INFO {
@@ -103,6 +102,7 @@
uint32_t wptr_val;
uint32_t rptr_val;
uint32_t unmapped;
+ uint32_t vmid;
};
struct amdgpu_umsch_mm;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index 7a65a2b..6695481 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -396,6 +396,12 @@
struct amdgpu_vpe *vpe = &adev->vpe;
int ret;
+ /* Power on VPE */
+ ret = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VPE,
+ AMD_PG_STATE_UNGATE);
+ if (ret)
+ return ret;
+
ret = vpe_load_microcode(vpe);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
index 8e7b763..84368cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
@@ -60,7 +60,7 @@
umsch->cmd_buf_curr_ptr = umsch->cmd_buf_ptr;
- if (amdgpu_ip_version(adev, VCN_HWIP, 0) == IP_VERSION(4, 0, 5)) {
+ if (amdgpu_ip_version(adev, VCN_HWIP, 0) >= IP_VERSION(4, 0, 5)) {
WREG32_SOC15(VCN, 0, regUVD_IPX_DLDO_CONFIG,
1 << UVD_IPX_DLDO_CONFIG__ONO0_PWR_CONFIG__SHIFT);
SOC15_WAIT_ON_RREG(VCN, 0, regUVD_IPX_DLDO_STATUS,
@@ -248,7 +248,7 @@
data = REG_SET_FIELD(data, VCN_UMSCH_RB_DB_CTRL, EN, 0);
WREG32_SOC15(VCN, 0, regVCN_UMSCH_RB_DB_CTRL, data);
- if (amdgpu_ip_version(adev, VCN_HWIP, 0) == IP_VERSION(4, 0, 5)) {
+ if (amdgpu_ip_version(adev, VCN_HWIP, 0) >= IP_VERSION(4, 0, 5)) {
WREG32_SOC15(VCN, 0, regUVD_IPX_DLDO_CONFIG,
2 << UVD_IPX_DLDO_CONFIG__ONO0_PWR_CONFIG__SHIFT);
SOC15_WAIT_ON_RREG(VCN, 0, regUVD_IPX_DLDO_STATUS,
@@ -271,6 +271,8 @@
set_hw_resources.vmid_mask_mm_vcn = umsch->vmid_mask_mm_vcn;
set_hw_resources.vmid_mask_mm_vpe = umsch->vmid_mask_mm_vpe;
+ set_hw_resources.collaboration_mask_vpe =
+ adev->vpe.collaborate_mode ? 0x3 : 0x0;
set_hw_resources.engine_mask = umsch->engine_mask;
set_hw_resources.vcn0_hqd_mask[0] = umsch->vcn0_hqd_mask;
@@ -346,6 +348,7 @@
add_queue.h_queue = input_ptr->h_queue;
add_queue.vm_context_cntl = input_ptr->vm_context_cntl;
add_queue.is_context_suspended = input_ptr->is_context_suspended;
+ add_queue.collaboration_mode = adev->vpe.collaborate_mode ? 1 : 0;
add_queue.api_status.api_completion_fence_addr = umsch->ring.fence_drv.gpu_addr;
add_queue.api_status.api_completion_fence_value = ++umsch->ring.fence_drv.sync_seq;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index dfa8c69..f9631f4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1523,7 +1523,7 @@
/* Find a KFD GPU device that supports the get_dmabuf_info query */
for (i = 0; kfd_topology_enum_kfd_devices(i, &dev) == 0; i++)
- if (dev)
+ if (dev && !kfd_devcgroup_check_permission(dev))
break;
if (!dev)
return -EINVAL;
@@ -1545,7 +1545,7 @@
if (xcp_id >= 0)
args->gpu_id = dmabuf_adev->kfd.dev->nodes[xcp_id]->id;
else
- args->gpu_id = dmabuf_adev->kfd.dev->nodes[0]->id;
+ args->gpu_id = dev->id;
args->flags = flags;
/* Copy metadata buffer to user mode */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
index 9a06c6f..40a21be 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c
@@ -339,7 +339,8 @@
break;
}
kfd_signal_event_interrupt(pasid, context_id0 & 0x7fffff, 23);
- } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) {
+ } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
+ KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) {
kfd_set_dbg_ev_from_interrupt(dev, pasid,
KFD_DEBUG_DOORBELL_ID(context_id0),
KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
index 7e28597..fe2ad0c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
@@ -328,7 +328,8 @@
/* CP */
if (source_id == SOC15_INTSRC_CP_END_OF_PIPE)
kfd_signal_event_interrupt(pasid, context_id0, 32);
- else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE)
+ else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
+ KFD_DBG_EC_TYPE_IS_PACKET(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)))
kfd_set_dbg_ev_from_interrupt(dev, pasid,
KFD_CTXID0_DOORBELL_ID(context_id0),
KFD_EC_MASK(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index 91dd5e0..c4c6a29 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -388,7 +388,8 @@
break;
}
kfd_signal_event_interrupt(pasid, sq_int_data, 24);
- } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) {
+ } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE &&
+ KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) {
kfd_set_dbg_ev_from_interrupt(dev, pasid,
KFD_DEBUG_DOORBELL_ID(context_id0),
KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 42d4056..a81ef23 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1473,7 +1473,7 @@
static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev)
{
- return KFD_GC_VERSION(dev) > IP_VERSION(9, 4, 2) ||
+ return KFD_GC_VERSION(dev) >= IP_VERSION(9, 4, 2) ||
(KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && dev->sdma_fw_version >= 18) ||
KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0);
}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 2851719..71d2d44 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -6305,9 +6305,8 @@
if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket);
- else if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT ||
- stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST ||
- stream->signal == SIGNAL_TYPE_EDP) {
+
+ if (stream->link->psr_settings.psr_feature_enabled || stream->link->replay_settings.replay_feature_enabled) {
//
// should decide stream support vsc sdp colorimetry capability
// before building vsc info packet
@@ -6323,9 +6322,8 @@
if (stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22)
tf = TRANSFER_FUNC_GAMMA_22;
mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf);
+ aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
- if (stream->link->psr_settings.psr_feature_enabled)
- aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
}
finish:
dc_sink_release(sink);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
index 1f08c65..286ecd2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
@@ -141,9 +141,8 @@
* amdgpu_dm_psr_enable() - enable psr f/w
* @stream: stream state
*
- * Return: true if success
*/
-bool amdgpu_dm_psr_enable(struct dc_stream_state *stream)
+void amdgpu_dm_psr_enable(struct dc_stream_state *stream)
{
struct dc_link *link = stream->link;
unsigned int vsync_rate_hz = 0;
@@ -190,7 +189,10 @@
if (link->psr_settings.psr_version < DC_PSR_VERSION_SU_1)
power_opt |= psr_power_opt_z10_static_screen;
- return dc_link_set_psr_allow_active(link, &psr_enable, false, false, &power_opt);
+ dc_link_set_psr_allow_active(link, &psr_enable, false, false, &power_opt);
+
+ if (link->ctx->dc->caps.ips_support)
+ dc_allow_idle_optimizations(link->ctx->dc, true);
}
/*
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h
index 6806b3c..1fdfd18 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h
@@ -32,7 +32,7 @@
#define AMDGPU_DM_PSR_ENTRY_DELAY 5
void amdgpu_dm_set_psr_caps(struct dc_link *link);
-bool amdgpu_dm_psr_enable(struct dc_stream_state *stream);
+void amdgpu_dm_psr_enable(struct dc_stream_state *stream);
bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream);
bool amdgpu_dm_psr_disable(struct dc_stream_state *stream);
bool amdgpu_dm_psr_disable_all(struct amdgpu_display_manager *dm);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index c378b87..101fe96 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -73,6 +73,8 @@
#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK 0x00000007L
#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV_MASK 0x000F0000L
+#define SMU_VER_THRESHOLD 0x5D4A00 //93.74.0
+
#define REG(reg_name) \
(ctx->clk_reg_offsets[reg ## reg_name ## _BASE_IDX] + reg ## reg_name)
@@ -411,9 +413,12 @@
static void init_clk_states(struct clk_mgr *clk_mgr)
{
+ struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz;
memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
+ if (clk_mgr_int->smu_ver >= SMU_VER_THRESHOLD)
+ clk_mgr->clks.dtbclk_en = true; // request DTBCLK disable on first commit
clk_mgr->clks.ref_dtbclk_khz = ref_dtbclk; // restore ref_dtbclk
clk_mgr->clks.p_state_change_support = true;
clk_mgr->clks.prev_p_state_change_support = true;
@@ -709,7 +714,7 @@
clock_table->NumFclkLevelsEnabled;
max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, num_fclk);
- num_dcfclk = (clock_table->NumFclkLevelsEnabled > NUM_DCFCLK_DPM_LEVELS) ? NUM_DCFCLK_DPM_LEVELS :
+ num_dcfclk = (clock_table->NumDcfClkLevelsEnabled > NUM_DCFCLK_DPM_LEVELS) ? NUM_DCFCLK_DPM_LEVELS :
clock_table->NumDcfClkLevelsEnabled;
for (i = 0; i < num_dcfclk; i++) {
int j;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index e7dc128..03b554e 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3024,7 +3024,8 @@
scratch->blend_tf[i] = *status->plane_states[i]->blend_tf;
}
scratch->stream_state = *stream;
- scratch->out_transfer_func = *stream->out_transfer_func;
+ if (stream->out_transfer_func)
+ scratch->out_transfer_func = *stream->out_transfer_func;
}
static void restore_planes_and_stream_state(
@@ -3046,7 +3047,8 @@
*status->plane_states[i]->blend_tf = scratch->blend_tf[i];
}
*stream = scratch->stream_state;
- *stream->out_transfer_func = scratch->out_transfer_func;
+ if (stream->out_transfer_func)
+ *stream->out_transfer_func = scratch->out_transfer_func;
}
static bool update_planes_and_stream_state(struct dc *dc,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/Makefile b/drivers/gpu/drm/amd/display/dc/dce110/Makefile
index f0777d6..c307f04 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce110/Makefile
@@ -23,7 +23,7 @@
# Makefile for the 'controller' sub-component of DAL.
# It provides the control and status of HW CRTC block.
-CFLAGS_$(AMDDALPATH)/dc/dce110/dce110_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce110/dce110_resource.o = -Wno-override-init
DCE110 = dce110_timing_generator.o \
dce110_compressor.o dce110_opp_regamma_v.o \
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/Makefile b/drivers/gpu/drm/amd/display/dc/dce112/Makefile
index 7e92eff..6838667 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce112/Makefile
@@ -23,7 +23,7 @@
# Makefile for the 'controller' sub-component of DAL.
# It provides the control and status of HW CRTC block.
-CFLAGS_$(AMDDALPATH)/dc/dce112/dce112_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce112/dce112_resource.o = -Wno-override-init
DCE112 = dce112_compressor.o
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/Makefile b/drivers/gpu/drm/amd/display/dc/dce120/Makefile
index 1e3ef68..8f508e6 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce120/Makefile
@@ -24,7 +24,7 @@
# It provides the control and status of HW CRTC block.
-CFLAGS_$(AMDDALPATH)/dc/dce120/dce120_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce120/dce120_resource.o = -Wno-override-init
DCE120 = dce120_timing_generator.o
diff --git a/drivers/gpu/drm/amd/display/dc/dce60/Makefile b/drivers/gpu/drm/amd/display/dc/dce60/Makefile
index fee331a..eede83a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce60/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce60/Makefile
@@ -23,7 +23,7 @@
# Makefile for the 'controller' sub-component of DAL.
# It provides the control and status of HW CRTC block.
-CFLAGS_$(AMDDALPATH)/dc/dce60/dce60_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce60/dce60_resource.o = -Wno-override-init
DCE60 = dce60_timing_generator.o dce60_hw_sequencer.o \
dce60_resource.o
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/Makefile b/drivers/gpu/drm/amd/display/dc/dce80/Makefile
index 7eefffb..fba189d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce80/Makefile
@@ -23,7 +23,7 @@
# Makefile for the 'controller' sub-component of DAL.
# It provides the control and status of HW CRTC block.
-CFLAGS_$(AMDDALPATH)/dc/dce80/dce80_resource.o = $(call cc-disable-warning, override-init)
+CFLAGS_$(AMDDALPATH)/dc/dce80/dce80_resource.o = -Wno-override-init
DCE80 = dce80_timing_generator.o
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
index bf3386c..5ebb5730 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
@@ -44,6 +44,36 @@
#define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0]))
+void mpc3_mpc_init(struct mpc *mpc)
+{
+ struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
+ int opp_id;
+
+ mpc1_mpc_init(mpc);
+
+ for (opp_id = 0; opp_id < MAX_OPP; opp_id++) {
+ if (REG(MUX[opp_id]))
+ /* disable mpc out rate and flow control */
+ REG_UPDATE_2(MUX[opp_id], MPC_OUT_RATE_CONTROL_DISABLE,
+ 1, MPC_OUT_FLOW_CONTROL_COUNT, 0);
+ }
+}
+
+void mpc3_mpc_init_single_inst(struct mpc *mpc, unsigned int mpcc_id)
+{
+ struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
+
+ mpc1_mpc_init_single_inst(mpc, mpcc_id);
+
+ /* assuming mpc out mux is connected to opp with the same index at this
+ * point in time (e.g. transitioning from vbios to driver)
+ */
+ if (mpcc_id < MAX_OPP && REG(MUX[mpcc_id]))
+ /* disable mpc out rate and flow control */
+ REG_UPDATE_2(MUX[mpcc_id], MPC_OUT_RATE_CONTROL_DISABLE,
+ 1, MPC_OUT_FLOW_CONTROL_COUNT, 0);
+}
+
bool mpc3_is_dwb_idle(
struct mpc *mpc,
int dwb_id)
@@ -80,25 +110,6 @@
MPC_DWB0_MUX, 0xf);
}
-void mpc3_set_out_rate_control(
- struct mpc *mpc,
- int opp_id,
- bool enable,
- bool rate_2x_mode,
- struct mpc_dwb_flow_control *flow_control)
-{
- struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
-
- REG_UPDATE_2(MUX[opp_id],
- MPC_OUT_RATE_CONTROL_DISABLE, !enable,
- MPC_OUT_RATE_CONTROL, rate_2x_mode);
-
- if (flow_control)
- REG_UPDATE_2(MUX[opp_id],
- MPC_OUT_FLOW_CONTROL_MODE, flow_control->flow_ctrl_mode,
- MPC_OUT_FLOW_CONTROL_COUNT, flow_control->flow_ctrl_cnt1);
-}
-
enum dc_lut_mode mpc3_get_ogam_current(struct mpc *mpc, int mpcc_id)
{
/*Contrary to DCN2 and DCN1 wherein a single status register field holds this info;
@@ -1490,8 +1501,8 @@
.read_mpcc_state = mpc3_read_mpcc_state,
.insert_plane = mpc1_insert_plane,
.remove_mpcc = mpc1_remove_mpcc,
- .mpc_init = mpc1_mpc_init,
- .mpc_init_single_inst = mpc1_mpc_init_single_inst,
+ .mpc_init = mpc3_mpc_init,
+ .mpc_init_single_inst = mpc3_mpc_init_single_inst,
.update_blending = mpc2_update_blending,
.cursor_lock = mpc1_cursor_lock,
.get_mpcc_for_dpp = mpc1_get_mpcc_for_dpp,
@@ -1508,7 +1519,6 @@
.set_dwb_mux = mpc3_set_dwb_mux,
.disable_dwb_mux = mpc3_disable_dwb_mux,
.is_dwb_idle = mpc3_is_dwb_idle,
- .set_out_rate_control = mpc3_set_out_rate_control,
.set_gamut_remap = mpc3_set_gamut_remap,
.program_shaper = mpc3_program_shaper,
.acquire_rmu = mpcc3_acquire_rmu,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h
index 9cb96ae..ce93003 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h
@@ -1007,6 +1007,13 @@
int num_mpcc,
int num_rmu);
+void mpc3_mpc_init(
+ struct mpc *mpc);
+
+void mpc3_mpc_init_single_inst(
+ struct mpc *mpc,
+ unsigned int mpcc_id);
+
bool mpc3_program_shaper(
struct mpc *mpc,
const struct pwl_params *params,
@@ -1078,13 +1085,6 @@
struct mpc *mpc,
int dwb_id);
-void mpc3_set_out_rate_control(
- struct mpc *mpc,
- int opp_id,
- bool enable,
- bool rate_2x_mode,
- struct mpc_dwb_flow_control *flow_control);
-
void mpc3_power_on_ogam_lut(
struct mpc *mpc, int mpcc_id,
bool power_on);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c
index e789e65..e408e85 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c
@@ -47,7 +47,7 @@
struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
int mpcc_id;
- mpc1_mpc_init(mpc);
+ mpc3_mpc_init(mpc);
if (mpc->ctx->dc->debug.enable_mem_low_power.bits.mpc) {
if (mpc30->mpc_mask->MPCC_MCM_SHAPER_MEM_LOW_PWR_MODE && mpc30->mpc_mask->MPCC_MCM_3DLUT_MEM_LOW_PWR_MODE) {
@@ -991,7 +991,7 @@
.insert_plane = mpc1_insert_plane,
.remove_mpcc = mpc1_remove_mpcc,
.mpc_init = mpc32_mpc_init,
- .mpc_init_single_inst = mpc1_mpc_init_single_inst,
+ .mpc_init_single_inst = mpc3_mpc_init_single_inst,
.update_blending = mpc2_update_blending,
.cursor_lock = mpc1_cursor_lock,
.get_mpcc_for_dpp = mpc1_get_mpcc_for_dpp,
@@ -1008,7 +1008,6 @@
.set_dwb_mux = mpc3_set_dwb_mux,
.disable_dwb_mux = mpc3_disable_dwb_mux,
.is_dwb_idle = mpc3_is_dwb_idle,
- .set_out_rate_control = mpc3_set_out_rate_control,
.set_gamut_remap = mpc3_set_gamut_remap,
.program_shaper = mpc32_program_shaper,
.program_3dlut = mpc32_program_3dlut,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index 80bebfc..21e0eef 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -166,8 +166,8 @@
.num_states = 5,
.sr_exit_time_us = 28.0,
.sr_enter_plus_exit_time_us = 30.0,
- .sr_exit_z8_time_us = 210.0,
- .sr_enter_plus_exit_z8_time_us = 320.0,
+ .sr_exit_z8_time_us = 250.0,
+ .sr_enter_plus_exit_z8_time_us = 350.0,
.fclk_change_latency_us = 24.0,
.usr_retraining_latency_us = 2,
.writeback_latency_us = 12.0,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
index dc9e1b7..b3ffab7 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
@@ -98,55 +98,114 @@
.clock_limits = {
{
.state = 0,
- .dispclk_mhz = 1200.0,
- .dppclk_mhz = 1200.0,
+ .dcfclk_mhz = 400.0,
+ .fabricclk_mhz = 400.0,
+ .socclk_mhz = 600.0,
+ .dram_speed_mts = 3200.0,
+ .dispclk_mhz = 600.0,
+ .dppclk_mhz = 600.0,
.phyclk_mhz = 600.0,
.phyclk_d18_mhz = 667.0,
- .dscclk_mhz = 186.0,
+ .dscclk_mhz = 200.0,
.dtbclk_mhz = 600.0,
},
{
.state = 1,
- .dispclk_mhz = 1200.0,
- .dppclk_mhz = 1200.0,
+ .dcfclk_mhz = 600.0,
+ .fabricclk_mhz = 1000.0,
+ .socclk_mhz = 733.0,
+ .dram_speed_mts = 6400.0,
+ .dispclk_mhz = 800.0,
+ .dppclk_mhz = 800.0,
.phyclk_mhz = 810.0,
.phyclk_d18_mhz = 667.0,
- .dscclk_mhz = 209.0,
+ .dscclk_mhz = 266.7,
.dtbclk_mhz = 600.0,
},
{
.state = 2,
- .dispclk_mhz = 1200.0,
- .dppclk_mhz = 1200.0,
+ .dcfclk_mhz = 738.0,
+ .fabricclk_mhz = 1200.0,
+ .socclk_mhz = 880.0,
+ .dram_speed_mts = 7500.0,
+ .dispclk_mhz = 800.0,
+ .dppclk_mhz = 800.0,
.phyclk_mhz = 810.0,
.phyclk_d18_mhz = 667.0,
- .dscclk_mhz = 209.0,
+ .dscclk_mhz = 266.7,
.dtbclk_mhz = 600.0,
},
{
.state = 3,
- .dispclk_mhz = 1200.0,
- .dppclk_mhz = 1200.0,
+ .dcfclk_mhz = 800.0,
+ .fabricclk_mhz = 1400.0,
+ .socclk_mhz = 978.0,
+ .dram_speed_mts = 7500.0,
+ .dispclk_mhz = 960.0,
+ .dppclk_mhz = 960.0,
.phyclk_mhz = 810.0,
.phyclk_d18_mhz = 667.0,
- .dscclk_mhz = 371.0,
+ .dscclk_mhz = 320.0,
.dtbclk_mhz = 600.0,
},
{
.state = 4,
+ .dcfclk_mhz = 873.0,
+ .fabricclk_mhz = 1600.0,
+ .socclk_mhz = 1100.0,
+ .dram_speed_mts = 8533.0,
+ .dispclk_mhz = 1066.7,
+ .dppclk_mhz = 1066.7,
+ .phyclk_mhz = 810.0,
+ .phyclk_d18_mhz = 667.0,
+ .dscclk_mhz = 355.6,
+ .dtbclk_mhz = 600.0,
+ },
+ {
+ .state = 5,
+ .dcfclk_mhz = 960.0,
+ .fabricclk_mhz = 1700.0,
+ .socclk_mhz = 1257.0,
+ .dram_speed_mts = 8533.0,
.dispclk_mhz = 1200.0,
.dppclk_mhz = 1200.0,
.phyclk_mhz = 810.0,
.phyclk_d18_mhz = 667.0,
- .dscclk_mhz = 417.0,
+ .dscclk_mhz = 400.0,
+ .dtbclk_mhz = 600.0,
+ },
+ {
+ .state = 6,
+ .dcfclk_mhz = 1067.0,
+ .fabricclk_mhz = 1850.0,
+ .socclk_mhz = 1257.0,
+ .dram_speed_mts = 8533.0,
+ .dispclk_mhz = 1371.4,
+ .dppclk_mhz = 1371.4,
+ .phyclk_mhz = 810.0,
+ .phyclk_d18_mhz = 667.0,
+ .dscclk_mhz = 457.1,
+ .dtbclk_mhz = 600.0,
+ },
+ {
+ .state = 7,
+ .dcfclk_mhz = 1200.0,
+ .fabricclk_mhz = 2000.0,
+ .socclk_mhz = 1467.0,
+ .dram_speed_mts = 8533.0,
+ .dispclk_mhz = 1600.0,
+ .dppclk_mhz = 1600.0,
+ .phyclk_mhz = 810.0,
+ .phyclk_d18_mhz = 667.0,
+ .dscclk_mhz = 533.3,
.dtbclk_mhz = 600.0,
},
},
- .num_states = 5,
+ .num_states = 8,
.sr_exit_time_us = 28.0,
.sr_enter_plus_exit_time_us = 30.0,
- .sr_exit_z8_time_us = 210.0,
- .sr_enter_plus_exit_z8_time_us = 320.0,
+ .sr_exit_z8_time_us = 250.0,
+ .sr_enter_plus_exit_z8_time_us = 350.0,
.fclk_change_latency_us = 24.0,
.usr_retraining_latency_us = 2,
.writeback_latency_us = 12.0,
@@ -177,6 +236,9 @@
.do_urgent_latency_adjustment = 0,
.urgent_latency_adjustment_fabric_clock_component_us = 0,
.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+ .num_chans = 4,
+ .dram_clock_change_latency_us = 11.72,
+ .dispclk_dppclk_vco_speed_mhz = 2400.0,
};
/*
@@ -340,6 +402,8 @@
clock_limits[i].socclk_mhz;
dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].memclk_mhz =
clk_table->entries[i].memclk_mhz * clk_table->entries[i].wck_ratio;
+ dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz =
+ clock_limits[i].dtbclk_mhz;
dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels =
clk_table->num_entries;
dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_fclk_levels =
@@ -352,6 +416,8 @@
clk_table->num_entries;
dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_memclk_levels =
clk_table->num_entries;
+ dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dtbclk_levels =
+ clk_table->num_entries;
}
}
@@ -551,6 +617,7 @@
if (context->res_ctx.pipe_ctx[i].plane_state)
plane_count++;
}
+
/*dcn351 does not support z9/z10*/
if (context->stream_count == 0 || plane_count == 0) {
support = DCN_ZSTATE_SUPPORT_ALLOW_Z8_ONLY;
@@ -564,11 +631,9 @@
dc->debug.minimum_z8_residency_time > 0 ? dc->debug.minimum_z8_residency_time : 1000;
bool allow_z8 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z8_residency;
-
/*for psr1/psr-su, we allow z8 and z10 based on latency, for replay with IPS enabled, it will enter ips2*/
- if (is_pwrseq0 && (is_psr || is_replay))
+ if (is_pwrseq0 && (is_psr || is_replay))
support = allow_z8 ? allow_z8 : DCN_ZSTATE_SUPPORT_DISALLOW;
-
}
context->bw_ctx.bw.dcn.clk.zstate_support = support;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 17a58f4..a20f28a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -228,17 +228,13 @@
break;
case dml_project_dcn35:
+ case dml_project_dcn351:
out->num_chans = 4;
out->round_trip_ping_latency_dcfclk_cycles = 106;
out->smn_latency_us = 2;
out->dispclk_dppclk_vco_speed_mhz = 3600;
break;
- case dml_project_dcn351:
- out->num_chans = 16;
- out->round_trip_ping_latency_dcfclk_cycles = 1100;
- out->smn_latency_us = 2;
- break;
}
/* ---Overrides if available--- */
if (dml2->config.bbox_overrides.dram_num_chan)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 9d5df4c..0ba1fea 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1185,7 +1185,8 @@
if (dccg) {
dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst);
dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, dp_hpo_inst);
- dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
+ if (dccg && dccg->funcs->set_dtbclk_dto)
+ dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
}
} else if (dccg && dccg->funcs->disable_symclk_se) {
dccg->funcs->disable_symclk_se(dccg, stream_enc->stream_enc_inst,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
index 3a9cc8ac..093f438 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
@@ -69,29 +69,6 @@
#define FN(reg_name, field_name) \
hws->shifts->field_name, hws->masks->field_name
-static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream,
- int opp_cnt)
-{
- bool hblank_halved = optc2_is_two_pixels_per_containter(&stream->timing);
- int flow_ctrl_cnt;
-
- if (opp_cnt >= 2)
- hblank_halved = true;
-
- flow_ctrl_cnt = stream->timing.h_total - stream->timing.h_addressable -
- stream->timing.h_border_left -
- stream->timing.h_border_right;
-
- if (hblank_halved)
- flow_ctrl_cnt /= 2;
-
- /* ODM combine 4:1 case */
- if (opp_cnt == 4)
- flow_ctrl_cnt /= 2;
-
- return flow_ctrl_cnt;
-}
-
static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
{
struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
@@ -183,10 +160,6 @@
struct pipe_ctx *odm_pipe;
int opp_cnt = 0;
int opp_inst[MAX_PIPES] = {0};
- bool rate_control_2x_pclk = (pipe_ctx->stream->timing.flags.INTERLACE || optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing));
- struct mpc_dwb_flow_control flow_control;
- struct mpc *mpc = dc->res_pool->mpc;
- int i;
opp_cnt = get_odm_config(pipe_ctx, opp_inst);
@@ -199,20 +172,6 @@
pipe_ctx->stream_res.tg->funcs->set_odm_bypass(
pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
- rate_control_2x_pclk = rate_control_2x_pclk || opp_cnt > 1;
- flow_control.flow_ctrl_mode = 0;
- flow_control.flow_ctrl_cnt0 = 0x80;
- flow_control.flow_ctrl_cnt1 = calc_mpc_flow_ctrl_cnt(pipe_ctx->stream, opp_cnt);
- if (mpc->funcs->set_out_rate_control) {
- for (i = 0; i < opp_cnt; ++i) {
- mpc->funcs->set_out_rate_control(
- mpc, opp_inst[i],
- true,
- rate_control_2x_pclk,
- &flow_control);
- }
- }
-
for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) {
odm_pipe->stream_res.opp->funcs->opp_pipe_clock_control(
odm_pipe->stream_res.opp,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
index c0b526c..7668229 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
@@ -966,29 +966,6 @@
}
}
-static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream,
- int opp_cnt)
-{
- bool hblank_halved = optc2_is_two_pixels_per_containter(&stream->timing);
- int flow_ctrl_cnt;
-
- if (opp_cnt >= 2)
- hblank_halved = true;
-
- flow_ctrl_cnt = stream->timing.h_total - stream->timing.h_addressable -
- stream->timing.h_border_left -
- stream->timing.h_border_right;
-
- if (hblank_halved)
- flow_ctrl_cnt /= 2;
-
- /* ODM combine 4:1 case */
- if (opp_cnt == 4)
- flow_ctrl_cnt /= 2;
-
- return flow_ctrl_cnt;
-}
-
static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
{
struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
@@ -1103,10 +1080,6 @@
struct pipe_ctx *odm_pipe;
int opp_cnt = 0;
int opp_inst[MAX_PIPES] = {0};
- bool rate_control_2x_pclk = (pipe_ctx->stream->timing.flags.INTERLACE || optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing));
- struct mpc_dwb_flow_control flow_control;
- struct mpc *mpc = dc->res_pool->mpc;
- int i;
opp_cnt = get_odm_config(pipe_ctx, opp_inst);
@@ -1119,20 +1092,6 @@
pipe_ctx->stream_res.tg->funcs->set_odm_bypass(
pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
- rate_control_2x_pclk = rate_control_2x_pclk || opp_cnt > 1;
- flow_control.flow_ctrl_mode = 0;
- flow_control.flow_ctrl_cnt0 = 0x80;
- flow_control.flow_ctrl_cnt1 = calc_mpc_flow_ctrl_cnt(pipe_ctx->stream, opp_cnt);
- if (mpc->funcs->set_out_rate_control) {
- for (i = 0; i < opp_cnt; ++i) {
- mpc->funcs->set_out_rate_control(
- mpc, opp_inst[i],
- true,
- rate_control_2x_pclk,
- &flow_control);
- }
- }
-
for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) {
odm_pipe->stream_res.opp->funcs->opp_pipe_clock_control(
odm_pipe->stream_res.opp,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index 4b92df2..a5560b3 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -358,29 +358,6 @@
}
}
-static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream,
- int opp_cnt)
-{
- bool hblank_halved = optc2_is_two_pixels_per_containter(&stream->timing);
- int flow_ctrl_cnt;
-
- if (opp_cnt >= 2)
- hblank_halved = true;
-
- flow_ctrl_cnt = stream->timing.h_total - stream->timing.h_addressable -
- stream->timing.h_border_left -
- stream->timing.h_border_right;
-
- if (hblank_halved)
- flow_ctrl_cnt /= 2;
-
- /* ODM combine 4:1 case */
- if (opp_cnt == 4)
- flow_ctrl_cnt /= 2;
-
- return flow_ctrl_cnt;
-}
-
static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
{
struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
@@ -474,10 +451,6 @@
struct pipe_ctx *odm_pipe;
int opp_cnt = 0;
int opp_inst[MAX_PIPES] = {0};
- bool rate_control_2x_pclk = (pipe_ctx->stream->timing.flags.INTERLACE || optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing));
- struct mpc_dwb_flow_control flow_control;
- struct mpc *mpc = dc->res_pool->mpc;
- int i;
opp_cnt = get_odm_config(pipe_ctx, opp_inst);
@@ -490,20 +463,6 @@
pipe_ctx->stream_res.tg->funcs->set_odm_bypass(
pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
- rate_control_2x_pclk = rate_control_2x_pclk || opp_cnt > 1;
- flow_control.flow_ctrl_mode = 0;
- flow_control.flow_ctrl_cnt0 = 0x80;
- flow_control.flow_ctrl_cnt1 = calc_mpc_flow_ctrl_cnt(pipe_ctx->stream, opp_cnt);
- if (mpc->funcs->set_out_rate_control) {
- for (i = 0; i < opp_cnt; ++i) {
- mpc->funcs->set_out_rate_control(
- mpc, opp_inst[i],
- true,
- rate_control_2x_pclk,
- &flow_control);
- }
- }
-
for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) {
odm_pipe->stream_res.opp->funcs->opp_pipe_clock_control(
odm_pipe->stream_res.opp,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
index ab17fa1..670255c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
@@ -67,7 +67,7 @@
.prepare_bandwidth = dcn35_prepare_bandwidth,
.optimize_bandwidth = dcn35_optimize_bandwidth,
.update_bandwidth = dcn20_update_bandwidth,
- .set_drr = dcn10_set_drr,
+ .set_drr = dcn35_set_drr,
.get_position = dcn10_get_position,
.set_static_screen_control = dcn35_set_static_screen_control,
.setup_stereo = dcn10_setup_stereo,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
index 5b48640..909e142 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
@@ -700,6 +700,8 @@
.disable_dcc = DCC_ENABLE,
.disable_dpp_power_gate = true,
.disable_hubp_power_gate = true,
+ .disable_optc_power_gate = true, /*should the same as above two*/
+ .disable_hpo_power_gate = true, /*dmubfw force domain25 on*/
.disable_clock_gate = false,
.disable_dsc_power_gate = true,
.vsr_support = true,
@@ -742,12 +744,13 @@
},
.seamless_boot_odm_combine = DML_FAIL_SOURCE_PIXEL_FORMAT,
.enable_z9_disable_interface = true, /* Allow support for the PMFW interface for disable Z9*/
+ .minimum_z8_residency_time = 2100,
.using_dml2 = true,
.support_eDP1_5 = true,
.enable_hpo_pg_support = false,
.enable_legacy_fast_update = true,
.enable_single_display_2to1_odm_policy = true,
- .disable_idle_power_optimizations = true,
+ .disable_idle_power_optimizations = false,
.dmcub_emulation = false,
.disable_boot_optimizations = false,
.disable_unbounded_requesting = false,
@@ -758,8 +761,10 @@
.disable_z10 = true,
.ignore_pg = true,
.psp_disabled_wa = true,
- .ips2_eval_delay_us = 200,
- .ips2_entry_delay_us = 400
+ .ips2_eval_delay_us = 2000,
+ .ips2_entry_delay_us = 800,
+ .disable_dmub_reallow_idle = true,
+ .static_screen_wait_frames = 2,
};
static const struct dc_panel_config panel_config_defaults = {
diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
index 738ee76..84f9b41 100644
--- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
+++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
@@ -147,15 +147,12 @@
}
/* VSC packet set to 4 for PSR-SU, or 2 for PSR1 */
- if (stream->link->psr_settings.psr_feature_enabled) {
- if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1)
- vsc_packet_revision = vsc_packet_rev4;
- else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1)
- vsc_packet_revision = vsc_packet_rev2;
- }
-
- if (stream->link->replay_settings.config.replay_supported)
+ if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1)
vsc_packet_revision = vsc_packet_rev4;
+ else if (stream->link->replay_settings.config.replay_supported)
+ vsc_packet_revision = vsc_packet_rev4;
+ else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1)
+ vsc_packet_revision = vsc_packet_rev2;
/* Update to revision 5 for extended colorimetry support */
if (stream->use_vsc_sdp_for_colorimetry)
diff --git a/drivers/gpu/drm/amd/include/umsch_mm_4_0_api_def.h b/drivers/gpu/drm/amd/include/umsch_mm_4_0_api_def.h
index beadb9e..ca83e9e 100644
--- a/drivers/gpu/drm/amd/include/umsch_mm_4_0_api_def.h
+++ b/drivers/gpu/drm/amd/include/umsch_mm_4_0_api_def.h
@@ -234,7 +234,8 @@
uint32_t enable_level_process_quantum_check : 1;
uint32_t is_vcn0_enabled : 1;
uint32_t is_vcn1_enabled : 1;
- uint32_t reserved : 27;
+ uint32_t use_rs64mem_for_proc_ctx_csa : 1;
+ uint32_t reserved : 26;
};
uint32_t uint32_all;
};
@@ -297,9 +298,12 @@
struct {
uint32_t is_context_suspended : 1;
- uint32_t reserved : 31;
+ uint32_t collaboration_mode : 1;
+ uint32_t reserved : 30;
};
struct UMSCH_API_STATUS api_status;
+ uint32_t process_csa_array_index;
+ uint32_t context_csa_array_index;
};
uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -314,6 +318,7 @@
uint64_t context_csa_addr;
struct UMSCH_API_STATUS api_status;
+ uint32_t context_csa_array_index;
};
uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -337,6 +342,7 @@
uint32_t suspend_fence_value;
struct UMSCH_API_STATUS api_status;
+ uint32_t context_csa_array_index;
};
uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -356,6 +362,7 @@
enum UMSCH_ENGINE_TYPE engine_type;
struct UMSCH_API_STATUS api_status;
+ uint32_t context_csa_array_index;
};
uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -404,6 +411,7 @@
union UMSCH_AFFINITY affinity;
uint64_t context_csa_addr;
struct UMSCH_API_STATUS api_status;
+ uint32_t context_csa_array_index;
};
uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -417,6 +425,7 @@
uint64_t context_quantum;
uint64_t context_csa_addr;
struct UMSCH_API_STATUS api_status;
+ uint32_t context_csa_array_index;
};
uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
index 8a8a57c..ca7ce42 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
@@ -54,14 +54,14 @@
#define PPSMC_MSG_TestMessage 0x01 ///< To check if PMFW is alive and responding. Requirement specified by PMFW team
#define PPSMC_MSG_GetPmfwVersion 0x02 ///< Get PMFW version
#define PPSMC_MSG_GetDriverIfVersion 0x03 ///< Get PMFW_DRIVER_IF version
-#define PPSMC_MSG_SPARE0 0x04 ///< SPARE
-#define PPSMC_MSG_SPARE1 0x05 ///< SPARE
-#define PPSMC_MSG_PowerDownVcn 0x06 ///< Power down VCN
-#define PPSMC_MSG_PowerUpVcn 0x07 ///< Power up VCN; VCN is power gated by default
-#define PPSMC_MSG_SetHardMinVcn 0x08 ///< For wireless display
+#define PPSMC_MSG_PowerDownVcn1 0x04 ///< Power down VCN1
+#define PPSMC_MSG_PowerUpVcn1 0x05 ///< Power up VCN1; VCN1 is power gated by default
+#define PPSMC_MSG_PowerDownVcn0 0x06 ///< Power down VCN0
+#define PPSMC_MSG_PowerUpVcn0 0x07 ///< Power up VCN0; VCN0 is power gated by default
+#define PPSMC_MSG_SetHardMinVcn0 0x08 ///< For wireless display
#define PPSMC_MSG_SetSoftMinGfxclk 0x09 ///< Set SoftMin for GFXCLK, argument is frequency in MHz
-#define PPSMC_MSG_SPARE2 0x0A ///< SPARE
-#define PPSMC_MSG_SPARE3 0x0B ///< SPARE
+#define PPSMC_MSG_SetHardMinVcn1 0x0A ///< For wireless display
+#define PPSMC_MSG_SetSoftMinVcn1 0x0B ///< Set soft min for VCN1 clocks (VCLK1 and DCLK1)
#define PPSMC_MSG_PrepareMp1ForUnload 0x0C ///< Prepare PMFW for GFX driver unload
#define PPSMC_MSG_SetDriverDramAddrHigh 0x0D ///< Set high 32 bits of DRAM address for Driver table transfer
#define PPSMC_MSG_SetDriverDramAddrLow 0x0E ///< Set low 32 bits of DRAM address for Driver table transfer
@@ -71,7 +71,7 @@
#define PPSMC_MSG_GetEnabledSmuFeatures 0x12 ///< Get enabled features in PMFW
#define PPSMC_MSG_SetHardMinSocclkByFreq 0x13 ///< Set hard min for SOC CLK
#define PPSMC_MSG_SetSoftMinFclk 0x14 ///< Set hard min for FCLK
-#define PPSMC_MSG_SetSoftMinVcn 0x15 ///< Set soft min for VCN clocks (VCLK and DCLK)
+#define PPSMC_MSG_SetSoftMinVcn0 0x15 ///< Set soft min for VCN0 clocks (VCLK0 and DCLK0)
#define PPSMC_MSG_EnableGfxImu 0x16 ///< Enable GFX IMU
@@ -84,17 +84,17 @@
#define PPSMC_MSG_SetSoftMaxSocclkByFreq 0x1D ///< Set soft max for SOC CLK
#define PPSMC_MSG_SetSoftMaxFclkByFreq 0x1E ///< Set soft max for FCLK
-#define PPSMC_MSG_SetSoftMaxVcn 0x1F ///< Set soft max for VCN clocks (VCLK and DCLK)
+#define PPSMC_MSG_SetSoftMaxVcn0 0x1F ///< Set soft max for VCN0 clocks (VCLK0 and DCLK0)
#define PPSMC_MSG_spare_0x20 0x20
-#define PPSMC_MSG_PowerDownJpeg 0x21 ///< Power down Jpeg
-#define PPSMC_MSG_PowerUpJpeg 0x22 ///< Power up Jpeg; VCN is power gated by default
+#define PPSMC_MSG_PowerDownJpeg0 0x21 ///< Power down Jpeg of VCN0
+#define PPSMC_MSG_PowerUpJpeg0 0x22 ///< Power up Jpeg of VCN0; VCN0 is power gated by default
#define PPSMC_MSG_SetHardMinFclkByFreq 0x23 ///< Set hard min for FCLK
#define PPSMC_MSG_SetSoftMinSocclkByFreq 0x24 ///< Set soft min for SOC CLK
#define PPSMC_MSG_AllowZstates 0x25 ///< Inform PMFM of allowing Zstate entry, i.e. no Miracast activity
-#define PPSMC_MSG_Reserved 0x26 ///< Not used
-#define PPSMC_MSG_Reserved1 0x27 ///< Not used, previously PPSMC_MSG_RequestActiveWgp
-#define PPSMC_MSG_Reserved2 0x28 ///< Not used, previously PPSMC_MSG_QueryActiveWgp
+#define PPSMC_MSG_PowerDownJpeg1 0x26 ///< Power down Jpeg of VCN1
+#define PPSMC_MSG_PowerUpJpeg1 0x27 ///< Power up Jpeg of VCN1; VCN1 is power gated by default
+#define PPSMC_MSG_SetSoftMaxVcn1 0x28 ///< Set soft max for VCN1 clocks (VCLK1 and DCLK1)
#define PPSMC_MSG_PowerDownIspByTile 0x29 ///< ISP is power gated by default
#define PPSMC_MSG_PowerUpIspByTile 0x2A ///< This message is used to power up ISP tiles and enable the ISP DPM
#define PPSMC_MSG_SetHardMinIspiclkByFreq 0x2B ///< Set HardMin by frequency for ISPICLK
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
index a941fdb..af427cc 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
@@ -115,6 +115,10 @@
__SMU_DUMMY_MAP(PowerDownVcn), \
__SMU_DUMMY_MAP(PowerUpJpeg), \
__SMU_DUMMY_MAP(PowerDownJpeg), \
+ __SMU_DUMMY_MAP(PowerUpJpeg0), \
+ __SMU_DUMMY_MAP(PowerDownJpeg0), \
+ __SMU_DUMMY_MAP(PowerUpJpeg1), \
+ __SMU_DUMMY_MAP(PowerDownJpeg1), \
__SMU_DUMMY_MAP(BacoAudioD3PME), \
__SMU_DUMMY_MAP(ArmD3), \
__SMU_DUMMY_MAP(RunDcBtc), \
@@ -135,6 +139,8 @@
__SMU_DUMMY_MAP(PowerUpSdma), \
__SMU_DUMMY_MAP(SetHardMinIspclkByFreq), \
__SMU_DUMMY_MAP(SetHardMinVcn), \
+ __SMU_DUMMY_MAP(SetHardMinVcn0), \
+ __SMU_DUMMY_MAP(SetHardMinVcn1), \
__SMU_DUMMY_MAP(SetAllowFclkSwitch), \
__SMU_DUMMY_MAP(SetMinVideoGfxclkFreq), \
__SMU_DUMMY_MAP(ActiveProcessNotify), \
@@ -150,6 +156,8 @@
__SMU_DUMMY_MAP(SetPhyclkVoltageByFreq), \
__SMU_DUMMY_MAP(SetDppclkVoltageByFreq), \
__SMU_DUMMY_MAP(SetSoftMinVcn), \
+ __SMU_DUMMY_MAP(SetSoftMinVcn0), \
+ __SMU_DUMMY_MAP(SetSoftMinVcn1), \
__SMU_DUMMY_MAP(EnablePostCode), \
__SMU_DUMMY_MAP(GetGfxclkFrequency), \
__SMU_DUMMY_MAP(GetFclkFrequency), \
@@ -161,6 +169,8 @@
__SMU_DUMMY_MAP(SetSoftMaxSocclkByFreq), \
__SMU_DUMMY_MAP(SetSoftMaxFclkByFreq), \
__SMU_DUMMY_MAP(SetSoftMaxVcn), \
+ __SMU_DUMMY_MAP(SetSoftMaxVcn0), \
+ __SMU_DUMMY_MAP(SetSoftMaxVcn1), \
__SMU_DUMMY_MAP(PowerGateMmHub), \
__SMU_DUMMY_MAP(UpdatePmeRestore), \
__SMU_DUMMY_MAP(GpuChangeState), \
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index b06a3cc..9e39f99 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -1402,9 +1402,22 @@
if (adev->vcn.harvest_config & (1 << i))
continue;
- ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
- SMU_MSG_PowerUpVcn : SMU_MSG_PowerDownVcn,
- i << 16U, NULL);
+ if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0) ||
+ amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) {
+ if (i == 0)
+ ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+ SMU_MSG_PowerUpVcn0 : SMU_MSG_PowerDownVcn0,
+ i << 16U, NULL);
+ else if (i == 1)
+ ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+ SMU_MSG_PowerUpVcn1 : SMU_MSG_PowerDownVcn1,
+ i << 16U, NULL);
+ } else {
+ ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+ SMU_MSG_PowerUpVcn : SMU_MSG_PowerDownVcn,
+ i << 16U, NULL);
+ }
+
if (ret)
return ret;
}
@@ -1415,9 +1428,34 @@
int smu_v14_0_set_jpeg_enable(struct smu_context *smu,
bool enable)
{
- return smu_cmn_send_smc_msg_with_param(smu, enable ?
- SMU_MSG_PowerUpJpeg : SMU_MSG_PowerDownJpeg,
- 0, NULL);
+ struct amdgpu_device *adev = smu->adev;
+ int i, ret = 0;
+
+ for (i = 0; i < adev->jpeg.num_jpeg_inst; i++) {
+ if (adev->jpeg.harvest_config & (1 << i))
+ continue;
+
+ if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0) ||
+ amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) {
+ if (i == 0)
+ ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+ SMU_MSG_PowerUpJpeg0 : SMU_MSG_PowerDownJpeg0,
+ i << 16U, NULL);
+ else if (i == 1 && amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+ ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+ SMU_MSG_PowerUpJpeg1 : SMU_MSG_PowerDownJpeg1,
+ i << 16U, NULL);
+ } else {
+ ret = smu_cmn_send_smc_msg_with_param(smu, enable ?
+ SMU_MSG_PowerUpJpeg : SMU_MSG_PowerDownJpeg,
+ i << 16U, NULL);
+ }
+
+ if (ret)
+ return ret;
+ }
+
+ return ret;
}
int smu_v14_0_run_btc(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index 9310c47..d6de6d9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -70,9 +70,12 @@
MSG_MAP(TestMessage, PPSMC_MSG_TestMessage, 1),
MSG_MAP(GetSmuVersion, PPSMC_MSG_GetPmfwVersion, 1),
MSG_MAP(GetDriverIfVersion, PPSMC_MSG_GetDriverIfVersion, 1),
- MSG_MAP(PowerDownVcn, PPSMC_MSG_PowerDownVcn, 1),
- MSG_MAP(PowerUpVcn, PPSMC_MSG_PowerUpVcn, 1),
- MSG_MAP(SetHardMinVcn, PPSMC_MSG_SetHardMinVcn, 1),
+ MSG_MAP(PowerDownVcn0, PPSMC_MSG_PowerDownVcn0, 1),
+ MSG_MAP(PowerUpVcn0, PPSMC_MSG_PowerUpVcn0, 1),
+ MSG_MAP(SetHardMinVcn0, PPSMC_MSG_SetHardMinVcn0, 1),
+ MSG_MAP(PowerDownVcn1, PPSMC_MSG_PowerDownVcn1, 1),
+ MSG_MAP(PowerUpVcn1, PPSMC_MSG_PowerUpVcn1, 1),
+ MSG_MAP(SetHardMinVcn1, PPSMC_MSG_SetHardMinVcn1, 1),
MSG_MAP(SetSoftMinGfxclk, PPSMC_MSG_SetSoftMinGfxclk, 1),
MSG_MAP(PrepareMp1ForUnload, PPSMC_MSG_PrepareMp1ForUnload, 1),
MSG_MAP(SetDriverDramAddrHigh, PPSMC_MSG_SetDriverDramAddrHigh, 1),
@@ -83,7 +86,8 @@
MSG_MAP(GetEnabledSmuFeatures, PPSMC_MSG_GetEnabledSmuFeatures, 1),
MSG_MAP(SetHardMinSocclkByFreq, PPSMC_MSG_SetHardMinSocclkByFreq, 1),
MSG_MAP(SetSoftMinFclk, PPSMC_MSG_SetSoftMinFclk, 1),
- MSG_MAP(SetSoftMinVcn, PPSMC_MSG_SetSoftMinVcn, 1),
+ MSG_MAP(SetSoftMinVcn0, PPSMC_MSG_SetSoftMinVcn0, 1),
+ MSG_MAP(SetSoftMinVcn1, PPSMC_MSG_SetSoftMinVcn1, 1),
MSG_MAP(EnableGfxImu, PPSMC_MSG_EnableGfxImu, 1),
MSG_MAP(AllowGfxOff, PPSMC_MSG_AllowGfxOff, 1),
MSG_MAP(DisallowGfxOff, PPSMC_MSG_DisallowGfxOff, 1),
@@ -91,9 +95,12 @@
MSG_MAP(SetHardMinGfxClk, PPSMC_MSG_SetHardMinGfxClk, 1),
MSG_MAP(SetSoftMaxSocclkByFreq, PPSMC_MSG_SetSoftMaxSocclkByFreq, 1),
MSG_MAP(SetSoftMaxFclkByFreq, PPSMC_MSG_SetSoftMaxFclkByFreq, 1),
- MSG_MAP(SetSoftMaxVcn, PPSMC_MSG_SetSoftMaxVcn, 1),
- MSG_MAP(PowerDownJpeg, PPSMC_MSG_PowerDownJpeg, 1),
- MSG_MAP(PowerUpJpeg, PPSMC_MSG_PowerUpJpeg, 1),
+ MSG_MAP(SetSoftMaxVcn0, PPSMC_MSG_SetSoftMaxVcn0, 1),
+ MSG_MAP(SetSoftMaxVcn1, PPSMC_MSG_SetSoftMaxVcn1, 1),
+ MSG_MAP(PowerDownJpeg0, PPSMC_MSG_PowerDownJpeg0, 1),
+ MSG_MAP(PowerUpJpeg0, PPSMC_MSG_PowerUpJpeg0, 1),
+ MSG_MAP(PowerDownJpeg1, PPSMC_MSG_PowerDownJpeg1, 1),
+ MSG_MAP(PowerUpJpeg1, PPSMC_MSG_PowerUpJpeg1, 1),
MSG_MAP(SetHardMinFclkByFreq, PPSMC_MSG_SetHardMinFclkByFreq, 1),
MSG_MAP(SetSoftMinSocclkByFreq, PPSMC_MSG_SetSoftMinSocclkByFreq, 1),
MSG_MAP(PowerDownIspByTile, PPSMC_MSG_PowerDownIspByTile, 1),
diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c
index 266826e..f5d4be8 100644
--- a/drivers/gpu/drm/display/drm_dp_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_helper.c
@@ -4111,6 +4111,13 @@
u32 overhead = 1000000;
int symbol_cycles;
+ if (lane_count == 0 || hactive == 0 || bpp_x16 == 0) {
+ DRM_DEBUG_KMS("Invalid BW overhead params: lane_count %d, hactive %d, bpp_x16 %d.%04d\n",
+ lane_count, hactive,
+ bpp_x16 >> 4, (bpp_x16 & 0xf) * 625);
+ return 0;
+ }
+
/*
* DP Standard v2.1 2.6.4.1
* SSC downspread and ref clock variation margin:
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 3ef6ed4..4c2f856 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -33,9 +33,9 @@
subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror
# Fine grained warnings disable
-CFLAGS_i915_pci.o = $(call cc-disable-warning, override-init)
-CFLAGS_display/intel_display_device.o = $(call cc-disable-warning, override-init)
-CFLAGS_display/intel_fbdev.o = $(call cc-disable-warning, override-init)
+CFLAGS_i915_pci.o = -Wno-override-init
+CFLAGS_display/intel_display_device.o = -Wno-override-init
+CFLAGS_display/intel_fbdev.o = -Wno-override-init
# Support compiling the display code separately for both i915 and xe
# drivers. Define I915 when building i915.
diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c
index dfe0b07..06ec04e 100644
--- a/drivers/gpu/drm/i915/display/g4x_dp.c
+++ b/drivers/gpu/drm/i915/display/g4x_dp.c
@@ -717,7 +717,6 @@
{
intel_enable_dp(state, encoder, pipe_config, conn_state);
intel_edp_backlight_on(pipe_config, conn_state);
- encoder->audio_enable(encoder, pipe_config, conn_state);
}
static void vlv_enable_dp(struct intel_atomic_state *state,
@@ -726,7 +725,6 @@
const struct drm_connector_state *conn_state)
{
intel_edp_backlight_on(pipe_config, conn_state);
- encoder->audio_enable(encoder, pipe_config, conn_state);
}
static void g4x_pre_enable_dp(struct intel_atomic_state *state,
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index eda4a8b..ac456a2 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1155,7 +1155,6 @@
}
intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_INIT_OTP);
- intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
/* ensure all panel commands dispatched before enabling transcoder */
wait_for_cmds_dispatched_to_panel(encoder);
@@ -1256,6 +1255,8 @@
/* step6d: enable dsi transcoder */
gen11_dsi_enable_transcoder(encoder);
+ intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
+
/* step7: enable backlight */
intel_backlight_enable(crtc_state, conn_state);
intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_ON);
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index fe52c06..52bd357 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1955,16 +1955,12 @@
* these devices we split the init OTP sequence into a deassert sequence and
* the actual init OTP part.
*/
-static void fixup_mipi_sequences(struct drm_i915_private *i915,
- struct intel_panel *panel)
+static void vlv_fixup_mipi_sequences(struct drm_i915_private *i915,
+ struct intel_panel *panel)
{
u8 *init_otp;
int len;
- /* Limit this to VLV for now. */
- if (!IS_VALLEYVIEW(i915))
- return;
-
/* Limit this to v1 vid-mode sequences */
if (panel->vbt.dsi.config->is_cmd_mode ||
panel->vbt.dsi.seq_version != 1)
@@ -2000,6 +1996,41 @@
panel->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] = init_otp + len - 1;
}
+/*
+ * Some machines (eg. Lenovo 82TQ) appear to have broken
+ * VBT sequences:
+ * - INIT_OTP is not present at all
+ * - what should be in INIT_OTP is in DISPLAY_ON
+ * - what should be in DISPLAY_ON is in BACKLIGHT_ON
+ * (along with the actual backlight stuff)
+ *
+ * To make those work we simply swap DISPLAY_ON and INIT_OTP.
+ *
+ * TODO: Do we need to limit this to specific machines,
+ * or examine the contents of the sequences to
+ * avoid false positives?
+ */
+static void icl_fixup_mipi_sequences(struct drm_i915_private *i915,
+ struct intel_panel *panel)
+{
+ if (!panel->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] &&
+ panel->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_ON]) {
+ drm_dbg_kms(&i915->drm, "Broken VBT: Swapping INIT_OTP and DISPLAY_ON sequences\n");
+
+ swap(panel->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP],
+ panel->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_ON]);
+ }
+}
+
+static void fixup_mipi_sequences(struct drm_i915_private *i915,
+ struct intel_panel *panel)
+{
+ if (DISPLAY_VER(i915) >= 11)
+ icl_fixup_mipi_sequences(i915, panel);
+ else if (IS_VALLEYVIEW(i915))
+ vlv_fixup_mipi_sequences(i915, panel);
+}
+
static void
parse_mipi_sequence(struct drm_i915_private *i915,
struct intel_panel *panel)
@@ -3351,6 +3382,9 @@
{
const struct child_device_config *child = &devdata->child;
+ if (!devdata)
+ return false;
+
if (!intel_bios_encoder_supports_dp(devdata) ||
!intel_bios_encoder_supports_hdmi(devdata))
return false;
diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c
index f8b3399..0d3da55 100644
--- a/drivers/gpu/drm/i915/display/intel_cursor.c
+++ b/drivers/gpu/drm/i915/display/intel_cursor.c
@@ -36,12 +36,10 @@
{
struct drm_i915_private *dev_priv =
to_i915(plane_state->uapi.plane->dev);
- const struct drm_framebuffer *fb = plane_state->hw.fb;
- struct drm_i915_gem_object *obj = intel_fb_obj(fb);
u32 base;
if (DISPLAY_INFO(dev_priv)->cursor_needs_physical)
- base = i915_gem_object_get_dma_address(obj, 0);
+ base = plane_state->phys_dma_addr;
else
base = intel_plane_ggtt_offset(plane_state);
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index e67cd5b..9104f18 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -727,6 +727,7 @@
#define PLANE_HAS_FENCE BIT(0)
struct intel_fb_view view;
+ u32 phys_dma_addr; /* for cursor_needs_physical */
/* Plane pxp decryption state */
bool decrypt;
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index f0c3ed3..f98ef4b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -67,6 +67,7 @@
#include "intel_dp_tunnel.h"
#include "intel_dpio_phy.h"
#include "intel_dpll.h"
+#include "intel_drrs.h"
#include "intel_fifo_underrun.h"
#include "intel_hdcp.h"
#include "intel_hdmi.h"
@@ -2683,15 +2684,6 @@
intel_hdmi_infoframe_enable(HDMI_PACKET_TYPE_GAMUT_METADATA);
}
-static bool cpu_transcoder_has_drrs(struct drm_i915_private *i915,
- enum transcoder cpu_transcoder)
-{
- if (HAS_DOUBLE_BUFFERED_M_N(i915))
- return true;
-
- return intel_cpu_transcoder_has_m2_n2(i915, cpu_transcoder);
-}
-
static bool can_enable_drrs(struct intel_connector *connector,
const struct intel_crtc_state *pipe_config,
const struct drm_display_mode *downclock_mode)
@@ -2714,7 +2706,7 @@
if (pipe_config->has_pch_encoder)
return false;
- if (!cpu_transcoder_has_drrs(i915, pipe_config->cpu_transcoder))
+ if (!intel_cpu_transcoder_has_drrs(i915, pipe_config->cpu_transcoder))
return false;
return downclock_mode &&
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index ff480f1..b6d2441 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -2554,7 +2554,7 @@
static bool
ehl_combo_pll_div_frac_wa_needed(struct drm_i915_private *i915)
{
- return (((IS_ELKHARTLAKE(i915) || IS_JASPERLAKE(i915)) &&
+ return ((IS_ELKHARTLAKE(i915) &&
IS_DISPLAY_STEP(i915, STEP_B0, STEP_FOREVER)) ||
IS_TIGERLAKE(i915) || IS_ALDERLAKE_S(i915) || IS_ALDERLAKE_P(i915)) &&
i915->display.dpll.ref_clks.nssc == 38400;
diff --git a/drivers/gpu/drm/i915/display/intel_drrs.c b/drivers/gpu/drm/i915/display/intel_drrs.c
index 169ef38..597f8bd6 100644
--- a/drivers/gpu/drm/i915/display/intel_drrs.c
+++ b/drivers/gpu/drm/i915/display/intel_drrs.c
@@ -63,6 +63,15 @@
return str[drrs_type];
}
+bool intel_cpu_transcoder_has_drrs(struct drm_i915_private *i915,
+ enum transcoder cpu_transcoder)
+{
+ if (HAS_DOUBLE_BUFFERED_M_N(i915))
+ return true;
+
+ return intel_cpu_transcoder_has_m2_n2(i915, cpu_transcoder);
+}
+
static void
intel_drrs_set_refresh_rate_pipeconf(struct intel_crtc *crtc,
enum drrs_refresh_rate refresh_rate)
@@ -312,9 +321,8 @@
mutex_lock(&crtc->drrs.mutex);
seq_printf(m, "DRRS capable: %s\n",
- str_yes_no(crtc_state->has_drrs ||
- HAS_DOUBLE_BUFFERED_M_N(i915) ||
- intel_cpu_transcoder_has_m2_n2(i915, crtc_state->cpu_transcoder)));
+ str_yes_no(intel_cpu_transcoder_has_drrs(i915,
+ crtc_state->cpu_transcoder)));
seq_printf(m, "DRRS enabled: %s\n",
str_yes_no(crtc_state->has_drrs));
diff --git a/drivers/gpu/drm/i915/display/intel_drrs.h b/drivers/gpu/drm/i915/display/intel_drrs.h
index 8ef5f93..0982f95 100644
--- a/drivers/gpu/drm/i915/display/intel_drrs.h
+++ b/drivers/gpu/drm/i915/display/intel_drrs.h
@@ -9,12 +9,15 @@
#include <linux/types.h>
enum drrs_type;
+enum transcoder;
struct drm_i915_private;
struct intel_atomic_state;
struct intel_crtc;
struct intel_crtc_state;
struct intel_connector;
+bool intel_cpu_transcoder_has_drrs(struct drm_i915_private *i915,
+ enum transcoder cpu_transcoder);
const char *intel_drrs_type_str(enum drrs_type drrs_type);
bool intel_drrs_is_active(struct intel_crtc *crtc);
void intel_drrs_activate(const struct intel_crtc_state *crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index d62e050..e4515bf 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -340,6 +340,17 @@
return max(0, vblank_start - intel_usecs_to_scanlines(adjusted_mode, latency));
}
+static u32 dsb_chicken(struct intel_crtc *crtc)
+{
+ if (crtc->mode_flags & I915_MODE_FLAG_VRR)
+ return DSB_CTRL_WAIT_SAFE_WINDOW |
+ DSB_CTRL_NO_WAIT_VBLANK |
+ DSB_INST_WAIT_SAFE_WINDOW |
+ DSB_INST_NO_WAIT_VBLANK;
+ else
+ return 0;
+}
+
static void _intel_dsb_commit(struct intel_dsb *dsb, u32 ctrl,
int dewake_scanline)
{
@@ -361,6 +372,9 @@
intel_de_write_fw(dev_priv, DSB_CTRL(pipe, dsb->id),
ctrl | DSB_ENABLE);
+ intel_de_write_fw(dev_priv, DSB_CHICKEN(pipe, dsb->id),
+ dsb_chicken(crtc));
+
intel_de_write_fw(dev_priv, DSB_HEAD(pipe, dsb->id),
intel_dsb_buffer_ggtt_offset(&dsb->dsb_buf));
diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c
index 7b42aef..b6df9ba 100644
--- a/drivers/gpu/drm/i915/display/intel_fb_pin.c
+++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c
@@ -255,6 +255,16 @@
return PTR_ERR(vma);
plane_state->ggtt_vma = vma;
+
+ /*
+ * Pre-populate the dma address before we enter the vblank
+ * evade critical section as i915_gem_object_get_dma_address()
+ * will trigger might_sleep() even if it won't actually sleep,
+ * which is the case when the fb has already been pinned.
+ */
+ if (phys_cursor)
+ plane_state->phys_dma_addr =
+ i915_gem_object_get_dma_address(intel_fb_obj(fb), 0);
} else {
struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index 5f9e748..0cd9c18 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -1842,8 +1842,6 @@
struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
u32 temp;
- encoder->audio_disable(encoder, old_crtc_state, conn_state);
-
intel_sdvo_set_active_outputs(intel_sdvo, 0);
if (0)
intel_sdvo_set_encoder_power_state(intel_sdvo,
@@ -1935,8 +1933,6 @@
intel_sdvo_set_encoder_power_state(intel_sdvo,
DRM_MODE_DPMS_ON);
intel_sdvo_set_active_outputs(intel_sdvo, intel_sdvo_connector->output_flag);
-
- encoder->audio_enable(encoder, pipe_config, conn_state);
}
static enum drm_mode_status
diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c
index 5d905f9..eb5bd07 100644
--- a/drivers/gpu/drm/i915/display/intel_vrr.c
+++ b/drivers/gpu/drm/i915/display/intel_vrr.c
@@ -187,10 +187,11 @@
enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
/*
- * TRANS_SET_CONTEXT_LATENCY with VRR enabled
- * requires this chicken bit on ADL/DG2.
+ * This bit seems to have two meanings depending on the platform:
+ * TGL: generate VRR "safe window" for DSB vblank waits
+ * ADL/DG2: make TRANS_SET_CONTEXT_LATENCY effective with VRR
*/
- if (DISPLAY_VER(dev_priv) == 13)
+ if (IS_DISPLAY_VER(dev_priv, 12, 13))
intel_de_rmw(dev_priv, CHICKEN_TRANS(cpu_transcoder),
0, PIPE_VBLANK_WITH_DELAY);
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index e941e2e..860574d 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -2295,6 +2295,9 @@
if (HAS_4TILE(i915))
caps |= INTEL_PLANE_CAP_TILING_4;
+ if (!IS_ENABLED(I915) && !HAS_FLAT_CCS(i915))
+ return caps;
+
if (skl_plane_has_rc_ccs(i915, pipe, plane_id)) {
caps |= INTEL_PLANE_CAP_CCS_RC;
if (DISPLAY_VER(i915) >= 12)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 96bdb93..fb7bff2 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -279,9 +279,6 @@
intel_engine_park_heartbeat(engine);
intel_breadcrumbs_park(engine->breadcrumbs);
- /* Must be reset upon idling, or we may miss the busy wakeup. */
- GEM_BUG_ON(engine->sched_engine->queue_priority_hint != INT_MIN);
-
if (engine->park)
engine->park(engine);
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 42aade0..b061a0a 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -3272,6 +3272,9 @@
{
cancel_timer(&engine->execlists.timer);
cancel_timer(&engine->execlists.preempt);
+
+ /* Reset upon idling, or we may delay the busy wakeup. */
+ WRITE_ONCE(engine->sched_engine->queue_priority_hint, INT_MIN);
}
static void add_to_engine(struct i915_request *rq)
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index d67d446..25413809 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1653,6 +1653,7 @@
xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
{
/* Wa_14018575942 / Wa_18018781329 */
+ wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB);
wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB);
/* Wa_22016670082 */
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index 9ee902d..4b9233c 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -800,7 +800,7 @@
goto out_cleanup_modeset2;
ret = intel_pxp_init(i915);
- if (ret != -ENODEV)
+ if (ret && ret != -ENODEV)
drm_dbg(&i915->drm, "pxp init failed with %d\n", ret);
ret = intel_display_driver_probe(i915);
diff --git a/drivers/gpu/drm/i915/i915_hwmon.c b/drivers/gpu/drm/i915/i915_hwmon.c
index 8c3f443..b758fd1 100644
--- a/drivers/gpu/drm/i915/i915_hwmon.c
+++ b/drivers/gpu/drm/i915/i915_hwmon.c
@@ -72,12 +72,13 @@
struct intel_uncore *uncore = ddat->uncore;
intel_wakeref_t wakeref;
- mutex_lock(&hwmon->hwmon_lock);
+ with_intel_runtime_pm(uncore->rpm, wakeref) {
+ mutex_lock(&hwmon->hwmon_lock);
- with_intel_runtime_pm(uncore->rpm, wakeref)
intel_uncore_rmw(uncore, reg, clear, set);
- mutex_unlock(&hwmon->hwmon_lock);
+ mutex_unlock(&hwmon->hwmon_lock);
+ }
}
/*
@@ -136,20 +137,21 @@
else
rgaddr = hwmon->rg.energy_status_all;
- mutex_lock(&hwmon->hwmon_lock);
+ with_intel_runtime_pm(uncore->rpm, wakeref) {
+ mutex_lock(&hwmon->hwmon_lock);
- with_intel_runtime_pm(uncore->rpm, wakeref)
reg_val = intel_uncore_read(uncore, rgaddr);
- if (reg_val >= ei->reg_val_prev)
- ei->accum_energy += reg_val - ei->reg_val_prev;
- else
- ei->accum_energy += UINT_MAX - ei->reg_val_prev + reg_val;
- ei->reg_val_prev = reg_val;
+ if (reg_val >= ei->reg_val_prev)
+ ei->accum_energy += reg_val - ei->reg_val_prev;
+ else
+ ei->accum_energy += UINT_MAX - ei->reg_val_prev + reg_val;
+ ei->reg_val_prev = reg_val;
- *energy = mul_u64_u32_shr(ei->accum_energy, SF_ENERGY,
- hwmon->scl_shift_energy);
- mutex_unlock(&hwmon->hwmon_lock);
+ *energy = mul_u64_u32_shr(ei->accum_energy, SF_ENERGY,
+ hwmon->scl_shift_energy);
+ mutex_unlock(&hwmon->hwmon_lock);
+ }
}
static ssize_t
@@ -404,6 +406,7 @@
/* Block waiting for GuC reset to complete when needed */
for (;;) {
+ wakeref = intel_runtime_pm_get(ddat->uncore->rpm);
mutex_lock(&hwmon->hwmon_lock);
prepare_to_wait(&ddat->waitq, &wait, TASK_INTERRUPTIBLE);
@@ -417,14 +420,13 @@
}
mutex_unlock(&hwmon->hwmon_lock);
+ intel_runtime_pm_put(ddat->uncore->rpm, wakeref);
schedule();
}
finish_wait(&ddat->waitq, &wait);
if (ret)
- goto unlock;
-
- wakeref = intel_runtime_pm_get(ddat->uncore->rpm);
+ goto exit;
/* Disable PL1 limit and verify, because the limit cannot be disabled on all platforms */
if (val == PL1_DISABLE) {
@@ -444,9 +446,8 @@
intel_uncore_rmw(ddat->uncore, hwmon->rg.pkg_rapl_limit,
PKG_PWR_LIM_1_EN | PKG_PWR_LIM_1, nval);
exit:
- intel_runtime_pm_put(ddat->uncore->rpm, wakeref);
-unlock:
mutex_unlock(&hwmon->hwmon_lock);
+ intel_runtime_pm_put(ddat->uncore->rpm, wakeref);
return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_memcpy.c b/drivers/gpu/drm/i915/i915_memcpy.c
index ba82277..cc41974 100644
--- a/drivers/gpu/drm/i915/i915_memcpy.c
+++ b/drivers/gpu/drm/i915/i915_memcpy.c
@@ -25,6 +25,8 @@
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/cpufeature.h>
+#include <linux/bug.h>
+#include <linux/build_bug.h>
#include <asm/fpu/api.h>
#include "i915_memcpy.h"
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index e00557e1..3b2e49ce 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4599,7 +4599,7 @@
#define MTL_CHICKEN_TRANS(trans) _MMIO_TRANS((trans), \
_MTL_CHICKEN_TRANS_A, \
_MTL_CHICKEN_TRANS_B)
-#define PIPE_VBLANK_WITH_DELAY REG_BIT(31) /* ADL/DG2 */
+#define PIPE_VBLANK_WITH_DELAY REG_BIT(31) /* tgl+ */
#define SKL_UNMASK_VBL_TO_PIPE_IN_SRD REG_BIT(30) /* skl+ */
#define HSW_FRAME_START_DELAY_MASK REG_GENMASK(28, 27)
#define HSW_FRAME_START_DELAY(x) REG_FIELD_PREP(HSW_FRAME_START_DELAY_MASK, x)
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index d09aad3..b70715b 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -34,6 +34,7 @@
#include "gt/intel_engine.h"
#include "gt/intel_engine_heartbeat.h"
#include "gt/intel_gt.h"
+#include "gt/intel_gt_pm.h"
#include "gt/intel_gt_requests.h"
#include "gt/intel_tlb.h"
@@ -103,12 +104,42 @@
static int __i915_vma_active(struct i915_active *ref)
{
- return i915_vma_tryget(active_to_vma(ref)) ? 0 : -ENOENT;
+ struct i915_vma *vma = active_to_vma(ref);
+
+ if (!i915_vma_tryget(vma))
+ return -ENOENT;
+
+ /*
+ * Exclude global GTT VMA from holding a GT wakeref
+ * while active, otherwise GPU never goes idle.
+ */
+ if (!i915_vma_is_ggtt(vma)) {
+ /*
+ * Since we and our _retire() counterpart can be
+ * called asynchronously, storing a wakeref tracking
+ * handle inside struct i915_vma is not safe, and
+ * there is no other good place for that. Hence,
+ * use untracked variants of intel_gt_pm_get/put().
+ */
+ intel_gt_pm_get_untracked(vma->vm->gt);
+ }
+
+ return 0;
}
static void __i915_vma_retire(struct i915_active *ref)
{
- i915_vma_put(active_to_vma(ref));
+ struct i915_vma *vma = active_to_vma(ref);
+
+ if (!i915_vma_is_ggtt(vma)) {
+ /*
+ * Since we can be called from atomic contexts,
+ * use an async variant of intel_gt_pm_put().
+ */
+ intel_gt_pm_put_async_untracked(vma->vm->gt);
+ }
+
+ i915_vma_put(vma);
}
static struct i915_vma *
@@ -1404,7 +1435,7 @@
struct i915_vma_work *work = NULL;
struct dma_fence *moving = NULL;
struct i915_vma_resource *vma_res = NULL;
- intel_wakeref_t wakeref = 0;
+ intel_wakeref_t wakeref;
unsigned int bound;
int err;
@@ -1424,8 +1455,14 @@
if (err)
return err;
- if (flags & PIN_GLOBAL)
- wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm);
+ /*
+ * In case of a global GTT, we must hold a runtime-pm wakeref
+ * while global PTEs are updated. In other cases, we hold
+ * the rpm reference while the VMA is active. Since runtime
+ * resume may require allocations, which are forbidden inside
+ * vm->mutex, get the first rpm wakeref outside of the mutex.
+ */
+ wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm);
if (flags & vma->vm->bind_async_flags) {
/* lock VM */
@@ -1561,8 +1598,7 @@
if (work)
dma_fence_work_commit_imm(&work->base);
err_rpm:
- if (wakeref)
- intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref);
+ intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref);
if (moving)
dma_fence_put(moving);
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 12feecf7..6fb65b0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -378,9 +378,9 @@
dma_addr_t *dma_addrs;
struct nouveau_fence *fence;
- src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL);
- dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL);
- dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL);
+ src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL);
+ dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL);
+ dma_addrs = kvcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL | __GFP_NOFAIL);
migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT,
npages);
@@ -406,11 +406,11 @@
migrate_device_pages(src_pfns, dst_pfns, npages);
nouveau_dmem_fence_done(&fence);
migrate_device_finalize(src_pfns, dst_pfns, npages);
- kfree(src_pfns);
- kfree(dst_pfns);
+ kvfree(src_pfns);
+ kvfree(dst_pfns);
for (i = 0; i < npages; i++)
dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL);
- kfree(dma_addrs);
+ kvfree(dma_addrs);
}
void
diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
index 281edab..d6ea01f 100644
--- a/drivers/gpu/drm/qxl/qxl_cmd.c
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -421,7 +421,6 @@
{
uint32_t handle;
int idr_ret;
- int count = 0;
again:
idr_preload(GFP_ATOMIC);
spin_lock(&qdev->surf_id_idr_lock);
@@ -433,7 +432,6 @@
handle = idr_ret;
if (handle >= qdev->rom->n_surfaces) {
- count++;
spin_lock(&qdev->surf_id_idr_lock);
idr_remove(&qdev->surf_id_idr, handle);
spin_unlock(&qdev->surf_id_idr_lock);
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index dd0f834..506ae1f 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -145,7 +145,7 @@
struct qxl_release *release;
struct qxl_bo *cmd_bo;
void *fb_cmd;
- int i, ret, num_relocs;
+ int i, ret;
int unwritten;
switch (cmd->type) {
@@ -200,7 +200,6 @@
}
/* fill out reloc info structs */
- num_relocs = 0;
for (i = 0; i < cmd->relocs_num; ++i) {
struct drm_qxl_reloc reloc;
struct drm_qxl_reloc __user *u = u64_to_user_ptr(cmd->relocs);
@@ -230,7 +229,6 @@
reloc_info[i].dst_bo = cmd_bo;
reloc_info[i].dst_offset = reloc.dst_offset + release->release_offset;
}
- num_relocs++;
/* reserve and validate the reloc dst bo */
if (reloc.reloc_type == QXL_RELOC_TYPE_BO || reloc.src_handle) {
diff --git a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
index 4817069..18efb3f 100644
--- a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
+++ b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
@@ -17,9 +17,7 @@
static const uint32_t formats_cluster[] = {
DRM_FORMAT_XRGB2101010,
- DRM_FORMAT_ARGB2101010,
DRM_FORMAT_XBGR2101010,
- DRM_FORMAT_ABGR2101010,
DRM_FORMAT_XRGB8888,
DRM_FORMAT_ARGB8888,
DRM_FORMAT_XBGR8888,
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 3c4f5a3..58c8161 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -71,13 +71,19 @@
entity->guilty = guilty;
entity->num_sched_list = num_sched_list;
entity->priority = priority;
+ /*
+ * It's perfectly valid to initialize an entity without having a valid
+ * scheduler attached. It's just not valid to use the scheduler before it
+ * is initialized itself.
+ */
entity->sched_list = num_sched_list > 1 ? sched_list : NULL;
RCU_INIT_POINTER(entity->last_scheduled, NULL);
RB_CLEAR_NODE(&entity->rb_tree_node);
- if (!sched_list[0]->sched_rq) {
- /* Warn drivers not to do this and to fix their DRM
- * calling order.
+ if (num_sched_list && !sched_list[0]->sched_rq) {
+ /* Since every entry covered by num_sched_list
+ * should be non-NULL and therefore we warn drivers
+ * not to do this and to fix their DRM calling order.
*/
pr_warn("%s: called with uninitialized scheduler\n", __func__);
} else if (num_sched_list) {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index d3e308f..c7d90f9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -1444,12 +1444,15 @@
root, "system_ttm");
ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, TTM_PL_VRAM),
root, "vram_ttm");
- ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_GMR),
- root, "gmr_ttm");
- ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_MOB),
- root, "mob_ttm");
- ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_SYSTEM),
- root, "system_mob_ttm");
+ if (vmw->has_gmr)
+ ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_GMR),
+ root, "gmr_ttm");
+ if (vmw->has_mob) {
+ ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_MOB),
+ root, "mob_ttm");
+ ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_SYSTEM),
+ root, "system_mob_ttm");
+ }
}
static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val,
diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 5a428ca0..c29a850 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -172,8 +172,8 @@
-Ddrm_i915_gem_object=xe_bo \
-Ddrm_i915_private=xe_device
-CFLAGS_i915-display/intel_fbdev.o = $(call cc-disable-warning, override-init)
-CFLAGS_i915-display/intel_display_device.o = $(call cc-disable-warning, override-init)
+CFLAGS_i915-display/intel_fbdev.o = -Wno-override-init
+CFLAGS_i915-display/intel_display_device.o = -Wno-override-init
# Rule to build SOC code shared with i915
$(obj)/i915-soc/%.o: $(srctree)/drivers/gpu/drm/i915/soc/%.c FORCE
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 6603a0e..9c0837b 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -144,9 +144,6 @@
.mem_type = XE_PL_TT,
};
*c += 1;
-
- if (bo->props.preferred_mem_type == XE_BO_PROPS_INVALID)
- bo->props.preferred_mem_type = XE_PL_TT;
}
}
@@ -181,25 +178,15 @@
}
places[*c] = place;
*c += 1;
-
- if (bo->props.preferred_mem_type == XE_BO_PROPS_INVALID)
- bo->props.preferred_mem_type = mem_type;
}
static void try_add_vram(struct xe_device *xe, struct xe_bo *bo,
u32 bo_flags, u32 *c)
{
- if (bo->props.preferred_gt == XE_GT1) {
- if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
- add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
- if (bo_flags & XE_BO_CREATE_VRAM0_BIT)
- add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c);
- } else {
- if (bo_flags & XE_BO_CREATE_VRAM0_BIT)
- add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c);
- if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
- add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
- }
+ if (bo_flags & XE_BO_CREATE_VRAM0_BIT)
+ add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c);
+ if (bo_flags & XE_BO_CREATE_VRAM1_BIT)
+ add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c);
}
static void try_add_stolen(struct xe_device *xe, struct xe_bo *bo,
@@ -223,17 +210,8 @@
{
u32 c = 0;
- bo->props.preferred_mem_type = XE_BO_PROPS_INVALID;
-
- /* The order of placements should indicate preferred location */
-
- if (bo->props.preferred_mem_class == DRM_XE_MEM_REGION_CLASS_SYSMEM) {
- try_add_system(xe, bo, bo_flags, &c);
- try_add_vram(xe, bo, bo_flags, &c);
- } else {
- try_add_vram(xe, bo, bo_flags, &c);
- try_add_system(xe, bo, bo_flags, &c);
- }
+ try_add_vram(xe, bo, bo_flags, &c);
+ try_add_system(xe, bo, bo_flags, &c);
try_add_stolen(xe, bo, bo_flags, &c);
if (!c)
@@ -1126,13 +1104,6 @@
}
}
-static bool should_migrate_to_system(struct xe_bo *bo)
-{
- struct xe_device *xe = xe_bo_device(bo);
-
- return xe_device_in_fault_mode(xe) && bo->props.cpu_atomic;
-}
-
static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
{
struct ttm_buffer_object *tbo = vmf->vma->vm_private_data;
@@ -1141,7 +1112,7 @@
struct xe_bo *bo = ttm_to_xe_bo(tbo);
bool needs_rpm = bo->flags & XE_BO_CREATE_VRAM_MASK;
vm_fault_t ret;
- int idx, r = 0;
+ int idx;
if (needs_rpm)
xe_device_mem_access_get(xe);
@@ -1153,17 +1124,8 @@
if (drm_dev_enter(ddev, &idx)) {
trace_xe_bo_cpu_fault(bo);
- if (should_migrate_to_system(bo)) {
- r = xe_bo_migrate(bo, XE_PL_TT);
- if (r == -EBUSY || r == -ERESTARTSYS || r == -EINTR)
- ret = VM_FAULT_NOPAGE;
- else if (r)
- ret = VM_FAULT_SIGBUS;
- }
- if (!ret)
- ret = ttm_bo_vm_fault_reserved(vmf,
- vmf->vma->vm_page_prot,
- TTM_BO_VM_NUM_PREFAULT);
+ ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
+ TTM_BO_VM_NUM_PREFAULT);
drm_dev_exit(idx);
} else {
ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot);
@@ -1291,9 +1253,6 @@
bo->flags = flags;
bo->cpu_caching = cpu_caching;
bo->ttm.base.funcs = &xe_gem_object_funcs;
- bo->props.preferred_mem_class = XE_BO_PROPS_INVALID;
- bo->props.preferred_gt = XE_BO_PROPS_INVALID;
- bo->props.preferred_mem_type = XE_BO_PROPS_INVALID;
bo->ttm.priority = XE_BO_PRIORITY_NORMAL;
INIT_LIST_HEAD(&bo->pinned_link);
#ifdef CONFIG_PROC_FS
diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
index 14ef13b..86422e1 100644
--- a/drivers/gpu/drm/xe/xe_bo_types.h
+++ b/drivers/gpu/drm/xe/xe_bo_types.h
@@ -56,25 +56,6 @@
*/
struct list_head client_link;
#endif
- /** @props: BO user controlled properties */
- struct {
- /** @preferred_mem: preferred memory class for this BO */
- s16 preferred_mem_class;
- /** @prefered_gt: preferred GT for this BO */
- s16 preferred_gt;
- /** @preferred_mem_type: preferred memory type */
- s32 preferred_mem_type;
- /**
- * @cpu_atomic: the CPU expects to do atomics operations to
- * this BO
- */
- bool cpu_atomic;
- /**
- * @device_atomic: the device expects to do atomics operations
- * to this BO
- */
- bool device_atomic;
- } props;
/** @freed: List node for delayed put. */
struct llist_node freed;
/** @created: Whether the bo has passed initial creation */
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index 14be34d..d413bc2 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -58,7 +58,7 @@
static inline struct xe_gt *xe_tile_get_gt(struct xe_tile *tile, u8 gt_id)
{
- if (drm_WARN_ON(&tile_to_xe(tile)->drm, gt_id > XE_MAX_GT_PER_TILE))
+ if (drm_WARN_ON(&tile_to_xe(tile)->drm, gt_id >= XE_MAX_GT_PER_TILE))
gt_id = 0;
return gt_id ? tile->media_gt : tile->primary_gt;
@@ -79,7 +79,7 @@
if (MEDIA_VER(xe) >= 13) {
gt = xe_tile_get_gt(root_tile, gt_id);
} else {
- if (drm_WARN_ON(&xe->drm, gt_id > XE_MAX_TILES_PER_DEVICE))
+ if (drm_WARN_ON(&xe->drm, gt_id >= XE_MAX_TILES_PER_DEVICE))
gt_id = 0;
gt = xe->tiles[gt_id].primary_gt;
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 11e150f..ead25d5 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -448,7 +448,7 @@
{
u32 idx;
- if (eci.engine_class > ARRAY_SIZE(user_to_xe_engine_class))
+ if (eci.engine_class >= ARRAY_SIZE(user_to_xe_engine_class))
return NULL;
if (eci.gt_id >= xe->info.gt_count)
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index ff77bc8..e2a4c3b 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1220,7 +1220,7 @@
init_waitqueue_head(&ge->suspend_wait);
timeout = (q->vm && xe_vm_in_lr_mode(q->vm)) ? MAX_SCHEDULE_TIMEOUT :
- q->sched_props.job_timeout_ms;
+ msecs_to_jiffies(q->sched_props.job_timeout_ms);
err = xe_sched_init(&ge->sched, &drm_sched_ops, &xe_sched_ops,
get_submit_wq(guc),
q->lrc[0].ring.size / MAX_JOB_SIZE_BYTES, 64,
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 7ad853b..1426feb 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -97,7 +97,6 @@
#define REG16(x) \
(((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \
(((x) >> 2) & 0x7f)
-#define END 0
{
const u32 base = hwe->mmio_base;
@@ -168,7 +167,7 @@
REG16(0x274),
REG16(0x270),
- END
+ 0
};
static const u8 dg2_xcs_offsets[] = {
@@ -202,7 +201,7 @@
REG16(0x274),
REG16(0x270),
- END
+ 0
};
static const u8 gen12_rcs_offsets[] = {
@@ -298,7 +297,7 @@
REG(0x084),
NOP(1),
- END
+ 0
};
static const u8 xehp_rcs_offsets[] = {
@@ -339,7 +338,7 @@
LRI(1, 0),
REG(0x0c8),
- END
+ 0
};
static const u8 dg2_rcs_offsets[] = {
@@ -382,7 +381,7 @@
LRI(1, 0),
REG(0x0c8),
- END
+ 0
};
static const u8 mtl_rcs_offsets[] = {
@@ -425,7 +424,7 @@
LRI(1, 0),
REG(0x0c8),
- END
+ 0
};
#define XE2_CTX_COMMON \
@@ -471,7 +470,7 @@
LRI(1, 0), /* [0x47] */
REG(0x0c8), /* [0x48] R_PWR_CLK_STATE */
- END
+ 0
};
static const u8 xe2_bcs_offsets[] = {
@@ -482,16 +481,15 @@
REG16(0x200), /* [0x42] BCS_SWCTRL */
REG16(0x204), /* [0x44] BLIT_CCTL */
- END
+ 0
};
static const u8 xe2_xcs_offsets[] = {
XE2_CTX_COMMON,
- END
+ 0
};
-#undef END
#undef REG16
#undef REG
#undef LRI
diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 92bb06c..075f9ea 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -132,7 +132,7 @@
return -EINVAL;
eci = &resp.eci;
- if (eci->gt_id > XE_MAX_GT_PER_TILE)
+ if (eci->gt_id >= XE_MAX_GT_PER_TILE)
return -EINVAL;
gt = xe_device_get_gt(xe, eci->gt_id);
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index a686166..79870dd 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -536,11 +536,12 @@
if (read_write == I2C_SMBUS_READ ||
command == I2C_SMBUS_BLOCK_PROC_CALL) {
- status = i801_get_block_len(priv);
- if (status < 0)
+ len = i801_get_block_len(priv);
+ if (len < 0) {
+ status = len;
goto out;
+ }
- len = status;
data->block[0] = len;
inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */
for (i = 0; i < len; i++)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 5ed0362..41f93c3 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1139,7 +1139,8 @@
* requires a breaking update, zero the V bit, write all qwords
* but 0, then set qword 0
*/
- unused_update.data[0] = entry->data[0] & (~STRTAB_STE_0_V);
+ unused_update.data[0] = entry->data[0] &
+ cpu_to_le64(~STRTAB_STE_0_V);
entry_set(smmu, sid, entry, &unused_update, 0, 1);
entry_set(smmu, sid, entry, target, 1, num_entry_qwords - 1);
entry_set(smmu, sid, entry, target, 0, 1);
@@ -1453,14 +1454,17 @@
FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_ABORT));
}
-static void arm_smmu_make_bypass_ste(struct arm_smmu_ste *target)
+static void arm_smmu_make_bypass_ste(struct arm_smmu_device *smmu,
+ struct arm_smmu_ste *target)
{
memset(target, 0, sizeof(*target));
target->data[0] = cpu_to_le64(
STRTAB_STE_0_V |
FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS));
- target->data[1] = cpu_to_le64(
- FIELD_PREP(STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING));
+
+ if (smmu->features & ARM_SMMU_FEAT_ATTR_TYPES_OVR)
+ target->data[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
+ STRTAB_STE_1_SHCFG_INCOMING));
}
static void arm_smmu_make_cdtable_ste(struct arm_smmu_ste *target,
@@ -1523,6 +1527,7 @@
typeof(&pgtbl_cfg->arm_lpae_s2_cfg.vtcr) vtcr =
&pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
u64 vtcr_val;
+ struct arm_smmu_device *smmu = master->smmu;
memset(target, 0, sizeof(*target));
target->data[0] = cpu_to_le64(
@@ -1531,9 +1536,11 @@
target->data[1] = cpu_to_le64(
FIELD_PREP(STRTAB_STE_1_EATS,
- master->ats_enabled ? STRTAB_STE_1_EATS_TRANS : 0) |
- FIELD_PREP(STRTAB_STE_1_SHCFG,
- STRTAB_STE_1_SHCFG_INCOMING));
+ master->ats_enabled ? STRTAB_STE_1_EATS_TRANS : 0));
+
+ if (smmu->features & ARM_SMMU_FEAT_ATTR_TYPES_OVR)
+ target->data[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
+ STRTAB_STE_1_SHCFG_INCOMING));
vtcr_val = FIELD_PREP(STRTAB_STE_2_VTCR_S2T0SZ, vtcr->tsz) |
FIELD_PREP(STRTAB_STE_2_VTCR_S2SL0, vtcr->sl) |
@@ -1560,7 +1567,8 @@
* This can safely directly manipulate the STE memory without a sync sequence
* because the STE table has not been installed in the SMMU yet.
*/
-static void arm_smmu_init_initial_stes(struct arm_smmu_ste *strtab,
+static void arm_smmu_init_initial_stes(struct arm_smmu_device *smmu,
+ struct arm_smmu_ste *strtab,
unsigned int nent)
{
unsigned int i;
@@ -1569,7 +1577,7 @@
if (disable_bypass)
arm_smmu_make_abort_ste(strtab);
else
- arm_smmu_make_bypass_ste(strtab);
+ arm_smmu_make_bypass_ste(smmu, strtab);
strtab++;
}
}
@@ -1597,7 +1605,7 @@
return -ENOMEM;
}
- arm_smmu_init_initial_stes(desc->l2ptr, 1 << STRTAB_SPLIT);
+ arm_smmu_init_initial_stes(smmu, desc->l2ptr, 1 << STRTAB_SPLIT);
arm_smmu_write_strtab_l1_desc(strtab, desc);
return 0;
}
@@ -2637,8 +2645,9 @@
struct device *dev)
{
struct arm_smmu_ste ste;
+ struct arm_smmu_master *master = dev_iommu_priv_get(dev);
- arm_smmu_make_bypass_ste(&ste);
+ arm_smmu_make_bypass_ste(master->smmu, &ste);
return arm_smmu_attach_dev_ste(dev, &ste);
}
@@ -3264,7 +3273,7 @@
reg |= FIELD_PREP(STRTAB_BASE_CFG_LOG2SIZE, smmu->sid_bits);
cfg->strtab_base_cfg = reg;
- arm_smmu_init_initial_stes(strtab, cfg->num_l1_ents);
+ arm_smmu_init_initial_stes(smmu, strtab, cfg->num_l1_ents);
return 0;
}
@@ -3777,6 +3786,9 @@
return -ENXIO;
}
+ if (reg & IDR1_ATTR_TYPES_OVR)
+ smmu->features |= ARM_SMMU_FEAT_ATTR_TYPES_OVR;
+
/* Queue sizes, capped to ensure natural alignment */
smmu->cmdq.q.llq.max_n_shift = min_t(u32, CMDQ_MAX_SZ_SHIFT,
FIELD_GET(IDR1_CMDQS, reg));
@@ -3992,7 +4004,7 @@
* STE table is not programmed to HW, see
* arm_smmu_initial_bypass_stes()
*/
- arm_smmu_make_bypass_ste(
+ arm_smmu_make_bypass_ste(smmu,
arm_smmu_get_step_for_sid(smmu, rmr->sids[i]));
}
}
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 23baf11..2a19bb6 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -44,6 +44,7 @@
#define IDR1_TABLES_PRESET (1 << 30)
#define IDR1_QUEUES_PRESET (1 << 29)
#define IDR1_REL (1 << 28)
+#define IDR1_ATTR_TYPES_OVR (1 << 27)
#define IDR1_CMDQS GENMASK(25, 21)
#define IDR1_EVTQS GENMASK(20, 16)
#define IDR1_PRIQS GENMASK(15, 11)
@@ -647,6 +648,7 @@
#define ARM_SMMU_FEAT_SVA (1 << 17)
#define ARM_SMMU_FEAT_E2H (1 << 18)
#define ARM_SMMU_FEAT_NESTING (1 << 19)
+#define ARM_SMMU_FEAT_ATTR_TYPES_OVR (1 << 20)
u32 features;
#define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0)
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 0988690..a95a483d 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -3354,6 +3354,7 @@
{
/* Caller must be a probed driver on dev */
struct iommu_group *group = dev->iommu_group;
+ struct group_device *device;
void *curr;
int ret;
@@ -3363,10 +3364,18 @@
if (!group)
return -ENODEV;
- if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner)
+ if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner ||
+ pasid == IOMMU_NO_PASID)
return -EINVAL;
mutex_lock(&group->mutex);
+ for_each_group_device(group, device) {
+ if (pasid >= device->dev->iommu->max_pasids) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+ }
+
curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL);
if (curr) {
ret = xa_err(curr) ? : -EBUSY;
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index a555284..4b021a6 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -316,7 +316,7 @@
return 0;
}
#else
-static void armada_370_xp_msi_reenable_percpu(void) {}
+static __maybe_unused void armada_370_xp_msi_reenable_percpu(void) {}
static inline int armada_370_xp_msi_init(struct device_node *node,
phys_addr_t main_int_phys_base)
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 37b9f8f..7f3dc8e 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -4221,7 +4221,7 @@
} else if (sscanf(opt_string, "sectors_per_bit:%llu%c", &llval, &dummy) == 1) {
log2_sectors_per_bitmap_bit = !llval ? 0 : __ilog2_u64(llval);
} else if (sscanf(opt_string, "bitmap_flush_interval:%u%c", &val, &dummy) == 1) {
- if (val >= (uint64_t)UINT_MAX * 1000 / HZ) {
+ if ((uint64_t)val >= (uint64_t)UINT_MAX * 1000 / HZ) {
r = -EINVAL;
ti->error = "Invalid bitmap_flush_interval argument";
goto bad;
diff --git a/drivers/md/dm-vdo/murmurhash3.c b/drivers/md/dm-vdo/murmurhash3.c
index 00c9b9c..01d2743 100644
--- a/drivers/md/dm-vdo/murmurhash3.c
+++ b/drivers/md/dm-vdo/murmurhash3.c
@@ -8,33 +8,14 @@
#include "murmurhash3.h"
+#include <asm/unaligned.h>
+
static inline u64 rotl64(u64 x, s8 r)
{
return (x << r) | (x >> (64 - r));
}
#define ROTL64(x, y) rotl64(x, y)
-static __always_inline u64 getblock64(const u64 *p, int i)
-{
-#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
- return p[i];
-#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
- return __builtin_bswap64(p[i]);
-#else
-#error "can't figure out byte order"
-#endif
-}
-
-static __always_inline void putblock64(u64 *p, int i, u64 value)
-{
-#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
- p[i] = value;
-#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
- p[i] = __builtin_bswap64(value);
-#else
-#error "can't figure out byte order"
-#endif
-}
/* Finalization mix - force all bits of a hash block to avalanche */
@@ -60,6 +41,8 @@
const u64 c1 = 0x87c37b91114253d5LLU;
const u64 c2 = 0x4cf5ad432745937fLLU;
+ u64 *hash_out = out;
+
/* body */
const u64 *blocks = (const u64 *)(data);
@@ -67,8 +50,8 @@
int i;
for (i = 0; i < nblocks; i++) {
- u64 k1 = getblock64(blocks, i * 2 + 0);
- u64 k2 = getblock64(blocks, i * 2 + 1);
+ u64 k1 = get_unaligned_le64(&blocks[i * 2]);
+ u64 k2 = get_unaligned_le64(&blocks[i * 2 + 1]);
k1 *= c1;
k1 = ROTL64(k1, 31);
@@ -170,6 +153,6 @@
h1 += h2;
h2 += h1;
- putblock64((u64 *)out, 0, h1);
- putblock64((u64 *)out, 1, h2);
+ put_unaligned_le64(h1, &hash_out[0]);
+ put_unaligned_le64(h2, &hash_out[1]);
}
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 64a3492..90c51b1 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -413,7 +413,7 @@
struct mmc_blk_ioc_data *idata;
int err;
- idata = kmalloc(sizeof(*idata), GFP_KERNEL);
+ idata = kzalloc(sizeof(*idata), GFP_KERNEL);
if (!idata) {
err = -ENOMEM;
goto out;
@@ -488,7 +488,7 @@
if (idata->flags & MMC_BLK_IOC_DROP)
return 0;
- if (idata->flags & MMC_BLK_IOC_SBC)
+ if (idata->flags & MMC_BLK_IOC_SBC && i > 0)
prev_idata = idatas[i - 1];
/*
diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c
index ab4b964..1d8f5a7 100644
--- a/drivers/mmc/host/sdhci-of-dwcmshc.c
+++ b/drivers/mmc/host/sdhci-of-dwcmshc.c
@@ -999,6 +999,17 @@
return err;
}
+static void dwcmshc_disable_card_clk(struct sdhci_host *host)
+{
+ u16 ctrl;
+
+ ctrl = sdhci_readw(host, SDHCI_CLOCK_CONTROL);
+ if (ctrl & SDHCI_CLOCK_CARD_EN) {
+ ctrl &= ~SDHCI_CLOCK_CARD_EN;
+ sdhci_writew(host, ctrl, SDHCI_CLOCK_CONTROL);
+ }
+}
+
static void dwcmshc_remove(struct platform_device *pdev)
{
struct sdhci_host *host = platform_get_drvdata(pdev);
@@ -1006,8 +1017,14 @@
struct dwcmshc_priv *priv = sdhci_pltfm_priv(pltfm_host);
struct rk35xx_priv *rk_priv = priv->priv;
+ pm_runtime_get_sync(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
+ pm_runtime_put_noidle(&pdev->dev);
+
sdhci_remove_host(host, 0);
+ dwcmshc_disable_card_clk(host);
+
clk_disable_unprepare(pltfm_host->clk);
clk_disable_unprepare(priv->bus_clk);
if (rk_priv)
@@ -1099,17 +1116,6 @@
}
}
-static void dwcmshc_disable_card_clk(struct sdhci_host *host)
-{
- u16 ctrl;
-
- ctrl = sdhci_readw(host, SDHCI_CLOCK_CONTROL);
- if (ctrl & SDHCI_CLOCK_CARD_EN) {
- ctrl &= ~SDHCI_CLOCK_CARD_EN;
- sdhci_writew(host, ctrl, SDHCI_CLOCK_CONTROL);
- }
-}
-
static int dwcmshc_runtime_suspend(struct device *dev)
{
struct sdhci_host *host = dev_get_drvdata(dev);
diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c
index e78faef..94076b0 100644
--- a/drivers/mmc/host/sdhci-omap.c
+++ b/drivers/mmc/host/sdhci-omap.c
@@ -1439,6 +1439,9 @@
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
struct sdhci_omap_host *omap_host = sdhci_pltfm_priv(pltfm_host);
+ if (host->tuning_mode != SDHCI_TUNING_MODE_3)
+ mmc_retune_needed(host->mmc);
+
if (omap_host->con != -EINVAL)
sdhci_runtime_suspend_host(host);
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 475e1e8..0786eb0 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -50,7 +50,7 @@
* the macros available to do this only define GCC 8.
*/
__diag_push();
-__diag_ignore(GCC, 8, "-Woverride-init",
+__diag_ignore_all("-Woverride-init",
"logic to initialize all and then override some is OK");
static const u16 sh_eth_offset_gigabit[SH_ETH_MAX_REGISTER_OFFSET] = {
SH_ETH_OFFSET_DEFAULTS,
diff --git a/drivers/pinctrl/aspeed/Makefile b/drivers/pinctrl/aspeed/Makefile
index 489ea17..db2a760 100644
--- a/drivers/pinctrl/aspeed/Makefile
+++ b/drivers/pinctrl/aspeed/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0-only
# Aspeed pinctrl support
-ccflags-y += $(call cc-option,-Woverride-init)
+ccflags-y += -Woverride-init
obj-$(CONFIG_PINCTRL_ASPEED) += pinctrl-aspeed.o pinmux-aspeed.o
obj-$(CONFIG_PINCTRL_ASPEED_G4) += pinctrl-aspeed-g4.o
obj-$(CONFIG_PINCTRL_ASPEED_G5) += pinctrl-aspeed-g5.o
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 49f89b7..7f66ec7 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -1159,7 +1159,7 @@
}
ret = devm_request_irq(&pdev->dev, gpio_dev->irq, amd_gpio_irq_handler,
- IRQF_SHARED | IRQF_ONESHOT, KBUILD_MODNAME, gpio_dev);
+ IRQF_SHARED | IRQF_COND_ONESHOT, KBUILD_MODNAME, gpio_dev);
if (ret)
goto out2;
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index d70f793..403525c 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -443,7 +443,7 @@
if (IS_ERR(pwm))
return pwm;
- if (args->args_count > 1)
+ if (args->args_count > 0)
pwm->args.period = args->args[0];
pwm->args.polarity = PWM_POLARITY_NORMAL;
diff --git a/drivers/ras/amd/fmpm.c b/drivers/ras/amd/fmpm.c
index 2f4ac95..271dfad 100644
--- a/drivers/ras/amd/fmpm.c
+++ b/drivers/ras/amd/fmpm.c
@@ -150,6 +150,8 @@
/* Total length of record including headers and list of descriptor entries. */
static size_t max_rec_len;
+#define FMPM_MAX_REC_LEN (sizeof(struct fru_rec) + (sizeof(struct cper_fru_poison_desc) * 255))
+
/* Total number of SPA entries across all FRUs. */
static unsigned int spa_nr_entries;
@@ -475,6 +477,16 @@
struct cper_section_descriptor *sec_desc = &rec->sec_desc;
struct cper_record_header *hdr = &rec->hdr;
+ /*
+ * This is a saved record created with fewer max_nr_entries.
+ * Update the record lengths and keep everything else as-is.
+ */
+ if (hdr->record_length && hdr->record_length < max_rec_len) {
+ pr_debug("Growing record 0x%016llx from %u to %zu bytes\n",
+ hdr->record_id, hdr->record_length, max_rec_len);
+ goto update_lengths;
+ }
+
memcpy(hdr->signature, CPER_SIG_RECORD, CPER_SIG_SIZE);
hdr->revision = CPER_RECORD_REV;
hdr->signature_end = CPER_SIG_END;
@@ -489,19 +501,21 @@
hdr->error_severity = CPER_SEV_RECOVERABLE;
hdr->validation_bits = 0;
- hdr->record_length = max_rec_len;
hdr->creator_id = CPER_CREATOR_FMP;
hdr->notification_type = CPER_NOTIFY_MCE;
hdr->record_id = cper_next_record_id();
hdr->flags = CPER_HW_ERROR_FLAGS_PREVERR;
sec_desc->section_offset = sizeof(struct cper_record_header);
- sec_desc->section_length = max_rec_len - sizeof(struct cper_record_header);
sec_desc->revision = CPER_SEC_REV;
sec_desc->validation_bits = 0;
sec_desc->flags = CPER_SEC_PRIMARY;
sec_desc->section_type = CPER_SECTION_TYPE_FMP;
sec_desc->section_severity = CPER_SEV_RECOVERABLE;
+
+update_lengths:
+ hdr->record_length = max_rec_len;
+ sec_desc->section_length = max_rec_len - sizeof(struct cper_record_header);
}
static int save_new_records(void)
@@ -512,16 +526,18 @@
int ret = 0;
for_each_fru(i, rec) {
- if (rec->hdr.record_length)
+ /* No need to update saved records that match the current record size. */
+ if (rec->hdr.record_length == max_rec_len)
continue;
+ if (!rec->hdr.record_length)
+ set_bit(i, new_records);
+
set_rec_fields(rec);
ret = update_record_on_storage(rec);
if (ret)
goto out_clear;
-
- set_bit(i, new_records);
}
return ret;
@@ -641,12 +657,7 @@
int ret, pos;
ssize_t len;
- /*
- * Assume saved records match current max size.
- *
- * However, this may not be true depending on module parameters.
- */
- old = kmalloc(max_rec_len, GFP_KERNEL);
+ old = kmalloc(FMPM_MAX_REC_LEN, GFP_KERNEL);
if (!old) {
ret = -ENOMEM;
goto out;
@@ -663,21 +674,31 @@
* Make sure to clear temporary buffer between reads to avoid
* leftover data from records of various sizes.
*/
- memset(old, 0, max_rec_len);
+ memset(old, 0, FMPM_MAX_REC_LEN);
- len = erst_read_record(record_id, &old->hdr, max_rec_len,
+ len = erst_read_record(record_id, &old->hdr, FMPM_MAX_REC_LEN,
sizeof(struct fru_rec), &CPER_CREATOR_FMP);
if (len < 0)
continue;
- if (len > max_rec_len) {
- pr_debug("Found record larger than max_rec_len\n");
+ new = get_valid_record(old);
+ if (!new) {
+ erst_clear(record_id);
continue;
}
- new = get_valid_record(old);
- if (!new)
- erst_clear(record_id);
+ if (len > max_rec_len) {
+ unsigned int saved_nr_entries;
+
+ saved_nr_entries = len - sizeof(struct fru_rec);
+ saved_nr_entries /= sizeof(struct cper_fru_poison_desc);
+
+ pr_warn("Saved record found with %u entries.\n", saved_nr_entries);
+ pr_warn("Please increase max_nr_entries to %u.\n", saved_nr_entries);
+
+ ret = -EINVAL;
+ goto out_end;
+ }
/* Restore the record */
memcpy(new, old, len);
diff --git a/drivers/ras/debugfs.h b/drivers/ras/debugfs.h
index 4749ccd..5a2f484 100644
--- a/drivers/ras/debugfs.h
+++ b/drivers/ras/debugfs.h
@@ -4,6 +4,10 @@
#include <linux/debugfs.h>
+#if IS_ENABLED(CONFIG_DEBUG_FS)
struct dentry *ras_get_debugfs_root(void);
+#else
+static inline struct dentry *ras_get_debugfs_root(void) { return NULL; }
+#endif /* DEBUG_FS */
#endif /* __RAS_DEBUGFS_H__ */
diff --git a/drivers/scsi/bnx2fc/bnx2fc_tgt.c b/drivers/scsi/bnx2fc/bnx2fc_tgt.c
index 2c246e8..d916598 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_tgt.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_tgt.c
@@ -833,7 +833,6 @@
BNX2FC_TGT_DBG(tgt, "Freeing up session resources\n");
- spin_lock_bh(&tgt->cq_lock);
ctx_base_ptr = tgt->ctx_base;
tgt->ctx_base = NULL;
@@ -889,7 +888,6 @@
tgt->sq, tgt->sq_dma);
tgt->sq = NULL;
}
- spin_unlock_bh(&tgt->cq_lock);
if (ctx_base_ptr)
iounmap(ctx_base_ptr);
diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index 1befcd5..fa07a6f 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -102,7 +102,9 @@
#define MAX_RETRIES 1
-static struct class * ch_sysfs_class;
+static const struct class ch_sysfs_class = {
+ .name = "scsi_changer",
+};
typedef struct {
struct kref ref;
@@ -930,7 +932,7 @@
mutex_init(&ch->lock);
kref_init(&ch->ref);
ch->device = sd;
- class_dev = device_create(ch_sysfs_class, dev,
+ class_dev = device_create(&ch_sysfs_class, dev,
MKDEV(SCSI_CHANGER_MAJOR, ch->minor), ch,
"s%s", ch->name);
if (IS_ERR(class_dev)) {
@@ -955,7 +957,7 @@
return 0;
destroy_dev:
- device_destroy(ch_sysfs_class, MKDEV(SCSI_CHANGER_MAJOR, ch->minor));
+ device_destroy(&ch_sysfs_class, MKDEV(SCSI_CHANGER_MAJOR, ch->minor));
put_device:
scsi_device_put(sd);
remove_idr:
@@ -974,7 +976,7 @@
dev_set_drvdata(dev, NULL);
spin_unlock(&ch_index_lock);
- device_destroy(ch_sysfs_class, MKDEV(SCSI_CHANGER_MAJOR,ch->minor));
+ device_destroy(&ch_sysfs_class, MKDEV(SCSI_CHANGER_MAJOR, ch->minor));
scsi_device_put(ch->device);
kref_put(&ch->ref, ch_destroy);
return 0;
@@ -1003,11 +1005,9 @@
int rc;
printk(KERN_INFO "SCSI Media Changer driver v" VERSION " \n");
- ch_sysfs_class = class_create("scsi_changer");
- if (IS_ERR(ch_sysfs_class)) {
- rc = PTR_ERR(ch_sysfs_class);
+ rc = class_register(&ch_sysfs_class);
+ if (rc)
return rc;
- }
rc = register_chrdev(SCSI_CHANGER_MAJOR,"ch",&changer_fops);
if (rc < 0) {
printk("Unable to get major %d for SCSI-Changer\n",
@@ -1022,7 +1022,7 @@
fail2:
unregister_chrdev(SCSI_CHANGER_MAJOR, "ch");
fail1:
- class_destroy(ch_sysfs_class);
+ class_unregister(&ch_sysfs_class);
return rc;
}
@@ -1030,7 +1030,7 @@
{
scsi_unregister_driver(&ch_template.gendrv);
unregister_chrdev(SCSI_CHANGER_MAJOR, "ch");
- class_destroy(ch_sysfs_class);
+ class_unregister(&ch_sysfs_class);
idr_destroy(&ch_index_idr);
}
diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index debd369..e8382cc 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -28,7 +28,12 @@
MODULE_AUTHOR("Matthew R. Ochs <mrochs@linux.vnet.ibm.com>");
MODULE_LICENSE("GPL");
-static struct class *cxlflash_class;
+static char *cxlflash_devnode(const struct device *dev, umode_t *mode);
+static const struct class cxlflash_class = {
+ .name = "cxlflash",
+ .devnode = cxlflash_devnode,
+};
+
static u32 cxlflash_major;
static DECLARE_BITMAP(cxlflash_minor, CXLFLASH_MAX_ADAPTERS);
@@ -3602,7 +3607,7 @@
goto err1;
}
- char_dev = device_create(cxlflash_class, NULL, devno,
+ char_dev = device_create(&cxlflash_class, NULL, devno,
NULL, "cxlflash%d", minor);
if (IS_ERR(char_dev)) {
rc = PTR_ERR(char_dev);
@@ -3880,14 +3885,12 @@
cxlflash_major = MAJOR(devno);
- cxlflash_class = class_create("cxlflash");
- if (IS_ERR(cxlflash_class)) {
- rc = PTR_ERR(cxlflash_class);
+ rc = class_register(&cxlflash_class);
+ if (rc) {
pr_err("%s: class_create failed rc=%d\n", __func__, rc);
goto err;
}
- cxlflash_class->devnode = cxlflash_devnode;
out:
pr_debug("%s: returning rc=%d\n", __func__, rc);
return rc;
@@ -3903,7 +3906,7 @@
{
dev_t devno = MKDEV(cxlflash_major, 0);
- class_destroy(cxlflash_class);
+ class_unregister(&cxlflash_class);
unregister_chrdev_region(devno, CXLFLASH_MAX_ADAPTERS);
}
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 4f495a4..2d92549 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -353,12 +353,13 @@
if (shost->shost_state == SHOST_CREATED) {
/*
- * Free the shost_dev device name here if scsi_host_alloc()
- * and scsi_host_put() have been called but neither
+ * Free the shost_dev device name and remove the proc host dir
+ * here if scsi_host_{alloc,put}() have been called but neither
* scsi_host_add() nor scsi_remove_host() has been called.
* This avoids that the memory allocated for the shost_dev
- * name is leaked.
+ * name as well as the proc dir structure are leaked.
*/
+ scsi_proc_hostdir_rm(shost->hostt);
kfree(dev_name(&shost->shost_dev));
}
diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index a220467..5c26100 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -1621,6 +1621,16 @@
/* ---------- Domain revalidation ---------- */
+static void sas_get_sas_addr_and_dev_type(struct smp_disc_resp *disc_resp,
+ u8 *sas_addr,
+ enum sas_device_type *type)
+{
+ memcpy(sas_addr, disc_resp->disc.attached_sas_addr, SAS_ADDR_SIZE);
+ *type = to_dev_type(&disc_resp->disc);
+ if (*type == SAS_PHY_UNUSED)
+ memset(sas_addr, 0, SAS_ADDR_SIZE);
+}
+
static int sas_get_phy_discover(struct domain_device *dev,
int phy_id, struct smp_disc_resp *disc_resp)
{
@@ -1674,13 +1684,8 @@
return -ENOMEM;
res = sas_get_phy_discover(dev, phy_id, disc_resp);
- if (res == 0) {
- memcpy(sas_addr, disc_resp->disc.attached_sas_addr,
- SAS_ADDR_SIZE);
- *type = to_dev_type(&disc_resp->disc);
- if (*type == 0)
- memset(sas_addr, 0, SAS_ADDR_SIZE);
- }
+ if (res == 0)
+ sas_get_sas_addr_and_dev_type(disc_resp, sas_addr, type);
kfree(disc_resp);
return res;
}
@@ -1940,6 +1945,7 @@
struct expander_device *ex = &dev->ex_dev;
struct ex_phy *phy = &ex->ex_phy[phy_id];
enum sas_device_type type = SAS_PHY_UNUSED;
+ struct smp_disc_resp *disc_resp;
u8 sas_addr[SAS_ADDR_SIZE];
char msg[80] = "";
int res;
@@ -1951,33 +1957,41 @@
SAS_ADDR(dev->sas_addr), phy_id, msg);
memset(sas_addr, 0, SAS_ADDR_SIZE);
- res = sas_get_phy_attached_dev(dev, phy_id, sas_addr, &type);
+ disc_resp = alloc_smp_resp(DISCOVER_RESP_SIZE);
+ if (!disc_resp)
+ return -ENOMEM;
+
+ res = sas_get_phy_discover(dev, phy_id, disc_resp);
switch (res) {
case SMP_RESP_NO_PHY:
phy->phy_state = PHY_NOT_PRESENT;
sas_unregister_devs_sas_addr(dev, phy_id, last);
- return res;
+ goto out_free_resp;
case SMP_RESP_PHY_VACANT:
phy->phy_state = PHY_VACANT;
sas_unregister_devs_sas_addr(dev, phy_id, last);
- return res;
+ goto out_free_resp;
case SMP_RESP_FUNC_ACC:
break;
case -ECOMM:
break;
default:
- return res;
+ goto out_free_resp;
}
+ if (res == 0)
+ sas_get_sas_addr_and_dev_type(disc_resp, sas_addr, &type);
+
if ((SAS_ADDR(sas_addr) == 0) || (res == -ECOMM)) {
phy->phy_state = PHY_EMPTY;
sas_unregister_devs_sas_addr(dev, phy_id, last);
/*
- * Even though the PHY is empty, for convenience we discover
- * the PHY to update the PHY info, like negotiated linkrate.
+ * Even though the PHY is empty, for convenience we update
+ * the PHY info, like negotiated linkrate.
*/
- sas_ex_phy_discover(dev, phy_id);
- return res;
+ if (res == 0)
+ sas_set_ex_phy(dev, phy_id, disc_resp);
+ goto out_free_resp;
} else if (SAS_ADDR(sas_addr) == SAS_ADDR(phy->attached_sas_addr) &&
dev_type_flutter(type, phy->attached_dev_type)) {
struct domain_device *ata_dev = sas_ex_to_ata(dev, phy_id);
@@ -1989,7 +2003,7 @@
action = ", needs recovery";
pr_debug("ex %016llx phy%02d broadcast flutter%s\n",
SAS_ADDR(dev->sas_addr), phy_id, action);
- return res;
+ goto out_free_resp;
}
/* we always have to delete the old device when we went here */
@@ -1998,7 +2012,10 @@
SAS_ADDR(phy->attached_sas_addr));
sas_unregister_devs_sas_addr(dev, phy_id, last);
- return sas_discover_new(dev, phy_id);
+ res = sas_discover_new(dev, phy_id);
+out_free_resp:
+ kfree(disc_resp);
+ return res;
}
/**
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 30d20d3..98ca7df 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -1333,7 +1333,6 @@
struct timer_list fabric_block_timer;
unsigned long bit_flags;
atomic_t num_rsrc_err;
- atomic_t num_cmd_success;
unsigned long last_rsrc_error_time;
unsigned long last_ramp_down_time;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
@@ -1438,6 +1437,7 @@
struct timer_list inactive_vmid_poll;
/* RAS Support */
+ spinlock_t ras_fwlog_lock; /* do not take while holding another lock */
struct lpfc_ras_fwlog ras_fwlog;
uint32_t iocb_cnt;
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 365c7e9..3c534b3 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -5865,9 +5865,9 @@
if (phba->cfg_ras_fwlog_func != PCI_FUNC(phba->pcidev->devfn))
return -EINVAL;
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irq(&phba->ras_fwlog_lock);
state = phba->ras_fwlog.state;
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
if (state == REG_INPROGRESS) {
lpfc_printf_log(phba, KERN_ERR, LOG_SLI, "6147 RAS Logging "
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index d80e6e8..529df17 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -2513,7 +2513,7 @@
return -ENOMEM;
}
- dmabuff = (struct lpfc_dmabuf *)mbox->ctx_buf;
+ dmabuff = mbox->ctx_buf;
mbox->ctx_buf = NULL;
mbox->ctx_ndlp = NULL;
status = lpfc_sli_issue_mbox_wait(phba, mbox, LPFC_MBOX_TMO);
@@ -3169,10 +3169,10 @@
}
cmdwqe = &cmdiocbq->wqe;
- memset(cmdwqe, 0, sizeof(union lpfc_wqe));
+ memset(cmdwqe, 0, sizeof(*cmdwqe));
if (phba->sli_rev < LPFC_SLI_REV4) {
rspwqe = &rspiocbq->wqe;
- memset(rspwqe, 0, sizeof(union lpfc_wqe));
+ memset(rspwqe, 0, sizeof(*rspwqe));
}
INIT_LIST_HEAD(&head);
@@ -3376,7 +3376,7 @@
unsigned long flags;
uint8_t *pmb, *pmb_buf;
- dd_data = pmboxq->ctx_ndlp;
+ dd_data = pmboxq->ctx_u.dd_data;
/*
* The outgoing buffer is readily referred from the dma buffer,
@@ -3553,7 +3553,7 @@
struct lpfc_sli_config_mbox *sli_cfg_mbx;
uint8_t *pmbx;
- dd_data = pmboxq->ctx_buf;
+ dd_data = pmboxq->ctx_u.dd_data;
/* Determine if job has been aborted */
spin_lock_irqsave(&phba->ct_ev_lock, flags);
@@ -3940,7 +3940,7 @@
pmboxq->mbox_cmpl = lpfc_bsg_issue_read_mbox_ext_cmpl;
/* context fields to callback function */
- pmboxq->ctx_buf = dd_data;
+ pmboxq->ctx_u.dd_data = dd_data;
dd_data->type = TYPE_MBOX;
dd_data->set_job = job;
dd_data->context_un.mbox.pmboxq = pmboxq;
@@ -4112,7 +4112,7 @@
pmboxq->mbox_cmpl = lpfc_bsg_issue_write_mbox_ext_cmpl;
/* context fields to callback function */
- pmboxq->ctx_buf = dd_data;
+ pmboxq->ctx_u.dd_data = dd_data;
dd_data->type = TYPE_MBOX;
dd_data->set_job = job;
dd_data->context_un.mbox.pmboxq = pmboxq;
@@ -4460,7 +4460,7 @@
pmboxq->mbox_cmpl = lpfc_bsg_issue_write_mbox_ext_cmpl;
/* context fields to callback function */
- pmboxq->ctx_buf = dd_data;
+ pmboxq->ctx_u.dd_data = dd_data;
dd_data->type = TYPE_MBOX;
dd_data->set_job = job;
dd_data->context_un.mbox.pmboxq = pmboxq;
@@ -4747,7 +4747,7 @@
if (mbox_req->inExtWLen || mbox_req->outExtWLen) {
from = pmbx;
ext = from + sizeof(MAILBOX_t);
- pmboxq->ctx_buf = ext;
+ pmboxq->ext_buf = ext;
pmboxq->in_ext_byte_len =
mbox_req->inExtWLen * sizeof(uint32_t);
pmboxq->out_ext_byte_len =
@@ -4875,7 +4875,7 @@
pmboxq->mbox_cmpl = lpfc_bsg_issue_mbox_cmpl;
/* setup context field to pass wait_queue pointer to wake function */
- pmboxq->ctx_ndlp = dd_data;
+ pmboxq->ctx_u.dd_data = dd_data;
dd_data->type = TYPE_MBOX;
dd_data->set_job = job;
dd_data->context_un.mbox.pmboxq = pmboxq;
@@ -5070,12 +5070,12 @@
bsg_reply->reply_data.vendor_reply.vendor_rsp;
/* Current logging state */
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irq(&phba->ras_fwlog_lock);
if (ras_fwlog->state == ACTIVE)
ras_reply->state = LPFC_RASLOG_STATE_RUNNING;
else
ras_reply->state = LPFC_RASLOG_STATE_STOPPED;
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
ras_reply->log_level = phba->ras_fwlog.fw_loglevel;
ras_reply->log_buff_sz = phba->cfg_ras_fwlog_buffsize;
@@ -5132,13 +5132,13 @@
if (action == LPFC_RASACTION_STOP_LOGGING) {
/* Check if already disabled */
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irq(&phba->ras_fwlog_lock);
if (ras_fwlog->state != ACTIVE) {
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
rc = -ESRCH;
goto ras_job_error;
}
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
/* Disable logging */
lpfc_ras_stop_fwlog(phba);
@@ -5149,10 +5149,10 @@
* FW-logging with new log-level. Return status
* "Logging already Running" to caller.
**/
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irq(&phba->ras_fwlog_lock);
if (ras_fwlog->state != INACTIVE)
action_status = -EINPROGRESS;
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
/* Enable logging */
rc = lpfc_sli4_ras_fwlog_init(phba, log_level,
@@ -5268,13 +5268,13 @@
goto ras_job_error;
/* Logging to be stopped before reading */
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irq(&phba->ras_fwlog_lock);
if (ras_fwlog->state == ACTIVE) {
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
rc = -EINPROGRESS;
goto ras_job_error;
}
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
if (job->request_len <
sizeof(struct fc_bsg_request) +
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index ab5af10..a2d2b02 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -2194,12 +2194,12 @@
memset(buffer, 0, size);
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irq(&phba->ras_fwlog_lock);
if (phba->ras_fwlog.state != ACTIVE) {
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
return -EINVAL;
}
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
list_for_each_entry_safe(dmabuf, next,
&phba->ras_fwlog.fwlog_buff_list, list) {
@@ -2250,13 +2250,13 @@
int size;
int rc = -ENOMEM;
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irq(&phba->ras_fwlog_lock);
if (phba->ras_fwlog.state != ACTIVE) {
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
rc = -EINVAL;
goto out;
}
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
if (check_mul_overflow(LPFC_RAS_MIN_BUFF_POST_SIZE,
phba->cfg_ras_fwlog_buffsize, &size))
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 28e5654..f7c28dc 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -4437,23 +4437,23 @@
unsigned long flags;
struct lpfc_work_evt *evtp = &ndlp->els_retry_evt;
+ /* Hold a node reference for outstanding queued work */
+ if (!lpfc_nlp_get(ndlp))
+ return;
+
spin_lock_irqsave(&phba->hbalock, flags);
if (!list_empty(&evtp->evt_listp)) {
spin_unlock_irqrestore(&phba->hbalock, flags);
+ lpfc_nlp_put(ndlp);
return;
}
- /* We need to hold the node by incrementing the reference
- * count until the queued work is done
- */
- evtp->evt_arg1 = lpfc_nlp_get(ndlp);
- if (evtp->evt_arg1) {
- evtp->evt = LPFC_EVT_ELS_RETRY;
- list_add_tail(&evtp->evt_listp, &phba->work_list);
- lpfc_worker_wake_up(phba);
- }
+ evtp->evt_arg1 = ndlp;
+ evtp->evt = LPFC_EVT_ELS_RETRY;
+ list_add_tail(&evtp->evt_listp, &phba->work_list);
spin_unlock_irqrestore(&phba->hbalock, flags);
- return;
+
+ lpfc_worker_wake_up(phba);
}
/**
@@ -7238,7 +7238,7 @@
goto rdp_fail;
mbox->vport = rdp_context->ndlp->vport;
mbox->mbox_cmpl = lpfc_mbx_cmpl_rdp_page_a0;
- mbox->ctx_ndlp = (struct lpfc_rdp_context *)rdp_context;
+ mbox->ctx_u.rdp = rdp_context;
rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
if (rc == MBX_NOT_FINISHED) {
lpfc_mbox_rsrc_cleanup(phba, mbox, MBOX_THD_UNLOCKED);
@@ -7290,7 +7290,7 @@
mbox->in_ext_byte_len = DMP_SFF_PAGE_A0_SIZE;
mbox->out_ext_byte_len = DMP_SFF_PAGE_A0_SIZE;
mbox->mbox_offset_word = 5;
- mbox->ctx_buf = virt;
+ mbox->ext_buf = virt;
} else {
bf_set(lpfc_mbx_memory_dump_type3_length,
&mbox->u.mqe.un.mem_dump_type3, DMP_SFF_PAGE_A0_SIZE);
@@ -7298,7 +7298,6 @@
mbox->u.mqe.un.mem_dump_type3.addr_hi = putPaddrHigh(mp->phys);
}
mbox->vport = phba->pport;
- mbox->ctx_ndlp = (struct lpfc_rdp_context *)rdp_context;
rc = lpfc_sli_issue_mbox_wait(phba, mbox, 30);
if (rc == MBX_NOT_FINISHED) {
@@ -7307,7 +7306,7 @@
}
if (phba->sli_rev == LPFC_SLI_REV4)
- mp = (struct lpfc_dmabuf *)(mbox->ctx_buf);
+ mp = mbox->ctx_buf;
else
mp = mpsave;
@@ -7350,7 +7349,7 @@
mbox->in_ext_byte_len = DMP_SFF_PAGE_A2_SIZE;
mbox->out_ext_byte_len = DMP_SFF_PAGE_A2_SIZE;
mbox->mbox_offset_word = 5;
- mbox->ctx_buf = virt;
+ mbox->ext_buf = virt;
} else {
bf_set(lpfc_mbx_memory_dump_type3_length,
&mbox->u.mqe.un.mem_dump_type3, DMP_SFF_PAGE_A2_SIZE);
@@ -7358,7 +7357,6 @@
mbox->u.mqe.un.mem_dump_type3.addr_hi = putPaddrHigh(mp->phys);
}
- mbox->ctx_ndlp = (struct lpfc_rdp_context *)rdp_context;
rc = lpfc_sli_issue_mbox_wait(phba, mbox, 30);
if (bf_get(lpfc_mqe_status, &mbox->u.mqe)) {
rc = 1;
@@ -7500,9 +7498,9 @@
int rc;
mb = &pmb->u.mb;
- lcb_context = (struct lpfc_lcb_context *)pmb->ctx_ndlp;
+ lcb_context = pmb->ctx_u.lcb;
ndlp = lcb_context->ndlp;
- pmb->ctx_ndlp = NULL;
+ memset(&pmb->ctx_u, 0, sizeof(pmb->ctx_u));
pmb->ctx_buf = NULL;
shdr = (union lpfc_sli4_cfg_shdr *)
@@ -7642,7 +7640,7 @@
lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_COMMON,
LPFC_MBOX_OPCODE_SET_BEACON_CONFIG, len,
LPFC_SLI4_MBX_EMBED);
- mbox->ctx_ndlp = (void *)lcb_context;
+ mbox->ctx_u.lcb = lcb_context;
mbox->vport = phba->pport;
mbox->mbox_cmpl = lpfc_els_lcb_rsp;
bf_set(lpfc_mbx_set_beacon_port_num, &mbox->u.mqe.un.beacon_config,
@@ -8639,9 +8637,9 @@
mb = &pmb->u.mb;
ndlp = pmb->ctx_ndlp;
- rxid = (uint16_t)((unsigned long)(pmb->ctx_buf) & 0xffff);
- oxid = (uint16_t)(((unsigned long)(pmb->ctx_buf) >> 16) & 0xffff);
- pmb->ctx_buf = NULL;
+ rxid = (uint16_t)(pmb->ctx_u.ox_rx_id & 0xffff);
+ oxid = (uint16_t)((pmb->ctx_u.ox_rx_id >> 16) & 0xffff);
+ memset(&pmb->ctx_u, 0, sizeof(pmb->ctx_u));
pmb->ctx_ndlp = NULL;
if (mb->mbxStatus) {
@@ -8745,8 +8743,7 @@
mbox = mempool_alloc(phba->mbox_mem_pool, GFP_ATOMIC);
if (mbox) {
lpfc_read_lnk_stat(phba, mbox);
- mbox->ctx_buf = (void *)((unsigned long)
- (ox_id << 16 | ctx));
+ mbox->ctx_u.ox_rx_id = ox_id << 16 | ctx;
mbox->ctx_ndlp = lpfc_nlp_get(ndlp);
if (!mbox->ctx_ndlp)
goto node_err;
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index a7a2309..e42fa9c 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -257,7 +257,9 @@
if (evtp->evt_arg1) {
evtp->evt = LPFC_EVT_DEV_LOSS;
list_add_tail(&evtp->evt_listp, &phba->work_list);
+ spin_unlock_irqrestore(&phba->hbalock, iflags);
lpfc_worker_wake_up(phba);
+ return;
}
spin_unlock_irqrestore(&phba->hbalock, iflags);
} else {
@@ -275,10 +277,7 @@
lpfc_disc_state_machine(vport, ndlp, NULL,
NLP_EVT_DEVICE_RM);
}
-
}
-
- return;
}
/**
@@ -3429,7 +3428,7 @@
lpfc_mbx_cmpl_read_sparam(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
{
MAILBOX_t *mb = &pmb->u.mb;
- struct lpfc_dmabuf *mp = (struct lpfc_dmabuf *)pmb->ctx_buf;
+ struct lpfc_dmabuf *mp = pmb->ctx_buf;
struct lpfc_vport *vport = pmb->vport;
struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
struct serv_parm *sp = &vport->fc_sparam;
@@ -3737,7 +3736,7 @@
struct lpfc_mbx_read_top *la;
struct lpfc_sli_ring *pring;
MAILBOX_t *mb = &pmb->u.mb;
- struct lpfc_dmabuf *mp = (struct lpfc_dmabuf *)(pmb->ctx_buf);
+ struct lpfc_dmabuf *mp = pmb->ctx_buf;
uint8_t attn_type;
/* Unblock ELS traffic */
@@ -3851,8 +3850,8 @@
lpfc_mbx_cmpl_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
{
struct lpfc_vport *vport = pmb->vport;
- struct lpfc_dmabuf *mp = (struct lpfc_dmabuf *)pmb->ctx_buf;
- struct lpfc_nodelist *ndlp = (struct lpfc_nodelist *)pmb->ctx_ndlp;
+ struct lpfc_dmabuf *mp = pmb->ctx_buf;
+ struct lpfc_nodelist *ndlp = pmb->ctx_ndlp;
/* The driver calls the state machine with the pmb pointer
* but wants to make sure a stale ctx_buf isn't acted on.
@@ -4066,7 +4065,7 @@
* the dump routine is a single-use construct.
*/
if (pmb->ctx_buf) {
- mp = (struct lpfc_dmabuf *)pmb->ctx_buf;
+ mp = pmb->ctx_buf;
lpfc_mbuf_free(phba, mp->virt, mp->phys);
kfree(mp);
pmb->ctx_buf = NULL;
@@ -4089,7 +4088,7 @@
if (phba->sli_rev == LPFC_SLI_REV4) {
byte_count = pmb->u.mqe.un.mb_words[5];
- mp = (struct lpfc_dmabuf *)pmb->ctx_buf;
+ mp = pmb->ctx_buf;
if (byte_count > sizeof(struct static_vport_info) -
offset)
byte_count = sizeof(struct static_vport_info)
@@ -4169,7 +4168,7 @@
{
struct lpfc_vport *vport = pmb->vport;
MAILBOX_t *mb = &pmb->u.mb;
- struct lpfc_nodelist *ndlp = (struct lpfc_nodelist *)pmb->ctx_ndlp;
+ struct lpfc_nodelist *ndlp = pmb->ctx_ndlp;
pmb->ctx_ndlp = NULL;
@@ -4307,7 +4306,7 @@
lpfc_mbx_cmpl_ns_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
{
MAILBOX_t *mb = &pmb->u.mb;
- struct lpfc_nodelist *ndlp = (struct lpfc_nodelist *)pmb->ctx_ndlp;
+ struct lpfc_nodelist *ndlp = pmb->ctx_ndlp;
struct lpfc_vport *vport = pmb->vport;
int rc;
@@ -4431,7 +4430,7 @@
{
struct lpfc_vport *vport = pmb->vport;
MAILBOX_t *mb = &pmb->u.mb;
- struct lpfc_nodelist *ndlp = (struct lpfc_nodelist *)pmb->ctx_ndlp;
+ struct lpfc_nodelist *ndlp = pmb->ctx_ndlp;
pmb->ctx_ndlp = NULL;
if (mb->mbxStatus) {
@@ -5174,7 +5173,7 @@
struct lpfc_vport *vport = pmb->vport;
struct lpfc_nodelist *ndlp;
- ndlp = (struct lpfc_nodelist *)(pmb->ctx_ndlp);
+ ndlp = pmb->ctx_ndlp;
if (!ndlp)
return;
lpfc_issue_els_logo(vport, ndlp, 0);
@@ -5496,7 +5495,7 @@
if ((mb = phba->sli.mbox_active)) {
if ((mb->u.mb.mbxCommand == MBX_REG_LOGIN64) &&
!(mb->mbox_flag & LPFC_MBX_IMED_UNREG) &&
- (ndlp == (struct lpfc_nodelist *)mb->ctx_ndlp)) {
+ (ndlp == mb->ctx_ndlp)) {
mb->ctx_ndlp = NULL;
mb->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
}
@@ -5507,7 +5506,7 @@
list_for_each_entry(mb, &phba->sli.mboxq_cmpl, list) {
if ((mb->u.mb.mbxCommand != MBX_REG_LOGIN64) ||
(mb->mbox_flag & LPFC_MBX_IMED_UNREG) ||
- (ndlp != (struct lpfc_nodelist *)mb->ctx_ndlp))
+ (ndlp != mb->ctx_ndlp))
continue;
mb->ctx_ndlp = NULL;
@@ -5517,7 +5516,7 @@
list_for_each_entry_safe(mb, nextmb, &phba->sli.mboxq, list) {
if ((mb->u.mb.mbxCommand == MBX_REG_LOGIN64) &&
!(mb->mbox_flag & LPFC_MBX_IMED_UNREG) &&
- (ndlp == (struct lpfc_nodelist *)mb->ctx_ndlp)) {
+ (ndlp == mb->ctx_ndlp)) {
list_del(&mb->list);
lpfc_mbox_rsrc_cleanup(phba, mb, MBOX_THD_LOCKED);
@@ -6357,7 +6356,7 @@
lpfc_mbx_cmpl_fdmi_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
{
MAILBOX_t *mb = &pmb->u.mb;
- struct lpfc_nodelist *ndlp = (struct lpfc_nodelist *)pmb->ctx_ndlp;
+ struct lpfc_nodelist *ndlp = pmb->ctx_ndlp;
struct lpfc_vport *vport = pmb->vport;
pmb->ctx_ndlp = NULL;
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 88b2e57..f7a0aa36 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -460,7 +460,7 @@
return -EIO;
}
- mp = (struct lpfc_dmabuf *)pmb->ctx_buf;
+ mp = pmb->ctx_buf;
/* This dmabuf was allocated by lpfc_read_sparam. The dmabuf is no
* longer needed. Prevent unintended ctx_buf access as the mbox is
@@ -2217,7 +2217,7 @@
/* Cleanup any outstanding ELS commands */
lpfc_els_flush_all_cmd(phba);
psli->slistat.link_event++;
- lpfc_read_topology(phba, pmb, (struct lpfc_dmabuf *)pmb->ctx_buf);
+ lpfc_read_topology(phba, pmb, pmb->ctx_buf);
pmb->mbox_cmpl = lpfc_mbx_cmpl_read_topology;
pmb->vport = vport;
/* Block ELS IOCBs until we have processed this mbox command */
@@ -5454,7 +5454,7 @@
phba->sli.slistat.link_event++;
/* Create lpfc_handle_latt mailbox command from link ACQE */
- lpfc_read_topology(phba, pmb, (struct lpfc_dmabuf *)pmb->ctx_buf);
+ lpfc_read_topology(phba, pmb, pmb->ctx_buf);
pmb->mbox_cmpl = lpfc_mbx_cmpl_read_topology;
pmb->vport = phba->pport;
@@ -6347,7 +6347,7 @@
phba->sli.slistat.link_event++;
/* Create lpfc_handle_latt mailbox command from link ACQE */
- lpfc_read_topology(phba, pmb, (struct lpfc_dmabuf *)pmb->ctx_buf);
+ lpfc_read_topology(phba, pmb, pmb->ctx_buf);
pmb->mbox_cmpl = lpfc_mbx_cmpl_read_topology;
pmb->vport = phba->pport;
@@ -7705,6 +7705,9 @@
"NVME" : " "),
(phba->nvmet_support ? "NVMET" : " "));
+ /* ras_fwlog state */
+ spin_lock_init(&phba->ras_fwlog_lock);
+
/* Initialize the IO buffer list used by driver for SLI3 SCSI */
spin_lock_init(&phba->scsi_buf_list_get_lock);
INIT_LIST_HEAD(&phba->lpfc_scsi_buf_list_get);
@@ -13055,7 +13058,7 @@
rc = request_threaded_irq(eqhdl->irq,
&lpfc_sli4_hba_intr_handler,
&lpfc_sli4_hba_intr_handler_th,
- IRQF_ONESHOT, name, eqhdl);
+ 0, name, eqhdl);
if (rc) {
lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
"0486 MSI-X fast-path (%d) "
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index f7c4195..e98f1c2 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -102,7 +102,7 @@
{
struct lpfc_dmabuf *mp;
- mp = (struct lpfc_dmabuf *)mbox->ctx_buf;
+ mp = mbox->ctx_buf;
mbox->ctx_buf = NULL;
/* Release the generic BPL buffer memory. */
@@ -204,10 +204,8 @@
uint16_t region_id)
{
MAILBOX_t *mb;
- void *ctx;
mb = &pmb->u.mb;
- ctx = pmb->ctx_buf;
/* Setup to dump VPD region */
memset(pmb, 0, sizeof (LPFC_MBOXQ_t));
@@ -219,7 +217,6 @@
mb->un.varDmp.word_cnt = (DMP_RSP_SIZE / sizeof (uint32_t));
mb->un.varDmp.co = 0;
mb->un.varDmp.resp_offset = 0;
- pmb->ctx_buf = ctx;
mb->mbxOwner = OWN_HOST;
return;
}
@@ -236,11 +233,8 @@
lpfc_dump_wakeup_param(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
{
MAILBOX_t *mb;
- void *ctx;
mb = &pmb->u.mb;
- /* Save context so that we can restore after memset */
- ctx = pmb->ctx_buf;
/* Setup to dump VPD region */
memset(pmb, 0, sizeof(LPFC_MBOXQ_t));
@@ -254,7 +248,6 @@
mb->un.varDmp.word_cnt = WAKE_UP_PARMS_WORD_SIZE;
mb->un.varDmp.co = 0;
mb->un.varDmp.resp_offset = 0;
- pmb->ctx_buf = ctx;
return;
}
@@ -372,7 +365,7 @@
/* Save address for later completion and set the owner to host so that
* the FW knows this mailbox is available for processing.
*/
- pmb->ctx_buf = (uint8_t *)mp;
+ pmb->ctx_buf = mp;
mb->mbxOwner = OWN_HOST;
return (0);
}
@@ -1816,7 +1809,7 @@
}
/* Reinitialize the context pointers to avoid stale usage. */
mbox->ctx_buf = NULL;
- mbox->context3 = NULL;
+ memset(&mbox->ctx_u, 0, sizeof(mbox->ctx_u));
kfree(mbox->sge_array);
/* Finally, free the mailbox command itself */
mempool_free(mbox, phba->mbox_mem_pool);
@@ -2366,8 +2359,7 @@
{
MAILBOX_t *mb;
int rc = FAILURE;
- struct lpfc_rdp_context *rdp_context =
- (struct lpfc_rdp_context *)(mboxq->ctx_ndlp);
+ struct lpfc_rdp_context *rdp_context = mboxq->ctx_u.rdp;
mb = &mboxq->u.mb;
if (mb->mbxStatus)
@@ -2385,9 +2377,8 @@
static void
lpfc_mbx_cmpl_rdp_page_a2(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox)
{
- struct lpfc_dmabuf *mp = (struct lpfc_dmabuf *)mbox->ctx_buf;
- struct lpfc_rdp_context *rdp_context =
- (struct lpfc_rdp_context *)(mbox->ctx_ndlp);
+ struct lpfc_dmabuf *mp = mbox->ctx_buf;
+ struct lpfc_rdp_context *rdp_context = mbox->ctx_u.rdp;
if (bf_get(lpfc_mqe_status, &mbox->u.mqe))
goto error_mbox_free;
@@ -2401,7 +2392,7 @@
/* Save the dma buffer for cleanup in the final completion. */
mbox->ctx_buf = mp;
mbox->mbox_cmpl = lpfc_mbx_cmpl_rdp_link_stat;
- mbox->ctx_ndlp = (struct lpfc_rdp_context *)rdp_context;
+ mbox->ctx_u.rdp = rdp_context;
if (lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT) == MBX_NOT_FINISHED)
goto error_mbox_free;
@@ -2416,9 +2407,8 @@
lpfc_mbx_cmpl_rdp_page_a0(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox)
{
int rc;
- struct lpfc_dmabuf *mp = (struct lpfc_dmabuf *)(mbox->ctx_buf);
- struct lpfc_rdp_context *rdp_context =
- (struct lpfc_rdp_context *)(mbox->ctx_ndlp);
+ struct lpfc_dmabuf *mp = mbox->ctx_buf;
+ struct lpfc_rdp_context *rdp_context = mbox->ctx_u.rdp;
if (bf_get(lpfc_mqe_status, &mbox->u.mqe))
goto error;
@@ -2448,7 +2438,7 @@
mbox->u.mqe.un.mem_dump_type3.addr_hi = putPaddrHigh(mp->phys);
mbox->mbox_cmpl = lpfc_mbx_cmpl_rdp_page_a2;
- mbox->ctx_ndlp = (struct lpfc_rdp_context *)rdp_context;
+ mbox->ctx_u.rdp = rdp_context;
rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
if (rc == MBX_NOT_FINISHED)
goto error;
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 8e425be..c417279 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -300,7 +300,7 @@
int rc;
ndlp = login_mbox->ctx_ndlp;
- save_iocb = login_mbox->context3;
+ save_iocb = login_mbox->ctx_u.save_iocb;
if (mb->mbxStatus == MBX_SUCCESS) {
/* Now that REG_RPI completed successfully,
@@ -640,7 +640,7 @@
if (!login_mbox->ctx_ndlp)
goto out;
- login_mbox->context3 = save_iocb; /* For PLOGI ACC */
+ login_mbox->ctx_u.save_iocb = save_iocb; /* For PLOGI ACC */
spin_lock_irq(&ndlp->lock);
ndlp->nlp_flag |= (NLP_ACC_REGLOGIN | NLP_RCV_PLOGI);
@@ -682,8 +682,8 @@
struct lpfc_nodelist *ndlp;
uint32_t cmd;
- elsiocb = (struct lpfc_iocbq *)mboxq->ctx_buf;
- ndlp = (struct lpfc_nodelist *)mboxq->ctx_ndlp;
+ elsiocb = mboxq->ctx_u.save_iocb;
+ ndlp = mboxq->ctx_ndlp;
vport = mboxq->vport;
cmd = elsiocb->drvrTimeout;
@@ -1875,7 +1875,7 @@
/* cleanup any ndlp on mbox q waiting for reglogin cmpl */
if ((mb = phba->sli.mbox_active)) {
if ((mb->u.mb.mbxCommand == MBX_REG_LOGIN64) &&
- (ndlp == (struct lpfc_nodelist *)mb->ctx_ndlp)) {
+ (ndlp == mb->ctx_ndlp)) {
ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
lpfc_nlp_put(ndlp);
mb->ctx_ndlp = NULL;
@@ -1886,7 +1886,7 @@
spin_lock_irq(&phba->hbalock);
list_for_each_entry_safe(mb, nextmb, &phba->sli.mboxq, list) {
if ((mb->u.mb.mbxCommand == MBX_REG_LOGIN64) &&
- (ndlp == (struct lpfc_nodelist *)mb->ctx_ndlp)) {
+ (ndlp == mb->ctx_ndlp)) {
ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
lpfc_nlp_put(ndlp);
list_del(&mb->list);
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 09c53b8..c5792ea 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -2616,9 +2616,9 @@
/* No concern about the role change on the nvme remoteport.
* The transport will update it.
*/
- spin_lock_irq(&vport->phba->hbalock);
+ spin_lock_irq(&ndlp->lock);
ndlp->fc4_xpt_flags |= NVME_XPT_UNREG_WAIT;
- spin_unlock_irq(&vport->phba->hbalock);
+ spin_unlock_irq(&ndlp->lock);
/* Don't let the host nvme transport keep sending keep-alives
* on this remoteport. Vport is unloading, no recovery. The
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 8258b77..561ced5 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -1586,7 +1586,7 @@
wqe = &nvmewqe->wqe;
/* Initialize WQE */
- memset(wqe, 0, sizeof(union lpfc_wqe));
+ memset(wqe, 0, sizeof(*wqe));
ctx_buf->iocbq->cmd_dmabuf = NULL;
spin_lock(&phba->sli4_hba.sgl_list_lock);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index c0038ea..4a6e522 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -167,11 +167,10 @@
struct Scsi_Host *shost;
struct scsi_device *sdev;
unsigned long new_queue_depth;
- unsigned long num_rsrc_err, num_cmd_success;
+ unsigned long num_rsrc_err;
int i;
num_rsrc_err = atomic_read(&phba->num_rsrc_err);
- num_cmd_success = atomic_read(&phba->num_cmd_success);
/*
* The error and success command counters are global per
@@ -186,20 +185,16 @@
for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
shost = lpfc_shost_from_vport(vports[i]);
shost_for_each_device(sdev, shost) {
- new_queue_depth =
- sdev->queue_depth * num_rsrc_err /
- (num_rsrc_err + num_cmd_success);
- if (!new_queue_depth)
- new_queue_depth = sdev->queue_depth - 1;
+ if (num_rsrc_err >= sdev->queue_depth)
+ new_queue_depth = 1;
else
new_queue_depth = sdev->queue_depth -
- new_queue_depth;
+ num_rsrc_err;
scsi_change_queue_depth(sdev, new_queue_depth);
}
}
lpfc_destroy_vport_work_array(phba, vports);
atomic_set(&phba->num_rsrc_err, 0);
- atomic_set(&phba->num_cmd_success, 0);
}
/**
@@ -5336,16 +5331,6 @@
}
err = lpfc_bg_scsi_prep_dma_buf(phba, lpfc_cmd);
} else {
- if (vport->phba->cfg_enable_bg) {
- lpfc_printf_vlog(vport,
- KERN_INFO, LOG_SCSI_CMD,
- "9038 BLKGRD: rcvd PROT_NORMAL cmd: "
- "x%x reftag x%x cnt %u pt %x\n",
- cmnd->cmnd[0],
- scsi_prot_ref_tag(cmnd),
- scsi_logical_block_count(cmnd),
- (cmnd->cmnd[1]>>5));
- }
err = lpfc_scsi_prep_dma_buf(phba, lpfc_cmd);
}
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 1f8a9b5..a028e00 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -1217,9 +1217,9 @@
empty = list_empty(&phba->active_rrq_list);
list_add_tail(&rrq->list, &phba->active_rrq_list);
phba->hba_flag |= HBA_RRQ_ACTIVE;
+ spin_unlock_irqrestore(&phba->hbalock, iflags);
if (empty)
lpfc_worker_wake_up(phba);
- spin_unlock_irqrestore(&phba->hbalock, iflags);
return 0;
out:
spin_unlock_irqrestore(&phba->hbalock, iflags);
@@ -2830,7 +2830,7 @@
*/
pmboxq->mbox_flag |= LPFC_MBX_WAKE;
spin_lock_irqsave(&phba->hbalock, drvr_flag);
- pmbox_done = (struct completion *)pmboxq->context3;
+ pmbox_done = pmboxq->ctx_u.mbox_wait;
if (pmbox_done)
complete(pmbox_done);
spin_unlock_irqrestore(&phba->hbalock, drvr_flag);
@@ -2885,7 +2885,7 @@
if (!test_bit(FC_UNLOADING, &phba->pport->load_flag) &&
pmb->u.mb.mbxCommand == MBX_REG_LOGIN64 &&
!pmb->u.mb.mbxStatus) {
- mp = (struct lpfc_dmabuf *)pmb->ctx_buf;
+ mp = pmb->ctx_buf;
if (mp) {
pmb->ctx_buf = NULL;
lpfc_mbuf_free(phba, mp->virt, mp->phys);
@@ -2914,12 +2914,12 @@
}
if (pmb->u.mb.mbxCommand == MBX_REG_LOGIN64) {
- ndlp = (struct lpfc_nodelist *)pmb->ctx_ndlp;
+ ndlp = pmb->ctx_ndlp;
lpfc_nlp_put(ndlp);
}
if (pmb->u.mb.mbxCommand == MBX_UNREG_LOGIN) {
- ndlp = (struct lpfc_nodelist *)pmb->ctx_ndlp;
+ ndlp = pmb->ctx_ndlp;
/* Check to see if there are any deferred events to process */
if (ndlp) {
@@ -2952,7 +2952,7 @@
/* This nlp_put pairs with lpfc_sli4_resume_rpi */
if (pmb->u.mb.mbxCommand == MBX_RESUME_RPI) {
- ndlp = (struct lpfc_nodelist *)pmb->ctx_ndlp;
+ ndlp = pmb->ctx_ndlp;
lpfc_nlp_put(ndlp);
}
@@ -5819,7 +5819,7 @@
goto out_free_mboxq;
}
- mp = (struct lpfc_dmabuf *)mboxq->ctx_buf;
+ mp = mboxq->ctx_buf;
rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
lpfc_printf_log(phba, KERN_INFO, LOG_MBOX | LOG_SLI,
@@ -6849,9 +6849,9 @@
{
struct lpfc_ras_fwlog *ras_fwlog = &phba->ras_fwlog;
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irq(&phba->ras_fwlog_lock);
ras_fwlog->state = INACTIVE;
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
/* Disable FW logging to host memory */
writel(LPFC_CTL_PDEV_CTL_DDL_RAS,
@@ -6894,9 +6894,9 @@
ras_fwlog->lwpd.virt = NULL;
}
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irq(&phba->ras_fwlog_lock);
ras_fwlog->state = INACTIVE;
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
}
/**
@@ -6998,9 +6998,9 @@
goto disable_ras;
}
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irq(&phba->ras_fwlog_lock);
ras_fwlog->state = ACTIVE;
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
mempool_free(pmb, phba->mbox_mem_pool);
return;
@@ -7032,9 +7032,9 @@
uint32_t len = 0, fwlog_buffsize, fwlog_entry_count;
int rc = 0;
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irq(&phba->ras_fwlog_lock);
ras_fwlog->state = INACTIVE;
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
fwlog_buffsize = (LPFC_RAS_MIN_BUFF_POST_SIZE *
phba->cfg_ras_fwlog_buffsize);
@@ -7095,9 +7095,9 @@
mbx_fwlog->u.request.lwpd.addr_lo = putPaddrLow(ras_fwlog->lwpd.phys);
mbx_fwlog->u.request.lwpd.addr_hi = putPaddrHigh(ras_fwlog->lwpd.phys);
- spin_lock_irq(&phba->hbalock);
+ spin_lock_irq(&phba->ras_fwlog_lock);
ras_fwlog->state = REG_INPROGRESS;
- spin_unlock_irq(&phba->hbalock);
+ spin_unlock_irq(&phba->ras_fwlog_lock);
mbox->vport = phba->pport;
mbox->mbox_cmpl = lpfc_sli4_ras_mbox_cmpl;
@@ -8766,7 +8766,7 @@
mboxq->vport = vport;
rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
- mp = (struct lpfc_dmabuf *)mboxq->ctx_buf;
+ mp = mboxq->ctx_buf;
if (rc == MBX_SUCCESS) {
memcpy(&vport->fc_sparam, mp->virt, sizeof(struct serv_parm));
rc = 0;
@@ -9548,8 +9548,8 @@
}
/* Copy the mailbox extension data */
- if (pmbox->in_ext_byte_len && pmbox->ctx_buf) {
- lpfc_sli_pcimem_bcopy(pmbox->ctx_buf,
+ if (pmbox->in_ext_byte_len && pmbox->ext_buf) {
+ lpfc_sli_pcimem_bcopy(pmbox->ext_buf,
(uint8_t *)phba->mbox_ext,
pmbox->in_ext_byte_len);
}
@@ -9562,10 +9562,10 @@
= MAILBOX_HBA_EXT_OFFSET;
/* Copy the mailbox extension data */
- if (pmbox->in_ext_byte_len && pmbox->ctx_buf)
+ if (pmbox->in_ext_byte_len && pmbox->ext_buf)
lpfc_memcpy_to_slim(phba->MBslimaddr +
MAILBOX_HBA_EXT_OFFSET,
- pmbox->ctx_buf, pmbox->in_ext_byte_len);
+ pmbox->ext_buf, pmbox->in_ext_byte_len);
if (mbx->mbxCommand == MBX_CONFIG_PORT)
/* copy command data into host mbox for cmpl */
@@ -9688,9 +9688,9 @@
lpfc_sli_pcimem_bcopy(phba->mbox, mbx,
MAILBOX_CMD_SIZE);
/* Copy the mailbox extension data */
- if (pmbox->out_ext_byte_len && pmbox->ctx_buf) {
+ if (pmbox->out_ext_byte_len && pmbox->ext_buf) {
lpfc_sli_pcimem_bcopy(phba->mbox_ext,
- pmbox->ctx_buf,
+ pmbox->ext_buf,
pmbox->out_ext_byte_len);
}
} else {
@@ -9698,9 +9698,9 @@
lpfc_memcpy_from_slim(mbx, phba->MBslimaddr,
MAILBOX_CMD_SIZE);
/* Copy the mailbox extension data */
- if (pmbox->out_ext_byte_len && pmbox->ctx_buf) {
+ if (pmbox->out_ext_byte_len && pmbox->ext_buf) {
lpfc_memcpy_from_slim(
- pmbox->ctx_buf,
+ pmbox->ext_buf,
phba->MBslimaddr +
MAILBOX_HBA_EXT_OFFSET,
pmbox->out_ext_byte_len);
@@ -11373,18 +11373,18 @@
unsigned long iflags;
struct lpfc_work_evt *evtp = &ndlp->recovery_evt;
+ /* Hold a node reference for outstanding queued work */
+ if (!lpfc_nlp_get(ndlp))
+ return;
+
spin_lock_irqsave(&phba->hbalock, iflags);
if (!list_empty(&evtp->evt_listp)) {
spin_unlock_irqrestore(&phba->hbalock, iflags);
+ lpfc_nlp_put(ndlp);
return;
}
- /* Incrementing the reference count until the queued work is done. */
- evtp->evt_arg1 = lpfc_nlp_get(ndlp);
- if (!evtp->evt_arg1) {
- spin_unlock_irqrestore(&phba->hbalock, iflags);
- return;
- }
+ evtp->evt_arg1 = ndlp;
evtp->evt = LPFC_EVT_RECOVER_PORT;
list_add_tail(&evtp->evt_listp, &phba->work_list);
spin_unlock_irqrestore(&phba->hbalock, iflags);
@@ -13262,9 +13262,9 @@
/* setup wake call as IOCB callback */
pmboxq->mbox_cmpl = lpfc_sli_wake_mbox_wait;
- /* setup context3 field to pass wait_queue pointer to wake function */
+ /* setup ctx_u field to pass wait_queue pointer to wake function */
init_completion(&mbox_done);
- pmboxq->context3 = &mbox_done;
+ pmboxq->ctx_u.mbox_wait = &mbox_done;
/* now issue the command */
retval = lpfc_sli_issue_mbox(phba, pmboxq, MBX_NOWAIT);
if (retval == MBX_BUSY || retval == MBX_SUCCESS) {
@@ -13272,7 +13272,7 @@
msecs_to_jiffies(timeout * 1000));
spin_lock_irqsave(&phba->hbalock, flag);
- pmboxq->context3 = NULL;
+ pmboxq->ctx_u.mbox_wait = NULL;
/*
* if LPFC_MBX_WAKE flag is set the mailbox is completed
* else do not free the resources.
@@ -13813,10 +13813,10 @@
lpfc_sli_pcimem_bcopy(mbox, pmbox,
MAILBOX_CMD_SIZE);
if (pmb->out_ext_byte_len &&
- pmb->ctx_buf)
+ pmb->ext_buf)
lpfc_sli_pcimem_bcopy(
phba->mbox_ext,
- pmb->ctx_buf,
+ pmb->ext_buf,
pmb->out_ext_byte_len);
}
if (pmb->mbox_flag & LPFC_MBX_IMED_UNREG) {
@@ -13830,10 +13830,8 @@
pmbox->un.varWords[0], 0);
if (!pmbox->mbxStatus) {
- mp = (struct lpfc_dmabuf *)
- (pmb->ctx_buf);
- ndlp = (struct lpfc_nodelist *)
- pmb->ctx_ndlp;
+ mp = pmb->ctx_buf;
+ ndlp = pmb->ctx_ndlp;
/* Reg_LOGIN of dflt RPI was
* successful. new lets get
@@ -14340,8 +14338,8 @@
mcqe_status,
pmbox->un.varWords[0], 0);
if (mcqe_status == MB_CQE_STATUS_SUCCESS) {
- mp = (struct lpfc_dmabuf *)(pmb->ctx_buf);
- ndlp = (struct lpfc_nodelist *)pmb->ctx_ndlp;
+ mp = pmb->ctx_buf;
+ ndlp = pmb->ctx_ndlp;
/* Reg_LOGIN of dflt RPI was successful. Mark the
* node as having an UNREG_LOGIN in progress to stop
@@ -19823,14 +19821,15 @@
* lpfc_sli4_resume_rpi - Remove the rpi bitmask region
* @ndlp: pointer to lpfc nodelist data structure.
* @cmpl: completion call-back.
- * @arg: data to load as MBox 'caller buffer information'
+ * @iocbq: data to load as mbox ctx_u information
*
* This routine is invoked to remove the memory region that
* provided rpi via a bitmask.
**/
int
lpfc_sli4_resume_rpi(struct lpfc_nodelist *ndlp,
- void (*cmpl)(struct lpfc_hba *, LPFC_MBOXQ_t *), void *arg)
+ void (*cmpl)(struct lpfc_hba *, LPFC_MBOXQ_t *),
+ struct lpfc_iocbq *iocbq)
{
LPFC_MBOXQ_t *mboxq;
struct lpfc_hba *phba = ndlp->phba;
@@ -19859,7 +19858,7 @@
lpfc_resume_rpi(mboxq, ndlp);
if (cmpl) {
mboxq->mbox_cmpl = cmpl;
- mboxq->ctx_buf = arg;
+ mboxq->ctx_u.save_iocb = iocbq;
} else
mboxq->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
mboxq->ctx_ndlp = ndlp;
@@ -20676,7 +20675,7 @@
if (lpfc_sli4_dump_cfg_rg23(phba, mboxq))
goto out;
mqe = &mboxq->u.mqe;
- mp = (struct lpfc_dmabuf *)mboxq->ctx_buf;
+ mp = mboxq->ctx_buf;
rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_POLL);
if (rc)
goto out;
@@ -21035,7 +21034,7 @@
(mb->u.mb.mbxCommand == MBX_REG_VPI))
mb->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
if (mb->u.mb.mbxCommand == MBX_REG_LOGIN64) {
- act_mbx_ndlp = (struct lpfc_nodelist *)mb->ctx_ndlp;
+ act_mbx_ndlp = mb->ctx_ndlp;
/* This reference is local to this routine. The
* reference is removed at routine exit.
@@ -21064,7 +21063,7 @@
mb->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
if (mb->u.mb.mbxCommand == MBX_REG_LOGIN64) {
- ndlp = (struct lpfc_nodelist *)mb->ctx_ndlp;
+ ndlp = mb->ctx_ndlp;
/* Unregister the RPI when mailbox complete */
mb->mbox_flag |= LPFC_MBX_IMED_UNREG;
restart_loop = 1;
@@ -21084,7 +21083,7 @@
while (!list_empty(&mbox_cmd_list)) {
list_remove_head(&mbox_cmd_list, mb, LPFC_MBOXQ_t, list);
if (mb->u.mb.mbxCommand == MBX_REG_LOGIN64) {
- ndlp = (struct lpfc_nodelist *)mb->ctx_ndlp;
+ ndlp = mb->ctx_ndlp;
mb->ctx_ndlp = NULL;
if (ndlp) {
spin_lock(&ndlp->lock);
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index c911a39..cf7c42e 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -1,7 +1,7 @@
/*******************************************************************
* This file is part of the Emulex Linux Device Driver for *
* Fibre Channel Host Bus Adapters. *
- * Copyright (C) 2017-2023 Broadcom. All Rights Reserved. The term *
+ * Copyright (C) 2017-2024 Broadcom. All Rights Reserved. The term *
* “Broadcom” refers to Broadcom Inc. and/or its subsidiaries. *
* Copyright (C) 2004-2016 Emulex. All rights reserved. *
* EMULEX and SLI are trademarks of Emulex. *
@@ -182,11 +182,29 @@
struct lpfc_mqe mqe;
} u;
struct lpfc_vport *vport; /* virtual port pointer */
- void *ctx_ndlp; /* an lpfc_nodelist pointer */
- void *ctx_buf; /* an lpfc_dmabuf pointer */
- void *context3; /* a generic pointer. Code must
- * accommodate the actual datatype.
- */
+ struct lpfc_nodelist *ctx_ndlp; /* caller ndlp pointer */
+ struct lpfc_dmabuf *ctx_buf; /* caller buffer information */
+ void *ext_buf; /* extended buffer for extended mbox
+ * cmds. Not a generic pointer.
+ * Use for storing virtual address.
+ */
+
+ /* Pointers that are seldom used during mbox execution, but require
+ * a saved context.
+ */
+ union {
+ unsigned long ox_rx_id; /* Used in els_rsp_rls_acc */
+ struct lpfc_rdp_context *rdp; /* Used in get_rdp_info */
+ struct lpfc_lcb_context *lcb; /* Used in set_beacon */
+ struct completion *mbox_wait; /* Used in issue_mbox_wait */
+ struct bsg_job_data *dd_data; /* Used in bsg_issue_mbox_cmpl
+ * and
+ * bsg_issue_mbox_ext_handle_job
+ */
+ struct lpfc_iocbq *save_iocb; /* Used in defer_plogi_acc and
+ * lpfc_mbx_cmpl_resume_rpi
+ */
+ } ctx_u;
void (*mbox_cmpl) (struct lpfc_hba *, struct lpfcMboxq *);
uint8_t mbox_flag;
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 2541a8f..c1e9ec0 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -1,7 +1,7 @@
/*******************************************************************
* This file is part of the Emulex Linux Device Driver for *
* Fibre Channel Host Bus Adapters. *
- * Copyright (C) 2017-2023 Broadcom. All Rights Reserved. The term *
+ * Copyright (C) 2017-2024 Broadcom. All Rights Reserved. The term *
* “Broadcom” refers to Broadcom Inc. and/or its subsidiaries. *
* Copyright (C) 2009-2016 Emulex. All rights reserved. *
* EMULEX and SLI are trademarks of Emulex. *
@@ -1118,8 +1118,9 @@
void lpfc_sli4_remove_rpis(struct lpfc_hba *);
void lpfc_sli4_async_event_proc(struct lpfc_hba *);
void lpfc_sli4_fcf_redisc_event_proc(struct lpfc_hba *);
-int lpfc_sli4_resume_rpi(struct lpfc_nodelist *,
- void (*)(struct lpfc_hba *, LPFC_MBOXQ_t *), void *);
+int lpfc_sli4_resume_rpi(struct lpfc_nodelist *ndlp,
+ void (*cmpl)(struct lpfc_hba *, LPFC_MBOXQ_t *),
+ struct lpfc_iocbq *iocbq);
void lpfc_sli4_els_xri_abort_event_proc(struct lpfc_hba *phba);
void lpfc_sli4_nvme_pci_offline_aborted(struct lpfc_hba *phba,
struct lpfc_io_buf *lpfc_ncmd);
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 56f5889..915f2f1 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
* included with this package. *
*******************************************************************/
-#define LPFC_DRIVER_VERSION "14.4.0.0"
+#define LPFC_DRIVER_VERSION "14.4.0.1"
#define LPFC_DRIVER_NAME "lpfc"
/* Used for SLI 2/3 */
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index 0f79840..4439167 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -166,7 +166,7 @@
}
}
- mp = (struct lpfc_dmabuf *)pmb->ctx_buf;
+ mp = pmb->ctx_buf;
memcpy(&vport->fc_sparam, mp->virt, sizeof (struct serv_parm));
memcpy(&vport->fc_nodename, &vport->fc_sparam.nodeName,
sizeof (struct lpfc_name));
@@ -674,10 +674,6 @@
lpfc_free_sysfs_attr(vport);
lpfc_debugfs_terminate(vport);
- /* Remove FC host to break driver binding. */
- fc_remove_host(shost);
- scsi_remove_host(shost);
-
/* Send the DA_ID and Fabric LOGO to cleanup Nameserver entries. */
ndlp = lpfc_findnode_did(vport, Fabric_DID);
if (!ndlp)
@@ -721,6 +717,10 @@
skip_logo:
+ /* Remove FC host to break driver binding. */
+ fc_remove_host(shost);
+ scsi_remove_host(shost);
+
lpfc_cleanup(vport);
/* Remove scsi host now. The nodes are cleaned up. */
diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c
index 0380996..55d590b 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_app.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_app.c
@@ -1644,7 +1644,7 @@
if ((mpirep_offset != 0xFF) &&
drv_bufs[mpirep_offset].bsg_buf_len) {
drv_buf_iter = &drv_bufs[mpirep_offset];
- drv_buf_iter->kern_buf_len = (sizeof(*bsg_reply_buf) - 1 +
+ drv_buf_iter->kern_buf_len = (sizeof(*bsg_reply_buf) +
mrioc->reply_sz);
bsg_reply_buf = kzalloc(drv_buf_iter->kern_buf_len, GFP_KERNEL);
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index e8bcc3a..0614b7e 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -61,7 +61,9 @@
* pmcraid_minor - minor number(s) to use
*/
static unsigned int pmcraid_major;
-static struct class *pmcraid_class;
+static const struct class pmcraid_class = {
+ .name = PMCRAID_DEVFILE,
+};
static DECLARE_BITMAP(pmcraid_minor, PMCRAID_MAX_ADAPTERS);
/*
@@ -4723,7 +4725,7 @@
if (error)
pmcraid_release_minor(minor);
else
- device_create(pmcraid_class, NULL, MKDEV(pmcraid_major, minor),
+ device_create(&pmcraid_class, NULL, MKDEV(pmcraid_major, minor),
NULL, "%s%u", PMCRAID_DEVFILE, minor);
return error;
}
@@ -4739,7 +4741,7 @@
static void pmcraid_release_chrdev(struct pmcraid_instance *pinstance)
{
pmcraid_release_minor(MINOR(pinstance->cdev.dev));
- device_destroy(pmcraid_class,
+ device_destroy(&pmcraid_class,
MKDEV(pmcraid_major, MINOR(pinstance->cdev.dev)));
cdev_del(&pinstance->cdev);
}
@@ -5390,10 +5392,10 @@
}
pmcraid_major = MAJOR(dev);
- pmcraid_class = class_create(PMCRAID_DEVFILE);
- if (IS_ERR(pmcraid_class)) {
- error = PTR_ERR(pmcraid_class);
+ error = class_register(&pmcraid_class);
+
+ if (error) {
pmcraid_err("failed to register with sysfs, error = %x\n",
error);
goto out_unreg_chrdev;
@@ -5402,7 +5404,7 @@
error = pmcraid_netlink_init();
if (error) {
- class_destroy(pmcraid_class);
+ class_unregister(&pmcraid_class);
goto out_unreg_chrdev;
}
@@ -5413,7 +5415,7 @@
pmcraid_err("failed to register pmcraid driver, error = %x\n",
error);
- class_destroy(pmcraid_class);
+ class_unregister(&pmcraid_class);
pmcraid_netlink_release();
out_unreg_chrdev:
@@ -5432,7 +5434,7 @@
unregister_chrdev_region(MKDEV(pmcraid_major, 0),
PMCRAID_MAX_ADAPTERS);
pci_unregister_driver(&pmcraid_driver);
- class_destroy(pmcraid_class);
+ class_unregister(&pmcraid_class);
}
module_init(pmcraid_init);
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 44449c7..76eeba4 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -2741,7 +2741,13 @@
return;
if (unlikely(pci_channel_offline(fcport->vha->hw->pdev))) {
- qla2x00_abort_all_cmds(fcport->vha, DID_NO_CONNECT << 16);
+ /* Will wait for wind down of adapter */
+ ql_dbg(ql_dbg_aer, fcport->vha, 0x900c,
+ "%s pci offline detected (id %06x)\n", __func__,
+ fcport->d_id.b24);
+ qla_pci_set_eeh_busy(fcport->vha);
+ qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24,
+ 0, WAIT_TARGET);
return;
}
}
@@ -2763,7 +2769,11 @@
vha = fcport->vha;
if (unlikely(pci_channel_offline(fcport->vha->hw->pdev))) {
- qla2x00_abort_all_cmds(fcport->vha, DID_NO_CONNECT << 16);
+ /* Will wait for wind down of adapter */
+ ql_dbg(ql_dbg_aer, fcport->vha, 0x900b,
+ "%s pci offline detected (id %06x)\n", __func__,
+ fcport->d_id.b24);
+ qla_pci_set_eeh_busy(vha);
qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24,
0, WAIT_TARGET);
return;
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index deb6426..2f49baf 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -82,7 +82,7 @@
#include "qla_nvme.h"
#define QLA2XXX_DRIVER_NAME "qla2xxx"
#define QLA2XXX_APIDEV "ql2xapidev"
-#define QLA2XXX_MANUFACTURER "Marvell Semiconductor, Inc."
+#define QLA2XXX_MANUFACTURER "Marvell"
/*
* We have MAILBOX_REGISTER_COUNT sized arrays in a few places,
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index 09cb941..7309310 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -44,7 +44,7 @@
extern int qla2x00_local_device_login(scsi_qla_host_t *, fc_port_t *);
extern int qla24xx_els_dcmd_iocb(scsi_qla_host_t *, int, port_id_t);
-extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *, bool);
+extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *);
extern void qla2x00_els_dcmd2_free(scsi_qla_host_t *vha,
struct els_plogi *els_plogi);
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index a314cfc5..8377624 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -1193,8 +1193,12 @@
return rval;
done_free_sp:
- /* ref: INIT */
- kref_put(&sp->cmd_kref, qla2x00_sp_release);
+ /*
+ * use qla24xx_async_gnl_sp_done to purge all pending gnl request.
+ * kref_put is call behind the scene.
+ */
+ sp->u.iocb_cmd.u.mbx.in_mb[0] = MBS_COMMAND_ERROR;
+ qla24xx_async_gnl_sp_done(sp, QLA_COMMAND_ERROR);
fcport->flags &= ~(FCF_ASYNC_SENT);
done:
fcport->flags &= ~(FCF_ASYNC_ACTIVE);
@@ -2665,6 +2669,40 @@
return rval;
}
+static void qla_enable_fce_trace(scsi_qla_host_t *vha)
+{
+ int rval;
+ struct qla_hw_data *ha = vha->hw;
+
+ if (ha->fce) {
+ ha->flags.fce_enabled = 1;
+ memset(ha->fce, 0, fce_calc_size(ha->fce_bufs));
+ rval = qla2x00_enable_fce_trace(vha,
+ ha->fce_dma, ha->fce_bufs, ha->fce_mb, &ha->fce_bufs);
+
+ if (rval) {
+ ql_log(ql_log_warn, vha, 0x8033,
+ "Unable to reinitialize FCE (%d).\n", rval);
+ ha->flags.fce_enabled = 0;
+ }
+ }
+}
+
+static void qla_enable_eft_trace(scsi_qla_host_t *vha)
+{
+ int rval;
+ struct qla_hw_data *ha = vha->hw;
+
+ if (ha->eft) {
+ memset(ha->eft, 0, EFT_SIZE);
+ rval = qla2x00_enable_eft_trace(vha, ha->eft_dma, EFT_NUM_BUFFERS);
+
+ if (rval) {
+ ql_log(ql_log_warn, vha, 0x8034,
+ "Unable to reinitialize EFT (%d).\n", rval);
+ }
+ }
+}
/*
* qla2x00_initialize_adapter
* Initialize board.
@@ -3668,9 +3706,8 @@
}
static void
-qla2x00_init_fce_trace(scsi_qla_host_t *vha)
+qla2x00_alloc_fce_trace(scsi_qla_host_t *vha)
{
- int rval;
dma_addr_t tc_dma;
void *tc;
struct qla_hw_data *ha = vha->hw;
@@ -3699,27 +3736,17 @@
return;
}
- rval = qla2x00_enable_fce_trace(vha, tc_dma, FCE_NUM_BUFFERS,
- ha->fce_mb, &ha->fce_bufs);
- if (rval) {
- ql_log(ql_log_warn, vha, 0x00bf,
- "Unable to initialize FCE (%d).\n", rval);
- dma_free_coherent(&ha->pdev->dev, FCE_SIZE, tc, tc_dma);
- return;
- }
-
ql_dbg(ql_dbg_init, vha, 0x00c0,
"Allocated (%d KB) for FCE...\n", FCE_SIZE / 1024);
- ha->flags.fce_enabled = 1;
ha->fce_dma = tc_dma;
ha->fce = tc;
+ ha->fce_bufs = FCE_NUM_BUFFERS;
}
static void
-qla2x00_init_eft_trace(scsi_qla_host_t *vha)
+qla2x00_alloc_eft_trace(scsi_qla_host_t *vha)
{
- int rval;
dma_addr_t tc_dma;
void *tc;
struct qla_hw_data *ha = vha->hw;
@@ -3744,14 +3771,6 @@
return;
}
- rval = qla2x00_enable_eft_trace(vha, tc_dma, EFT_NUM_BUFFERS);
- if (rval) {
- ql_log(ql_log_warn, vha, 0x00c2,
- "Unable to initialize EFT (%d).\n", rval);
- dma_free_coherent(&ha->pdev->dev, EFT_SIZE, tc, tc_dma);
- return;
- }
-
ql_dbg(ql_dbg_init, vha, 0x00c3,
"Allocated (%d KB) EFT ...\n", EFT_SIZE / 1024);
@@ -3759,13 +3778,6 @@
ha->eft = tc;
}
-static void
-qla2x00_alloc_offload_mem(scsi_qla_host_t *vha)
-{
- qla2x00_init_fce_trace(vha);
- qla2x00_init_eft_trace(vha);
-}
-
void
qla2x00_alloc_fw_dump(scsi_qla_host_t *vha)
{
@@ -3820,10 +3832,10 @@
if (ha->tgt.atio_ring)
mq_size += ha->tgt.atio_q_length * sizeof(request_t);
- qla2x00_init_fce_trace(vha);
+ qla2x00_alloc_fce_trace(vha);
if (ha->fce)
fce_size = sizeof(struct qla2xxx_fce_chain) + FCE_SIZE;
- qla2x00_init_eft_trace(vha);
+ qla2x00_alloc_eft_trace(vha);
if (ha->eft)
eft_size = EFT_SIZE;
}
@@ -4253,7 +4265,6 @@
struct qla_hw_data *ha = vha->hw;
struct device_reg_2xxx __iomem *reg = &ha->iobase->isp;
unsigned long flags;
- uint16_t fw_major_version;
int done_once = 0;
if (IS_P3P_TYPE(ha)) {
@@ -4320,7 +4331,6 @@
goto failed;
enable_82xx_npiv:
- fw_major_version = ha->fw_major_version;
if (IS_P3P_TYPE(ha))
qla82xx_check_md_needed(vha);
else
@@ -4349,12 +4359,11 @@
if (rval != QLA_SUCCESS)
goto failed;
- if (!fw_major_version && !(IS_P3P_TYPE(ha)))
- qla2x00_alloc_offload_mem(vha);
-
if (ql2xallocfwdump && !(IS_P3P_TYPE(ha)))
qla2x00_alloc_fw_dump(vha);
+ qla_enable_fce_trace(vha);
+ qla_enable_eft_trace(vha);
} else {
goto failed;
}
@@ -7487,12 +7496,12 @@
int
qla2x00_abort_isp(scsi_qla_host_t *vha)
{
- int rval;
uint8_t status = 0;
struct qla_hw_data *ha = vha->hw;
struct scsi_qla_host *vp, *tvp;
struct req_que *req = ha->req_q_map[0];
unsigned long flags;
+ fc_port_t *fcport;
if (vha->flags.online) {
qla2x00_abort_isp_cleanup(vha);
@@ -7561,6 +7570,15 @@
"ISP Abort - ISP reg disconnect post nvmram config, exiting.\n");
return status;
}
+
+ /* User may have updated [fcp|nvme] prefer in flash */
+ list_for_each_entry(fcport, &vha->vp_fcports, list) {
+ if (NVME_PRIORITY(ha, fcport))
+ fcport->do_prli_nvme = 1;
+ else
+ fcport->do_prli_nvme = 0;
+ }
+
if (!qla2x00_restart_isp(vha)) {
clear_bit(RESET_MARKER_NEEDED, &vha->dpc_flags);
@@ -7581,31 +7599,7 @@
if (IS_QLA81XX(ha) || IS_QLA8031(ha))
qla2x00_get_fw_version(vha);
- if (ha->fce) {
- ha->flags.fce_enabled = 1;
- memset(ha->fce, 0,
- fce_calc_size(ha->fce_bufs));
- rval = qla2x00_enable_fce_trace(vha,
- ha->fce_dma, ha->fce_bufs, ha->fce_mb,
- &ha->fce_bufs);
- if (rval) {
- ql_log(ql_log_warn, vha, 0x8033,
- "Unable to reinitialize FCE "
- "(%d).\n", rval);
- ha->flags.fce_enabled = 0;
- }
- }
- if (ha->eft) {
- memset(ha->eft, 0, EFT_SIZE);
- rval = qla2x00_enable_eft_trace(vha,
- ha->eft_dma, EFT_NUM_BUFFERS);
- if (rval) {
- ql_log(ql_log_warn, vha, 0x8034,
- "Unable to reinitialize EFT "
- "(%d).\n", rval);
- }
- }
} else { /* failed the ISP abort */
vha->flags.online = 1;
if (test_bit(ISP_ABORT_RETRY, &vha->dpc_flags)) {
@@ -7655,6 +7649,14 @@
atomic_inc(&vp->vref_count);
spin_unlock_irqrestore(&ha->vport_slock, flags);
+ /* User may have updated [fcp|nvme] prefer in flash */
+ list_for_each_entry(fcport, &vp->vp_fcports, list) {
+ if (NVME_PRIORITY(ha, fcport))
+ fcport->do_prli_nvme = 1;
+ else
+ fcport->do_prli_nvme = 0;
+ }
+
qla2x00_vp_abort_isp(vp);
spin_lock_irqsave(&ha->vport_slock, flags);
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index df90169..0b41e8a 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2587,6 +2587,33 @@
qla2x00_sp_release(struct kref *kref)
{
struct srb *sp = container_of(kref, struct srb, cmd_kref);
+ struct scsi_qla_host *vha = sp->vha;
+
+ switch (sp->type) {
+ case SRB_CT_PTHRU_CMD:
+ /* GPSC & GFPNID use fcport->ct_desc.ct_sns for both req & rsp */
+ if (sp->u.iocb_cmd.u.ctarg.req &&
+ (!sp->fcport ||
+ sp->u.iocb_cmd.u.ctarg.req != sp->fcport->ct_desc.ct_sns)) {
+ dma_free_coherent(&vha->hw->pdev->dev,
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size,
+ sp->u.iocb_cmd.u.ctarg.req,
+ sp->u.iocb_cmd.u.ctarg.req_dma);
+ sp->u.iocb_cmd.u.ctarg.req = NULL;
+ }
+ if (sp->u.iocb_cmd.u.ctarg.rsp &&
+ (!sp->fcport ||
+ sp->u.iocb_cmd.u.ctarg.rsp != sp->fcport->ct_desc.ct_sns)) {
+ dma_free_coherent(&vha->hw->pdev->dev,
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
+ sp->u.iocb_cmd.u.ctarg.rsp,
+ sp->u.iocb_cmd.u.ctarg.rsp_dma);
+ sp->u.iocb_cmd.u.ctarg.rsp = NULL;
+ }
+ break;
+ default:
+ break;
+ }
sp->free(sp);
}
@@ -2610,7 +2637,8 @@
{
struct srb_iocb *elsio = &sp->u.iocb_cmd;
- kfree(sp->fcport);
+ if (sp->fcport)
+ qla2x00_free_fcport(sp->fcport);
if (elsio->u.els_logo.els_logo_pyld)
dma_free_coherent(&sp->vha->hw->pdev->dev, DMA_POOL_SIZE,
@@ -2692,7 +2720,7 @@
*/
sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL);
if (!sp) {
- kfree(fcport);
+ qla2x00_free_fcport(fcport);
ql_log(ql_log_info, vha, 0x70e6,
"SRB allocation failed\n");
return -ENOMEM;
@@ -2723,6 +2751,7 @@
if (!elsio->u.els_logo.els_logo_pyld) {
/* ref: INIT */
kref_put(&sp->cmd_kref, qla2x00_sp_release);
+ qla2x00_free_fcport(fcport);
return QLA_FUNCTION_FAILED;
}
@@ -2747,6 +2776,7 @@
if (rval != QLA_SUCCESS) {
/* ref: INIT */
kref_put(&sp->cmd_kref, qla2x00_sp_release);
+ qla2x00_free_fcport(fcport);
return QLA_FUNCTION_FAILED;
}
@@ -3012,7 +3042,7 @@
int
qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
- fc_port_t *fcport, bool wait)
+ fc_port_t *fcport)
{
srb_t *sp;
struct srb_iocb *elsio = NULL;
@@ -3027,8 +3057,7 @@
if (!sp) {
ql_log(ql_log_info, vha, 0x70e6,
"SRB allocation failed\n");
- fcport->flags &= ~FCF_ASYNC_ACTIVE;
- return -ENOMEM;
+ goto done;
}
fcport->flags |= FCF_ASYNC_SENT;
@@ -3037,9 +3066,6 @@
ql_dbg(ql_dbg_io, vha, 0x3073,
"%s Enter: PLOGI portid=%06x\n", __func__, fcport->d_id.b24);
- if (wait)
- sp->flags = SRB_WAKEUP_ON_COMP;
-
sp->type = SRB_ELS_DCMD;
sp->name = "ELS_DCMD";
sp->fcport = fcport;
@@ -3055,7 +3081,7 @@
if (!elsio->u.els_plogi.els_plogi_pyld) {
rval = QLA_FUNCTION_FAILED;
- goto out;
+ goto done_free_sp;
}
resp_ptr = elsio->u.els_plogi.els_resp_pyld =
@@ -3064,7 +3090,7 @@
if (!elsio->u.els_plogi.els_resp_pyld) {
rval = QLA_FUNCTION_FAILED;
- goto out;
+ goto done_free_sp;
}
ql_dbg(ql_dbg_io, vha, 0x3073, "PLOGI %p %p\n", ptr, resp_ptr);
@@ -3080,7 +3106,6 @@
if (els_opcode == ELS_DCMD_PLOGI && DBELL_ACTIVE(vha)) {
struct fc_els_flogi *p = ptr;
-
p->fl_csp.sp_features |= cpu_to_be16(FC_SP_FT_SEC);
}
@@ -3089,10 +3114,11 @@
(uint8_t *)elsio->u.els_plogi.els_plogi_pyld,
sizeof(*elsio->u.els_plogi.els_plogi_pyld));
- init_completion(&elsio->u.els_plogi.comp);
rval = qla2x00_start_sp(sp);
if (rval != QLA_SUCCESS) {
- rval = QLA_FUNCTION_FAILED;
+ fcport->flags |= FCF_LOGIN_NEEDED;
+ set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+ goto done_free_sp;
} else {
ql_dbg(ql_dbg_disc, vha, 0x3074,
"%s PLOGI sent, hdl=%x, loopid=%x, to port_id %06x from port_id %06x\n",
@@ -3100,21 +3126,15 @@
fcport->d_id.b24, vha->d_id.b24);
}
- if (wait) {
- wait_for_completion(&elsio->u.els_plogi.comp);
+ return rval;
- if (elsio->u.els_plogi.comp_status != CS_COMPLETE)
- rval = QLA_FUNCTION_FAILED;
- } else {
- goto done;
- }
-
-out:
- fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
+done_free_sp:
qla2x00_els_dcmd2_free(vha, &elsio->u.els_plogi);
/* ref: INIT */
kref_put(&sp->cmd_kref, qla2x00_sp_release);
done:
+ fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
+ qla2x00_set_fcport_disc_state(fcport, DSC_DELETED);
return rval;
}
@@ -3918,7 +3938,7 @@
return -EAGAIN;
}
- pkt = __qla2x00_alloc_iocbs(sp->qpair, sp);
+ pkt = qla2x00_alloc_iocbs_ready(sp->qpair, sp);
if (!pkt) {
rval = -EAGAIN;
ql_log(ql_log_warn, vha, 0x700c,
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 21ec32b..0cd6f3e 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -194,7 +194,7 @@
if (ha->flags.purge_mbox || chip_reset != ha->chip_reset ||
ha->flags.eeh_busy) {
ql_log(ql_log_warn, vha, 0xd035,
- "Error detected: purge[%d] eeh[%d] cmd=0x%x, Exiting.\n",
+ "Purge mbox: purge[%d] eeh[%d] cmd=0x%x, Exiting.\n",
ha->flags.purge_mbox, ha->flags.eeh_busy, mcp->mb[0]);
rval = QLA_ABORTED;
goto premature_exit;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index dd67437..1e2f522 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -4602,6 +4602,7 @@
ha->init_cb_dma = 0;
fail_free_vp_map:
kfree(ha->vp_map);
+ ha->vp_map = NULL;
fail:
ql_log(ql_log_fatal, NULL, 0x0030,
"Memory allocation failure.\n");
@@ -5583,7 +5584,7 @@
break;
case QLA_EVT_ELS_PLOGI:
qla24xx_els_dcmd2_iocb(vha, ELS_DCMD_PLOGI,
- e->u.fcport.fcport, false);
+ e->u.fcport.fcport);
break;
case QLA_EVT_SA_REPLACE:
rc = qla24xx_issue_sa_replace_iocb(vha, e);
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 2ef2dba..d7551b1 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1062,6 +1062,16 @@
"%s: sess %p logout completed\n", __func__, sess);
}
+ /* check for any straggling io left behind */
+ if (!(sess->flags & FCF_FCP2_DEVICE) &&
+ qla2x00_eh_wait_for_pending_commands(sess->vha, sess->d_id.b24, 0, WAIT_TARGET)) {
+ ql_log(ql_log_warn, vha, 0x3027,
+ "IO not return. Resetting.\n");
+ set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags);
+ qla2xxx_wake_dpc(vha);
+ qla2x00_wait_for_chip_reset(vha);
+ }
+
if (sess->logo_ack_needed) {
sess->logo_ack_needed = 0;
qla24xx_async_notify_ack(vha, sess,
diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h
index d903563..7627fd8 100644
--- a/drivers/scsi/qla2xxx/qla_version.h
+++ b/drivers/scsi/qla2xxx/qla_version.h
@@ -6,9 +6,9 @@
/*
* Driver version
*/
-#define QLA2XXX_VERSION "10.02.09.100-k"
+#define QLA2XXX_VERSION "10.02.09.200-k"
#define QLA_DRIVER_MAJOR_VER 10
#define QLA_DRIVER_MINOR_VER 2
#define QLA_DRIVER_PATCH_VER 9
-#define QLA_DRIVER_BETA_VER 100
+#define QLA_DRIVER_BETA_VER 200
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 8d06475..ffd7e7e 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -1642,6 +1642,40 @@
}
EXPORT_SYMBOL(scsi_add_device);
+int scsi_resume_device(struct scsi_device *sdev)
+{
+ struct device *dev = &sdev->sdev_gendev;
+ int ret = 0;
+
+ device_lock(dev);
+
+ /*
+ * Bail out if the device or its queue are not running. Otherwise,
+ * the rescan may block waiting for commands to be executed, with us
+ * holding the device lock. This can result in a potential deadlock
+ * in the power management core code when system resume is on-going.
+ */
+ if (sdev->sdev_state != SDEV_RUNNING ||
+ blk_queue_pm_only(sdev->request_queue)) {
+ ret = -EWOULDBLOCK;
+ goto unlock;
+ }
+
+ if (dev->driver && try_module_get(dev->driver->owner)) {
+ struct scsi_driver *drv = to_scsi_driver(dev->driver);
+
+ if (drv->resume)
+ ret = drv->resume(dev);
+ module_put(dev->driver->owner);
+ }
+
+unlock:
+ device_unlock(dev);
+
+ return ret;
+}
+EXPORT_SYMBOL(scsi_resume_device);
+
int scsi_rescan_device(struct scsi_device *sdev)
{
struct device *dev = &sdev->sdev_gendev;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index ccff8f2..3cf8986 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -4108,7 +4108,21 @@
return sd_suspend_common(dev, true);
}
-static int sd_resume(struct device *dev, bool runtime)
+static int sd_resume(struct device *dev)
+{
+ struct scsi_disk *sdkp = dev_get_drvdata(dev);
+
+ sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
+
+ if (opal_unlock_from_suspend(sdkp->opal_dev)) {
+ sd_printk(KERN_NOTICE, sdkp, "OPAL unlock failed\n");
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static int sd_resume_common(struct device *dev, bool runtime)
{
struct scsi_disk *sdkp = dev_get_drvdata(dev);
int ret;
@@ -4124,7 +4138,7 @@
sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
ret = sd_start_stop_device(sdkp, 1);
if (!ret) {
- opal_unlock_from_suspend(sdkp->opal_dev);
+ sd_resume(dev);
sdkp->suspended = false;
}
@@ -4143,7 +4157,7 @@
return 0;
}
- return sd_resume(dev, false);
+ return sd_resume_common(dev, false);
}
static int sd_resume_runtime(struct device *dev)
@@ -4170,7 +4184,7 @@
"Failed to clear sense data\n");
}
- return sd_resume(dev, true);
+ return sd_resume_common(dev, true);
}
static const struct dev_pm_ops sd_pm_ops = {
@@ -4193,6 +4207,7 @@
.pm = &sd_pm_ops,
},
.rescan = sd_rescan,
+ .resume = sd_resume,
.init_command = sd_init_command,
.uninit_command = sd_uninit_command,
.done = sd_done,
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 86210e4..386981c6 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1424,7 +1424,9 @@
.llseek = no_llseek,
};
-static struct class *sg_sysfs_class;
+static const struct class sg_sysfs_class = {
+ .name = "scsi_generic"
+};
static int sg_sysfs_valid = 0;
@@ -1526,7 +1528,7 @@
if (sg_sysfs_valid) {
struct device *sg_class_member;
- sg_class_member = device_create(sg_sysfs_class, cl_dev->parent,
+ sg_class_member = device_create(&sg_sysfs_class, cl_dev->parent,
MKDEV(SCSI_GENERIC_MAJOR,
sdp->index),
sdp, "%s", sdp->name);
@@ -1616,7 +1618,7 @@
read_unlock_irqrestore(&sdp->sfd_lock, iflags);
sysfs_remove_link(&scsidp->sdev_gendev.kobj, "generic");
- device_destroy(sg_sysfs_class, MKDEV(SCSI_GENERIC_MAJOR, sdp->index));
+ device_destroy(&sg_sysfs_class, MKDEV(SCSI_GENERIC_MAJOR, sdp->index));
cdev_del(sdp->cdev);
sdp->cdev = NULL;
@@ -1687,11 +1689,9 @@
SG_MAX_DEVS, "sg");
if (rc)
return rc;
- sg_sysfs_class = class_create("scsi_generic");
- if ( IS_ERR(sg_sysfs_class) ) {
- rc = PTR_ERR(sg_sysfs_class);
+ rc = class_register(&sg_sysfs_class);
+ if (rc)
goto err_out;
- }
sg_sysfs_valid = 1;
rc = scsi_register_interface(&sg_interface);
if (0 == rc) {
@@ -1700,7 +1700,7 @@
#endif /* CONFIG_SCSI_PROC_FS */
return 0;
}
- class_destroy(sg_sysfs_class);
+ class_unregister(&sg_sysfs_class);
register_sg_sysctls();
err_out:
unregister_chrdev_region(MKDEV(SCSI_GENERIC_MAJOR, 0), SG_MAX_DEVS);
@@ -1715,7 +1715,7 @@
remove_proc_subtree("scsi/sg", NULL);
#endif /* CONFIG_SCSI_PROC_FS */
scsi_unregister_interface(&sg_interface);
- class_destroy(sg_sysfs_class);
+ class_unregister(&sg_sysfs_class);
sg_sysfs_valid = 0;
unregister_chrdev_region(MKDEV(SCSI_GENERIC_MAJOR, 0),
SG_MAX_DEVS);
@@ -2207,6 +2207,7 @@
{
struct sg_fd *sfp = container_of(work, struct sg_fd, ew.work);
struct sg_device *sdp = sfp->parentdp;
+ struct scsi_device *device = sdp->device;
Sg_request *srp;
unsigned long iflags;
@@ -2232,8 +2233,9 @@
"sg_remove_sfp: sfp=0x%p\n", sfp));
kfree(sfp);
- scsi_device_put(sdp->device);
+ WARN_ON_ONCE(kref_read(&sdp->d_ref) != 1);
kref_put(&sdp->d_ref, sg_device_destroy);
+ scsi_device_put(device);
module_put(THIS_MODULE);
}
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 338aa8c..5a9bcf8 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -87,7 +87,7 @@
static int try_wdio = 1;
static int debug_flag;
-static struct class st_sysfs_class;
+static const struct class st_sysfs_class;
static const struct attribute_group *st_dev_groups[];
static const struct attribute_group *st_drv_groups[];
@@ -4438,7 +4438,7 @@
return;
}
-static struct class st_sysfs_class = {
+static const struct class st_sysfs_class = {
.name = "scsi_tape",
.dev_groups = st_dev_groups,
};
diff --git a/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c b/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c
index 258aa0e..4c3684d 100644
--- a/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c
+++ b/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c
@@ -937,8 +937,9 @@
/* build component create message */
m.h.type = MMAL_MSG_TYPE_COMPONENT_CREATE;
m.u.component_create.client_component = component->client_component;
- strncpy(m.u.component_create.name, name,
- sizeof(m.u.component_create.name));
+ strscpy_pad(m.u.component_create.name, name,
+ sizeof(m.u.component_create.name));
+ m.u.component_create.pid = 0;
ret = send_synchronous_mmal_msg(instance, &m,
sizeof(m.u.component_create),
diff --git a/drivers/target/iscsi/iscsi_target_erl1.c b/drivers/target/iscsi/iscsi_target_erl1.c
index 6797200..d9a6242 100644
--- a/drivers/target/iscsi/iscsi_target_erl1.c
+++ b/drivers/target/iscsi/iscsi_target_erl1.c
@@ -583,7 +583,7 @@
struct iscsi_pdu *pdu)
{
int i, send_recovery_r2t = 0, recovery = 0;
- u32 length = 0, offset = 0, pdu_count = 0, xfer_len = 0;
+ u32 length = 0, offset = 0, pdu_count = 0;
struct iscsit_conn *conn = cmd->conn;
struct iscsi_pdu *first_pdu = NULL;
@@ -596,7 +596,6 @@
if (cmd->pdu_list[i].seq_no == pdu->seq_no) {
if (!first_pdu)
first_pdu = &cmd->pdu_list[i];
- xfer_len += cmd->pdu_list[i].length;
pdu_count++;
} else if (pdu_count)
break;
diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
index 50dec24..8fd7cf1 100644
--- a/drivers/thermal/devfreq_cooling.c
+++ b/drivers/thermal/devfreq_cooling.c
@@ -214,7 +214,7 @@
res = dfc->power_ops->get_real_power(df, power, freq, voltage);
if (!res) {
- state = dfc->capped_state;
+ state = dfc->max_state - dfc->capped_state;
/* Convert EM power into milli-Watts first */
rcu_read_lock();
diff --git a/drivers/thermal/thermal_trip.c b/drivers/thermal/thermal_trip.c
index 09f6050..497abf0 100644
--- a/drivers/thermal/thermal_trip.c
+++ b/drivers/thermal/thermal_trip.c
@@ -65,7 +65,6 @@
{
const struct thermal_trip *trip;
int low = -INT_MAX, high = INT_MAX;
- bool same_trip = false;
int ret;
lockdep_assert_held(&tz->lock);
@@ -74,36 +73,22 @@
return;
for_each_trip(tz, trip) {
- bool low_set = false;
int trip_low;
trip_low = trip->temperature - trip->hysteresis;
- if (trip_low < tz->temperature && trip_low > low) {
+ if (trip_low < tz->temperature && trip_low > low)
low = trip_low;
- low_set = true;
- same_trip = false;
- }
if (trip->temperature > tz->temperature &&
- trip->temperature < high) {
+ trip->temperature < high)
high = trip->temperature;
- same_trip = low_set;
- }
}
/* No need to change trip points */
if (tz->prev_low_trip == low && tz->prev_high_trip == high)
return;
- /*
- * If "high" and "low" are the same, skip the change unless this is the
- * first time.
- */
- if (same_trip && (tz->prev_low_trip != -INT_MAX ||
- tz->prev_high_trip != INT_MAX))
- return;
-
tz->prev_low_trip = low;
tz->prev_high_trip = high;
diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 8db81f1..768bf87 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -94,7 +94,7 @@
val = ufshcd_readl(hba, REG_UFS_MCQ_CFG);
val &= ~MCQ_CFG_MAC_MASK;
- val |= FIELD_PREP(MCQ_CFG_MAC_MASK, max_active_cmds);
+ val |= FIELD_PREP(MCQ_CFG_MAC_MASK, max_active_cmds - 1);
ufshcd_writel(hba, val, REG_UFS_MCQ_CFG);
}
EXPORT_SYMBOL_GPL(ufshcd_mcq_config_mac);
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 8d68bd2..06859e1 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -1210,8 +1210,10 @@
list_for_each_entry(clki, head, list) {
if (!IS_ERR_OR_NULL(clki->clk) &&
- !strcmp(clki->name, "core_clk_unipro")) {
- if (is_scale_up)
+ !strcmp(clki->name, "core_clk_unipro")) {
+ if (!clki->max_freq)
+ cycles_in_1us = 150; /* default for backwards compatibility */
+ else if (is_scale_up)
cycles_in_1us = ceil(clki->max_freq, (1000 * 1000));
else
cycles_in_1us = ceil(clk_get_rate(clki->clk), (1000 * 1000));
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index c553dec..c8262e2 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -485,6 +485,7 @@
static int service_outstanding_interrupt(struct wdm_device *desc)
{
int rv = 0;
+ int used;
/* submit read urb only if the device is waiting for it */
if (!desc->resp_count || !--desc->resp_count)
@@ -499,7 +500,10 @@
goto out;
}
- set_bit(WDM_RESPONDING, &desc->flags);
+ used = test_and_set_bit(WDM_RESPONDING, &desc->flags);
+ if (used)
+ goto out;
+
spin_unlock_irq(&desc->iuspin);
rv = usb_submit_urb(desc->response, GFP_KERNEL);
spin_lock_irq(&desc->iuspin);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 3ee8455..9446660 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -130,7 +130,6 @@
#define HUB_DEBOUNCE_STEP 25
#define HUB_DEBOUNCE_STABLE 100
-static void hub_release(struct kref *kref);
static int usb_reset_and_verify_device(struct usb_device *udev);
static int hub_port_disable(struct usb_hub *hub, int port1, int set_state);
static bool hub_port_warm_reset_required(struct usb_hub *hub, int port1,
@@ -720,14 +719,14 @@
*/
intf = to_usb_interface(hub->intfdev);
usb_autopm_get_interface_no_resume(intf);
- kref_get(&hub->kref);
+ hub_get(hub);
if (queue_work(hub_wq, &hub->events))
return;
/* the work has already been scheduled */
usb_autopm_put_interface_async(intf);
- kref_put(&hub->kref, hub_release);
+ hub_put(hub);
}
void usb_kick_hub_wq(struct usb_device *hdev)
@@ -1095,7 +1094,7 @@
goto init2;
goto init3;
}
- kref_get(&hub->kref);
+ hub_get(hub);
/* The superspeed hub except for root hub has to use Hub Depth
* value as an offset into the route string to locate the bits
@@ -1343,7 +1342,7 @@
device_unlock(&hdev->dev);
}
- kref_put(&hub->kref, hub_release);
+ hub_put(hub);
}
/* Implement the continuations for the delays above */
@@ -1759,6 +1758,16 @@
kfree(hub);
}
+void hub_get(struct usb_hub *hub)
+{
+ kref_get(&hub->kref);
+}
+
+void hub_put(struct usb_hub *hub)
+{
+ kref_put(&hub->kref, hub_release);
+}
+
static unsigned highspeed_hubs;
static void hub_disconnect(struct usb_interface *intf)
@@ -1807,7 +1816,7 @@
onboard_hub_destroy_pdevs(&hub->onboard_hub_devs);
- kref_put(&hub->kref, hub_release);
+ hub_put(hub);
}
static bool hub_descriptor_is_sane(struct usb_host_interface *desc)
@@ -5934,7 +5943,7 @@
/* Balance the stuff in kick_hub_wq() and allow autosuspend */
usb_autopm_put_interface(intf);
- kref_put(&hub->kref, hub_release);
+ hub_put(hub);
kcov_remote_stop();
}
diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h
index 43ce21c..183b69d 100644
--- a/drivers/usb/core/hub.h
+++ b/drivers/usb/core/hub.h
@@ -129,6 +129,8 @@
extern int usb_hub_set_port_power(struct usb_device *hdev, struct usb_hub *hub,
int port1, bool set);
extern struct usb_hub *usb_hub_to_struct_hub(struct usb_device *hdev);
+extern void hub_get(struct usb_hub *hub);
+extern void hub_put(struct usb_hub *hub);
extern int hub_port_debounce(struct usb_hub *hub, int port1,
bool must_be_connected);
extern int usb_clear_port_feature(struct usb_device *hdev,
diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c
index 5b5e613..686c01a 100644
--- a/drivers/usb/core/port.c
+++ b/drivers/usb/core/port.c
@@ -56,11 +56,22 @@
u16 portstatus, unused;
bool disabled;
int rc;
+ struct kernfs_node *kn;
+ hub_get(hub);
rc = usb_autopm_get_interface(intf);
if (rc < 0)
- return rc;
+ goto out_hub_get;
+ /*
+ * Prevent deadlock if another process is concurrently
+ * trying to unregister hdev.
+ */
+ kn = sysfs_break_active_protection(&dev->kobj, &attr->attr);
+ if (!kn) {
+ rc = -ENODEV;
+ goto out_autopm;
+ }
usb_lock_device(hdev);
if (hub->disconnected) {
rc = -ENODEV;
@@ -70,9 +81,13 @@
usb_hub_port_status(hub, port1, &portstatus, &unused);
disabled = !usb_port_is_power_on(hub, portstatus);
-out_hdev_lock:
+ out_hdev_lock:
usb_unlock_device(hdev);
+ sysfs_unbreak_active_protection(kn);
+ out_autopm:
usb_autopm_put_interface(intf);
+ out_hub_get:
+ hub_put(hub);
if (rc)
return rc;
@@ -90,15 +105,26 @@
int port1 = port_dev->portnum;
bool disabled;
int rc;
+ struct kernfs_node *kn;
rc = kstrtobool(buf, &disabled);
if (rc)
return rc;
+ hub_get(hub);
rc = usb_autopm_get_interface(intf);
if (rc < 0)
- return rc;
+ goto out_hub_get;
+ /*
+ * Prevent deadlock if another process is concurrently
+ * trying to unregister hdev.
+ */
+ kn = sysfs_break_active_protection(&dev->kobj, &attr->attr);
+ if (!kn) {
+ rc = -ENODEV;
+ goto out_autopm;
+ }
usb_lock_device(hdev);
if (hub->disconnected) {
rc = -ENODEV;
@@ -119,9 +145,13 @@
if (!rc)
rc = count;
-out_hdev_lock:
+ out_hdev_lock:
usb_unlock_device(hdev);
+ sysfs_unbreak_active_protection(kn);
+ out_autopm:
usb_autopm_put_interface(intf);
+ out_hub_get:
+ hub_put(hub);
return rc;
}
diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c
index f98263e..d83231d 100644
--- a/drivers/usb/core/sysfs.c
+++ b/drivers/usb/core/sysfs.c
@@ -1217,14 +1217,24 @@
{
struct usb_interface *intf = to_usb_interface(dev);
bool val;
+ struct kernfs_node *kn;
if (kstrtobool(buf, &val) != 0)
return -EINVAL;
- if (val)
+ if (val) {
usb_authorize_interface(intf);
- else
- usb_deauthorize_interface(intf);
+ } else {
+ /*
+ * Prevent deadlock if another process is concurrently
+ * trying to unregister intf.
+ */
+ kn = sysfs_break_active_protection(&dev->kobj, &attr->attr);
+ if (kn) {
+ usb_deauthorize_interface(intf);
+ sysfs_unbreak_active_protection(kn);
+ }
+ }
return count;
}
diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h
index c92a1da..a141f83 100644
--- a/drivers/usb/dwc2/core.h
+++ b/drivers/usb/dwc2/core.h
@@ -729,8 +729,14 @@
* struct dwc2_hregs_backup - Holds host registers state before
* entering partial power down
* @hcfg: Backup of HCFG register
+ * @hflbaddr: Backup of HFLBADDR register
* @haintmsk: Backup of HAINTMSK register
+ * @hcchar: Backup of HCCHAR register
+ * @hcsplt: Backup of HCSPLT register
* @hcintmsk: Backup of HCINTMSK register
+ * @hctsiz: Backup of HCTSIZ register
+ * @hdma: Backup of HCDMA register
+ * @hcdmab: Backup of HCDMAB register
* @hprt0: Backup of HPTR0 register
* @hfir: Backup of HFIR register
* @hptxfsiz: Backup of HPTXFSIZ register
@@ -738,8 +744,14 @@
*/
struct dwc2_hregs_backup {
u32 hcfg;
+ u32 hflbaddr;
u32 haintmsk;
+ u32 hcchar[MAX_EPS_CHANNELS];
+ u32 hcsplt[MAX_EPS_CHANNELS];
u32 hcintmsk[MAX_EPS_CHANNELS];
+ u32 hctsiz[MAX_EPS_CHANNELS];
+ u32 hcidma[MAX_EPS_CHANNELS];
+ u32 hcidmab[MAX_EPS_CHANNELS];
u32 hprt0;
u32 hfir;
u32 hptxfsiz;
@@ -1086,6 +1098,7 @@
bool needs_byte_swap;
/* DWC OTG HW Release versions */
+#define DWC2_CORE_REV_4_30a 0x4f54430a
#define DWC2_CORE_REV_2_71a 0x4f54271a
#define DWC2_CORE_REV_2_72a 0x4f54272a
#define DWC2_CORE_REV_2_80a 0x4f54280a
@@ -1323,6 +1336,7 @@
int dwc2_restore_global_registers(struct dwc2_hsotg *hsotg);
void dwc2_enable_acg(struct dwc2_hsotg *hsotg);
+void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg, bool remotewakeup);
/* This function should be called on every hardware interrupt. */
irqreturn_t dwc2_handle_common_intr(int irq, void *dev);
diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c
index 158ede7..26d752a 100644
--- a/drivers/usb/dwc2/core_intr.c
+++ b/drivers/usb/dwc2/core_intr.c
@@ -297,7 +297,8 @@
/* Exit gadget mode clock gating. */
if (hsotg->params.power_down ==
- DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended)
+ DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended &&
+ !hsotg->params.no_clock_gating)
dwc2_gadget_exit_clock_gating(hsotg, 0);
}
@@ -322,10 +323,11 @@
* @hsotg: Programming view of DWC_otg controller
*
*/
-static void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg)
+void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg, bool remotewakeup)
{
u32 glpmcfg;
- u32 i = 0;
+ u32 pcgctl;
+ u32 dctl;
if (hsotg->lx_state != DWC2_L1) {
dev_err(hsotg->dev, "Core isn't in DWC2_L1 state\n");
@@ -334,37 +336,57 @@
glpmcfg = dwc2_readl(hsotg, GLPMCFG);
if (dwc2_is_device_mode(hsotg)) {
- dev_dbg(hsotg->dev, "Exit from L1 state\n");
+ dev_dbg(hsotg->dev, "Exit from L1 state, remotewakeup=%d\n", remotewakeup);
glpmcfg &= ~GLPMCFG_ENBLSLPM;
- glpmcfg &= ~GLPMCFG_HIRD_THRES_EN;
+ glpmcfg &= ~GLPMCFG_HIRD_THRES_MASK;
dwc2_writel(hsotg, glpmcfg, GLPMCFG);
- do {
- glpmcfg = dwc2_readl(hsotg, GLPMCFG);
+ pcgctl = dwc2_readl(hsotg, PCGCTL);
+ pcgctl &= ~PCGCTL_ENBL_SLEEP_GATING;
+ dwc2_writel(hsotg, pcgctl, PCGCTL);
- if (!(glpmcfg & (GLPMCFG_COREL1RES_MASK |
- GLPMCFG_L1RESUMEOK | GLPMCFG_SLPSTS)))
- break;
+ glpmcfg = dwc2_readl(hsotg, GLPMCFG);
+ if (glpmcfg & GLPMCFG_ENBESL) {
+ glpmcfg |= GLPMCFG_RSTRSLPSTS;
+ dwc2_writel(hsotg, glpmcfg, GLPMCFG);
+ }
- udelay(1);
- } while (++i < 200);
+ if (remotewakeup) {
+ if (dwc2_hsotg_wait_bit_set(hsotg, GLPMCFG, GLPMCFG_L1RESUMEOK, 1000)) {
+ dev_warn(hsotg->dev, "%s: timeout GLPMCFG_L1RESUMEOK\n", __func__);
+ goto fail;
+ return;
+ }
- if (i == 200) {
- dev_err(hsotg->dev, "Failed to exit L1 sleep state in 200us.\n");
+ dctl = dwc2_readl(hsotg, DCTL);
+ dctl |= DCTL_RMTWKUPSIG;
+ dwc2_writel(hsotg, dctl, DCTL);
+
+ if (dwc2_hsotg_wait_bit_set(hsotg, GINTSTS, GINTSTS_WKUPINT, 1000)) {
+ dev_warn(hsotg->dev, "%s: timeout GINTSTS_WKUPINT\n", __func__);
+ goto fail;
+ return;
+ }
+ }
+
+ glpmcfg = dwc2_readl(hsotg, GLPMCFG);
+ if (glpmcfg & GLPMCFG_COREL1RES_MASK || glpmcfg & GLPMCFG_SLPSTS ||
+ glpmcfg & GLPMCFG_L1RESUMEOK) {
+ goto fail;
return;
}
- dwc2_gadget_init_lpm(hsotg);
+
+ /* Inform gadget to exit from L1 */
+ call_gadget(hsotg, resume);
+ /* Change to L0 state */
+ hsotg->lx_state = DWC2_L0;
+ hsotg->bus_suspended = false;
+fail: dwc2_gadget_init_lpm(hsotg);
} else {
/* TODO */
dev_err(hsotg->dev, "Host side LPM is not supported.\n");
return;
}
-
- /* Change to L0 state */
- hsotg->lx_state = DWC2_L0;
-
- /* Inform gadget to exit from L1 */
- call_gadget(hsotg, resume);
}
/*
@@ -385,7 +407,7 @@
dev_dbg(hsotg->dev, "%s lxstate = %d\n", __func__, hsotg->lx_state);
if (hsotg->lx_state == DWC2_L1) {
- dwc2_wakeup_from_lpm_l1(hsotg);
+ dwc2_wakeup_from_lpm_l1(hsotg, false);
return;
}
@@ -408,7 +430,8 @@
/* Exit gadget mode clock gating. */
if (hsotg->params.power_down ==
- DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended)
+ DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended &&
+ !hsotg->params.no_clock_gating)
dwc2_gadget_exit_clock_gating(hsotg, 0);
} else {
/* Change to L0 state */
@@ -425,7 +448,8 @@
}
if (hsotg->params.power_down ==
- DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended)
+ DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended &&
+ !hsotg->params.no_clock_gating)
dwc2_host_exit_clock_gating(hsotg, 1);
/*
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index b517a72..b2f6da5 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -1415,6 +1415,10 @@
ep->name, req, req->length, req->buf, req->no_interrupt,
req->zero, req->short_not_ok);
+ if (hs->lx_state == DWC2_L1) {
+ dwc2_wakeup_from_lpm_l1(hs, true);
+ }
+
/* Prevent new request submission when controller is suspended */
if (hs->lx_state != DWC2_L0) {
dev_dbg(hs->dev, "%s: submit request only in active state\n",
@@ -3727,6 +3731,12 @@
if (hsotg->in_ppd && hsotg->lx_state == DWC2_L2)
dwc2_exit_partial_power_down(hsotg, 0, true);
+ /* Exit gadget mode clock gating. */
+ if (hsotg->params.power_down ==
+ DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended &&
+ !hsotg->params.no_clock_gating)
+ dwc2_gadget_exit_clock_gating(hsotg, 0);
+
hsotg->lx_state = DWC2_L0;
}
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index 35c7a4d..dd5b1c5 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -2701,8 +2701,11 @@
hsotg->available_host_channels--;
}
qh = list_entry(qh_ptr, struct dwc2_qh, qh_list_entry);
- if (dwc2_assign_and_init_hc(hsotg, qh))
+ if (dwc2_assign_and_init_hc(hsotg, qh)) {
+ if (hsotg->params.uframe_sched)
+ hsotg->available_host_channels++;
break;
+ }
/*
* Move the QH from the periodic ready schedule to the
@@ -2735,8 +2738,11 @@
hsotg->available_host_channels--;
}
- if (dwc2_assign_and_init_hc(hsotg, qh))
+ if (dwc2_assign_and_init_hc(hsotg, qh)) {
+ if (hsotg->params.uframe_sched)
+ hsotg->available_host_channels++;
break;
+ }
/*
* Move the QH from the non-periodic inactive schedule to the
@@ -4143,6 +4149,8 @@
urb->actual_length);
if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) {
+ if (!hsotg->params.dma_desc_enable)
+ urb->start_frame = qtd->qh->start_active_frame;
urb->error_count = dwc2_hcd_urb_get_error_count(qtd->urb);
for (i = 0; i < urb->number_of_packets; ++i) {
urb->iso_frame_desc[i].actual_length =
@@ -4649,7 +4657,7 @@
}
if (hsotg->params.power_down == DWC2_POWER_DOWN_PARAM_NONE &&
- hsotg->bus_suspended) {
+ hsotg->bus_suspended && !hsotg->params.no_clock_gating) {
if (dwc2_is_device_mode(hsotg))
dwc2_gadget_exit_clock_gating(hsotg, 0);
else
@@ -5406,9 +5414,16 @@
/* Backup Host regs */
hr = &hsotg->hr_backup;
hr->hcfg = dwc2_readl(hsotg, HCFG);
+ hr->hflbaddr = dwc2_readl(hsotg, HFLBADDR);
hr->haintmsk = dwc2_readl(hsotg, HAINTMSK);
- for (i = 0; i < hsotg->params.host_channels; ++i)
+ for (i = 0; i < hsotg->params.host_channels; ++i) {
+ hr->hcchar[i] = dwc2_readl(hsotg, HCCHAR(i));
+ hr->hcsplt[i] = dwc2_readl(hsotg, HCSPLT(i));
hr->hcintmsk[i] = dwc2_readl(hsotg, HCINTMSK(i));
+ hr->hctsiz[i] = dwc2_readl(hsotg, HCTSIZ(i));
+ hr->hcidma[i] = dwc2_readl(hsotg, HCDMA(i));
+ hr->hcidmab[i] = dwc2_readl(hsotg, HCDMAB(i));
+ }
hr->hprt0 = dwc2_read_hprt0(hsotg);
hr->hfir = dwc2_readl(hsotg, HFIR);
@@ -5442,10 +5457,17 @@
hr->valid = false;
dwc2_writel(hsotg, hr->hcfg, HCFG);
+ dwc2_writel(hsotg, hr->hflbaddr, HFLBADDR);
dwc2_writel(hsotg, hr->haintmsk, HAINTMSK);
- for (i = 0; i < hsotg->params.host_channels; ++i)
+ for (i = 0; i < hsotg->params.host_channels; ++i) {
+ dwc2_writel(hsotg, hr->hcchar[i], HCCHAR(i));
+ dwc2_writel(hsotg, hr->hcsplt[i], HCSPLT(i));
dwc2_writel(hsotg, hr->hcintmsk[i], HCINTMSK(i));
+ dwc2_writel(hsotg, hr->hctsiz[i], HCTSIZ(i));
+ dwc2_writel(hsotg, hr->hcidma[i], HCDMA(i));
+ dwc2_writel(hsotg, hr->hcidmab[i], HCDMAB(i));
+ }
dwc2_writel(hsotg, hr->hprt0, HPRT0);
dwc2_writel(hsotg, hr->hfir, HFIR);
@@ -5610,10 +5632,12 @@
dwc2_writel(hsotg, hr->hcfg, HCFG);
/* De-assert Wakeup Logic */
- gpwrdn = dwc2_readl(hsotg, GPWRDN);
- gpwrdn &= ~GPWRDN_PMUACTV;
- dwc2_writel(hsotg, gpwrdn, GPWRDN);
- udelay(10);
+ if (!(rem_wakeup && hsotg->hw_params.snpsid >= DWC2_CORE_REV_4_30a)) {
+ gpwrdn = dwc2_readl(hsotg, GPWRDN);
+ gpwrdn &= ~GPWRDN_PMUACTV;
+ dwc2_writel(hsotg, gpwrdn, GPWRDN);
+ udelay(10);
+ }
hprt0 = hr->hprt0;
hprt0 |= HPRT0_PWR;
@@ -5638,6 +5662,13 @@
hprt0 |= HPRT0_RES;
dwc2_writel(hsotg, hprt0, HPRT0);
+ /* De-assert Wakeup Logic */
+ if ((rem_wakeup && hsotg->hw_params.snpsid >= DWC2_CORE_REV_4_30a)) {
+ gpwrdn = dwc2_readl(hsotg, GPWRDN);
+ gpwrdn &= ~GPWRDN_PMUACTV;
+ dwc2_writel(hsotg, gpwrdn, GPWRDN);
+ udelay(10);
+ }
/* Wait for Resume time and then program HPRT again */
mdelay(100);
hprt0 &= ~HPRT0_RES;
diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c
index 6b4d825..79582b1 100644
--- a/drivers/usb/dwc2/hcd_ddma.c
+++ b/drivers/usb/dwc2/hcd_ddma.c
@@ -559,7 +559,7 @@
idx = qh->td_last;
inc = qh->host_interval;
hsotg->frame_number = dwc2_hcd_get_frame_number(hsotg);
- cur_idx = dwc2_frame_list_idx(hsotg->frame_number);
+ cur_idx = idx;
next_idx = dwc2_desclist_idx_inc(qh->td_last, inc, qh->dev_speed);
/*
@@ -866,6 +866,8 @@
{
struct dwc2_dma_desc *dma_desc;
struct dwc2_hcd_iso_packet_desc *frame_desc;
+ u16 frame_desc_idx;
+ struct urb *usb_urb = qtd->urb->priv;
u16 remain = 0;
int rc = 0;
@@ -878,8 +880,11 @@
DMA_FROM_DEVICE);
dma_desc = &qh->desc_list[idx];
+ frame_desc_idx = (idx - qtd->isoc_td_first) & (usb_urb->number_of_packets - 1);
- frame_desc = &qtd->urb->iso_descs[qtd->isoc_frame_index_last];
+ frame_desc = &qtd->urb->iso_descs[frame_desc_idx];
+ if (idx == qtd->isoc_td_first)
+ usb_urb->start_frame = dwc2_hcd_get_frame_number(hsotg);
dma_desc->buf = (u32)(qtd->urb->dma + frame_desc->offset);
if (chan->ep_is_in)
remain = (dma_desc->status & HOST_DMA_ISOC_NBYTES_MASK) >>
@@ -900,7 +905,7 @@
frame_desc->status = 0;
}
- if (++qtd->isoc_frame_index == qtd->urb->packet_count) {
+ if (++qtd->isoc_frame_index == usb_urb->number_of_packets) {
/*
* urb->status is not used for isoc transfers here. The
* individual frame_desc status are used instead.
@@ -1005,11 +1010,11 @@
return;
idx = dwc2_desclist_idx_inc(idx, qh->host_interval,
chan->speed);
- if (!rc)
+ if (rc == 0)
continue;
- if (rc == DWC2_CMPL_DONE)
- break;
+ if (rc == DWC2_CMPL_DONE || rc == DWC2_CMPL_STOP)
+ goto stop_scan;
/* rc == DWC2_CMPL_STOP */
diff --git a/drivers/usb/dwc2/hw.h b/drivers/usb/dwc2/hw.h
index 13abdd5..12f8c7f 100644
--- a/drivers/usb/dwc2/hw.h
+++ b/drivers/usb/dwc2/hw.h
@@ -698,7 +698,7 @@
#define TXSTS_QTOP_TOKEN_MASK (0x3 << 25)
#define TXSTS_QTOP_TOKEN_SHIFT 25
#define TXSTS_QTOP_TERMINATE BIT(24)
-#define TXSTS_QSPCAVAIL_MASK (0xff << 16)
+#define TXSTS_QSPCAVAIL_MASK (0x7f << 16)
#define TXSTS_QSPCAVAIL_SHIFT 16
#define TXSTS_FSPCAVAIL_MASK (0xffff << 0)
#define TXSTS_FSPCAVAIL_SHIFT 0
diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c
index b1d4801..7b84416 100644
--- a/drivers/usb/dwc2/platform.c
+++ b/drivers/usb/dwc2/platform.c
@@ -331,7 +331,7 @@
/* Exit clock gating when driver is removed. */
if (hsotg->params.power_down == DWC2_POWER_DOWN_PARAM_NONE &&
- hsotg->bus_suspended) {
+ hsotg->bus_suspended && !hsotg->params.no_clock_gating) {
if (dwc2_is_device_mode(hsotg))
dwc2_gadget_exit_clock_gating(hsotg, 0);
else
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 3e55838..31684cd 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -1519,6 +1519,8 @@
else
dwc->sysdev = dwc->dev;
+ dwc->sys_wakeup = device_may_wakeup(dwc->sysdev);
+
ret = device_property_read_string(dev, "usb-psy-name", &usb_psy_name);
if (ret >= 0) {
dwc->usb_psy = power_supply_get_by_name(usb_psy_name);
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index c07edfc..7e80dd3 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -1133,6 +1133,7 @@
* 3 - Reserved
* @dis_metastability_quirk: set to disable metastability quirk.
* @dis_split_quirk: set to disable split boundary.
+ * @sys_wakeup: set if the device may do system wakeup.
* @wakeup_configured: set if the device is configured for remote wakeup.
* @suspended: set to track suspend event due to U3/L2.
* @imod_interval: set the interrupt moderation interval in 250ns
@@ -1357,6 +1358,7 @@
unsigned dis_split_quirk:1;
unsigned async_callbacks:1;
+ unsigned sys_wakeup:1;
unsigned wakeup_configured:1;
unsigned suspended:1;
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 39564e1..497deed 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -51,7 +51,6 @@
#define PCI_DEVICE_ID_INTEL_MTLP 0x7ec1
#define PCI_DEVICE_ID_INTEL_MTLS 0x7f6f
#define PCI_DEVICE_ID_INTEL_MTL 0x7e7e
-#define PCI_DEVICE_ID_INTEL_ARLH 0x7ec1
#define PCI_DEVICE_ID_INTEL_ARLH_PCH 0x777e
#define PCI_DEVICE_ID_INTEL_TGL 0x9a15
#define PCI_DEVICE_ID_AMD_MR 0x163a
@@ -423,7 +422,6 @@
{ PCI_DEVICE_DATA(INTEL, MTLP, &dwc3_pci_intel_swnode) },
{ PCI_DEVICE_DATA(INTEL, MTL, &dwc3_pci_intel_swnode) },
{ PCI_DEVICE_DATA(INTEL, MTLS, &dwc3_pci_intel_swnode) },
- { PCI_DEVICE_DATA(INTEL, ARLH, &dwc3_pci_intel_swnode) },
{ PCI_DEVICE_DATA(INTEL, ARLH_PCH, &dwc3_pci_intel_swnode) },
{ PCI_DEVICE_DATA(INTEL, TGL, &dwc3_pci_intel_swnode) },
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 40c52db..4df2661 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2955,6 +2955,9 @@
dwc->gadget_driver = driver;
spin_unlock_irqrestore(&dwc->lock, flags);
+ if (dwc->sys_wakeup)
+ device_wakeup_enable(dwc->sysdev);
+
return 0;
}
@@ -2970,6 +2973,9 @@
struct dwc3 *dwc = gadget_to_dwc(g);
unsigned long flags;
+ if (dwc->sys_wakeup)
+ device_wakeup_disable(dwc->sysdev);
+
spin_lock_irqsave(&dwc->lock, flags);
dwc->gadget_driver = NULL;
dwc->max_cfg_eps = 0;
@@ -4651,6 +4657,10 @@
else
dwc3_gadget_set_speed(dwc->gadget, dwc->maximum_speed);
+ /* No system wakeup if no gadget driver bound */
+ if (dwc->sys_wakeup)
+ device_wakeup_disable(dwc->sysdev);
+
return 0;
err5:
diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c
index 5a5cb6c..0204787 100644
--- a/drivers/usb/dwc3/host.c
+++ b/drivers/usb/dwc3/host.c
@@ -173,6 +173,14 @@
goto err;
}
+ if (dwc->sys_wakeup) {
+ /* Restore wakeup setting if switched from device */
+ device_wakeup_enable(dwc->sysdev);
+
+ /* Pass on wakeup setting to the new xhci platform device */
+ device_init_wakeup(&xhci->dev, true);
+ }
+
return 0;
err:
platform_device_put(xhci);
@@ -181,6 +189,9 @@
void dwc3_host_exit(struct dwc3 *dwc)
{
+ if (dwc->sys_wakeup)
+ device_init_wakeup(&dwc->xhci->dev, false);
+
platform_device_unregister(dwc->xhci);
dwc->xhci = NULL;
}
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 9d41501..b3a9d18 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -292,7 +292,9 @@
{
int ret = 0;
- if (WARN_ON_ONCE(!ep->enabled && ep->address)) {
+ if (!ep->enabled && ep->address) {
+ pr_debug("USB gadget: queue request to disabled ep 0x%x (%s)\n",
+ ep->address, ep->name);
ret = -ESHUTDOWN;
goto out;
}
diff --git a/drivers/usb/misc/usb-ljca.c b/drivers/usb/misc/usb-ljca.c
index 35770e6..2d30fc1 100644
--- a/drivers/usb/misc/usb-ljca.c
+++ b/drivers/usb/misc/usb-ljca.c
@@ -518,8 +518,10 @@
int ret;
client = kzalloc(sizeof *client, GFP_KERNEL);
- if (!client)
+ if (!client) {
+ kfree(data);
return -ENOMEM;
+ }
client->type = type;
client->id = id;
@@ -535,8 +537,10 @@
auxdev->dev.release = ljca_auxdev_release;
ret = auxiliary_device_init(auxdev);
- if (ret)
+ if (ret) {
+ kfree(data);
goto err_free;
+ }
ljca_auxdev_acpi_bind(adap, auxdev, adr, id);
@@ -590,12 +594,8 @@
valid_pin[i] = get_unaligned_le32(&desc->bank_desc[i].valid_pins);
bitmap_from_arr32(gpio_info->valid_pin_map, valid_pin, gpio_num);
- ret = ljca_new_client_device(adap, LJCA_CLIENT_GPIO, 0, "ljca-gpio",
+ return ljca_new_client_device(adap, LJCA_CLIENT_GPIO, 0, "ljca-gpio",
gpio_info, LJCA_GPIO_ACPI_ADR);
- if (ret)
- kfree(gpio_info);
-
- return ret;
}
static int ljca_enumerate_i2c(struct ljca_adapter *adap)
@@ -629,10 +629,8 @@
ret = ljca_new_client_device(adap, LJCA_CLIENT_I2C, i,
"ljca-i2c", i2c_info,
LJCA_I2C1_ACPI_ADR + i);
- if (ret) {
- kfree(i2c_info);
+ if (ret)
return ret;
- }
}
return 0;
@@ -669,10 +667,8 @@
ret = ljca_new_client_device(adap, LJCA_CLIENT_SPI, i,
"ljca-spi", spi_info,
LJCA_SPI1_ACPI_ADR + i);
- if (ret) {
- kfree(spi_info);
+ if (ret)
return ret;
- }
}
return 0;
diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c
index 8f735a8..fdcffeb 100644
--- a/drivers/usb/phy/phy-generic.c
+++ b/drivers/usb/phy/phy-generic.c
@@ -262,13 +262,6 @@
return dev_err_probe(dev, PTR_ERR(nop->vbus_draw),
"could not get vbus regulator\n");
- nop->vbus_draw = devm_regulator_get_exclusive(dev, "vbus");
- if (PTR_ERR(nop->vbus_draw) == -ENODEV)
- nop->vbus_draw = NULL;
- if (IS_ERR(nop->vbus_draw))
- return dev_err_probe(dev, PTR_ERR(nop->vbus_draw),
- "could not get vbus regulator\n");
-
nop->dev = dev;
nop->phy.dev = nop->dev;
nop->phy.label = "nop-xceiv";
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 71ace27..08953f0 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -533,7 +533,7 @@
* daft to me.
*/
-static struct urb *uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp)
+static int uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp)
{
struct uas_dev_info *devinfo = cmnd->device->hostdata;
struct urb *urb;
@@ -541,30 +541,28 @@
urb = uas_alloc_sense_urb(devinfo, gfp, cmnd);
if (!urb)
- return NULL;
+ return -ENOMEM;
usb_anchor_urb(urb, &devinfo->sense_urbs);
err = usb_submit_urb(urb, gfp);
if (err) {
usb_unanchor_urb(urb);
uas_log_cmd_state(cmnd, "sense submit err", err);
usb_free_urb(urb);
- return NULL;
}
- return urb;
+ return err;
}
static int uas_submit_urbs(struct scsi_cmnd *cmnd,
struct uas_dev_info *devinfo)
{
struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd);
- struct urb *urb;
int err;
lockdep_assert_held(&devinfo->lock);
if (cmdinfo->state & SUBMIT_STATUS_URB) {
- urb = uas_submit_sense_urb(cmnd, GFP_ATOMIC);
- if (!urb)
- return SCSI_MLQUEUE_DEVICE_BUSY;
+ err = uas_submit_sense_urb(cmnd, GFP_ATOMIC);
+ if (err)
+ return err;
cmdinfo->state &= ~SUBMIT_STATUS_URB;
}
@@ -572,7 +570,7 @@
cmdinfo->data_in_urb = uas_alloc_data_urb(devinfo, GFP_ATOMIC,
cmnd, DMA_FROM_DEVICE);
if (!cmdinfo->data_in_urb)
- return SCSI_MLQUEUE_DEVICE_BUSY;
+ return -ENOMEM;
cmdinfo->state &= ~ALLOC_DATA_IN_URB;
}
@@ -582,7 +580,7 @@
if (err) {
usb_unanchor_urb(cmdinfo->data_in_urb);
uas_log_cmd_state(cmnd, "data in submit err", err);
- return SCSI_MLQUEUE_DEVICE_BUSY;
+ return err;
}
cmdinfo->state &= ~SUBMIT_DATA_IN_URB;
cmdinfo->state |= DATA_IN_URB_INFLIGHT;
@@ -592,7 +590,7 @@
cmdinfo->data_out_urb = uas_alloc_data_urb(devinfo, GFP_ATOMIC,
cmnd, DMA_TO_DEVICE);
if (!cmdinfo->data_out_urb)
- return SCSI_MLQUEUE_DEVICE_BUSY;
+ return -ENOMEM;
cmdinfo->state &= ~ALLOC_DATA_OUT_URB;
}
@@ -602,7 +600,7 @@
if (err) {
usb_unanchor_urb(cmdinfo->data_out_urb);
uas_log_cmd_state(cmnd, "data out submit err", err);
- return SCSI_MLQUEUE_DEVICE_BUSY;
+ return err;
}
cmdinfo->state &= ~SUBMIT_DATA_OUT_URB;
cmdinfo->state |= DATA_OUT_URB_INFLIGHT;
@@ -611,7 +609,7 @@
if (cmdinfo->state & ALLOC_CMD_URB) {
cmdinfo->cmd_urb = uas_alloc_cmd_urb(devinfo, GFP_ATOMIC, cmnd);
if (!cmdinfo->cmd_urb)
- return SCSI_MLQUEUE_DEVICE_BUSY;
+ return -ENOMEM;
cmdinfo->state &= ~ALLOC_CMD_URB;
}
@@ -621,7 +619,7 @@
if (err) {
usb_unanchor_urb(cmdinfo->cmd_urb);
uas_log_cmd_state(cmnd, "cmd submit err", err);
- return SCSI_MLQUEUE_DEVICE_BUSY;
+ return err;
}
cmdinfo->cmd_urb = NULL;
cmdinfo->state &= ~SUBMIT_CMD_URB;
@@ -698,7 +696,7 @@
* of queueing, no matter how fatal the error
*/
if (err == -ENODEV) {
- set_host_byte(cmnd, DID_ERROR);
+ set_host_byte(cmnd, DID_NO_CONNECT);
scsi_done(cmnd);
goto zombie;
}
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 389c7f0..9610e64 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -1310,6 +1310,7 @@
{
struct typec_port *port = to_typec_port(dev);
struct usb_power_delivery *pd;
+ int ret;
if (!port->ops || !port->ops->pd_set)
return -EOPNOTSUPP;
@@ -1318,7 +1319,11 @@
if (!pd)
return -EINVAL;
- return port->ops->pd_set(port, pd);
+ ret = port->ops->pd_set(port, pd);
+ if (ret)
+ return ret;
+
+ return size;
}
static ssize_t select_usb_power_delivery_show(struct device *dev,
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index ae2b6c9..c26fb70 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -6861,7 +6861,7 @@
if (data->source_desc.pdo[0]) {
for (i = 0; i < PDO_MAX_OBJECTS && data->source_desc.pdo[i]; i++)
- port->snk_pdo[i] = data->source_desc.pdo[i];
+ port->src_pdo[i] = data->source_desc.pdo[i];
port->nr_src_pdo = i + 1;
}
@@ -6910,7 +6910,9 @@
port->port_source_caps = data->source_cap;
port->port_sink_caps = data->sink_cap;
+ typec_port_set_usb_power_delivery(p, NULL);
port->selected_pd = pd;
+ typec_port_set_usb_power_delivery(p, port->selected_pd);
unlock:
mutex_unlock(&port->lock);
return ret;
@@ -6943,9 +6945,7 @@
port->port_source_caps = NULL;
for (i = 0; i < port->pd_count; i++) {
usb_power_delivery_unregister_capabilities(port->pd_list[i]->sink_cap);
- kfree(port->pd_list[i]->sink_cap);
usb_power_delivery_unregister_capabilities(port->pd_list[i]->source_cap);
- kfree(port->pd_list[i]->source_cap);
devm_kfree(port->dev, port->pd_list[i]);
port->pd_list[i] = NULL;
usb_power_delivery_unregister(port->pds[i]);
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index cf52cb3..31d8a46 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -151,8 +151,12 @@
if (!(cci & UCSI_CCI_COMMAND_COMPLETE))
return -EIO;
- if (cci & UCSI_CCI_NOT_SUPPORTED)
+ if (cci & UCSI_CCI_NOT_SUPPORTED) {
+ if (ucsi_acknowledge_command(ucsi) < 0)
+ dev_err(ucsi->dev,
+ "ACK of unsupported command failed\n");
return -EOPNOTSUPP;
+ }
if (cci & UCSI_CCI_ERROR) {
if (cmd == UCSI_GET_ERROR_STATUS)
@@ -1133,17 +1137,21 @@
if (ret < 0)
return ret;
- ret = ucsi_get_cable_identity(con);
- if (ret < 0)
- return ret;
+ if (con->ucsi->cap.features & UCSI_CAP_GET_PD_MESSAGE) {
+ ret = ucsi_get_cable_identity(con);
+ if (ret < 0)
+ return ret;
+ }
- ret = ucsi_register_plug(con);
- if (ret < 0)
- return ret;
+ if (con->ucsi->cap.features & UCSI_CAP_ALT_MODE_DETAILS) {
+ ret = ucsi_register_plug(con);
+ if (ret < 0)
+ return ret;
- ret = ucsi_register_altmodes(con, UCSI_RECIPIENT_SOP_P);
- if (ret < 0)
- return ret;
+ ret = ucsi_register_altmodes(con, UCSI_RECIPIENT_SOP_P);
+ if (ret < 0)
+ return ret;
+ }
return 0;
}
@@ -1189,8 +1197,10 @@
ucsi_register_partner(con);
ucsi_partner_task(con, ucsi_check_connection, 1, HZ);
ucsi_partner_task(con, ucsi_check_connector_capability, 1, HZ);
- ucsi_partner_task(con, ucsi_get_partner_identity, 1, HZ);
- ucsi_partner_task(con, ucsi_check_cable, 1, HZ);
+ if (con->ucsi->cap.features & UCSI_CAP_GET_PD_MESSAGE)
+ ucsi_partner_task(con, ucsi_get_partner_identity, 1, HZ);
+ if (con->ucsi->cap.features & UCSI_CAP_CABLE_DETAILS)
+ ucsi_partner_task(con, ucsi_check_cable, 1, HZ);
if (UCSI_CONSTAT_PWR_OPMODE(con->status.flags) ==
UCSI_CONSTAT_PWR_OPMODE_PD)
@@ -1215,11 +1225,11 @@
if (con->status.change & UCSI_CONSTAT_CAM_CHANGE)
ucsi_partner_task(con, ucsi_check_altmodes, 1, 0);
- clear_bit(EVENT_PENDING, &con->ucsi->flags);
-
mutex_lock(&ucsi->ppm_lock);
+ clear_bit(EVENT_PENDING, &con->ucsi->flags);
ret = ucsi_acknowledge_connector_change(ucsi);
mutex_unlock(&ucsi->ppm_lock);
+
if (ret)
dev_err(ucsi->dev, "%s: ACK failed (%d)", __func__, ret);
@@ -1237,7 +1247,7 @@
struct ucsi_connector *con = &ucsi->connector[num - 1];
if (!(ucsi->ntfy & UCSI_ENABLE_NTFY_CONNECTOR_CHANGE)) {
- dev_dbg(ucsi->dev, "Bogus connector change event\n");
+ dev_dbg(ucsi->dev, "Early connector change event\n");
return;
}
@@ -1260,13 +1270,47 @@
static int ucsi_reset_ppm(struct ucsi *ucsi)
{
- u64 command = UCSI_PPM_RESET;
+ u64 command;
unsigned long tmo;
u32 cci;
int ret;
mutex_lock(&ucsi->ppm_lock);
+ ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci));
+ if (ret < 0)
+ goto out;
+
+ /*
+ * If UCSI_CCI_RESET_COMPLETE is already set we must clear
+ * the flag before we start another reset. Send a
+ * UCSI_SET_NOTIFICATION_ENABLE command to achieve this.
+ * Ignore a timeout and try the reset anyway if this fails.
+ */
+ if (cci & UCSI_CCI_RESET_COMPLETE) {
+ command = UCSI_SET_NOTIFICATION_ENABLE;
+ ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command,
+ sizeof(command));
+ if (ret < 0)
+ goto out;
+
+ tmo = jiffies + msecs_to_jiffies(UCSI_TIMEOUT_MS);
+ do {
+ ret = ucsi->ops->read(ucsi, UCSI_CCI,
+ &cci, sizeof(cci));
+ if (ret < 0)
+ goto out;
+ if (cci & UCSI_CCI_COMMAND_COMPLETE)
+ break;
+ if (time_is_before_jiffies(tmo))
+ break;
+ msleep(20);
+ } while (1);
+
+ WARN_ON(cci & UCSI_CCI_RESET_COMPLETE);
+ }
+
+ command = UCSI_PPM_RESET;
ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command,
sizeof(command));
if (ret < 0)
@@ -1589,8 +1633,10 @@
ucsi_register_partner(con);
ucsi_pwr_opmode_change(con);
ucsi_port_psy_changed(con);
- ucsi_get_partner_identity(con);
- ucsi_check_cable(con);
+ if (con->ucsi->cap.features & UCSI_CAP_GET_PD_MESSAGE)
+ ucsi_get_partner_identity(con);
+ if (con->ucsi->cap.features & UCSI_CAP_CABLE_DETAILS)
+ ucsi_check_cable(con);
}
/* Only notify USB controller if partner supports USB data */
@@ -1636,6 +1682,7 @@
{
struct ucsi_connector *con, *connector;
u64 command, ntfy;
+ u32 cci;
int ret;
int i;
@@ -1688,6 +1735,13 @@
ucsi->connector = connector;
ucsi->ntfy = ntfy;
+
+ ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci));
+ if (ret)
+ return ret;
+ if (UCSI_CCI_CONNECTOR(READ_ONCE(cci)))
+ ucsi_connector_change(ucsi, cci);
+
return 0;
err_unregister:
diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
index 32daf5f..0e7c92eb 100644
--- a/drivers/usb/typec/ucsi/ucsi.h
+++ b/drivers/usb/typec/ucsi/ucsi.h
@@ -206,7 +206,7 @@
#define UCSI_CAP_ATTR_POWER_OTHER BIT(10)
#define UCSI_CAP_ATTR_POWER_VBUS BIT(14)
u8 num_connectors;
- u8 features;
+ u16 features;
#define UCSI_CAP_SET_UOM BIT(0)
#define UCSI_CAP_SET_PDM BIT(1)
#define UCSI_CAP_ALT_MODE_DETAILS BIT(2)
@@ -215,7 +215,8 @@
#define UCSI_CAP_CABLE_DETAILS BIT(5)
#define UCSI_CAP_EXT_SUPPLY_NOTIFICATIONS BIT(6)
#define UCSI_CAP_PD_RESET BIT(7)
- u16 reserved_1;
+#define UCSI_CAP_GET_PD_MESSAGE BIT(8)
+ u8 reserved_1;
u8 num_alt_modes;
u8 reserved_2;
u16 bc_version;
diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c
index 928eacb..7b3ac13 100644
--- a/drivers/usb/typec/ucsi/ucsi_acpi.c
+++ b/drivers/usb/typec/ucsi/ucsi_acpi.c
@@ -23,10 +23,11 @@
void *base;
struct completion complete;
unsigned long flags;
+#define UCSI_ACPI_SUPPRESS_EVENT 0
+#define UCSI_ACPI_COMMAND_PENDING 1
+#define UCSI_ACPI_ACK_PENDING 2
guid_t guid;
u64 cmd;
- bool dell_quirk_probed;
- bool dell_quirk_active;
};
static int ucsi_acpi_dsm(struct ucsi_acpi *ua, int func)
@@ -79,9 +80,9 @@
int ret;
if (ack)
- set_bit(ACK_PENDING, &ua->flags);
+ set_bit(UCSI_ACPI_ACK_PENDING, &ua->flags);
else
- set_bit(COMMAND_PENDING, &ua->flags);
+ set_bit(UCSI_ACPI_COMMAND_PENDING, &ua->flags);
ret = ucsi_acpi_async_write(ucsi, offset, val, val_len);
if (ret)
@@ -92,9 +93,9 @@
out_clear_bit:
if (ack)
- clear_bit(ACK_PENDING, &ua->flags);
+ clear_bit(UCSI_ACPI_ACK_PENDING, &ua->flags);
else
- clear_bit(COMMAND_PENDING, &ua->flags);
+ clear_bit(UCSI_ACPI_COMMAND_PENDING, &ua->flags);
return ret;
}
@@ -129,51 +130,40 @@
};
/*
- * Some Dell laptops expect that an ACK command with the
- * UCSI_ACK_CONNECTOR_CHANGE bit set is followed by a (separate)
- * ACK command that only has the UCSI_ACK_COMMAND_COMPLETE bit set.
- * If this is not done events are not delivered to OSPM and
- * subsequent commands will timeout.
+ * Some Dell laptops don't like ACK commands with the
+ * UCSI_ACK_CONNECTOR_CHANGE but not the UCSI_ACK_COMMAND_COMPLETE
+ * bit set. To work around this send a dummy command and bundle the
+ * UCSI_ACK_CONNECTOR_CHANGE with the UCSI_ACK_COMMAND_COMPLETE
+ * for the dummy command.
*/
static int
ucsi_dell_sync_write(struct ucsi *ucsi, unsigned int offset,
const void *val, size_t val_len)
{
struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
- u64 cmd = *(u64 *)val, ack = 0;
+ u64 cmd = *(u64 *)val;
+ u64 dummycmd = UCSI_GET_CAPABILITY;
int ret;
- if (UCSI_COMMAND(cmd) == UCSI_ACK_CC_CI &&
- cmd & UCSI_ACK_CONNECTOR_CHANGE)
- ack = UCSI_ACK_CC_CI | UCSI_ACK_COMMAND_COMPLETE;
+ if (cmd == (UCSI_ACK_CC_CI | UCSI_ACK_CONNECTOR_CHANGE)) {
+ cmd |= UCSI_ACK_COMMAND_COMPLETE;
- ret = ucsi_acpi_sync_write(ucsi, offset, val, val_len);
- if (ret != 0)
- return ret;
- if (ack == 0)
- return ret;
+ /*
+ * The UCSI core thinks it is sending a connector change ack
+ * and will accept new connector change events. We don't want
+ * this to happen for the dummy command as its response will
+ * still report the very event that the core is trying to clear.
+ */
+ set_bit(UCSI_ACPI_SUPPRESS_EVENT, &ua->flags);
+ ret = ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &dummycmd,
+ sizeof(dummycmd));
+ clear_bit(UCSI_ACPI_SUPPRESS_EVENT, &ua->flags);
- if (!ua->dell_quirk_probed) {
- ua->dell_quirk_probed = true;
-
- cmd = UCSI_GET_CAPABILITY;
- ret = ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &cmd,
- sizeof(cmd));
- if (ret == 0)
- return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL,
- &ack, sizeof(ack));
- if (ret != -ETIMEDOUT)
+ if (ret < 0)
return ret;
-
- ua->dell_quirk_active = true;
- dev_err(ua->dev, "Firmware bug: Additional ACK required after ACKing a connector change.\n");
- dev_err(ua->dev, "Firmware bug: Enabling workaround\n");
}
- if (!ua->dell_quirk_active)
- return ret;
-
- return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &ack, sizeof(ack));
+ return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &cmd, sizeof(cmd));
}
static const struct ucsi_operations ucsi_dell_ops = {
@@ -209,13 +199,14 @@
if (ret)
return;
- if (UCSI_CCI_CONNECTOR(cci))
+ if (UCSI_CCI_CONNECTOR(cci) &&
+ !test_bit(UCSI_ACPI_SUPPRESS_EVENT, &ua->flags))
ucsi_connector_change(ua->ucsi, UCSI_CCI_CONNECTOR(cci));
if (cci & UCSI_CCI_ACK_COMPLETE && test_bit(ACK_PENDING, &ua->flags))
complete(&ua->complete);
if (cci & UCSI_CCI_COMMAND_COMPLETE &&
- test_bit(COMMAND_PENDING, &ua->flags))
+ test_bit(UCSI_ACPI_COMMAND_PENDING, &ua->flags))
complete(&ua->complete);
}
diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c
index 932e7bf..ce08eb3 100644
--- a/drivers/usb/typec/ucsi/ucsi_glink.c
+++ b/drivers/usb/typec/ucsi/ucsi_glink.c
@@ -255,6 +255,20 @@
static void pmic_glink_ucsi_register(struct work_struct *work)
{
struct pmic_glink_ucsi *ucsi = container_of(work, struct pmic_glink_ucsi, register_work);
+ int orientation;
+ int i;
+
+ for (i = 0; i < PMIC_GLINK_MAX_PORTS; i++) {
+ if (!ucsi->port_orientation[i])
+ continue;
+ orientation = gpiod_get_value(ucsi->port_orientation[i]);
+
+ if (orientation >= 0) {
+ typec_switch_set(ucsi->port_switch[i],
+ orientation ? TYPEC_ORIENTATION_REVERSE
+ : TYPEC_ORIENTATION_NORMAL);
+ }
+ }
ucsi_register(ucsi->ucsi);
}
diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index e3179e9..197b6d5 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -494,6 +494,7 @@
select FB_CFB_COPYAREA
select FB_CFB_FILLRECT
select FB_CFB_IMAGEBLIT
+ select FB_IOMEM_FOPS
config FB_BW2
bool "BWtwo support"
@@ -514,6 +515,7 @@
depends on (FB = y) && (SPARC && FB_SBUS)
select FB_CFB_COPYAREA
select FB_CFB_IMAGEBLIT
+ select FB_IOMEM_FOPS
help
This is the frame buffer device driver for the CGsix (GX, TurboGX)
frame buffer.
@@ -523,6 +525,7 @@
depends on FB_SBUS && SPARC64
select FB_CFB_COPYAREA
select FB_CFB_IMAGEBLIT
+ select FB_IOMEM_FOPS
help
This is the frame buffer device driver for the Creator, Creator3D,
and Elite3D graphics boards.
diff --git a/fs/bcachefs/Makefile b/fs/bcachefs/Makefile
index b02796c..66ca0bb 100644
--- a/fs/bcachefs/Makefile
+++ b/fs/bcachefs/Makefile
@@ -17,6 +17,7 @@
btree_journal_iter.o \
btree_key_cache.o \
btree_locking.o \
+ btree_node_scan.o \
btree_trans_commit.o \
btree_update.o \
btree_update_interior.o \
@@ -37,6 +38,7 @@
error.o \
extents.o \
extent_update.o \
+ eytzinger.o \
fs.o \
fs-common.o \
fs-ioctl.o \
@@ -67,6 +69,7 @@
quota.o \
rebalance.o \
recovery.o \
+ recovery_passes.o \
reflink.o \
replicas.o \
sb-clean.o \
diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index 893e38f..4ff56fa 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -1713,34 +1713,37 @@
if (ret)
goto out;
- if (BCH_ALLOC_V4_NEED_INC_GEN(&a->v)) {
- a->v.gen++;
- SET_BCH_ALLOC_V4_NEED_INC_GEN(&a->v, false);
- goto write;
- }
-
- if (a->v.journal_seq > c->journal.flushed_seq_ondisk) {
- if (c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info) {
- bch2_trans_inconsistent(trans,
- "clearing need_discard but journal_seq %llu > flushed_seq %llu\n"
- "%s",
- a->v.journal_seq,
- c->journal.flushed_seq_ondisk,
- (bch2_bkey_val_to_text(&buf, c, k), buf.buf));
+ if (a->v.dirty_sectors) {
+ if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info,
+ trans, "attempting to discard bucket with dirty data\n%s",
+ (bch2_bkey_val_to_text(&buf, c, k), buf.buf)))
ret = -EIO;
- }
goto out;
}
if (a->v.data_type != BCH_DATA_need_discard) {
- if (c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info) {
- bch2_trans_inconsistent(trans,
- "bucket incorrectly set in need_discard btree\n"
- "%s",
- (bch2_bkey_val_to_text(&buf, c, k), buf.buf));
- ret = -EIO;
+ if (data_type_is_empty(a->v.data_type) &&
+ BCH_ALLOC_V4_NEED_INC_GEN(&a->v)) {
+ a->v.gen++;
+ SET_BCH_ALLOC_V4_NEED_INC_GEN(&a->v, false);
+ goto write;
}
+ if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info,
+ trans, "bucket incorrectly set in need_discard btree\n"
+ "%s",
+ (bch2_bkey_val_to_text(&buf, c, k), buf.buf)))
+ ret = -EIO;
+ goto out;
+ }
+
+ if (a->v.journal_seq > c->journal.flushed_seq_ondisk) {
+ if (bch2_trans_inconsistent_on(c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_info,
+ trans, "clearing need_discard but journal_seq %llu > flushed_seq %llu\n%s",
+ a->v.journal_seq,
+ c->journal.flushed_seq_ondisk,
+ (bch2_bkey_val_to_text(&buf, c, k), buf.buf)))
+ ret = -EIO;
goto out;
}
@@ -1835,6 +1838,7 @@
if (ret)
goto err;
+ BUG_ON(a->v.dirty_sectors);
SET_BCH_ALLOC_V4_NEED_DISCARD(&a->v, false);
a->v.data_type = alloc_data_type(a->v, a->v.data_type);
@@ -1942,6 +1946,7 @@
goto out;
BUG_ON(a->v.data_type != BCH_DATA_cached);
+ BUG_ON(a->v.dirty_sectors);
if (!a->v.cached_sectors)
bch_err(c, "invalidating empty bucket, confused");
diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index 214b15c8..a1fc30a 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -188,8 +188,10 @@
static inline unsigned open_buckets_reserved(enum bch_watermark watermark)
{
switch (watermark) {
- case BCH_WATERMARK_reclaim:
+ case BCH_WATERMARK_interior_updates:
return 0;
+ case BCH_WATERMARK_reclaim:
+ return OPEN_BUCKETS_COUNT / 6;
case BCH_WATERMARK_btree:
case BCH_WATERMARK_btree_copygc:
return OPEN_BUCKETS_COUNT / 4;
diff --git a/fs/bcachefs/alloc_types.h b/fs/bcachefs/alloc_types.h
index b91b7a4..c2226e9 100644
--- a/fs/bcachefs/alloc_types.h
+++ b/fs/bcachefs/alloc_types.h
@@ -22,7 +22,8 @@
x(copygc) \
x(btree) \
x(btree_copygc) \
- x(reclaim)
+ x(reclaim) \
+ x(interior_updates)
enum bch_watermark {
#define x(name) BCH_WATERMARK_##name,
diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index 8cb35ea..114328a 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -8,6 +8,7 @@
#include "btree_update.h"
#include "btree_update_interior.h"
#include "btree_write_buffer.h"
+#include "checksum.h"
#include "error.h"
#include <linux/mm.h>
@@ -29,8 +30,7 @@
if (p.ptr.cached)
continue;
- bch2_extent_ptr_to_bp(c, btree_id, level, k, p,
- &bucket2, &bp2);
+ bch2_extent_ptr_to_bp(c, btree_id, level, k, p, entry, &bucket2, &bp2);
if (bpos_eq(bucket, bucket2) &&
!memcmp(&bp, &bp2, sizeof(bp)))
return true;
@@ -44,6 +44,11 @@
struct printbuf *err)
{
struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(k);
+
+ /* these will be caught by fsck */
+ if (!bch2_dev_exists2(c, bp.k->p.inode))
+ return 0;
+
struct bpos bucket = bp_pos_to_bucket(c, bp.k->p);
int ret = 0;
@@ -378,7 +383,7 @@
backpointer_to_missing_alloc,
"backpointer for nonexistent alloc key: %llu:%llu:0\n%s",
alloc_iter.pos.inode, alloc_iter.pos.offset,
- (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) {
+ (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) {
ret = bch2_btree_delete_at(trans, bp_iter, 0);
goto out;
}
@@ -414,6 +419,84 @@
struct bkey_buf last_flushed;
};
+static int drop_dev_and_update(struct btree_trans *trans, enum btree_id btree,
+ struct bkey_s_c extent, unsigned dev)
+{
+ struct bkey_i *n = bch2_bkey_make_mut_noupdate(trans, extent);
+ int ret = PTR_ERR_OR_ZERO(n);
+ if (ret)
+ return ret;
+
+ bch2_bkey_drop_device(bkey_i_to_s(n), dev);
+ return bch2_btree_insert_trans(trans, btree, n, 0);
+}
+
+static int check_extent_checksum(struct btree_trans *trans,
+ enum btree_id btree, struct bkey_s_c extent,
+ enum btree_id o_btree, struct bkey_s_c extent2, unsigned dev)
+{
+ struct bch_fs *c = trans->c;
+ struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(extent);
+ const union bch_extent_entry *entry;
+ struct extent_ptr_decoded p;
+ struct printbuf buf = PRINTBUF;
+ void *data_buf = NULL;
+ struct bio *bio = NULL;
+ size_t bytes;
+ int ret = 0;
+
+ if (bkey_is_btree_ptr(extent.k))
+ return false;
+
+ bkey_for_each_ptr_decode(extent.k, ptrs, p, entry)
+ if (p.ptr.dev == dev)
+ goto found;
+ BUG();
+found:
+ if (!p.crc.csum_type)
+ return false;
+
+ bytes = p.crc.compressed_size << 9;
+
+ struct bch_dev *ca = bch_dev_bkey_exists(c, dev);
+ if (!bch2_dev_get_ioref(ca, READ))
+ return false;
+
+ data_buf = kvmalloc(bytes, GFP_KERNEL);
+ if (!data_buf) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ bio = bio_alloc(ca->disk_sb.bdev, 1, REQ_OP_READ, GFP_KERNEL);
+ bio->bi_iter.bi_sector = p.ptr.offset;
+ bch2_bio_map(bio, data_buf, bytes);
+ ret = submit_bio_wait(bio);
+ if (ret)
+ goto err;
+
+ prt_str(&buf, "extents pointing to same space, but first extent checksum bad:");
+ prt_printf(&buf, "\n %s ", bch2_btree_id_str(btree));
+ bch2_bkey_val_to_text(&buf, c, extent);
+ prt_printf(&buf, "\n %s ", bch2_btree_id_str(o_btree));
+ bch2_bkey_val_to_text(&buf, c, extent2);
+
+ struct nonce nonce = extent_nonce(extent.k->version, p.crc);
+ struct bch_csum csum = bch2_checksum(c, p.crc.csum_type, nonce, data_buf, bytes);
+ if (fsck_err_on(bch2_crc_cmp(csum, p.crc.csum),
+ c, dup_backpointer_to_bad_csum_extent,
+ "%s", buf.buf))
+ ret = drop_dev_and_update(trans, btree, extent, dev) ?: 1;
+fsck_err:
+err:
+ if (bio)
+ bio_put(bio);
+ kvfree(data_buf);
+ percpu_ref_put(&ca->io_ref);
+ printbuf_exit(&buf);
+ return ret;
+}
+
static int check_bp_exists(struct btree_trans *trans,
struct extents_to_bp_state *s,
struct bpos bucket,
@@ -421,7 +504,8 @@
struct bkey_s_c orig_k)
{
struct bch_fs *c = trans->c;
- struct btree_iter bp_iter = { NULL };
+ struct btree_iter bp_iter = {};
+ struct btree_iter other_extent_iter = {};
struct printbuf buf = PRINTBUF;
struct bkey_s_c bp_k;
struct bkey_buf tmp;
@@ -429,13 +513,19 @@
bch2_bkey_buf_init(&tmp);
+ if (!bch2_dev_bucket_exists(c, bucket)) {
+ prt_str(&buf, "extent for nonexistent device:bucket ");
+ bch2_bpos_to_text(&buf, bucket);
+ prt_str(&buf, "\n ");
+ bch2_bkey_val_to_text(&buf, c, orig_k);
+ bch_err(c, "%s", buf.buf);
+ return -BCH_ERR_fsck_repair_unimplemented;
+ }
+
if (bpos_lt(bucket, s->bucket_start) ||
bpos_gt(bucket, s->bucket_end))
return 0;
- if (!bch2_dev_bucket_exists(c, bucket))
- goto missing;
-
bp_k = bch2_bkey_get_iter(trans, &bp_iter, BTREE_ID_backpointers,
bucket_pos_to_bp(c, bucket, bp.bucket_offset),
0);
@@ -461,21 +551,94 @@
ret = -BCH_ERR_transaction_restart_write_buffer_flush;
goto out;
}
- goto missing;
+
+ goto check_existing_bp;
}
out:
err:
fsck_err:
+ bch2_trans_iter_exit(trans, &other_extent_iter);
bch2_trans_iter_exit(trans, &bp_iter);
bch2_bkey_buf_exit(&tmp, c);
printbuf_exit(&buf);
return ret;
+check_existing_bp:
+ /* Do we have a backpointer for a different extent? */
+ if (bp_k.k->type != KEY_TYPE_backpointer)
+ goto missing;
+
+ struct bch_backpointer other_bp = *bkey_s_c_to_backpointer(bp_k).v;
+
+ struct bkey_s_c other_extent =
+ bch2_backpointer_get_key(trans, &other_extent_iter, bp_k.k->p, other_bp, 0);
+ ret = bkey_err(other_extent);
+ if (ret == -BCH_ERR_backpointer_to_overwritten_btree_node)
+ ret = 0;
+ if (ret)
+ goto err;
+
+ if (!other_extent.k)
+ goto missing;
+
+ if (bch2_extents_match(orig_k, other_extent)) {
+ printbuf_reset(&buf);
+ prt_printf(&buf, "duplicate versions of same extent, deleting smaller\n ");
+ bch2_bkey_val_to_text(&buf, c, orig_k);
+ prt_str(&buf, "\n ");
+ bch2_bkey_val_to_text(&buf, c, other_extent);
+ bch_err(c, "%s", buf.buf);
+
+ if (other_extent.k->size <= orig_k.k->size) {
+ ret = drop_dev_and_update(trans, other_bp.btree_id, other_extent, bucket.inode);
+ if (ret)
+ goto err;
+ goto out;
+ } else {
+ ret = drop_dev_and_update(trans, bp.btree_id, orig_k, bucket.inode);
+ if (ret)
+ goto err;
+ goto missing;
+ }
+ }
+
+ ret = check_extent_checksum(trans, other_bp.btree_id, other_extent, bp.btree_id, orig_k, bucket.inode);
+ if (ret < 0)
+ goto err;
+ if (ret) {
+ ret = 0;
+ goto missing;
+ }
+
+ ret = check_extent_checksum(trans, bp.btree_id, orig_k, other_bp.btree_id, other_extent, bucket.inode);
+ if (ret < 0)
+ goto err;
+ if (ret) {
+ ret = 0;
+ goto out;
+ }
+
+ printbuf_reset(&buf);
+ prt_printf(&buf, "duplicate extents pointing to same space on dev %llu\n ", bucket.inode);
+ bch2_bkey_val_to_text(&buf, c, orig_k);
+ prt_str(&buf, "\n ");
+ bch2_bkey_val_to_text(&buf, c, other_extent);
+ bch_err(c, "%s", buf.buf);
+ ret = -BCH_ERR_fsck_repair_unimplemented;
+ goto err;
missing:
+ printbuf_reset(&buf);
prt_printf(&buf, "missing backpointer for btree=%s l=%u ",
bch2_btree_id_str(bp.btree_id), bp.level);
bch2_bkey_val_to_text(&buf, c, orig_k);
- prt_printf(&buf, "\nbp pos ");
- bch2_bpos_to_text(&buf, bp_iter.pos);
+ prt_printf(&buf, "\n got: ");
+ bch2_bkey_val_to_text(&buf, c, bp_k);
+
+ struct bkey_i_backpointer n_bp_k;
+ bkey_backpointer_init(&n_bp_k.k_i);
+ n_bp_k.k.p = bucket_pos_to_bp(trans->c, bucket, bp.bucket_offset);
+ n_bp_k.v = bp;
+ prt_printf(&buf, "\n want: ");
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&n_bp_k.k_i));
if (fsck_err(c, ptr_to_missing_backpointer, "%s", buf.buf))
ret = bch2_bucket_backpointer_mod(trans, bucket, bp, orig_k, true);
@@ -502,8 +665,7 @@
if (p.ptr.cached)
continue;
- bch2_extent_ptr_to_bp(c, btree, level,
- k, p, &bucket_pos, &bp);
+ bch2_extent_ptr_to_bp(c, btree, level, k, p, entry, &bucket_pos, &bp);
ret = check_bp_exists(trans, s, bucket_pos, bp, k);
if (ret)
diff --git a/fs/bcachefs/backpointers.h b/fs/bcachefs/backpointers.h
index 327365a..da012ca 100644
--- a/fs/bcachefs/backpointers.h
+++ b/fs/bcachefs/backpointers.h
@@ -90,20 +90,40 @@
return bch2_trans_update_buffered(trans, BTREE_ID_backpointers, &bp_k.k_i);
}
-static inline enum bch_data_type bkey_ptr_data_type(enum btree_id btree_id, unsigned level,
- struct bkey_s_c k, struct extent_ptr_decoded p)
+static inline enum bch_data_type bch2_bkey_ptr_data_type(struct bkey_s_c k,
+ struct extent_ptr_decoded p,
+ const union bch_extent_entry *entry)
{
- return level ? BCH_DATA_btree :
- p.has_ec ? BCH_DATA_stripe :
- BCH_DATA_user;
+ switch (k.k->type) {
+ case KEY_TYPE_btree_ptr:
+ case KEY_TYPE_btree_ptr_v2:
+ return BCH_DATA_btree;
+ case KEY_TYPE_extent:
+ case KEY_TYPE_reflink_v:
+ return p.has_ec ? BCH_DATA_stripe : BCH_DATA_user;
+ case KEY_TYPE_stripe: {
+ const struct bch_extent_ptr *ptr = &entry->ptr;
+ struct bkey_s_c_stripe s = bkey_s_c_to_stripe(k);
+
+ BUG_ON(ptr < s.v->ptrs ||
+ ptr >= s.v->ptrs + s.v->nr_blocks);
+
+ return ptr >= s.v->ptrs + s.v->nr_blocks - s.v->nr_redundant
+ ? BCH_DATA_parity
+ : BCH_DATA_user;
+ }
+ default:
+ BUG();
+ }
}
static inline void bch2_extent_ptr_to_bp(struct bch_fs *c,
enum btree_id btree_id, unsigned level,
struct bkey_s_c k, struct extent_ptr_decoded p,
+ const union bch_extent_entry *entry,
struct bpos *bucket_pos, struct bch_backpointer *bp)
{
- enum bch_data_type data_type = bkey_ptr_data_type(btree_id, level, k, p);
+ enum bch_data_type data_type = bch2_bkey_ptr_data_type(k, p, entry);
s64 sectors = level ? btree_sectors(c) : k.k->size;
u32 bucket_offset;
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 799aa32..a31a5f7 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -209,7 +209,7 @@
#include "fifo.h"
#include "nocow_locking_types.h"
#include "opts.h"
-#include "recovery_types.h"
+#include "recovery_passes_types.h"
#include "sb-errors_types.h"
#include "seqmutex.h"
#include "time_stats.h"
@@ -456,6 +456,7 @@
#include "alloc_types.h"
#include "btree_types.h"
+#include "btree_node_scan_types.h"
#include "btree_write_buffer_types.h"
#include "buckets_types.h"
#include "buckets_waiting_for_journal_types.h"
@@ -614,6 +615,7 @@
*/
#define BCH_FS_FLAGS() \
+ x(new_fs) \
x(started) \
x(may_go_rw) \
x(rw) \
@@ -796,6 +798,7 @@
u64 features;
u64 compat;
unsigned long errors_silent[BITS_TO_LONGS(BCH_SB_ERR_MAX)];
+ u64 btrees_lost_data;
} sb;
@@ -810,7 +813,6 @@
/* snapshot.c: */
struct snapshot_table __rcu *snapshots;
- size_t snapshot_table_size;
struct mutex snapshot_table_lock;
struct rw_semaphore snapshot_create_lock;
@@ -1104,6 +1106,8 @@
struct journal_keys journal_keys;
struct list_head journal_iters;
+ struct find_btree_nodes found_btree_nodes;
+
u64 last_bucket_seq_cleanup;
u64 counters_on_mount[BCH_COUNTER_NR];
diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index bff8750..6310299 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -818,6 +818,7 @@
struct bch_sb_field field;
__le64 recovery_passes_required[2];
__le64 errors_silent[8];
+ __le64 btrees_lost_data;
};
struct bch_sb_field_downgrade_entry {
diff --git a/fs/bcachefs/bset.c b/fs/bcachefs/bset.c
index 3fd1085..3bb4778 100644
--- a/fs/bcachefs/bset.c
+++ b/fs/bcachefs/bset.c
@@ -134,18 +134,24 @@
printbuf_exit(&buf);
}
-#ifdef CONFIG_BCACHEFS_DEBUG
-
-void __bch2_verify_btree_nr_keys(struct btree *b)
+struct btree_nr_keys bch2_btree_node_count_keys(struct btree *b)
{
struct bset_tree *t;
struct bkey_packed *k;
- struct btree_nr_keys nr = { 0 };
+ struct btree_nr_keys nr = {};
for_each_bset(b, t)
bset_tree_for_each_key(b, t, k)
if (!bkey_deleted(k))
btree_keys_account_key_add(&nr, t - b->set, k);
+ return nr;
+}
+
+#ifdef CONFIG_BCACHEFS_DEBUG
+
+void __bch2_verify_btree_nr_keys(struct btree *b)
+{
+ struct btree_nr_keys nr = bch2_btree_node_count_keys(b);
BUG_ON(memcmp(&nr, &b->nr, sizeof(nr)));
}
diff --git a/fs/bcachefs/bset.h b/fs/bcachefs/bset.h
index 79c77ba..120a79f 100644
--- a/fs/bcachefs/bset.h
+++ b/fs/bcachefs/bset.h
@@ -458,6 +458,8 @@
/* Accounting: */
+struct btree_nr_keys bch2_btree_node_count_keys(struct btree *);
+
static inline void btree_keys_account_key(struct btree_nr_keys *n,
unsigned bset,
struct bkey_packed *k,
diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index 562561a..8447432 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -808,7 +808,8 @@
prt_printf(&buf, "\nmax ");
bch2_bpos_to_text(&buf, b->data->max_key);
- bch2_fs_inconsistent(c, "%s", buf.buf);
+ bch2_fs_topology_error(c, "%s", buf.buf);
+
printbuf_exit(&buf);
}
@@ -1134,6 +1135,8 @@
b = btree_cache_find(bc, k);
if (!b)
return;
+
+ BUG_ON(b == btree_node_root(trans->c, b));
wait_on_io:
/* not allowed to wait on io with btree locks held: */
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index bdaed29..6280da1 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -7,11 +7,13 @@
#include "bcachefs.h"
#include "alloc_background.h"
#include "alloc_foreground.h"
+#include "backpointers.h"
#include "bkey_methods.h"
#include "bkey_buf.h"
#include "btree_journal_iter.h"
#include "btree_key_cache.h"
#include "btree_locking.h"
+#include "btree_node_scan.h"
#include "btree_update_interior.h"
#include "btree_io.h"
#include "btree_gc.h"
@@ -24,7 +26,7 @@
#include "journal.h"
#include "keylist.h"
#include "move.h"
-#include "recovery.h"
+#include "recovery_passes.h"
#include "reflink.h"
#include "replicas.h"
#include "super-io.h"
@@ -40,6 +42,7 @@
#define DROP_THIS_NODE 10
#define DROP_PREV_NODE 11
+#define DID_FILL_FROM_SCAN 12
static struct bkey_s unsafe_bkey_s_c_to_s(struct bkey_s_c k)
{
@@ -70,90 +73,6 @@
__gc_pos_set(c, new_pos);
}
-/*
- * Missing: if an interior btree node is empty, we need to do something -
- * perhaps just kill it
- */
-static int bch2_gc_check_topology(struct bch_fs *c,
- struct btree *b,
- struct bkey_buf *prev,
- struct bkey_buf cur,
- bool is_last)
-{
- struct bpos node_start = b->data->min_key;
- struct bpos node_end = b->data->max_key;
- struct bpos expected_start = bkey_deleted(&prev->k->k)
- ? node_start
- : bpos_successor(prev->k->k.p);
- struct printbuf buf1 = PRINTBUF, buf2 = PRINTBUF;
- int ret = 0;
-
- if (cur.k->k.type == KEY_TYPE_btree_ptr_v2) {
- struct bkey_i_btree_ptr_v2 *bp = bkey_i_to_btree_ptr_v2(cur.k);
-
- if (!bpos_eq(expected_start, bp->v.min_key)) {
- bch2_topology_error(c);
-
- if (bkey_deleted(&prev->k->k)) {
- prt_printf(&buf1, "start of node: ");
- bch2_bpos_to_text(&buf1, node_start);
- } else {
- bch2_bkey_val_to_text(&buf1, c, bkey_i_to_s_c(prev->k));
- }
- bch2_bkey_val_to_text(&buf2, c, bkey_i_to_s_c(cur.k));
-
- if (__fsck_err(c,
- FSCK_CAN_FIX|
- FSCK_CAN_IGNORE|
- FSCK_NO_RATELIMIT,
- btree_node_topology_bad_min_key,
- "btree node with incorrect min_key at btree %s level %u:\n"
- " prev %s\n"
- " cur %s",
- bch2_btree_id_str(b->c.btree_id), b->c.level,
- buf1.buf, buf2.buf) && should_restart_for_topology_repair(c)) {
- bch_info(c, "Halting mark and sweep to start topology repair pass");
- ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_topology);
- goto err;
- } else {
- set_bit(BCH_FS_initial_gc_unfixed, &c->flags);
- }
- }
- }
-
- if (is_last && !bpos_eq(cur.k->k.p, node_end)) {
- bch2_topology_error(c);
-
- printbuf_reset(&buf1);
- printbuf_reset(&buf2);
-
- bch2_bkey_val_to_text(&buf1, c, bkey_i_to_s_c(cur.k));
- bch2_bpos_to_text(&buf2, node_end);
-
- if (__fsck_err(c, FSCK_CAN_FIX|FSCK_CAN_IGNORE|FSCK_NO_RATELIMIT,
- btree_node_topology_bad_max_key,
- "btree node with incorrect max_key at btree %s level %u:\n"
- " %s\n"
- " expected %s",
- bch2_btree_id_str(b->c.btree_id), b->c.level,
- buf1.buf, buf2.buf) &&
- should_restart_for_topology_repair(c)) {
- bch_info(c, "Halting mark and sweep to start topology repair pass");
- ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_topology);
- goto err;
- } else {
- set_bit(BCH_FS_initial_gc_unfixed, &c->flags);
- }
- }
-
- bch2_bkey_buf_copy(prev, c, cur.k);
-err:
-fsck_err:
- printbuf_exit(&buf2);
- printbuf_exit(&buf1);
- return ret;
-}
-
static void btree_ptr_to_v2(struct btree *b, struct bkey_i_btree_ptr_v2 *dst)
{
switch (b->key.k.type) {
@@ -212,6 +131,17 @@
struct bkey_i_btree_ptr_v2 *new;
int ret;
+ if (c->opts.verbose) {
+ struct printbuf buf = PRINTBUF;
+
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key));
+ prt_str(&buf, " -> ");
+ bch2_bpos_to_text(&buf, new_min);
+
+ bch_info(c, "%s(): %s", __func__, buf.buf);
+ printbuf_exit(&buf);
+ }
+
new = kmalloc_array(BKEY_BTREE_PTR_U64s_MAX, sizeof(u64), GFP_KERNEL);
if (!new)
return -BCH_ERR_ENOMEM_gc_repair_key;
@@ -237,6 +167,17 @@
struct bkey_i_btree_ptr_v2 *new;
int ret;
+ if (c->opts.verbose) {
+ struct printbuf buf = PRINTBUF;
+
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key));
+ prt_str(&buf, " -> ");
+ bch2_bpos_to_text(&buf, new_max);
+
+ bch_info(c, "%s(): %s", __func__, buf.buf);
+ printbuf_exit(&buf);
+ }
+
ret = bch2_journal_key_delete(c, b->c.btree_id, b->c.level + 1, b->key.k.p);
if (ret)
return ret;
@@ -268,127 +209,138 @@
return 0;
}
-static int btree_repair_node_boundaries(struct bch_fs *c, struct btree *b,
- struct btree *prev, struct btree *cur)
+static int btree_check_node_boundaries(struct bch_fs *c, struct btree *b,
+ struct btree *prev, struct btree *cur,
+ struct bpos *pulled_from_scan)
{
struct bpos expected_start = !prev
? b->data->min_key
: bpos_successor(prev->key.k.p);
- struct printbuf buf1 = PRINTBUF, buf2 = PRINTBUF;
+ struct printbuf buf = PRINTBUF;
int ret = 0;
- if (!prev) {
- prt_printf(&buf1, "start of node: ");
- bch2_bpos_to_text(&buf1, b->data->min_key);
- } else {
- bch2_bkey_val_to_text(&buf1, c, bkey_i_to_s_c(&prev->key));
+ BUG_ON(b->key.k.type == KEY_TYPE_btree_ptr_v2 &&
+ !bpos_eq(bkey_i_to_btree_ptr_v2(&b->key)->v.min_key,
+ b->data->min_key));
+
+ if (bpos_eq(expected_start, cur->data->min_key))
+ return 0;
+
+ prt_printf(&buf, " at btree %s level %u:\n parent: ",
+ bch2_btree_id_str(b->c.btree_id), b->c.level);
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key));
+
+ if (prev) {
+ prt_printf(&buf, "\n prev: ");
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&prev->key));
}
- bch2_bkey_val_to_text(&buf2, c, bkey_i_to_s_c(&cur->key));
+ prt_str(&buf, "\n next: ");
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&cur->key));
- if (prev &&
- bpos_gt(expected_start, cur->data->min_key) &&
- BTREE_NODE_SEQ(cur->data) > BTREE_NODE_SEQ(prev->data)) {
- /* cur overwrites prev: */
+ if (bpos_lt(expected_start, cur->data->min_key)) { /* gap */
+ if (b->c.level == 1 &&
+ bpos_lt(*pulled_from_scan, cur->data->min_key)) {
+ ret = bch2_get_scanned_nodes(c, b->c.btree_id, 0,
+ expected_start,
+ bpos_predecessor(cur->data->min_key));
+ if (ret)
+ goto err;
- if (mustfix_fsck_err_on(bpos_ge(prev->data->min_key,
- cur->data->min_key), c,
- btree_node_topology_overwritten_by_next_node,
- "btree node overwritten by next node at btree %s level %u:\n"
- " node %s\n"
- " next %s",
- bch2_btree_id_str(b->c.btree_id), b->c.level,
- buf1.buf, buf2.buf)) {
- ret = DROP_PREV_NODE;
- goto out;
+ *pulled_from_scan = cur->data->min_key;
+ ret = DID_FILL_FROM_SCAN;
+ } else {
+ if (mustfix_fsck_err(c, btree_node_topology_bad_min_key,
+ "btree node with incorrect min_key%s", buf.buf))
+ ret = set_node_min(c, cur, expected_start);
}
-
- if (mustfix_fsck_err_on(!bpos_eq(prev->key.k.p,
- bpos_predecessor(cur->data->min_key)), c,
- btree_node_topology_bad_max_key,
- "btree node with incorrect max_key at btree %s level %u:\n"
- " node %s\n"
- " next %s",
- bch2_btree_id_str(b->c.btree_id), b->c.level,
- buf1.buf, buf2.buf))
- ret = set_node_max(c, prev,
- bpos_predecessor(cur->data->min_key));
- } else {
- /* prev overwrites cur: */
-
- if (mustfix_fsck_err_on(bpos_ge(expected_start,
- cur->data->max_key), c,
- btree_node_topology_overwritten_by_prev_node,
- "btree node overwritten by prev node at btree %s level %u:\n"
- " prev %s\n"
- " node %s",
- bch2_btree_id_str(b->c.btree_id), b->c.level,
- buf1.buf, buf2.buf)) {
- ret = DROP_THIS_NODE;
- goto out;
+ } else { /* overlap */
+ if (prev && BTREE_NODE_SEQ(cur->data) > BTREE_NODE_SEQ(prev->data)) { /* cur overwrites prev */
+ if (bpos_ge(prev->data->min_key, cur->data->min_key)) { /* fully? */
+ if (mustfix_fsck_err(c, btree_node_topology_overwritten_by_next_node,
+ "btree node overwritten by next node%s", buf.buf))
+ ret = DROP_PREV_NODE;
+ } else {
+ if (mustfix_fsck_err(c, btree_node_topology_bad_max_key,
+ "btree node with incorrect max_key%s", buf.buf))
+ ret = set_node_max(c, prev,
+ bpos_predecessor(cur->data->min_key));
+ }
+ } else {
+ if (bpos_ge(expected_start, cur->data->max_key)) { /* fully? */
+ if (mustfix_fsck_err(c, btree_node_topology_overwritten_by_prev_node,
+ "btree node overwritten by prev node%s", buf.buf))
+ ret = DROP_THIS_NODE;
+ } else {
+ if (mustfix_fsck_err(c, btree_node_topology_bad_min_key,
+ "btree node with incorrect min_key%s", buf.buf))
+ ret = set_node_min(c, cur, expected_start);
+ }
}
-
- if (mustfix_fsck_err_on(!bpos_eq(expected_start, cur->data->min_key), c,
- btree_node_topology_bad_min_key,
- "btree node with incorrect min_key at btree %s level %u:\n"
- " prev %s\n"
- " node %s",
- bch2_btree_id_str(b->c.btree_id), b->c.level,
- buf1.buf, buf2.buf))
- ret = set_node_min(c, cur, expected_start);
}
-out:
+err:
fsck_err:
- printbuf_exit(&buf2);
- printbuf_exit(&buf1);
+ printbuf_exit(&buf);
return ret;
}
static int btree_repair_node_end(struct bch_fs *c, struct btree *b,
- struct btree *child)
+ struct btree *child, struct bpos *pulled_from_scan)
{
- struct printbuf buf1 = PRINTBUF, buf2 = PRINTBUF;
+ struct printbuf buf = PRINTBUF;
int ret = 0;
- bch2_bkey_val_to_text(&buf1, c, bkey_i_to_s_c(&child->key));
- bch2_bpos_to_text(&buf2, b->key.k.p);
+ if (bpos_eq(child->key.k.p, b->key.k.p))
+ return 0;
- if (mustfix_fsck_err_on(!bpos_eq(child->key.k.p, b->key.k.p), c,
- btree_node_topology_bad_max_key,
- "btree node with incorrect max_key at btree %s level %u:\n"
- " %s\n"
- " expected %s",
- bch2_btree_id_str(b->c.btree_id), b->c.level,
- buf1.buf, buf2.buf)) {
- ret = set_node_max(c, child, b->key.k.p);
- if (ret)
- goto err;
+ prt_printf(&buf, "at btree %s level %u:\n parent: ",
+ bch2_btree_id_str(b->c.btree_id), b->c.level);
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key));
+
+ prt_str(&buf, "\n child: ");
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&child->key));
+
+ if (mustfix_fsck_err(c, btree_node_topology_bad_max_key,
+ "btree node with incorrect max_key%s", buf.buf)) {
+ if (b->c.level == 1 &&
+ bpos_lt(*pulled_from_scan, b->key.k.p)) {
+ ret = bch2_get_scanned_nodes(c, b->c.btree_id, 0,
+ bpos_successor(child->key.k.p), b->key.k.p);
+ if (ret)
+ goto err;
+
+ *pulled_from_scan = b->key.k.p;
+ ret = DID_FILL_FROM_SCAN;
+ } else {
+ ret = set_node_max(c, child, b->key.k.p);
+ }
}
err:
fsck_err:
- printbuf_exit(&buf2);
- printbuf_exit(&buf1);
+ printbuf_exit(&buf);
return ret;
}
-static int bch2_btree_repair_topology_recurse(struct btree_trans *trans, struct btree *b)
+static int bch2_btree_repair_topology_recurse(struct btree_trans *trans, struct btree *b,
+ struct bpos *pulled_from_scan)
{
struct bch_fs *c = trans->c;
struct btree_and_journal_iter iter;
struct bkey_s_c k;
struct bkey_buf prev_k, cur_k;
struct btree *prev = NULL, *cur = NULL;
- bool have_child, dropped_children = false;
+ bool have_child, new_pass = false;
struct printbuf buf = PRINTBUF;
int ret = 0;
if (!b->c.level)
return 0;
-again:
- prev = NULL;
- have_child = dropped_children = false;
+
bch2_bkey_buf_init(&prev_k);
bch2_bkey_buf_init(&cur_k);
+again:
+ cur = prev = NULL;
+ have_child = new_pass = false;
bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b);
iter.prefetch = true;
@@ -415,9 +367,10 @@
b->c.level - 1,
buf.buf)) {
bch2_btree_node_evict(trans, cur_k.k);
- ret = bch2_journal_key_delete(c, b->c.btree_id,
- b->c.level, cur_k.k->k.p);
cur = NULL;
+ ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes) ?:
+ bch2_journal_key_delete(c, b->c.btree_id,
+ b->c.level, cur_k.k->k.p);
if (ret)
break;
continue;
@@ -427,7 +380,23 @@
if (ret)
break;
- ret = btree_repair_node_boundaries(c, b, prev, cur);
+ if (bch2_btree_node_is_stale(c, cur)) {
+ bch_info(c, "btree node %s older than nodes found by scanning", buf.buf);
+ six_unlock_read(&cur->c.lock);
+ bch2_btree_node_evict(trans, cur_k.k);
+ ret = bch2_journal_key_delete(c, b->c.btree_id,
+ b->c.level, cur_k.k->k.p);
+ cur = NULL;
+ if (ret)
+ break;
+ continue;
+ }
+
+ ret = btree_check_node_boundaries(c, b, prev, cur, pulled_from_scan);
+ if (ret == DID_FILL_FROM_SCAN) {
+ new_pass = true;
+ ret = 0;
+ }
if (ret == DROP_THIS_NODE) {
six_unlock_read(&cur->c.lock);
@@ -445,6 +414,7 @@
prev = NULL;
if (ret == DROP_PREV_NODE) {
+ bch_info(c, "dropped prev node");
bch2_btree_node_evict(trans, prev_k.k);
ret = bch2_journal_key_delete(c, b->c.btree_id,
b->c.level, prev_k.k->k.p);
@@ -452,8 +422,6 @@
break;
bch2_btree_and_journal_iter_exit(&iter);
- bch2_bkey_buf_exit(&prev_k, c);
- bch2_bkey_buf_exit(&cur_k, c);
goto again;
} else if (ret)
break;
@@ -465,7 +433,11 @@
if (!ret && !IS_ERR_OR_NULL(prev)) {
BUG_ON(cur);
- ret = btree_repair_node_end(c, b, prev);
+ ret = btree_repair_node_end(c, b, prev, pulled_from_scan);
+ if (ret == DID_FILL_FROM_SCAN) {
+ new_pass = true;
+ ret = 0;
+ }
}
if (!IS_ERR_OR_NULL(prev))
@@ -479,6 +451,10 @@
goto err;
bch2_btree_and_journal_iter_exit(&iter);
+
+ if (new_pass)
+ goto again;
+
bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b);
iter.prefetch = true;
@@ -495,7 +471,7 @@
if (ret)
goto err;
- ret = bch2_btree_repair_topology_recurse(trans, cur);
+ ret = bch2_btree_repair_topology_recurse(trans, cur, pulled_from_scan);
six_unlock_read(&cur->c.lock);
cur = NULL;
@@ -503,7 +479,7 @@
bch2_btree_node_evict(trans, cur_k.k);
ret = bch2_journal_key_delete(c, b->c.btree_id,
b->c.level, cur_k.k->k.p);
- dropped_children = true;
+ new_pass = true;
}
if (ret)
@@ -530,12 +506,14 @@
six_unlock_read(&cur->c.lock);
bch2_btree_and_journal_iter_exit(&iter);
- bch2_bkey_buf_exit(&prev_k, c);
- bch2_bkey_buf_exit(&cur_k, c);
- if (!ret && dropped_children)
+ if (!ret && new_pass)
goto again;
+ BUG_ON(!ret && bch2_btree_node_check_topology(trans, b));
+
+ bch2_bkey_buf_exit(&prev_k, c);
+ bch2_bkey_buf_exit(&cur_k, c);
printbuf_exit(&buf);
return ret;
}
@@ -543,32 +521,63 @@
int bch2_check_topology(struct bch_fs *c)
{
struct btree_trans *trans = bch2_trans_get(c);
- struct btree *b;
- unsigned i;
+ struct bpos pulled_from_scan = POS_MIN;
int ret = 0;
- for (i = 0; i < btree_id_nr_alive(c) && !ret; i++) {
+ for (unsigned i = 0; i < btree_id_nr_alive(c) && !ret; i++) {
struct btree_root *r = bch2_btree_id_root(c, i);
+ bool reconstructed_root = false;
- if (!r->alive)
- continue;
+ if (r->error) {
+ ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes);
+ if (ret)
+ break;
+reconstruct_root:
+ bch_info(c, "btree root %s unreadable, must recover from scan", bch2_btree_id_str(i));
- b = r->b;
- if (btree_node_fake(b))
- continue;
+ r->alive = false;
+ r->error = 0;
+
+ if (!bch2_btree_has_scanned_nodes(c, i)) {
+ mustfix_fsck_err(c, btree_root_unreadable_and_scan_found_nothing,
+ "no nodes found for btree %s, continue?", bch2_btree_id_str(i));
+ bch2_btree_root_alloc_fake(c, i, 0);
+ } else {
+ bch2_btree_root_alloc_fake(c, i, 1);
+ ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX);
+ if (ret)
+ break;
+ }
+
+ bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+ reconstructed_root = true;
+ }
+
+ struct btree *b = r->b;
btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read);
- ret = bch2_btree_repair_topology_recurse(trans, b);
+ ret = bch2_btree_repair_topology_recurse(trans, b, &pulled_from_scan);
six_unlock_read(&b->c.lock);
if (ret == DROP_THIS_NODE) {
- bch_err(c, "empty btree root - repair unimplemented");
- ret = -BCH_ERR_fsck_repair_unimplemented;
+ bch2_btree_node_hash_remove(&c->btree_cache, b);
+ mutex_lock(&c->btree_cache.lock);
+ list_move(&b->list, &c->btree_cache.freeable);
+ mutex_unlock(&c->btree_cache.lock);
+
+ r->b = NULL;
+
+ if (!reconstructed_root)
+ goto reconstruct_root;
+
+ bch_err(c, "empty btree root %s", bch2_btree_id_str(i));
+ bch2_btree_root_alloc_fake(c, i, 0);
+ r->alive = false;
+ ret = 0;
}
}
-
+fsck_err:
bch2_trans_put(trans);
-
return ret;
}
@@ -591,7 +600,7 @@
bkey_for_each_ptr_decode(k->k, ptrs_c, p, entry_c) {
struct bch_dev *ca = bch_dev_bkey_exists(c, p.ptr.dev);
struct bucket *g = PTR_GC_BUCKET(ca, &p.ptr);
- enum bch_data_type data_type = bch2_bkey_ptr_data_type(*k, &entry_c->ptr);
+ enum bch_data_type data_type = bch2_bkey_ptr_data_type(*k, p, entry_c);
if (fsck_err_on(!g->gen_valid,
c, ptr_to_missing_alloc_key,
@@ -657,7 +666,8 @@
continue;
if (fsck_err_on(bucket_data_type(g->data_type) &&
- bucket_data_type(g->data_type) != data_type, c,
+ bucket_data_type(g->data_type) !=
+ bucket_data_type(data_type), c,
ptr_bucket_data_type_mismatch,
"bucket %u:%zu different types of data in same bucket: %s, %s\n"
"while marking %s",
@@ -698,18 +708,13 @@
}
if (do_update) {
- struct bkey_ptrs ptrs;
- union bch_extent_entry *entry;
- struct bch_extent_ptr *ptr;
- struct bkey_i *new;
-
if (is_root) {
bch_err(c, "cannot update btree roots yet");
ret = -EINVAL;
goto err;
}
- new = kmalloc(bkey_bytes(k->k), GFP_KERNEL);
+ struct bkey_i *new = kmalloc(bkey_bytes(k->k), GFP_KERNEL);
if (!new) {
ret = -BCH_ERR_ENOMEM_gc_repair_key;
bch_err_msg(c, ret, "allocating new key");
@@ -724,7 +729,7 @@
* btree node isn't there anymore, the read path will
* sort it out:
*/
- ptrs = bch2_bkey_ptrs(bkey_i_to_s(new));
+ struct bkey_ptrs ptrs = bch2_bkey_ptrs(bkey_i_to_s(new));
bkey_for_each_ptr(ptrs, ptr) {
struct bch_dev *ca = bch_dev_bkey_exists(c, ptr->dev);
struct bucket *g = PTR_GC_BUCKET(ca, ptr);
@@ -732,19 +737,26 @@
ptr->gen = g->gen;
}
} else {
- bch2_bkey_drop_ptrs(bkey_i_to_s(new), ptr, ({
- struct bch_dev *ca = bch_dev_bkey_exists(c, ptr->dev);
- struct bucket *g = PTR_GC_BUCKET(ca, ptr);
- enum bch_data_type data_type = bch2_bkey_ptr_data_type(*k, ptr);
+ struct bkey_ptrs ptrs;
+ union bch_extent_entry *entry;
+restart_drop_ptrs:
+ ptrs = bch2_bkey_ptrs(bkey_i_to_s(new));
+ bkey_for_each_ptr_decode(bkey_i_to_s(new).k, ptrs, p, entry) {
+ struct bch_dev *ca = bch_dev_bkey_exists(c, p.ptr.dev);
+ struct bucket *g = PTR_GC_BUCKET(ca, &p.ptr);
+ enum bch_data_type data_type = bch2_bkey_ptr_data_type(bkey_i_to_s_c(new), p, entry);
- (ptr->cached &&
- (!g->gen_valid || gen_cmp(ptr->gen, g->gen) > 0)) ||
- (!ptr->cached &&
- gen_cmp(ptr->gen, g->gen) < 0) ||
- gen_cmp(g->gen, ptr->gen) > BUCKET_GC_GEN_MAX ||
- (g->data_type &&
- g->data_type != data_type);
- }));
+ if ((p.ptr.cached &&
+ (!g->gen_valid || gen_cmp(p.ptr.gen, g->gen) > 0)) ||
+ (!p.ptr.cached &&
+ gen_cmp(p.ptr.gen, g->gen) < 0) ||
+ gen_cmp(g->gen, p.ptr.gen) > BUCKET_GC_GEN_MAX ||
+ (g->data_type &&
+ g->data_type != data_type)) {
+ bch2_bkey_drop_ptr(bkey_i_to_s(new), &entry->ptr);
+ goto restart_drop_ptrs;
+ }
+ }
again:
ptrs = bch2_bkey_ptrs(bkey_i_to_s(new));
bkey_extent_entry_for_each(ptrs, entry) {
@@ -774,12 +786,6 @@
}
}
- ret = bch2_journal_key_insert_take(c, btree_id, level, new);
- if (ret) {
- kfree(new);
- goto err;
- }
-
if (level)
bch2_btree_node_update_key_early(trans, btree_id, level - 1, *k, new);
@@ -793,6 +799,12 @@
bch_info(c, "new key %s", buf.buf);
}
+ ret = bch2_journal_key_insert_take(c, btree_id, level, new);
+ if (ret) {
+ kfree(new);
+ goto err;
+ }
+
*k = bkey_i_to_s_c(new);
}
err:
@@ -819,10 +831,6 @@
BUG_ON(bch2_journal_seq_verify &&
k->k->version.lo > atomic64_read(&c->journal.seq));
- ret = bch2_check_fix_ptrs(trans, btree_id, level, is_root, k);
- if (ret)
- goto err;
-
if (fsck_err_on(k->k->version.lo > atomic64_read(&c->key_version), c,
bkey_version_in_future,
"key version number higher than recorded: %llu > %llu",
@@ -831,8 +839,13 @@
atomic64_set(&c->key_version, k->k->version.lo);
}
+ ret = bch2_check_fix_ptrs(trans, btree_id, level, is_root, k);
+ if (ret)
+ goto err;
+
ret = commit_do(trans, NULL, NULL, 0,
- bch2_key_trigger(trans, btree_id, level, old, unsafe_bkey_s_c_to_s(*k), BTREE_TRIGGER_GC));
+ bch2_key_trigger(trans, btree_id, level, old,
+ unsafe_bkey_s_c_to_s(*k), BTREE_TRIGGER_GC));
fsck_err:
err:
bch_err_fn(c, ret);
@@ -841,42 +854,30 @@
static int btree_gc_mark_node(struct btree_trans *trans, struct btree *b, bool initial)
{
- struct bch_fs *c = trans->c;
struct btree_node_iter iter;
struct bkey unpacked;
struct bkey_s_c k;
- struct bkey_buf prev, cur;
int ret = 0;
+ ret = bch2_btree_node_check_topology(trans, b);
+ if (ret)
+ return ret;
+
if (!btree_node_type_needs_gc(btree_node_type(b)))
return 0;
bch2_btree_node_iter_init_from_start(&iter, b);
- bch2_bkey_buf_init(&prev);
- bch2_bkey_buf_init(&cur);
- bkey_init(&prev.k->k);
while ((k = bch2_btree_node_iter_peek_unpack(&iter, b, &unpacked)).k) {
ret = bch2_gc_mark_key(trans, b->c.btree_id, b->c.level, false,
&k, initial);
if (ret)
- break;
+ return ret;
bch2_btree_node_iter_advance(&iter, b);
-
- if (b->c.level) {
- bch2_bkey_buf_reassemble(&cur, c, k);
-
- ret = bch2_gc_check_topology(c, b, &prev, cur,
- bch2_btree_node_iter_end(&iter));
- if (ret)
- break;
- }
}
- bch2_bkey_buf_exit(&cur, c);
- bch2_bkey_buf_exit(&prev, c);
- return ret;
+ return 0;
}
static int bch2_gc_btree(struct btree_trans *trans, enum btree_id btree_id,
@@ -925,14 +926,16 @@
struct bch_fs *c = trans->c;
struct btree_and_journal_iter iter;
struct bkey_s_c k;
- struct bkey_buf cur, prev;
+ struct bkey_buf cur;
struct printbuf buf = PRINTBUF;
int ret = 0;
+ ret = bch2_btree_node_check_topology(trans, b);
+ if (ret)
+ return ret;
+
bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b);
- bch2_bkey_buf_init(&prev);
bch2_bkey_buf_init(&cur);
- bkey_init(&prev.k->k);
while ((k = bch2_btree_and_journal_iter_peek(&iter)).k) {
BUG_ON(bpos_lt(k.k->p, b->data->min_key));
@@ -943,20 +946,7 @@
if (ret)
goto fsck_err;
- if (b->c.level) {
- bch2_bkey_buf_reassemble(&cur, c, k);
- k = bkey_i_to_s_c(cur.k);
-
- bch2_btree_and_journal_iter_advance(&iter);
-
- ret = bch2_gc_check_topology(c, b,
- &prev, cur,
- !bch2_btree_and_journal_iter_peek(&iter).k);
- if (ret)
- goto fsck_err;
- } else {
- bch2_btree_and_journal_iter_advance(&iter);
- }
+ bch2_btree_and_journal_iter_advance(&iter);
}
if (b->c.level > target_depth) {
@@ -1015,7 +1005,6 @@
}
fsck_err:
bch2_bkey_buf_exit(&cur, c);
- bch2_bkey_buf_exit(&prev, c);
bch2_btree_and_journal_iter_exit(&iter);
printbuf_exit(&buf);
return ret;
@@ -1033,9 +1022,6 @@
b = bch2_btree_id_root(c, btree_id)->b;
- if (btree_node_fake(b))
- return 0;
-
six_lock_read(&b->c.lock, NULL, NULL);
printbuf_reset(&buf);
bch2_bpos_to_text(&buf, b->data->min_key);
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 34df8cc..d7de82a 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -654,6 +654,7 @@
*/
bch2_bset_set_no_aux_tree(b, b->set);
bch2_btree_build_aux_trees(b);
+ b->nr = bch2_btree_node_count_keys(b);
struct bkey_s_c k;
struct bkey unpacked;
@@ -1263,10 +1264,12 @@
return retry_read;
fsck_err:
if (ret == -BCH_ERR_btree_node_read_err_want_retry ||
- ret == -BCH_ERR_btree_node_read_err_must_retry)
+ ret == -BCH_ERR_btree_node_read_err_must_retry) {
retry_read = 1;
- else
+ } else {
set_btree_node_read_error(b);
+ bch2_btree_lost_data(c, b->c.btree_id);
+ }
goto out;
}
@@ -1327,6 +1330,7 @@
if (!can_retry) {
set_btree_node_read_error(b);
+ bch2_btree_lost_data(c, b->c.btree_id);
break;
}
}
@@ -1526,9 +1530,10 @@
ret = -1;
}
- if (ret)
+ if (ret) {
set_btree_node_read_error(b);
- else if (*saw_error)
+ bch2_btree_lost_data(c, b->c.btree_id);
+ } else if (*saw_error)
bch2_btree_node_rewrite_async(c, b);
for (i = 0; i < ra->nr; i++) {
@@ -1657,13 +1662,14 @@
prt_str(&buf, "btree node read error: no device to read from\n at ");
bch2_btree_pos_to_text(&buf, c, b);
- bch_err(c, "%s", buf.buf);
+ bch_err_ratelimited(c, "%s", buf.buf);
if (c->recovery_passes_explicit & BIT_ULL(BCH_RECOVERY_PASS_check_topology) &&
c->curr_recovery_pass > BCH_RECOVERY_PASS_check_topology)
bch2_fatal_error(c);
set_btree_node_read_error(b);
+ bch2_btree_lost_data(c, b->c.btree_id);
clear_btree_node_read_in_flight(b);
wake_up_bit(&b->flags, BTREE_NODE_read_in_flight);
printbuf_exit(&buf);
@@ -1860,7 +1866,7 @@
} else {
ret = bch2_trans_do(c, NULL, NULL, 0,
bch2_btree_node_update_key_get_iter(trans, b, &wbio->key,
- BCH_WATERMARK_reclaim|
+ BCH_WATERMARK_interior_updates|
BCH_TRANS_COMMIT_journal_reclaim|
BCH_TRANS_COMMIT_no_enospc|
BCH_TRANS_COMMIT_no_check_rw,
diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index 51bcdc6..2a211a4 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -927,8 +927,22 @@
if (ret)
goto err;
} else {
- bch2_bkey_buf_unpack(&tmp, c, l->b,
- bch2_btree_node_iter_peek(&l->iter, l->b));
+ struct bkey_packed *k = bch2_btree_node_iter_peek(&l->iter, l->b);
+ if (!k) {
+ struct printbuf buf = PRINTBUF;
+
+ prt_str(&buf, "node not found at pos ");
+ bch2_bpos_to_text(&buf, path->pos);
+ prt_str(&buf, " within parent node ");
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&l->b->key));
+
+ bch2_fs_fatal_error(c, "%s", buf.buf);
+ printbuf_exit(&buf);
+ ret = -BCH_ERR_btree_need_topology_repair;
+ goto err;
+ }
+
+ bch2_bkey_buf_unpack(&tmp, c, l->b, k);
if ((flags & BTREE_ITER_PREFETCH) &&
c->opts.btree_node_prefetch) {
@@ -962,7 +976,6 @@
return ret;
}
-
static int bch2_btree_path_traverse_all(struct btree_trans *trans)
{
struct bch_fs *c = trans->c;
@@ -2790,6 +2803,31 @@
struct btree_transaction_stats *s = btree_trans_stats(trans);
s->max_mem = max(s->max_mem, new_bytes);
+ if (trans->used_mempool) {
+ if (trans->mem_bytes >= new_bytes)
+ goto out_change_top;
+
+ /* No more space from mempool item, need malloc new one */
+ new_mem = kmalloc(new_bytes, GFP_NOWAIT|__GFP_NOWARN);
+ if (unlikely(!new_mem)) {
+ bch2_trans_unlock(trans);
+
+ new_mem = kmalloc(new_bytes, GFP_KERNEL);
+ if (!new_mem)
+ return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc);
+
+ ret = bch2_trans_relock(trans);
+ if (ret) {
+ kfree(new_mem);
+ return ERR_PTR(ret);
+ }
+ }
+ memcpy(new_mem, trans->mem, trans->mem_top);
+ trans->used_mempool = false;
+ mempool_free(trans->mem, &c->btree_trans_mem_pool);
+ goto out_new_mem;
+ }
+
new_mem = krealloc(trans->mem, new_bytes, GFP_NOWAIT|__GFP_NOWARN);
if (unlikely(!new_mem)) {
bch2_trans_unlock(trans);
@@ -2798,6 +2836,8 @@
if (!new_mem && new_bytes <= BTREE_TRANS_MEM_MAX) {
new_mem = mempool_alloc(&c->btree_trans_mem_pool, GFP_KERNEL);
new_bytes = BTREE_TRANS_MEM_MAX;
+ memcpy(new_mem, trans->mem, trans->mem_top);
+ trans->used_mempool = true;
kfree(trans->mem);
}
@@ -2811,7 +2851,7 @@
if (ret)
return ERR_PTR(ret);
}
-
+out_new_mem:
trans->mem = new_mem;
trans->mem_bytes = new_bytes;
@@ -2819,7 +2859,7 @@
trace_and_count(c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes);
return ERR_PTR(btree_trans_restart(trans, BCH_ERR_transaction_restart_mem_realloced));
}
-
+out_change_top:
p = trans->mem + trans->mem_top;
trans->mem_top += size;
memset(p, 0, size);
@@ -3093,7 +3133,7 @@
if (paths_allocated != trans->_paths_allocated)
kvfree_rcu_mightsleep(paths_allocated);
- if (trans->mem_bytes == BTREE_TRANS_MEM_MAX)
+ if (trans->used_mempool)
mempool_free(trans->mem, &c->btree_trans_mem_pool);
else
kfree(trans->mem);
diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c
index 50e0435..5cbcbfe 100644
--- a/fs/bcachefs/btree_journal_iter.c
+++ b/fs/bcachefs/btree_journal_iter.c
@@ -261,6 +261,22 @@
return bch2_journal_key_insert(c, id, level, &whiteout);
}
+bool bch2_key_deleted_in_journal(struct btree_trans *trans, enum btree_id btree,
+ unsigned level, struct bpos pos)
+{
+ struct journal_keys *keys = &trans->c->journal_keys;
+ size_t idx = bch2_journal_key_search(keys, btree, level, pos);
+
+ if (!trans->journal_replay_not_finished)
+ return false;
+
+ return (idx < keys->size &&
+ keys->data[idx].btree_id == btree &&
+ keys->data[idx].level == level &&
+ bpos_eq(keys->data[idx].k->k.p, pos) &&
+ bkey_deleted(&keys->data[idx].k->k));
+}
+
void bch2_journal_key_overwritten(struct bch_fs *c, enum btree_id btree,
unsigned level, struct bpos pos)
{
@@ -363,7 +379,7 @@
struct bkey_s_c bch2_btree_and_journal_iter_peek(struct btree_and_journal_iter *iter)
{
- struct bkey_s_c btree_k, journal_k, ret;
+ struct bkey_s_c btree_k, journal_k = bkey_s_c_null, ret;
if (iter->prefetch && iter->journal.level)
btree_and_journal_iter_prefetch(iter);
@@ -375,9 +391,10 @@
bpos_lt(btree_k.k->p, iter->pos))
bch2_journal_iter_advance_btree(iter);
- while ((journal_k = bch2_journal_iter_peek(&iter->journal)).k &&
- bpos_lt(journal_k.k->p, iter->pos))
- bch2_journal_iter_advance(&iter->journal);
+ if (iter->trans->journal_replay_not_finished)
+ while ((journal_k = bch2_journal_iter_peek(&iter->journal)).k &&
+ bpos_lt(journal_k.k->p, iter->pos))
+ bch2_journal_iter_advance(&iter->journal);
ret = journal_k.k &&
(!btree_k.k || bpos_le(journal_k.k->p, btree_k.k->p))
@@ -435,7 +452,9 @@
bch2_btree_node_iter_init_from_start(&node_iter, b);
__bch2_btree_and_journal_iter_init_node_iter(trans, iter, b, node_iter, b->data->min_key);
- list_add(&iter->journal.list, &trans->c->journal_iters);
+ if (trans->journal_replay_not_finished &&
+ !test_bit(BCH_FS_may_go_rw, &trans->c->flags))
+ list_add(&iter->journal.list, &trans->c->journal_iters);
}
/* sort and dedup all keys in the journal: */
@@ -548,3 +567,22 @@
bch_verbose(c, "Journal keys: %zu read, %zu after sorting and compacting", nr_read, keys->nr);
return 0;
}
+
+void bch2_shoot_down_journal_keys(struct bch_fs *c, enum btree_id btree,
+ unsigned level_min, unsigned level_max,
+ struct bpos start, struct bpos end)
+{
+ struct journal_keys *keys = &c->journal_keys;
+ size_t dst = 0;
+
+ move_gap(keys, keys->nr);
+
+ darray_for_each(*keys, i)
+ if (!(i->btree_id == btree &&
+ i->level >= level_min &&
+ i->level <= level_max &&
+ bpos_ge(i->k->k.p, start) &&
+ bpos_le(i->k->k.p, end)))
+ keys->data[dst++] = *i;
+ keys->nr = keys->gap = dst;
+}
diff --git a/fs/bcachefs/btree_journal_iter.h b/fs/bcachefs/btree_journal_iter.h
index c9d19da..af25046 100644
--- a/fs/bcachefs/btree_journal_iter.h
+++ b/fs/bcachefs/btree_journal_iter.h
@@ -40,8 +40,8 @@
unsigned, struct bkey_i *);
int bch2_journal_key_delete(struct bch_fs *, enum btree_id,
unsigned, struct bpos);
-void bch2_journal_key_overwritten(struct bch_fs *, enum btree_id,
- unsigned, struct bpos);
+bool bch2_key_deleted_in_journal(struct btree_trans *, enum btree_id, unsigned, struct bpos);
+void bch2_journal_key_overwritten(struct bch_fs *, enum btree_id, unsigned, struct bpos);
void bch2_btree_and_journal_iter_advance(struct btree_and_journal_iter *);
struct bkey_s_c bch2_btree_and_journal_iter_peek(struct btree_and_journal_iter *);
@@ -66,4 +66,8 @@
int bch2_journal_keys_sort(struct bch_fs *);
+void bch2_shoot_down_journal_keys(struct bch_fs *, enum btree_id,
+ unsigned, unsigned,
+ struct bpos, struct bpos);
+
#endif /* _BCACHEFS_BTREE_JOURNAL_ITER_H */
diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c
new file mode 100644
index 0000000..3f33be7
--- /dev/null
+++ b/fs/bcachefs/btree_node_scan.c
@@ -0,0 +1,495 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "bcachefs.h"
+#include "btree_cache.h"
+#include "btree_io.h"
+#include "btree_journal_iter.h"
+#include "btree_node_scan.h"
+#include "btree_update_interior.h"
+#include "buckets.h"
+#include "error.h"
+#include "journal_io.h"
+#include "recovery_passes.h"
+
+#include <linux/kthread.h>
+#include <linux/sort.h>
+
+struct find_btree_nodes_worker {
+ struct closure *cl;
+ struct find_btree_nodes *f;
+ struct bch_dev *ca;
+};
+
+static void found_btree_node_to_text(struct printbuf *out, struct bch_fs *c, const struct found_btree_node *n)
+{
+ prt_printf(out, "%s l=%u seq=%u cookie=%llx ", bch2_btree_id_str(n->btree_id), n->level, n->seq, n->cookie);
+ bch2_bpos_to_text(out, n->min_key);
+ prt_str(out, "-");
+ bch2_bpos_to_text(out, n->max_key);
+
+ if (n->range_updated)
+ prt_str(out, " range updated");
+ if (n->overwritten)
+ prt_str(out, " overwritten");
+
+ for (unsigned i = 0; i < n->nr_ptrs; i++) {
+ prt_char(out, ' ');
+ bch2_extent_ptr_to_text(out, c, n->ptrs + i);
+ }
+}
+
+static void found_btree_nodes_to_text(struct printbuf *out, struct bch_fs *c, found_btree_nodes nodes)
+{
+ printbuf_indent_add(out, 2);
+ darray_for_each(nodes, i) {
+ found_btree_node_to_text(out, c, i);
+ prt_newline(out);
+ }
+ printbuf_indent_sub(out, 2);
+}
+
+static void found_btree_node_to_key(struct bkey_i *k, const struct found_btree_node *f)
+{
+ struct bkey_i_btree_ptr_v2 *bp = bkey_btree_ptr_v2_init(k);
+
+ set_bkey_val_u64s(&bp->k, sizeof(struct bch_btree_ptr_v2) / sizeof(u64) + f->nr_ptrs);
+ bp->k.p = f->max_key;
+ bp->v.seq = cpu_to_le64(f->cookie);
+ bp->v.sectors_written = 0;
+ bp->v.flags = 0;
+ bp->v.min_key = f->min_key;
+ SET_BTREE_PTR_RANGE_UPDATED(&bp->v, f->range_updated);
+ memcpy(bp->v.start, f->ptrs, sizeof(struct bch_extent_ptr) * f->nr_ptrs);
+}
+
+static bool found_btree_node_is_readable(struct btree_trans *trans,
+ const struct found_btree_node *f)
+{
+ struct { __BKEY_PADDED(k, BKEY_BTREE_PTR_VAL_U64s_MAX); } k;
+
+ found_btree_node_to_key(&k.k, f);
+
+ struct btree *b = bch2_btree_node_get_noiter(trans, &k.k, f->btree_id, f->level, false);
+ bool ret = !IS_ERR_OR_NULL(b);
+ if (ret)
+ six_unlock_read(&b->c.lock);
+
+ /*
+ * We might update this node's range; if that happens, we need the node
+ * to be re-read so the read path can trim keys that are no longer in
+ * this node
+ */
+ if (b != btree_node_root(trans->c, b))
+ bch2_btree_node_evict(trans, &k.k);
+ return ret;
+}
+
+static int found_btree_node_cmp_cookie(const void *_l, const void *_r)
+{
+ const struct found_btree_node *l = _l;
+ const struct found_btree_node *r = _r;
+
+ return cmp_int(l->btree_id, r->btree_id) ?:
+ cmp_int(l->level, r->level) ?:
+ cmp_int(l->cookie, r->cookie);
+}
+
+/*
+ * Given two found btree nodes, if their sequence numbers are equal, take the
+ * one that's readable:
+ */
+static int found_btree_node_cmp_time(const struct found_btree_node *l,
+ const struct found_btree_node *r)
+{
+ return cmp_int(l->seq, r->seq);
+}
+
+static int found_btree_node_cmp_pos(const void *_l, const void *_r)
+{
+ const struct found_btree_node *l = _l;
+ const struct found_btree_node *r = _r;
+
+ return cmp_int(l->btree_id, r->btree_id) ?:
+ -cmp_int(l->level, r->level) ?:
+ bpos_cmp(l->min_key, r->min_key) ?:
+ -found_btree_node_cmp_time(l, r);
+}
+
+static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca,
+ struct bio *bio, struct btree_node *bn, u64 offset)
+{
+ struct bch_fs *c = container_of(f, struct bch_fs, found_btree_nodes);
+
+ bio_reset(bio, ca->disk_sb.bdev, REQ_OP_READ);
+ bio->bi_iter.bi_sector = offset;
+ bch2_bio_map(bio, bn, PAGE_SIZE);
+
+ submit_bio_wait(bio);
+ if (bch2_dev_io_err_on(bio->bi_status, ca, BCH_MEMBER_ERROR_read,
+ "IO error in try_read_btree_node() at %llu: %s",
+ offset, bch2_blk_status_to_str(bio->bi_status)))
+ return;
+
+ if (le64_to_cpu(bn->magic) != bset_magic(c))
+ return;
+
+ rcu_read_lock();
+ struct found_btree_node n = {
+ .btree_id = BTREE_NODE_ID(bn),
+ .level = BTREE_NODE_LEVEL(bn),
+ .seq = BTREE_NODE_SEQ(bn),
+ .cookie = le64_to_cpu(bn->keys.seq),
+ .min_key = bn->min_key,
+ .max_key = bn->max_key,
+ .nr_ptrs = 1,
+ .ptrs[0].type = 1 << BCH_EXTENT_ENTRY_ptr,
+ .ptrs[0].offset = offset,
+ .ptrs[0].dev = ca->dev_idx,
+ .ptrs[0].gen = *bucket_gen(ca, sector_to_bucket(ca, offset)),
+ };
+ rcu_read_unlock();
+
+ if (bch2_trans_run(c, found_btree_node_is_readable(trans, &n))) {
+ mutex_lock(&f->lock);
+ if (BSET_BIG_ENDIAN(&bn->keys) != CPU_BIG_ENDIAN) {
+ bch_err(c, "try_read_btree_node() can't handle endian conversion");
+ f->ret = -EINVAL;
+ goto unlock;
+ }
+
+ if (darray_push(&f->nodes, n))
+ f->ret = -ENOMEM;
+unlock:
+ mutex_unlock(&f->lock);
+ }
+}
+
+static int read_btree_nodes_worker(void *p)
+{
+ struct find_btree_nodes_worker *w = p;
+ struct bch_fs *c = container_of(w->f, struct bch_fs, found_btree_nodes);
+ struct bch_dev *ca = w->ca;
+ void *buf = (void *) __get_free_page(GFP_KERNEL);
+ struct bio *bio = bio_alloc(NULL, 1, 0, GFP_KERNEL);
+ unsigned long last_print = jiffies;
+
+ if (!buf || !bio) {
+ bch_err(c, "read_btree_nodes_worker: error allocating bio/buf");
+ w->f->ret = -ENOMEM;
+ goto err;
+ }
+
+ for (u64 bucket = ca->mi.first_bucket; bucket < ca->mi.nbuckets; bucket++)
+ for (unsigned bucket_offset = 0;
+ bucket_offset + btree_sectors(c) <= ca->mi.bucket_size;
+ bucket_offset += btree_sectors(c)) {
+ if (time_after(jiffies, last_print + HZ * 30)) {
+ u64 cur_sector = bucket * ca->mi.bucket_size + bucket_offset;
+ u64 end_sector = ca->mi.nbuckets * ca->mi.bucket_size;
+
+ bch_info(ca, "%s: %2u%% done", __func__,
+ (unsigned) div64_u64(cur_sector * 100, end_sector));
+ last_print = jiffies;
+ }
+
+ try_read_btree_node(w->f, ca, bio, buf,
+ bucket * ca->mi.bucket_size + bucket_offset);
+ }
+err:
+ bio_put(bio);
+ free_page((unsigned long) buf);
+ percpu_ref_get(&ca->io_ref);
+ closure_put(w->cl);
+ kfree(w);
+ return 0;
+}
+
+static int read_btree_nodes(struct find_btree_nodes *f)
+{
+ struct bch_fs *c = container_of(f, struct bch_fs, found_btree_nodes);
+ struct closure cl;
+ int ret = 0;
+
+ closure_init_stack(&cl);
+
+ for_each_online_member(c, ca) {
+ struct find_btree_nodes_worker *w = kmalloc(sizeof(*w), GFP_KERNEL);
+ struct task_struct *t;
+
+ if (!w) {
+ percpu_ref_put(&ca->io_ref);
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ percpu_ref_get(&ca->io_ref);
+ closure_get(&cl);
+ w->cl = &cl;
+ w->f = f;
+ w->ca = ca;
+
+ t = kthread_run(read_btree_nodes_worker, w, "read_btree_nodes/%s", ca->name);
+ ret = IS_ERR_OR_NULL(t);
+ if (ret) {
+ percpu_ref_put(&ca->io_ref);
+ closure_put(&cl);
+ f->ret = ret;
+ bch_err(c, "error starting kthread: %i", ret);
+ break;
+ }
+ }
+err:
+ closure_sync(&cl);
+ return f->ret ?: ret;
+}
+
+static void bubble_up(struct found_btree_node *n, struct found_btree_node *end)
+{
+ while (n + 1 < end &&
+ found_btree_node_cmp_pos(n, n + 1) > 0) {
+ swap(n[0], n[1]);
+ n++;
+ }
+}
+
+static int handle_overwrites(struct bch_fs *c,
+ struct found_btree_node *start,
+ struct found_btree_node *end)
+{
+ struct found_btree_node *n;
+again:
+ for (n = start + 1;
+ n < end &&
+ n->btree_id == start->btree_id &&
+ n->level == start->level &&
+ bpos_lt(n->min_key, start->max_key);
+ n++) {
+ int cmp = found_btree_node_cmp_time(start, n);
+
+ if (cmp > 0) {
+ if (bpos_cmp(start->max_key, n->max_key) >= 0)
+ n->overwritten = true;
+ else {
+ n->range_updated = true;
+ n->min_key = bpos_successor(start->max_key);
+ n->range_updated = true;
+ bubble_up(n, end);
+ goto again;
+ }
+ } else if (cmp < 0) {
+ BUG_ON(bpos_cmp(n->min_key, start->min_key) <= 0);
+
+ start->max_key = bpos_predecessor(n->min_key);
+ start->range_updated = true;
+ } else {
+ struct printbuf buf = PRINTBUF;
+
+ prt_str(&buf, "overlapping btree nodes with same seq! halting\n ");
+ found_btree_node_to_text(&buf, c, start);
+ prt_str(&buf, "\n ");
+ found_btree_node_to_text(&buf, c, n);
+ bch_err(c, "%s", buf.buf);
+ printbuf_exit(&buf);
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+int bch2_scan_for_btree_nodes(struct bch_fs *c)
+{
+ struct find_btree_nodes *f = &c->found_btree_nodes;
+ struct printbuf buf = PRINTBUF;
+ size_t dst;
+ int ret = 0;
+
+ if (f->nodes.nr)
+ return 0;
+
+ mutex_init(&f->lock);
+
+ ret = read_btree_nodes(f);
+ if (ret)
+ return ret;
+
+ if (!f->nodes.nr) {
+ bch_err(c, "%s: no btree nodes found", __func__);
+ ret = -EINVAL;
+ goto err;
+ }
+
+ if (0 && c->opts.verbose) {
+ printbuf_reset(&buf);
+ prt_printf(&buf, "%s: nodes found:\n", __func__);
+ found_btree_nodes_to_text(&buf, c, f->nodes);
+ bch2_print_string_as_lines(KERN_INFO, buf.buf);
+ }
+
+ sort(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_cookie, NULL);
+
+ dst = 0;
+ darray_for_each(f->nodes, i) {
+ struct found_btree_node *prev = dst ? f->nodes.data + dst - 1 : NULL;
+
+ if (prev &&
+ prev->cookie == i->cookie) {
+ if (prev->nr_ptrs == ARRAY_SIZE(prev->ptrs)) {
+ bch_err(c, "%s: found too many replicas for btree node", __func__);
+ ret = -EINVAL;
+ goto err;
+ }
+ prev->ptrs[prev->nr_ptrs++] = i->ptrs[0];
+ } else {
+ f->nodes.data[dst++] = *i;
+ }
+ }
+ f->nodes.nr = dst;
+
+ sort(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_pos, NULL);
+
+ if (0 && c->opts.verbose) {
+ printbuf_reset(&buf);
+ prt_printf(&buf, "%s: nodes after merging replicas:\n", __func__);
+ found_btree_nodes_to_text(&buf, c, f->nodes);
+ bch2_print_string_as_lines(KERN_INFO, buf.buf);
+ }
+
+ dst = 0;
+ darray_for_each(f->nodes, i) {
+ if (i->overwritten)
+ continue;
+
+ ret = handle_overwrites(c, i, &darray_top(f->nodes));
+ if (ret)
+ goto err;
+
+ BUG_ON(i->overwritten);
+ f->nodes.data[dst++] = *i;
+ }
+ f->nodes.nr = dst;
+
+ if (c->opts.verbose) {
+ printbuf_reset(&buf);
+ prt_printf(&buf, "%s: nodes found after overwrites:\n", __func__);
+ found_btree_nodes_to_text(&buf, c, f->nodes);
+ bch2_print_string_as_lines(KERN_INFO, buf.buf);
+ }
+
+ eytzinger0_sort(f->nodes.data, f->nodes.nr, sizeof(f->nodes.data[0]), found_btree_node_cmp_pos, NULL);
+err:
+ printbuf_exit(&buf);
+ return ret;
+}
+
+static int found_btree_node_range_start_cmp(const void *_l, const void *_r)
+{
+ const struct found_btree_node *l = _l;
+ const struct found_btree_node *r = _r;
+
+ return cmp_int(l->btree_id, r->btree_id) ?:
+ -cmp_int(l->level, r->level) ?:
+ bpos_cmp(l->max_key, r->min_key);
+}
+
+#define for_each_found_btree_node_in_range(_f, _search, _idx) \
+ for (size_t _idx = eytzinger0_find_gt((_f)->nodes.data, (_f)->nodes.nr, \
+ sizeof((_f)->nodes.data[0]), \
+ found_btree_node_range_start_cmp, &search); \
+ _idx < (_f)->nodes.nr && \
+ (_f)->nodes.data[_idx].btree_id == _search.btree_id && \
+ (_f)->nodes.data[_idx].level == _search.level && \
+ bpos_lt((_f)->nodes.data[_idx].min_key, _search.max_key); \
+ _idx = eytzinger0_next(_idx, (_f)->nodes.nr))
+
+bool bch2_btree_node_is_stale(struct bch_fs *c, struct btree *b)
+{
+ struct find_btree_nodes *f = &c->found_btree_nodes;
+
+ struct found_btree_node search = {
+ .btree_id = b->c.btree_id,
+ .level = b->c.level,
+ .min_key = b->data->min_key,
+ .max_key = b->key.k.p,
+ };
+
+ for_each_found_btree_node_in_range(f, search, idx)
+ if (f->nodes.data[idx].seq > BTREE_NODE_SEQ(b->data))
+ return true;
+ return false;
+}
+
+bool bch2_btree_has_scanned_nodes(struct bch_fs *c, enum btree_id btree)
+{
+ struct found_btree_node search = {
+ .btree_id = btree,
+ .level = 0,
+ .min_key = POS_MIN,
+ .max_key = SPOS_MAX,
+ };
+
+ for_each_found_btree_node_in_range(&c->found_btree_nodes, search, idx)
+ return true;
+ return false;
+}
+
+int bch2_get_scanned_nodes(struct bch_fs *c, enum btree_id btree,
+ unsigned level, struct bpos node_min, struct bpos node_max)
+{
+ struct find_btree_nodes *f = &c->found_btree_nodes;
+
+ int ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes);
+ if (ret)
+ return ret;
+
+ if (c->opts.verbose) {
+ struct printbuf buf = PRINTBUF;
+
+ prt_printf(&buf, "recovering %s l=%u ", bch2_btree_id_str(btree), level);
+ bch2_bpos_to_text(&buf, node_min);
+ prt_str(&buf, " - ");
+ bch2_bpos_to_text(&buf, node_max);
+
+ bch_info(c, "%s(): %s", __func__, buf.buf);
+ printbuf_exit(&buf);
+ }
+
+ struct found_btree_node search = {
+ .btree_id = btree,
+ .level = level,
+ .min_key = node_min,
+ .max_key = node_max,
+ };
+
+ for_each_found_btree_node_in_range(f, search, idx) {
+ struct found_btree_node n = f->nodes.data[idx];
+
+ n.range_updated |= bpos_lt(n.min_key, node_min);
+ n.min_key = bpos_max(n.min_key, node_min);
+
+ n.range_updated |= bpos_gt(n.max_key, node_max);
+ n.max_key = bpos_min(n.max_key, node_max);
+
+ struct { __BKEY_PADDED(k, BKEY_BTREE_PTR_VAL_U64s_MAX); } tmp;
+
+ found_btree_node_to_key(&tmp.k, &n);
+
+ struct printbuf buf = PRINTBUF;
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&tmp.k));
+ bch_verbose(c, "%s(): recovering %s", __func__, buf.buf);
+ printbuf_exit(&buf);
+
+ BUG_ON(bch2_bkey_invalid(c, bkey_i_to_s_c(&tmp.k), BKEY_TYPE_btree, 0, NULL));
+
+ ret = bch2_journal_key_insert(c, btree, level + 1, &tmp.k);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+void bch2_find_btree_nodes_exit(struct find_btree_nodes *f)
+{
+ darray_exit(&f->nodes);
+}
diff --git a/fs/bcachefs/btree_node_scan.h b/fs/bcachefs/btree_node_scan.h
new file mode 100644
index 0000000..08687b2
--- /dev/null
+++ b/fs/bcachefs/btree_node_scan.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_BTREE_NODE_SCAN_H
+#define _BCACHEFS_BTREE_NODE_SCAN_H
+
+int bch2_scan_for_btree_nodes(struct bch_fs *);
+bool bch2_btree_node_is_stale(struct bch_fs *, struct btree *);
+bool bch2_btree_has_scanned_nodes(struct bch_fs *, enum btree_id);
+int bch2_get_scanned_nodes(struct bch_fs *, enum btree_id, unsigned, struct bpos, struct bpos);
+void bch2_find_btree_nodes_exit(struct find_btree_nodes *);
+
+#endif /* _BCACHEFS_BTREE_NODE_SCAN_H */
diff --git a/fs/bcachefs/btree_node_scan_types.h b/fs/bcachefs/btree_node_scan_types.h
new file mode 100644
index 0000000..abb7b27
--- /dev/null
+++ b/fs/bcachefs/btree_node_scan_types.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_BTREE_NODE_SCAN_TYPES_H
+#define _BCACHEFS_BTREE_NODE_SCAN_TYPES_H
+
+#include "darray.h"
+
+struct found_btree_node {
+ bool range_updated:1;
+ bool overwritten:1;
+ u8 btree_id;
+ u8 level;
+ u32 seq;
+ u64 cookie;
+
+ struct bpos min_key;
+ struct bpos max_key;
+
+ unsigned nr_ptrs;
+ struct bch_extent_ptr ptrs[BCH_REPLICAS_MAX];
+};
+
+typedef DARRAY(struct found_btree_node) found_btree_nodes;
+
+struct find_btree_nodes {
+ int ret;
+ struct mutex lock;
+ found_btree_nodes nodes;
+};
+
+#endif /* _BCACHEFS_BTREE_NODE_SCAN_TYPES_H */
diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index 30d69a6..aa9da49 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -318,7 +318,7 @@
!(i->flags & BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) &&
test_bit(JOURNAL_REPLAY_DONE, &trans->c->journal.flags) &&
i->k->k.p.snapshot &&
- bch2_snapshot_is_internal_node(trans->c, i->k->k.p.snapshot));
+ bch2_snapshot_is_internal_node(trans->c, i->k->k.p.snapshot) > 0);
}
static __always_inline int bch2_trans_journal_res_get(struct btree_trans *trans,
@@ -887,6 +887,7 @@
int ret, unsigned long trace_ip)
{
struct bch_fs *c = trans->c;
+ enum bch_watermark watermark = flags & BCH_WATERMARK_MASK;
switch (ret) {
case -BCH_ERR_btree_insert_btree_node_full:
@@ -905,7 +906,7 @@
* flag
*/
if ((flags & BCH_TRANS_COMMIT_journal_reclaim) &&
- (flags & BCH_WATERMARK_MASK) != BCH_WATERMARK_reclaim) {
+ watermark < BCH_WATERMARK_reclaim) {
ret = -BCH_ERR_journal_reclaim_would_deadlock;
break;
}
diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c
index a4b40c1..8e47e26 100644
--- a/fs/bcachefs/btree_update.c
+++ b/fs/bcachefs/btree_update.c
@@ -38,6 +38,9 @@
struct bkey_i *update;
int ret;
+ if (unlikely(trans->journal_replay_not_finished))
+ return 0;
+
update = bch2_bkey_make_mut_noupdate(trans, k);
ret = PTR_ERR_OR_ZERO(update);
if (ret)
@@ -69,6 +72,9 @@
struct bch_fs *c = trans->c;
int ret;
+ if (unlikely(trans->journal_replay_not_finished))
+ return 0;
+
ret = bch2_key_has_snapshot_overwrites(trans, iter->btree_id, insert->k.p) ?:
bch2_key_has_snapshot_overwrites(trans, iter->btree_id, k.k->p);
if (ret < 0)
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index b2f5f2e..32397b9 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -2,6 +2,7 @@
#include "bcachefs.h"
#include "alloc_foreground.h"
+#include "bkey_buf.h"
#include "bkey_methods.h"
#include "btree_cache.h"
#include "btree_gc.h"
@@ -18,12 +19,20 @@
#include "journal.h"
#include "journal_reclaim.h"
#include "keylist.h"
+#include "recovery_passes.h"
#include "replicas.h"
#include "super-io.h"
#include "trace.h"
#include <linux/random.h>
+const char * const bch2_btree_update_modes[] = {
+#define x(t) #t,
+ BCH_WATERMARKS()
+#undef x
+ NULL
+};
+
static int bch2_btree_insert_node(struct btree_update *, struct btree_trans *,
btree_path_idx_t, struct btree *, struct keylist *);
static void bch2_btree_update_add_new_node(struct btree_update *, struct btree *);
@@ -44,56 +53,103 @@
return path_idx;
}
-/* Debug code: */
-
/*
* Verify that child nodes correctly span parent node's range:
*/
-static void btree_node_interior_verify(struct bch_fs *c, struct btree *b)
+int bch2_btree_node_check_topology(struct btree_trans *trans, struct btree *b)
{
-#ifdef CONFIG_BCACHEFS_DEBUG
- struct bpos next_node = b->data->min_key;
- struct btree_node_iter iter;
+ struct bch_fs *c = trans->c;
+ struct bpos node_min = b->key.k.type == KEY_TYPE_btree_ptr_v2
+ ? bkey_i_to_btree_ptr_v2(&b->key)->v.min_key
+ : b->data->min_key;
+ struct btree_and_journal_iter iter;
struct bkey_s_c k;
- struct bkey_s_c_btree_ptr_v2 bp;
- struct bkey unpacked;
- struct printbuf buf1 = PRINTBUF, buf2 = PRINTBUF;
+ struct printbuf buf = PRINTBUF;
+ struct bkey_buf prev;
+ int ret = 0;
- BUG_ON(!b->c.level);
+ BUG_ON(b->key.k.type == KEY_TYPE_btree_ptr_v2 &&
+ !bpos_eq(bkey_i_to_btree_ptr_v2(&b->key)->v.min_key,
+ b->data->min_key));
- if (!test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags))
- return;
+ if (!b->c.level)
+ return 0;
- bch2_btree_node_iter_init_from_start(&iter, b);
+ bch2_bkey_buf_init(&prev);
+ bkey_init(&prev.k->k);
+ bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b);
- while (1) {
- k = bch2_btree_node_iter_peek_unpack(&iter, b, &unpacked);
+ while ((k = bch2_btree_and_journal_iter_peek(&iter)).k) {
if (k.k->type != KEY_TYPE_btree_ptr_v2)
- break;
- bp = bkey_s_c_to_btree_ptr_v2(k);
+ goto out;
- if (!bpos_eq(next_node, bp.v->min_key)) {
- bch2_dump_btree_node(c, b);
- bch2_bpos_to_text(&buf1, next_node);
- bch2_bpos_to_text(&buf2, bp.v->min_key);
- panic("expected next min_key %s got %s\n", buf1.buf, buf2.buf);
+ struct bkey_s_c_btree_ptr_v2 bp = bkey_s_c_to_btree_ptr_v2(k);
+
+ struct bpos expected_min = bkey_deleted(&prev.k->k)
+ ? node_min
+ : bpos_successor(prev.k->k.p);
+
+ if (!bpos_eq(expected_min, bp.v->min_key)) {
+ bch2_topology_error(c);
+
+ printbuf_reset(&buf);
+ prt_str(&buf, "end of prev node doesn't match start of next node\n"),
+ prt_printf(&buf, " in btree %s level %u node ",
+ bch2_btree_id_str(b->c.btree_id), b->c.level);
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key));
+ prt_str(&buf, "\n prev ");
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k));
+ prt_str(&buf, "\n next ");
+ bch2_bkey_val_to_text(&buf, c, k);
+
+ need_fsck_err(c, btree_node_topology_bad_min_key, "%s", buf.buf);
+ goto topology_repair;
}
- bch2_btree_node_iter_advance(&iter, b);
-
- if (bch2_btree_node_iter_end(&iter)) {
- if (!bpos_eq(k.k->p, b->key.k.p)) {
- bch2_dump_btree_node(c, b);
- bch2_bpos_to_text(&buf1, b->key.k.p);
- bch2_bpos_to_text(&buf2, k.k->p);
- panic("expected end %s got %s\n", buf1.buf, buf2.buf);
- }
- break;
- }
-
- next_node = bpos_successor(k.k->p);
+ bch2_bkey_buf_reassemble(&prev, c, k);
+ bch2_btree_and_journal_iter_advance(&iter);
}
-#endif
+
+ if (bkey_deleted(&prev.k->k)) {
+ bch2_topology_error(c);
+
+ printbuf_reset(&buf);
+ prt_str(&buf, "empty interior node\n");
+ prt_printf(&buf, " in btree %s level %u node ",
+ bch2_btree_id_str(b->c.btree_id), b->c.level);
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key));
+
+ need_fsck_err(c, btree_node_topology_empty_interior_node, "%s", buf.buf);
+ goto topology_repair;
+ } else if (!bpos_eq(prev.k->k.p, b->key.k.p)) {
+ bch2_topology_error(c);
+
+ printbuf_reset(&buf);
+ prt_str(&buf, "last child node doesn't end at end of parent node\n");
+ prt_printf(&buf, " in btree %s level %u node ",
+ bch2_btree_id_str(b->c.btree_id), b->c.level);
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key));
+ prt_str(&buf, "\n last key ");
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(prev.k));
+
+ need_fsck_err(c, btree_node_topology_bad_max_key, "%s", buf.buf);
+ goto topology_repair;
+ }
+out:
+fsck_err:
+ bch2_btree_and_journal_iter_exit(&iter);
+ bch2_bkey_buf_exit(&prev, c);
+ printbuf_exit(&buf);
+ return ret;
+topology_repair:
+ if ((c->recovery_passes_explicit & BIT_ULL(BCH_RECOVERY_PASS_check_topology)) &&
+ c->curr_recovery_pass > BCH_RECOVERY_PASS_check_topology) {
+ bch2_inconsistent_error(c);
+ ret = -BCH_ERR_btree_need_topology_repair;
+ } else {
+ ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_check_topology);
+ }
+ goto out;
}
/* Calculate ideal packed bkey format for new btree nodes: */
@@ -254,7 +310,7 @@
struct open_buckets obs = { .nr = 0 };
struct bch_devs_list devs_have = (struct bch_devs_list) { 0 };
enum bch_watermark watermark = flags & BCH_WATERMARK_MASK;
- unsigned nr_reserve = watermark > BCH_WATERMARK_reclaim
+ unsigned nr_reserve = watermark < BCH_WATERMARK_reclaim
? BTREE_NODE_RESERVE
: 0;
int ret;
@@ -638,7 +694,7 @@
* which may require allocations as well.
*/
ret = commit_do(trans, &as->disk_res, &journal_seq,
- BCH_WATERMARK_reclaim|
+ BCH_WATERMARK_interior_updates|
BCH_TRANS_COMMIT_no_enospc|
BCH_TRANS_COMMIT_no_check_rw|
BCH_TRANS_COMMIT_journal_reclaim,
@@ -797,11 +853,11 @@
mutex_lock(&c->btree_interior_update_lock);
list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten);
- BUG_ON(as->mode != BTREE_INTERIOR_NO_UPDATE);
+ BUG_ON(as->mode != BTREE_UPDATE_none);
BUG_ON(!btree_node_dirty(b));
BUG_ON(!b->c.level);
- as->mode = BTREE_INTERIOR_UPDATING_NODE;
+ as->mode = BTREE_UPDATE_node;
as->b = b;
set_btree_node_write_blocked(b);
@@ -824,7 +880,7 @@
lockdep_assert_held(&c->btree_interior_update_lock);
child->b = NULL;
- child->mode = BTREE_INTERIOR_UPDATING_AS;
+ child->mode = BTREE_UPDATE_update;
bch2_journal_pin_copy(&c->journal, &as->journal, &child->journal,
bch2_update_reparent_journal_pin_flush);
@@ -835,7 +891,7 @@
struct bkey_i *insert = &b->key;
struct bch_fs *c = as->c;
- BUG_ON(as->mode != BTREE_INTERIOR_NO_UPDATE);
+ BUG_ON(as->mode != BTREE_UPDATE_none);
BUG_ON(as->journal_u64s + jset_u64s(insert->k.u64s) >
ARRAY_SIZE(as->journal_entries));
@@ -849,7 +905,7 @@
mutex_lock(&c->btree_interior_update_lock);
list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten);
- as->mode = BTREE_INTERIOR_UPDATING_ROOT;
+ as->mode = BTREE_UPDATE_root;
mutex_unlock(&c->btree_interior_update_lock);
}
@@ -1027,7 +1083,7 @@
struct bch_fs *c = as->c;
u64 start_time = as->start_time;
- BUG_ON(as->mode == BTREE_INTERIOR_NO_UPDATE);
+ BUG_ON(as->mode == BTREE_UPDATE_none);
if (as->took_gc_lock)
up_read(&as->c->gc_lock);
@@ -1072,7 +1128,7 @@
unsigned journal_flags = watermark|JOURNAL_RES_GET_CHECK;
if ((flags & BCH_TRANS_COMMIT_journal_reclaim) &&
- watermark != BCH_WATERMARK_reclaim)
+ watermark < BCH_WATERMARK_reclaim)
journal_flags |= JOURNAL_RES_GET_NONBLOCK;
ret = drop_locks_do(trans,
@@ -1123,7 +1179,8 @@
as->c = c;
as->start_time = start_time;
as->ip_started = _RET_IP_;
- as->mode = BTREE_INTERIOR_NO_UPDATE;
+ as->mode = BTREE_UPDATE_none;
+ as->watermark = watermark;
as->took_gc_lock = true;
as->btree_id = path->btree_id;
as->update_level = update_level;
@@ -1168,7 +1225,7 @@
*/
if (bch2_err_matches(ret, ENOSPC) &&
(flags & BCH_TRANS_COMMIT_journal_reclaim) &&
- watermark != BCH_WATERMARK_reclaim) {
+ watermark < BCH_WATERMARK_reclaim) {
ret = -BCH_ERR_journal_reclaim_would_deadlock;
goto err;
}
@@ -1380,9 +1437,16 @@
if (bkey_deleted(k))
continue;
+ uk = bkey_unpack_key(b, k);
+
+ if (b->c.level &&
+ u64s < n1_u64s &&
+ u64s + k->u64s >= n1_u64s &&
+ bch2_key_deleted_in_journal(trans, b->c.btree_id, b->c.level, uk.p))
+ n1_u64s += k->u64s;
+
i = u64s >= n1_u64s;
u64s += k->u64s;
- uk = bkey_unpack_key(b, k);
if (!i)
n1_pos = uk.p;
bch2_bkey_format_add_key(&format[i], &uk);
@@ -1441,8 +1505,7 @@
bch2_verify_btree_nr_keys(n[i]);
- if (b->c.level)
- btree_node_interior_verify(as->c, n[i]);
+ BUG_ON(bch2_btree_node_check_topology(trans, n[i]));
}
}
@@ -1473,7 +1536,7 @@
__bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys);
- btree_node_interior_verify(as->c, b);
+ BUG_ON(bch2_btree_node_check_topology(trans, b));
}
}
@@ -1488,9 +1551,14 @@
u64 start_time = local_clock();
int ret = 0;
+ bch2_verify_btree_nr_keys(b);
BUG_ON(!parent && (b != btree_node_root(c, b)));
BUG_ON(parent && !btree_node_intent_locked(trans->paths + path, b->c.level + 1));
+ ret = bch2_btree_node_check_topology(trans, b);
+ if (ret)
+ return ret;
+
bch2_btree_interior_update_will_free_node(as, b);
if (b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c)) {
@@ -1710,7 +1778,11 @@
goto split;
}
- btree_node_interior_verify(c, b);
+ ret = bch2_btree_node_check_topology(trans, b);
+ if (ret) {
+ bch2_btree_node_unlock_write(trans, path, b);
+ return ret;
+ }
bch2_btree_insert_keys_interior(as, trans, path, b, keys);
@@ -1728,7 +1800,7 @@
bch2_btree_node_unlock_write(trans, path, b);
- btree_node_interior_verify(c, b);
+ BUG_ON(bch2_btree_node_check_topology(trans, b));
return 0;
split:
/*
@@ -1818,9 +1890,12 @@
{
struct bch_fs *c = trans->c;
struct btree *b = bch2_btree_id_root(c, trans->paths[path].btree_id)->b;
+
+ if (btree_node_fake(b))
+ return bch2_btree_split_leaf(trans, path, flags);
+
struct btree_update *as =
- bch2_btree_update_start(trans, trans->paths + path,
- b->c.level, true, flags);
+ bch2_btree_update_start(trans, trans->paths + path, b->c.level, true, flags);
if (IS_ERR(as))
return PTR_ERR(as);
@@ -2391,7 +2466,7 @@
bch2_btree_set_root_inmem(c, b);
}
-static int __bch2_btree_root_alloc(struct btree_trans *trans, enum btree_id id)
+static int __bch2_btree_root_alloc_fake(struct btree_trans *trans, enum btree_id id, unsigned level)
{
struct bch_fs *c = trans->c;
struct closure cl;
@@ -2410,7 +2485,7 @@
set_btree_node_fake(b);
set_btree_node_need_rewrite(b);
- b->c.level = 0;
+ b->c.level = level;
b->c.btree_id = id;
bkey_btree_ptr_init(&b->key);
@@ -2437,9 +2512,21 @@
return 0;
}
-void bch2_btree_root_alloc(struct bch_fs *c, enum btree_id id)
+void bch2_btree_root_alloc_fake(struct bch_fs *c, enum btree_id id, unsigned level)
{
- bch2_trans_run(c, __bch2_btree_root_alloc(trans, id));
+ bch2_trans_run(c, __bch2_btree_root_alloc_fake(trans, id, level));
+}
+
+static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update *as)
+{
+ prt_printf(out, "%ps: btree=%s watermark=%s mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n",
+ (void *) as->ip_started,
+ bch2_btree_id_str(as->btree_id),
+ bch2_watermarks[as->watermark],
+ bch2_btree_update_modes[as->mode],
+ as->nodes_written,
+ closure_nr_remaining(&as->cl),
+ as->journal.seq);
}
void bch2_btree_updates_to_text(struct printbuf *out, struct bch_fs *c)
@@ -2448,12 +2535,7 @@
mutex_lock(&c->btree_interior_update_lock);
list_for_each_entry(as, &c->btree_interior_update_list, list)
- prt_printf(out, "%ps: mode=%u nodes_written=%u cl.remaining=%u journal_seq=%llu\n",
- (void *) as->ip_started,
- as->mode,
- as->nodes_written,
- closure_nr_remaining(&as->cl),
- as->journal.seq);
+ bch2_btree_update_to_text(out, as);
mutex_unlock(&c->btree_interior_update_lock);
}
diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h
index f651dd48..88dcf5a 100644
--- a/fs/bcachefs/btree_update_interior.h
+++ b/fs/bcachefs/btree_update_interior.h
@@ -10,6 +10,20 @@
#define BTREE_UPDATE_JOURNAL_RES (BTREE_UPDATE_NODES_MAX * (BKEY_BTREE_PTR_U64s_MAX + 1))
+int bch2_btree_node_check_topology(struct btree_trans *, struct btree *);
+
+#define BTREE_UPDATE_MODES() \
+ x(none) \
+ x(node) \
+ x(root) \
+ x(update)
+
+enum btree_update_mode {
+#define x(n) BTREE_UPDATE_##n,
+ BTREE_UPDATE_MODES()
+#undef x
+};
+
/*
* Tracks an in progress split/rewrite of a btree node and the update to the
* parent node:
@@ -37,14 +51,8 @@
struct list_head list;
struct list_head unwritten_list;
- /* What kind of update are we doing? */
- enum {
- BTREE_INTERIOR_NO_UPDATE,
- BTREE_INTERIOR_UPDATING_NODE,
- BTREE_INTERIOR_UPDATING_ROOT,
- BTREE_INTERIOR_UPDATING_AS,
- } mode;
-
+ enum btree_update_mode mode;
+ enum bch_watermark watermark;
unsigned nodes_written:1;
unsigned took_gc_lock:1;
@@ -54,7 +62,7 @@
struct disk_reservation disk_res;
/*
- * BTREE_INTERIOR_UPDATING_NODE:
+ * BTREE_UPDATE_node:
* The update that made the new nodes visible was a regular update to an
* existing interior node - @b. We can't write out the update to @b
* until the new nodes we created are finished writing, so we block @b
@@ -163,7 +171,7 @@
struct bkey_i *, unsigned, bool);
void bch2_btree_set_root_for_read(struct bch_fs *, struct btree *);
-void bch2_btree_root_alloc(struct bch_fs *, enum btree_id);
+void bch2_btree_root_alloc_fake(struct bch_fs *, enum btree_id, unsigned);
static inline unsigned btree_update_reserve_required(struct bch_fs *c,
struct btree *b)
diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c
index 5cbad84..baf63e2 100644
--- a/fs/bcachefs/btree_write_buffer.c
+++ b/fs/bcachefs/btree_write_buffer.c
@@ -11,6 +11,7 @@
#include "journal_reclaim.h"
#include <linux/prefetch.h>
+#include <linux/sort.h>
static int bch2_btree_write_buffer_journal_flush(struct journal *,
struct journal_entry_pin *, u64);
@@ -46,6 +47,14 @@
#endif
}
+static int wb_key_seq_cmp(const void *_l, const void *_r)
+{
+ const struct btree_write_buffered_key *l = _l;
+ const struct btree_write_buffered_key *r = _r;
+
+ return cmp_int(l->journal_seq, r->journal_seq);
+}
+
/* Compare excluding idx, the low 24 bits: */
static inline bool wb_key_eq(const void *_l, const void *_r)
{
@@ -357,6 +366,11 @@
*/
trace_and_count(c, write_buffer_flush_slowpath, trans, slowpath, wb->flushing.keys.nr);
+ sort(wb->flushing.keys.data,
+ wb->flushing.keys.nr,
+ sizeof(wb->flushing.keys.data[0]),
+ wb_key_seq_cmp, NULL);
+
darray_for_each(wb->flushing.keys, i) {
if (!i->journal_seq)
continue;
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index 96edf2c..941401a2 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -525,6 +525,7 @@
"different types of data in same bucket: %s, %s",
bch2_data_type_str(g->data_type),
bch2_data_type_str(data_type))) {
+ BUG();
ret = -EIO;
goto err;
}
@@ -628,6 +629,7 @@
bch2_data_type_str(ptr_data_type),
(printbuf_reset(&buf),
bch2_bkey_val_to_text(&buf, c, k), buf.buf));
+ BUG();
ret = -EIO;
goto err;
}
@@ -815,14 +817,14 @@
static int bch2_trigger_pointer(struct btree_trans *trans,
enum btree_id btree_id, unsigned level,
struct bkey_s_c k, struct extent_ptr_decoded p,
- s64 *sectors,
- unsigned flags)
+ const union bch_extent_entry *entry,
+ s64 *sectors, unsigned flags)
{
bool insert = !(flags & BTREE_TRIGGER_OVERWRITE);
struct bpos bucket;
struct bch_backpointer bp;
- bch2_extent_ptr_to_bp(trans->c, btree_id, level, k, p, &bucket, &bp);
+ bch2_extent_ptr_to_bp(trans->c, btree_id, level, k, p, entry, &bucket, &bp);
*sectors = insert ? bp.bucket_len : -((s64) bp.bucket_len);
if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
@@ -851,7 +853,7 @@
if (flags & BTREE_TRIGGER_GC) {
struct bch_fs *c = trans->c;
struct bch_dev *ca = bch_dev_bkey_exists(c, p.ptr.dev);
- enum bch_data_type data_type = bkey_ptr_data_type(btree_id, level, k, p);
+ enum bch_data_type data_type = bch2_bkey_ptr_data_type(k, p, entry);
percpu_down_read(&c->mark_lock);
struct bucket *g = PTR_GC_BUCKET(ca, &p.ptr);
@@ -979,7 +981,7 @@
bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
s64 disk_sectors;
- ret = bch2_trigger_pointer(trans, btree_id, level, k, p, &disk_sectors, flags);
+ ret = bch2_trigger_pointer(trans, btree_id, level, k, p, entry, &disk_sectors, flags);
if (ret < 0)
return ret;
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index 6387e03..00aaf4b 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -226,6 +226,7 @@
fallthrough;
case BCH_WATERMARK_btree_copygc:
case BCH_WATERMARK_reclaim:
+ case BCH_WATERMARK_interior_updates:
break;
}
diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c
index 38defa1..cbfa645 100644
--- a/fs/bcachefs/chardev.c
+++ b/fs/bcachefs/chardev.c
@@ -7,7 +7,7 @@
#include "chardev.h"
#include "journal.h"
#include "move.h"
-#include "recovery.h"
+#include "recovery_passes.h"
#include "replicas.h"
#include "super.h"
#include "super-io.h"
diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index 4150fec..34731ee 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -14,6 +14,7 @@
#include "move.h"
#include "nocow_locking.h"
#include "rebalance.h"
+#include "snapshot.h"
#include "subvolume.h"
#include "trace.h"
@@ -509,6 +510,14 @@
unsigned ptrs_locked = 0;
int ret = 0;
+ /*
+ * fs is corrupt we have a key for a snapshot node that doesn't exist,
+ * and we have to check for this because we go rw before repairing the
+ * snapshots table - just skip it, we can move it later.
+ */
+ if (unlikely(k.k->p.snapshot && !bch2_snapshot_equiv(c, k.k->p.snapshot)))
+ return -BCH_ERR_data_update_done;
+
bch2_bkey_buf_init(&m->k);
bch2_bkey_buf_reassemble(&m->k, c, k);
m->btree_id = btree_id;
@@ -571,8 +580,7 @@
move_ctxt_wait_event(ctxt,
(locked = bch2_bucket_nocow_trylock(&c->nocow_locks,
PTR_BUCKET_POS(c, &p.ptr), 0)) ||
- (!atomic_read(&ctxt->read_sectors) &&
- !atomic_read(&ctxt->write_sectors)));
+ list_empty(&ctxt->ios));
if (!locked)
bch2_bucket_nocow_lock(&c->nocow_locks,
diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h
index af25d8ec..01a79fa 100644
--- a/fs/bcachefs/errcode.h
+++ b/fs/bcachefs/errcode.h
@@ -252,7 +252,8 @@
x(BCH_ERR_nopromote, nopromote_in_flight) \
x(BCH_ERR_nopromote, nopromote_no_writes) \
x(BCH_ERR_nopromote, nopromote_enomem) \
- x(0, need_inode_lock)
+ x(0, need_inode_lock) \
+ x(0, invalid_snapshot_node)
enum bch_errcode {
BCH_ERR_START = 2048,
diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index 0434312..82a6656 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -1,7 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
#include "bcachefs.h"
#include "error.h"
-#include "recovery.h"
+#include "journal.h"
+#include "recovery_passes.h"
#include "super.h"
#include "thread_with_file.h"
@@ -16,7 +17,8 @@
return false;
case BCH_ON_ERROR_ro:
if (bch2_fs_emergency_read_only(c))
- bch_err(c, "inconsistency detected - emergency read only");
+ bch_err(c, "inconsistency detected - emergency read only at journal seq %llu",
+ journal_cur_seq(&c->journal));
return true;
case BCH_ON_ERROR_panic:
panic(bch2_fmt(c, "panic after error"));
diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h
index ae1d667..36caedf 100644
--- a/fs/bcachefs/error.h
+++ b/fs/bcachefs/error.h
@@ -32,6 +32,12 @@
int bch2_topology_error(struct bch_fs *);
+#define bch2_fs_topology_error(c, ...) \
+({ \
+ bch_err(c, "btree topology error: " __VA_ARGS__); \
+ bch2_topology_error(c); \
+})
+
#define bch2_fs_inconsistent(c, ...) \
({ \
bch_err(c, __VA_ARGS__); \
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index 61395b1..0e3ca99 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -189,13 +189,18 @@
enum bkey_invalid_flags flags,
struct printbuf *err)
{
+ struct bkey_s_c_btree_ptr_v2 bp = bkey_s_c_to_btree_ptr_v2(k);
int ret = 0;
- bkey_fsck_err_on(bkey_val_u64s(k.k) > BKEY_BTREE_PTR_VAL_U64s_MAX, c, err,
- btree_ptr_v2_val_too_big,
+ bkey_fsck_err_on(bkey_val_u64s(k.k) > BKEY_BTREE_PTR_VAL_U64s_MAX,
+ c, err, btree_ptr_v2_val_too_big,
"value too big (%zu > %zu)",
bkey_val_u64s(k.k), BKEY_BTREE_PTR_VAL_U64s_MAX);
+ bkey_fsck_err_on(bpos_ge(bp.v->min_key, bp.k->p),
+ c, err, btree_ptr_v2_min_key_bad,
+ "min_key > key");
+
ret = bch2_bkey_ptrs_invalid(c, k, flags, err);
fsck_err:
return ret;
@@ -973,6 +978,31 @@
return bkey_deleted(k.k);
}
+void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *c, const struct bch_extent_ptr *ptr)
+{
+ struct bch_dev *ca = c && ptr->dev < c->sb.nr_devices && c->devs[ptr->dev]
+ ? bch_dev_bkey_exists(c, ptr->dev)
+ : NULL;
+
+ if (!ca) {
+ prt_printf(out, "ptr: %u:%llu gen %u%s", ptr->dev,
+ (u64) ptr->offset, ptr->gen,
+ ptr->cached ? " cached" : "");
+ } else {
+ u32 offset;
+ u64 b = sector_to_bucket_and_offset(ca, ptr->offset, &offset);
+
+ prt_printf(out, "ptr: %u:%llu:%u gen %u",
+ ptr->dev, b, offset, ptr->gen);
+ if (ptr->cached)
+ prt_str(out, " cached");
+ if (ptr->unwritten)
+ prt_str(out, " unwritten");
+ if (ca && ptr_stale(ca, ptr))
+ prt_printf(out, " stale");
+ }
+}
+
void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c,
struct bkey_s_c k)
{
@@ -988,31 +1018,10 @@
prt_printf(out, " ");
switch (__extent_entry_type(entry)) {
- case BCH_EXTENT_ENTRY_ptr: {
- const struct bch_extent_ptr *ptr = entry_to_ptr(entry);
- struct bch_dev *ca = c && ptr->dev < c->sb.nr_devices && c->devs[ptr->dev]
- ? bch_dev_bkey_exists(c, ptr->dev)
- : NULL;
-
- if (!ca) {
- prt_printf(out, "ptr: %u:%llu gen %u%s", ptr->dev,
- (u64) ptr->offset, ptr->gen,
- ptr->cached ? " cached" : "");
- } else {
- u32 offset;
- u64 b = sector_to_bucket_and_offset(ca, ptr->offset, &offset);
-
- prt_printf(out, "ptr: %u:%llu:%u gen %u",
- ptr->dev, b, offset, ptr->gen);
- if (ptr->cached)
- prt_str(out, " cached");
- if (ptr->unwritten)
- prt_str(out, " unwritten");
- if (ca && ptr_stale(ca, ptr))
- prt_printf(out, " stale");
- }
+ case BCH_EXTENT_ENTRY_ptr:
+ bch2_extent_ptr_to_text(out, c, entry_to_ptr(entry));
break;
- }
+
case BCH_EXTENT_ENTRY_crc32:
case BCH_EXTENT_ENTRY_crc64:
case BCH_EXTENT_ENTRY_crc128: {
diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h
index fd2669c..528e817 100644
--- a/fs/bcachefs/extents.h
+++ b/fs/bcachefs/extents.h
@@ -596,30 +596,6 @@
return ret;
}
-static inline unsigned bch2_bkey_ptr_data_type(struct bkey_s_c k, const struct bch_extent_ptr *ptr)
-{
- switch (k.k->type) {
- case KEY_TYPE_btree_ptr:
- case KEY_TYPE_btree_ptr_v2:
- return BCH_DATA_btree;
- case KEY_TYPE_extent:
- case KEY_TYPE_reflink_v:
- return BCH_DATA_user;
- case KEY_TYPE_stripe: {
- struct bkey_s_c_stripe s = bkey_s_c_to_stripe(k);
-
- BUG_ON(ptr < s.v->ptrs ||
- ptr >= s.v->ptrs + s.v->nr_blocks);
-
- return ptr >= s.v->ptrs + s.v->nr_blocks - s.v->nr_redundant
- ? BCH_DATA_parity
- : BCH_DATA_user;
- }
- default:
- BUG();
- }
-}
-
unsigned bch2_bkey_nr_ptrs(struct bkey_s_c);
unsigned bch2_bkey_nr_ptrs_allocated(struct bkey_s_c);
unsigned bch2_bkey_nr_ptrs_fully_allocated(struct bkey_s_c);
@@ -700,6 +676,7 @@
void bch2_extent_ptr_set_cached(struct bkey_s, struct bch_extent_ptr *);
bool bch2_extent_normalize(struct bch_fs *, struct bkey_s);
+void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *, const struct bch_extent_ptr *);
void bch2_bkey_ptrs_to_text(struct printbuf *, struct bch_fs *,
struct bkey_s_c);
int bch2_bkey_ptrs_invalid(struct bch_fs *, struct bkey_s_c,
diff --git a/fs/bcachefs/eytzinger.c b/fs/bcachefs/eytzinger.c
new file mode 100644
index 0000000..4ce5e95
--- /dev/null
+++ b/fs/bcachefs/eytzinger.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "eytzinger.h"
+
+/**
+ * is_aligned - is this pointer & size okay for word-wide copying?
+ * @base: pointer to data
+ * @size: size of each element
+ * @align: required alignment (typically 4 or 8)
+ *
+ * Returns true if elements can be copied using word loads and stores.
+ * The size must be a multiple of the alignment, and the base address must
+ * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS.
+ *
+ * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)"
+ * to "if ((a | b) & mask)", so we do that by hand.
+ */
+__attribute_const__ __always_inline
+static bool is_aligned(const void *base, size_t size, unsigned char align)
+{
+ unsigned char lsbits = (unsigned char)size;
+
+ (void)base;
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ lsbits |= (unsigned char)(uintptr_t)base;
+#endif
+ return (lsbits & (align - 1)) == 0;
+}
+
+/**
+ * swap_words_32 - swap two elements in 32-bit chunks
+ * @a: pointer to the first element to swap
+ * @b: pointer to the second element to swap
+ * @n: element size (must be a multiple of 4)
+ *
+ * Exchange the two objects in memory. This exploits base+index addressing,
+ * which basically all CPUs have, to minimize loop overhead computations.
+ *
+ * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the
+ * bottom of the loop, even though the zero flag is still valid from the
+ * subtract (since the intervening mov instructions don't alter the flags).
+ * Gcc 8.1.0 doesn't have that problem.
+ */
+static void swap_words_32(void *a, void *b, size_t n)
+{
+ do {
+ u32 t = *(u32 *)(a + (n -= 4));
+ *(u32 *)(a + n) = *(u32 *)(b + n);
+ *(u32 *)(b + n) = t;
+ } while (n);
+}
+
+/**
+ * swap_words_64 - swap two elements in 64-bit chunks
+ * @a: pointer to the first element to swap
+ * @b: pointer to the second element to swap
+ * @n: element size (must be a multiple of 8)
+ *
+ * Exchange the two objects in memory. This exploits base+index
+ * addressing, which basically all CPUs have, to minimize loop overhead
+ * computations.
+ *
+ * We'd like to use 64-bit loads if possible. If they're not, emulating
+ * one requires base+index+4 addressing which x86 has but most other
+ * processors do not. If CONFIG_64BIT, we definitely have 64-bit loads,
+ * but it's possible to have 64-bit loads without 64-bit pointers (e.g.
+ * x32 ABI). Are there any cases the kernel needs to worry about?
+ */
+static void swap_words_64(void *a, void *b, size_t n)
+{
+ do {
+#ifdef CONFIG_64BIT
+ u64 t = *(u64 *)(a + (n -= 8));
+ *(u64 *)(a + n) = *(u64 *)(b + n);
+ *(u64 *)(b + n) = t;
+#else
+ /* Use two 32-bit transfers to avoid base+index+4 addressing */
+ u32 t = *(u32 *)(a + (n -= 4));
+ *(u32 *)(a + n) = *(u32 *)(b + n);
+ *(u32 *)(b + n) = t;
+
+ t = *(u32 *)(a + (n -= 4));
+ *(u32 *)(a + n) = *(u32 *)(b + n);
+ *(u32 *)(b + n) = t;
+#endif
+ } while (n);
+}
+
+/**
+ * swap_bytes - swap two elements a byte at a time
+ * @a: pointer to the first element to swap
+ * @b: pointer to the second element to swap
+ * @n: element size
+ *
+ * This is the fallback if alignment doesn't allow using larger chunks.
+ */
+static void swap_bytes(void *a, void *b, size_t n)
+{
+ do {
+ char t = ((char *)a)[--n];
+ ((char *)a)[n] = ((char *)b)[n];
+ ((char *)b)[n] = t;
+ } while (n);
+}
+
+/*
+ * The values are arbitrary as long as they can't be confused with
+ * a pointer, but small integers make for the smallest compare
+ * instructions.
+ */
+#define SWAP_WORDS_64 (swap_r_func_t)0
+#define SWAP_WORDS_32 (swap_r_func_t)1
+#define SWAP_BYTES (swap_r_func_t)2
+#define SWAP_WRAPPER (swap_r_func_t)3
+
+struct wrapper {
+ cmp_func_t cmp;
+ swap_func_t swap;
+};
+
+/*
+ * The function pointer is last to make tail calls most efficient if the
+ * compiler decides not to inline this function.
+ */
+static void do_swap(void *a, void *b, size_t size, swap_r_func_t swap_func, const void *priv)
+{
+ if (swap_func == SWAP_WRAPPER) {
+ ((const struct wrapper *)priv)->swap(a, b, (int)size);
+ return;
+ }
+
+ if (swap_func == SWAP_WORDS_64)
+ swap_words_64(a, b, size);
+ else if (swap_func == SWAP_WORDS_32)
+ swap_words_32(a, b, size);
+ else if (swap_func == SWAP_BYTES)
+ swap_bytes(a, b, size);
+ else
+ swap_func(a, b, (int)size, priv);
+}
+
+#define _CMP_WRAPPER ((cmp_r_func_t)0L)
+
+static int do_cmp(const void *a, const void *b, cmp_r_func_t cmp, const void *priv)
+{
+ if (cmp == _CMP_WRAPPER)
+ return ((const struct wrapper *)priv)->cmp(a, b);
+ return cmp(a, b, priv);
+}
+
+static inline int eytzinger0_do_cmp(void *base, size_t n, size_t size,
+ cmp_r_func_t cmp_func, const void *priv,
+ size_t l, size_t r)
+{
+ return do_cmp(base + inorder_to_eytzinger0(l, n) * size,
+ base + inorder_to_eytzinger0(r, n) * size,
+ cmp_func, priv);
+}
+
+static inline void eytzinger0_do_swap(void *base, size_t n, size_t size,
+ swap_r_func_t swap_func, const void *priv,
+ size_t l, size_t r)
+{
+ do_swap(base + inorder_to_eytzinger0(l, n) * size,
+ base + inorder_to_eytzinger0(r, n) * size,
+ size, swap_func, priv);
+}
+
+void eytzinger0_sort_r(void *base, size_t n, size_t size,
+ cmp_r_func_t cmp_func,
+ swap_r_func_t swap_func,
+ const void *priv)
+{
+ int i, c, r;
+
+ /* called from 'sort' without swap function, let's pick the default */
+ if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap)
+ swap_func = NULL;
+
+ if (!swap_func) {
+ if (is_aligned(base, size, 8))
+ swap_func = SWAP_WORDS_64;
+ else if (is_aligned(base, size, 4))
+ swap_func = SWAP_WORDS_32;
+ else
+ swap_func = SWAP_BYTES;
+ }
+
+ /* heapify */
+ for (i = n / 2 - 1; i >= 0; --i) {
+ for (r = i; r * 2 + 1 < n; r = c) {
+ c = r * 2 + 1;
+
+ if (c + 1 < n &&
+ eytzinger0_do_cmp(base, n, size, cmp_func, priv, c, c + 1) < 0)
+ c++;
+
+ if (eytzinger0_do_cmp(base, n, size, cmp_func, priv, r, c) >= 0)
+ break;
+
+ eytzinger0_do_swap(base, n, size, swap_func, priv, r, c);
+ }
+ }
+
+ /* sort */
+ for (i = n - 1; i > 0; --i) {
+ eytzinger0_do_swap(base, n, size, swap_func, priv, 0, i);
+
+ for (r = 0; r * 2 + 1 < i; r = c) {
+ c = r * 2 + 1;
+
+ if (c + 1 < i &&
+ eytzinger0_do_cmp(base, n, size, cmp_func, priv, c, c + 1) < 0)
+ c++;
+
+ if (eytzinger0_do_cmp(base, n, size, cmp_func, priv, r, c) >= 0)
+ break;
+
+ eytzinger0_do_swap(base, n, size, swap_func, priv, r, c);
+ }
+ }
+}
+
+void eytzinger0_sort(void *base, size_t n, size_t size,
+ cmp_func_t cmp_func,
+ swap_func_t swap_func)
+{
+ struct wrapper w = {
+ .cmp = cmp_func,
+ .swap = swap_func,
+ };
+
+ return eytzinger0_sort_r(base, n, size, _CMP_WRAPPER, SWAP_WRAPPER, &w);
+}
diff --git a/fs/bcachefs/eytzinger.h b/fs/bcachefs/eytzinger.h
index b04750d..ee0e2df 100644
--- a/fs/bcachefs/eytzinger.h
+++ b/fs/bcachefs/eytzinger.h
@@ -5,23 +5,33 @@
#include <linux/bitops.h>
#include <linux/log2.h>
-#include "util.h"
+#ifdef EYTZINGER_DEBUG
+#define EYTZINGER_BUG_ON(cond) BUG_ON(cond)
+#else
+#define EYTZINGER_BUG_ON(cond)
+#endif
/*
* Traversal for trees in eytzinger layout - a full binary tree layed out in an
- * array
- */
-
-/*
- * One based indexing version:
+ * array.
*
- * With one based indexing each level of the tree starts at a power of two -
- * good for cacheline alignment:
+ * Consider using an eytzinger tree any time you would otherwise be doing binary
+ * search over an array. Binary search is a worst case scenario for branch
+ * prediction and prefetching, but in an eytzinger tree every node's children
+ * are adjacent in memory, thus we can prefetch children before knowing the
+ * result of the comparison, assuming multiple nodes fit on a cacheline.
+ *
+ * Two variants are provided, for one based indexing and zero based indexing.
+ *
+ * Zero based indexing is more convenient, but one based indexing has better
+ * alignment and thus better performance because each new level of the tree
+ * starts at a power of two, and thus if element 0 was cacheline aligned, each
+ * new level will be as well.
*/
static inline unsigned eytzinger1_child(unsigned i, unsigned child)
{
- EBUG_ON(child > 1);
+ EYTZINGER_BUG_ON(child > 1);
return (i << 1) + child;
}
@@ -58,7 +68,7 @@
static inline unsigned eytzinger1_next(unsigned i, unsigned size)
{
- EBUG_ON(i > size);
+ EYTZINGER_BUG_ON(i > size);
if (eytzinger1_right_child(i) <= size) {
i = eytzinger1_right_child(i);
@@ -74,7 +84,7 @@
static inline unsigned eytzinger1_prev(unsigned i, unsigned size)
{
- EBUG_ON(i > size);
+ EYTZINGER_BUG_ON(i > size);
if (eytzinger1_left_child(i) <= size) {
i = eytzinger1_left_child(i) + 1;
@@ -101,7 +111,7 @@
unsigned shift = __fls(size) - b;
int s;
- EBUG_ON(!i || i > size);
+ EYTZINGER_BUG_ON(!i || i > size);
i ^= 1U << b;
i <<= 1;
@@ -126,7 +136,7 @@
unsigned shift;
int s;
- EBUG_ON(!i || i > size);
+ EYTZINGER_BUG_ON(!i || i > size);
/*
* sign bit trick:
@@ -164,7 +174,7 @@
static inline unsigned eytzinger0_child(unsigned i, unsigned child)
{
- EBUG_ON(child > 1);
+ EYTZINGER_BUG_ON(child > 1);
return (i << 1) + 1 + child;
}
@@ -231,11 +241,9 @@
(_i) != -1; \
(_i) = eytzinger0_next((_i), (_size)))
-typedef int (*eytzinger_cmp_fn)(const void *l, const void *r, size_t size);
-
/* return greatest node <= @search, or -1 if not found */
static inline ssize_t eytzinger0_find_le(void *base, size_t nr, size_t size,
- eytzinger_cmp_fn cmp, const void *search)
+ cmp_func_t cmp, const void *search)
{
unsigned i, n = 0;
@@ -244,21 +252,24 @@
do {
i = n;
- n = eytzinger0_child(i, cmp(search, base + i * size, size) >= 0);
+ n = eytzinger0_child(i, cmp(base + i * size, search) <= 0);
} while (n < nr);
if (n & 1) {
/* @i was greater than @search, return previous node: */
-
- if (i == eytzinger0_first(nr))
- return -1;
-
return eytzinger0_prev(i, nr);
} else {
return i;
}
}
+static inline ssize_t eytzinger0_find_gt(void *base, size_t nr, size_t size,
+ cmp_func_t cmp, const void *search)
+{
+ ssize_t idx = eytzinger0_find_le(base, nr, size, cmp, search);
+ return eytzinger0_next(idx, size);
+}
+
#define eytzinger0_find(base, nr, size, _cmp, search) \
({ \
void *_base = (base); \
@@ -269,13 +280,13 @@
int _res; \
\
while (_i < _nr && \
- (_res = _cmp(_search, _base + _i * _size, _size))) \
+ (_res = _cmp(_search, _base + _i * _size))) \
_i = eytzinger0_child(_i, _res > 0); \
_i; \
})
-void eytzinger0_sort(void *, size_t, size_t,
- int (*cmp_func)(const void *, const void *, size_t),
- void (*swap_func)(void *, void *, size_t));
+void eytzinger0_sort_r(void *, size_t, size_t,
+ cmp_r_func_t, swap_r_func_t, const void *);
+void eytzinger0_sort(void *, size_t, size_t, cmp_func_t, swap_func_t);
#endif /* _EYTZINGER_H */
diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c
index 33cb6da..f49e6c0 100644
--- a/fs/bcachefs/fs-io-direct.c
+++ b/fs/bcachefs/fs-io-direct.c
@@ -536,7 +536,7 @@
if (likely(!dio->iter.count) || dio->op.error)
break;
- bio_reset(bio, NULL, REQ_OP_WRITE);
+ bio_reset(bio, NULL, REQ_OP_WRITE | REQ_SYNC | REQ_IDLE);
}
out:
return bch2_dio_write_done(dio);
@@ -618,7 +618,7 @@
bio = bio_alloc_bioset(NULL,
bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS),
- REQ_OP_WRITE,
+ REQ_OP_WRITE | REQ_SYNC | REQ_IDLE,
GFP_KERNEL,
&c->dio_write_bioset);
dio = container_of(bio, struct dio_write, op.wbio.bio);
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 0ccee05..b5ea9fa 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -1997,6 +1997,7 @@
return dget(sb->s_root);
err_put_super:
+ __bch2_fs_stop(c);
deactivate_locked_super(sb);
return ERR_PTR(bch2_err_class(ret));
}
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 47d4eef..8e20102 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -12,7 +12,7 @@
#include "fsck.h"
#include "inode.h"
#include "keylist.h"
-#include "recovery.h"
+#include "recovery_passes.h"
#include "snapshot.h"
#include "super.h"
#include "xattr.h"
@@ -63,9 +63,7 @@
u32 *snapshot, u64 *inum)
{
struct bch_subvolume s;
- int ret;
-
- ret = bch2_subvolume_get(trans, subvol, false, 0, &s);
+ int ret = bch2_subvolume_get(trans, subvol, false, 0, &s);
*snapshot = le32_to_cpu(s.snapshot);
*inum = le64_to_cpu(s.inode);
@@ -158,9 +156,10 @@
bch2_trans_iter_init(trans, &iter, BTREE_ID_dirents, pos, BTREE_ITER_INTENT);
- ret = bch2_hash_delete_at(trans, bch2_dirent_hash_desc,
- &dir_hash_info, &iter,
- BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE);
+ ret = bch2_btree_iter_traverse(&iter) ?:
+ bch2_hash_delete_at(trans, bch2_dirent_hash_desc,
+ &dir_hash_info, &iter,
+ BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE);
bch2_trans_iter_exit(trans, &iter);
err:
bch_err_fn(c, ret);
@@ -169,7 +168,8 @@
/* Get lost+found, create if it doesn't exist: */
static int lookup_lostfound(struct btree_trans *trans, u32 snapshot,
- struct bch_inode_unpacked *lostfound)
+ struct bch_inode_unpacked *lostfound,
+ u64 reattaching_inum)
{
struct bch_fs *c = trans->c;
struct qstr lostfound_str = QSTR("lost+found");
@@ -184,19 +184,36 @@
return ret;
subvol_inum root_inum = { .subvol = le32_to_cpu(st.master_subvol) };
- u32 subvol_snapshot;
- ret = subvol_lookup(trans, le32_to_cpu(st.master_subvol),
- &subvol_snapshot, &root_inum.inum);
- bch_err_msg(c, ret, "looking up root subvol");
+ struct bch_subvolume subvol;
+ ret = bch2_subvolume_get(trans, le32_to_cpu(st.master_subvol),
+ false, 0, &subvol);
+ bch_err_msg(c, ret, "looking up root subvol %u for snapshot %u",
+ le32_to_cpu(st.master_subvol), snapshot);
if (ret)
return ret;
+ if (!subvol.inode) {
+ struct btree_iter iter;
+ struct bkey_i_subvolume *subvol = bch2_bkey_get_mut_typed(trans, &iter,
+ BTREE_ID_subvolumes, POS(0, le32_to_cpu(st.master_subvol)),
+ 0, subvolume);
+ ret = PTR_ERR_OR_ZERO(subvol);
+ if (ret)
+ return ret;
+
+ subvol->v.inode = cpu_to_le64(reattaching_inum);
+ bch2_trans_iter_exit(trans, &iter);
+ }
+
+ root_inum.inum = le64_to_cpu(subvol.inode);
+
struct bch_inode_unpacked root_inode;
struct bch_hash_info root_hash_info;
u32 root_inode_snapshot = snapshot;
ret = lookup_inode(trans, root_inum.inum, &root_inode, &root_inode_snapshot);
- bch_err_msg(c, ret, "looking up root inode");
+ bch_err_msg(c, ret, "looking up root inode %llu for subvol %u",
+ root_inum.inum, le32_to_cpu(st.master_subvol));
if (ret)
return ret;
@@ -292,7 +309,7 @@
snprintf(name_buf, sizeof(name_buf), "%llu", inode->bi_inum);
}
- ret = lookup_lostfound(trans, dirent_snapshot, &lostfound);
+ ret = lookup_lostfound(trans, dirent_snapshot, &lostfound, inode->bi_inum);
if (ret)
return ret;
@@ -363,6 +380,112 @@
return ret;
}
+static int reconstruct_subvol(struct btree_trans *trans, u32 snapshotid, u32 subvolid, u64 inum)
+{
+ struct bch_fs *c = trans->c;
+
+ if (!bch2_snapshot_is_leaf(c, snapshotid)) {
+ bch_err(c, "need to reconstruct subvol, but have interior node snapshot");
+ return -BCH_ERR_fsck_repair_unimplemented;
+ }
+
+ /*
+ * If inum isn't set, that means we're being called from check_dirents,
+ * not check_inodes - the root of this subvolume doesn't exist or we
+ * would have found it there:
+ */
+ if (!inum) {
+ struct btree_iter inode_iter = {};
+ struct bch_inode_unpacked new_inode;
+ u64 cpu = raw_smp_processor_id();
+
+ bch2_inode_init_early(c, &new_inode);
+ bch2_inode_init_late(&new_inode, bch2_current_time(c), 0, 0, S_IFDIR|0755, 0, NULL);
+
+ new_inode.bi_subvol = subvolid;
+
+ int ret = bch2_inode_create(trans, &inode_iter, &new_inode, snapshotid, cpu) ?:
+ bch2_btree_iter_traverse(&inode_iter) ?:
+ bch2_inode_write(trans, &inode_iter, &new_inode);
+ bch2_trans_iter_exit(trans, &inode_iter);
+ if (ret)
+ return ret;
+
+ inum = new_inode.bi_inum;
+ }
+
+ bch_info(c, "reconstructing subvol %u with root inode %llu", subvolid, inum);
+
+ struct bkey_i_subvolume *new_subvol = bch2_trans_kmalloc(trans, sizeof(*new_subvol));
+ int ret = PTR_ERR_OR_ZERO(new_subvol);
+ if (ret)
+ return ret;
+
+ bkey_subvolume_init(&new_subvol->k_i);
+ new_subvol->k.p.offset = subvolid;
+ new_subvol->v.snapshot = cpu_to_le32(snapshotid);
+ new_subvol->v.inode = cpu_to_le64(inum);
+ ret = bch2_btree_insert_trans(trans, BTREE_ID_subvolumes, &new_subvol->k_i, 0);
+ if (ret)
+ return ret;
+
+ struct btree_iter iter;
+ struct bkey_i_snapshot *s = bch2_bkey_get_mut_typed(trans, &iter,
+ BTREE_ID_snapshots, POS(0, snapshotid),
+ 0, snapshot);
+ ret = PTR_ERR_OR_ZERO(s);
+ bch_err_msg(c, ret, "getting snapshot %u", snapshotid);
+ if (ret)
+ return ret;
+
+ u32 snapshot_tree = le32_to_cpu(s->v.tree);
+
+ s->v.subvol = cpu_to_le32(subvolid);
+ SET_BCH_SNAPSHOT_SUBVOL(&s->v, true);
+ bch2_trans_iter_exit(trans, &iter);
+
+ struct bkey_i_snapshot_tree *st = bch2_bkey_get_mut_typed(trans, &iter,
+ BTREE_ID_snapshot_trees, POS(0, snapshot_tree),
+ 0, snapshot_tree);
+ ret = PTR_ERR_OR_ZERO(st);
+ bch_err_msg(c, ret, "getting snapshot tree %u", snapshot_tree);
+ if (ret)
+ return ret;
+
+ if (!st->v.master_subvol)
+ st->v.master_subvol = cpu_to_le32(subvolid);
+
+ bch2_trans_iter_exit(trans, &iter);
+ return 0;
+}
+
+static int reconstruct_inode(struct btree_trans *trans, u32 snapshot, u64 inum, u64 size, unsigned mode)
+{
+ struct bch_fs *c = trans->c;
+ struct bch_inode_unpacked new_inode;
+
+ bch2_inode_init_early(c, &new_inode);
+ bch2_inode_init_late(&new_inode, bch2_current_time(c), 0, 0, mode|0755, 0, NULL);
+ new_inode.bi_size = size;
+ new_inode.bi_inum = inum;
+
+ return __bch2_fsck_write_inode(trans, &new_inode, snapshot);
+}
+
+static int reconstruct_reg_inode(struct btree_trans *trans, u32 snapshot, u64 inum)
+{
+ struct btree_iter iter = {};
+
+ bch2_trans_iter_init(trans, &iter, BTREE_ID_extents, SPOS(inum, U64_MAX, snapshot), 0);
+ struct bkey_s_c k = bch2_btree_iter_peek_prev(&iter);
+ bch2_trans_iter_exit(trans, &iter);
+ int ret = bkey_err(k);
+ if (ret)
+ return ret;
+
+ return reconstruct_inode(trans, snapshot, inum, k.k->p.offset << 9, S_IFREG);
+}
+
struct snapshots_seen_entry {
u32 id;
u32 equiv;
@@ -1064,6 +1187,11 @@
if (ret && !bch2_err_matches(ret, ENOENT))
goto err;
+ if (ret && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_subvolumes))) {
+ ret = reconstruct_subvol(trans, k.k->p.snapshot, u.bi_subvol, u.bi_inum);
+ goto do_update;
+ }
+
if (fsck_err_on(ret,
c, inode_bi_subvol_missing,
"inode %llu:%u bi_subvol points to missing subvolume %u",
@@ -1081,7 +1209,7 @@
do_update = true;
}
}
-
+do_update:
if (do_update) {
ret = __bch2_fsck_write_inode(trans, &u, iter->pos.snapshot);
bch_err_msg(c, ret, "in fsck updating inode");
@@ -1130,8 +1258,8 @@
i->count = count2;
if (i->count != count2) {
- bch_err(c, "fsck counted i_sectors wrong for inode %llu:%u: got %llu should be %llu",
- w->last_pos.inode, i->snapshot, i->count, count2);
+ bch_err_ratelimited(c, "fsck counted i_sectors wrong for inode %llu:%u: got %llu should be %llu",
+ w->last_pos.inode, i->snapshot, i->count, count2);
return -BCH_ERR_internal_fsck_err;
}
@@ -1371,10 +1499,6 @@
goto err;
}
- ret = extent_ends_at(c, extent_ends, seen, k);
- if (ret)
- goto err;
-
extent_ends->last_pos = k.k->p;
err:
return ret;
@@ -1438,6 +1562,17 @@
goto err;
if (k.k->type != KEY_TYPE_whiteout) {
+ if (!i && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes))) {
+ ret = reconstruct_reg_inode(trans, k.k->p.snapshot, k.k->p.inode) ?:
+ bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
+ if (ret)
+ goto err;
+
+ inode->last_pos.inode--;
+ ret = -BCH_ERR_transaction_restart_nested;
+ goto err;
+ }
+
if (fsck_err_on(!i, c, extent_in_missing_inode,
"extent in missing inode:\n %s",
(printbuf_reset(&buf),
@@ -1504,6 +1639,12 @@
i->seen_this_pos = true;
}
+
+ if (k.k->type != KEY_TYPE_whiteout) {
+ ret = extent_ends_at(c, extent_ends, s, k);
+ if (ret)
+ goto err;
+ }
out:
err:
fsck_err:
@@ -1584,8 +1725,8 @@
return count2;
if (i->count != count2) {
- bch_err(c, "fsck counted subdirectories wrong: got %llu should be %llu",
- i->count, count2);
+ bch_err_ratelimited(c, "fsck counted subdirectories wrong for inum %llu:%u: got %llu should be %llu",
+ w->last_pos.inode, i->snapshot, i->count, count2);
i->count = count2;
if (i->inode.bi_nlink == i->count)
continue;
@@ -1782,6 +1923,7 @@
u32 parent_subvol = le32_to_cpu(d.v->d_parent_subvol);
u32 target_subvol = le32_to_cpu(d.v->d_child_subvol);
u32 parent_snapshot;
+ u32 new_parent_subvol = 0;
u64 parent_inum;
struct printbuf buf = PRINTBUF;
int ret = 0;
@@ -1790,6 +1932,27 @@
if (ret && !bch2_err_matches(ret, ENOENT))
return ret;
+ if (ret ||
+ (!ret && !bch2_snapshot_is_ancestor(c, parent_snapshot, d.k->p.snapshot))) {
+ int ret2 = find_snapshot_subvol(trans, d.k->p.snapshot, &new_parent_subvol);
+ if (ret2 && !bch2_err_matches(ret, ENOENT))
+ return ret2;
+ }
+
+ if (ret &&
+ !new_parent_subvol &&
+ (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_subvolumes))) {
+ /*
+ * Couldn't find a subvol for dirent's snapshot - but we lost
+ * subvols, so we need to reconstruct:
+ */
+ ret = reconstruct_subvol(trans, d.k->p.snapshot, parent_subvol, 0);
+ if (ret)
+ return ret;
+
+ parent_snapshot = d.k->p.snapshot;
+ }
+
if (fsck_err_on(ret, c, dirent_to_missing_parent_subvol,
"dirent parent_subvol points to missing subvolume\n%s",
(bch2_bkey_val_to_text(&buf, c, d.s_c), buf.buf)) ||
@@ -1798,10 +1961,10 @@
"dirent not visible in parent_subvol (not an ancestor of subvol snap %u)\n%s",
parent_snapshot,
(bch2_bkey_val_to_text(&buf, c, d.s_c), buf.buf))) {
- u32 new_parent_subvol;
- ret = find_snapshot_subvol(trans, d.k->p.snapshot, &new_parent_subvol);
- if (ret)
- goto err;
+ if (!new_parent_subvol) {
+ bch_err(c, "could not find a subvol for snapshot %u", d.k->p.snapshot);
+ return -BCH_ERR_fsck_repair_unimplemented;
+ }
struct bkey_i_dirent *new_dirent = bch2_bkey_make_mut_typed(trans, iter, &d.s_c, 0, dirent);
ret = PTR_ERR_OR_ZERO(new_dirent);
@@ -1847,9 +2010,16 @@
ret = lookup_inode(trans, target_inum, &subvol_root, &target_snapshot);
if (ret && !bch2_err_matches(ret, ENOENT))
- return ret;
+ goto err;
- if (fsck_err_on(parent_subvol != subvol_root.bi_parent_subvol,
+ if (ret) {
+ bch_err(c, "subvol %u points to missing inode root %llu", target_subvol, target_inum);
+ ret = -BCH_ERR_fsck_repair_unimplemented;
+ ret = 0;
+ goto err;
+ }
+
+ if (fsck_err_on(!ret && parent_subvol != subvol_root.bi_parent_subvol,
c, inode_bi_parent_wrong,
"subvol root %llu has wrong bi_parent_subvol: got %u, should be %u",
target_inum,
@@ -1857,13 +2027,13 @@
subvol_root.bi_parent_subvol = parent_subvol;
ret = __bch2_fsck_write_inode(trans, &subvol_root, target_snapshot);
if (ret)
- return ret;
+ goto err;
}
ret = check_dirent_target(trans, iter, d, &subvol_root,
target_snapshot);
if (ret)
- return ret;
+ goto err;
out:
err:
fsck_err:
@@ -1880,7 +2050,6 @@
struct snapshots_seen *s)
{
struct bch_fs *c = trans->c;
- struct bkey_s_c_dirent d;
struct inode_walker_entry *i;
struct printbuf buf = PRINTBUF;
struct bpos equiv;
@@ -1919,6 +2088,17 @@
*hash_info = bch2_hash_info_init(c, &dir->inodes.data[0].inode);
dir->first_this_inode = false;
+ if (!i && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes))) {
+ ret = reconstruct_inode(trans, k.k->p.snapshot, k.k->p.inode, 0, S_IFDIR) ?:
+ bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
+ if (ret)
+ goto err;
+
+ dir->last_pos.inode--;
+ ret = -BCH_ERR_transaction_restart_nested;
+ goto err;
+ }
+
if (fsck_err_on(!i, c, dirent_in_missing_dir_inode,
"dirent in nonexisting directory:\n%s",
(printbuf_reset(&buf),
@@ -1953,7 +2133,7 @@
if (k.k->type != KEY_TYPE_dirent)
goto out;
- d = bkey_s_c_to_dirent(k);
+ struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k);
if (d.v->d_type == DT_SUBVOL) {
ret = check_dirent_to_subvol(trans, iter, d);
@@ -2098,17 +2278,21 @@
if (mustfix_fsck_err_on(ret, c, root_subvol_missing,
"root subvol missing")) {
- struct bkey_i_subvolume root_subvol;
+ struct bkey_i_subvolume *root_subvol =
+ bch2_trans_kmalloc(trans, sizeof(*root_subvol));
+ ret = PTR_ERR_OR_ZERO(root_subvol);
+ if (ret)
+ goto err;
snapshot = U32_MAX;
inum = BCACHEFS_ROOT_INO;
- bkey_subvolume_init(&root_subvol.k_i);
- root_subvol.k.p.offset = BCACHEFS_ROOT_SUBVOL;
- root_subvol.v.flags = 0;
- root_subvol.v.snapshot = cpu_to_le32(snapshot);
- root_subvol.v.inode = cpu_to_le64(inum);
- ret = bch2_btree_insert_trans(trans, BTREE_ID_subvolumes, &root_subvol.k_i, 0);
+ bkey_subvolume_init(&root_subvol->k_i);
+ root_subvol->k.p.offset = BCACHEFS_ROOT_SUBVOL;
+ root_subvol->v.flags = 0;
+ root_subvol->v.snapshot = cpu_to_le32(snapshot);
+ root_subvol->v.inode = cpu_to_le64(inum);
+ ret = bch2_btree_insert_trans(trans, BTREE_ID_subvolumes, &root_subvol->k_i, 0);
bch_err_msg(c, ret, "writing root subvol");
if (ret)
goto err;
diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index 2b5e067..ca4a066 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -552,8 +552,8 @@
prt_printf(out, "bi_sectors=%llu", inode->bi_sectors);
prt_newline(out);
- prt_newline(out);
prt_printf(out, "bi_version=%llu", inode->bi_version);
+ prt_newline(out);
#define x(_name, _bits) \
prt_printf(out, #_name "=%llu", (u64) inode->_name); \
diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c
index 1baf785..82f9170 100644
--- a/fs/bcachefs/io_misc.c
+++ b/fs/bcachefs/io_misc.c
@@ -264,6 +264,7 @@
ret = 0;
err:
bch2_logged_op_finish(trans, op_k);
+ bch_err_fn(c, ret);
return ret;
}
@@ -476,6 +477,7 @@
break;
}
err:
+ bch_err_fn(c, ret);
bch2_logged_op_finish(trans, op_k);
bch2_trans_iter_exit(trans, &iter);
return ret;
diff --git a/fs/bcachefs/journal_seq_blacklist.c b/fs/bcachefs/journal_seq_blacklist.c
index b530387..37a024e 100644
--- a/fs/bcachefs/journal_seq_blacklist.c
+++ b/fs/bcachefs/journal_seq_blacklist.c
@@ -95,8 +95,7 @@
return ret ?: bch2_blacklist_table_initialize(c);
}
-static int journal_seq_blacklist_table_cmp(const void *_l,
- const void *_r, size_t size)
+static int journal_seq_blacklist_table_cmp(const void *_l, const void *_r)
{
const struct journal_seq_blacklist_table_entry *l = _l;
const struct journal_seq_blacklist_table_entry *r = _r;
diff --git a/fs/bcachefs/logged_ops.c b/fs/bcachefs/logged_ops.c
index 9fac838..b82f820 100644
--- a/fs/bcachefs/logged_ops.c
+++ b/fs/bcachefs/logged_ops.c
@@ -37,7 +37,6 @@
const struct bch_logged_op_fn *fn = logged_op_fn(k.k->type);
struct bkey_buf sk;
u32 restart_count = trans->restart_count;
- int ret;
if (!fn)
return 0;
@@ -45,11 +44,11 @@
bch2_bkey_buf_init(&sk);
bch2_bkey_buf_reassemble(&sk, c, k);
- ret = drop_locks_do(trans, (bch2_fs_lazy_rw(c), 0)) ?:
- fn->resume(trans, sk.k) ?: trans_was_restarted(trans, restart_count);
+ fn->resume(trans, sk.k);
bch2_bkey_buf_exit(&sk, c);
- return ret;
+
+ return trans_was_restarted(trans, restart_count);
}
int bch2_resume_logged_ops(struct bch_fs *c)
diff --git a/fs/bcachefs/mean_and_variance_test.c b/fs/bcachefs/mean_and_variance_test.c
index db63b3f..4c298e74 100644
--- a/fs/bcachefs/mean_and_variance_test.c
+++ b/fs/bcachefs/mean_and_variance_test.c
@@ -136,20 +136,8 @@
d, mean, stddev, weighted_mean, weighted_stddev);
}
-static void mean_and_variance_test_2(struct kunit *test)
-{
- s64 d[] = { 100, 10, 10, 10, 10, 10, 10 };
- s64 mean[] = { 10, 10, 10, 10, 10, 10, 10 };
- s64 stddev[] = { 9, 9, 9, 9, 9, 9, 9 };
- s64 weighted_mean[] = { 32, 27, 22, 19, 17, 15, 14 };
- s64 weighted_stddev[] = { 38, 35, 31, 27, 24, 21, 18 };
-
- do_mean_and_variance_test(test, 10, 6, ARRAY_SIZE(d), 2,
- d, mean, stddev, weighted_mean, weighted_stddev);
-}
-
/* Test behaviour where we switch from one steady state to another: */
-static void mean_and_variance_test_3(struct kunit *test)
+static void mean_and_variance_test_2(struct kunit *test)
{
s64 d[] = { 100, 100, 100, 100, 100 };
s64 mean[] = { 22, 32, 40, 46, 50 };
@@ -161,18 +149,6 @@
d, mean, stddev, weighted_mean, weighted_stddev);
}
-static void mean_and_variance_test_4(struct kunit *test)
-{
- s64 d[] = { 100, 100, 100, 100, 100 };
- s64 mean[] = { 10, 11, 12, 13, 14 };
- s64 stddev[] = { 9, 13, 15, 17, 19 };
- s64 weighted_mean[] = { 32, 49, 61, 71, 78 };
- s64 weighted_stddev[] = { 38, 44, 44, 41, 38 };
-
- do_mean_and_variance_test(test, 10, 6, ARRAY_SIZE(d), 2,
- d, mean, stddev, weighted_mean, weighted_stddev);
-}
-
static void mean_and_variance_fast_divpow2(struct kunit *test)
{
s64 i;
@@ -230,8 +206,6 @@
KUNIT_CASE(mean_and_variance_weighted_advanced_test),
KUNIT_CASE(mean_and_variance_test_1),
KUNIT_CASE(mean_and_variance_test_2),
- KUNIT_CASE(mean_and_variance_test_3),
- KUNIT_CASE(mean_and_variance_test_4),
{}
};
diff --git a/fs/bcachefs/opts.c b/fs/bcachefs/opts.c
index 08ea0cf..e1800c4 100644
--- a/fs/bcachefs/opts.c
+++ b/fs/bcachefs/opts.c
@@ -7,6 +7,7 @@
#include "disk_groups.h"
#include "error.h"
#include "opts.h"
+#include "recovery_passes.h"
#include "super-io.h"
#include "util.h"
@@ -205,6 +206,9 @@
#define OPT_STR(_choices) .type = BCH_OPT_STR, \
.min = 0, .max = ARRAY_SIZE(_choices), \
.choices = _choices
+#define OPT_STR_NOLIMIT(_choices) .type = BCH_OPT_STR, \
+ .min = 0, .max = U64_MAX, \
+ .choices = _choices
#define OPT_FN(_fn) .type = BCH_OPT_FN, .fn = _fn
#define x(_name, _bits, _flags, _type, _sb_opt, _default, _hint, _help) \
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index 136083c..1ac4135 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -362,12 +362,17 @@
OPT_FS|OPT_MOUNT, \
OPT_BOOL(), \
BCH2_NO_SB_OPT, false, \
- NULL, "Don't replay the journal") \
- x(keep_journal, u8, \
+ NULL, "Exit recovery immediately prior to journal replay")\
+ x(recovery_pass_last, u8, \
+ OPT_FS|OPT_MOUNT, \
+ OPT_STR_NOLIMIT(bch2_recovery_passes), \
+ BCH2_NO_SB_OPT, 0, \
+ NULL, "Exit recovery after specified pass") \
+ x(retain_recovery_info, u8, \
0, \
OPT_BOOL(), \
BCH2_NO_SB_OPT, false, \
- NULL, "Don't free journal entries/keys after startup")\
+ NULL, "Don't free journal entries/keys, scanned btree nodes after startup")\
x(read_entire_journal, u8, \
0, \
OPT_BOOL(), \
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 03f9d6af..b76c161 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -1,35 +1,31 @@
// SPDX-License-Identifier: GPL-2.0
#include "bcachefs.h"
-#include "backpointers.h"
-#include "bkey_buf.h"
#include "alloc_background.h"
-#include "btree_gc.h"
+#include "bkey_buf.h"
#include "btree_journal_iter.h"
+#include "btree_node_scan.h"
#include "btree_update.h"
#include "btree_update_interior.h"
#include "btree_io.h"
#include "buckets.h"
#include "dirent.h"
-#include "ec.h"
#include "errcode.h"
#include "error.h"
#include "fs-common.h"
-#include "fsck.h"
#include "journal_io.h"
#include "journal_reclaim.h"
#include "journal_seq_blacklist.h"
-#include "lru.h"
#include "logged_ops.h"
#include "move.h"
#include "quota.h"
#include "rebalance.h"
#include "recovery.h"
+#include "recovery_passes.h"
#include "replicas.h"
#include "sb-clean.h"
#include "sb-downgrade.h"
#include "snapshot.h"
-#include "subvolume.h"
#include "super-io.h"
#include <linux/sort.h>
@@ -37,6 +33,20 @@
#define QSTR(n) { { { .len = strlen(n) } }, .name = n }
+void bch2_btree_lost_data(struct bch_fs *c, enum btree_id btree)
+{
+ u64 b = BIT_ULL(btree);
+
+ if (!(c->sb.btrees_lost_data & b)) {
+ bch_err(c, "flagging btree %s lost data", bch2_btree_id_str(btree));
+
+ mutex_lock(&c->sb_lock);
+ bch2_sb_field_get(c->disk_sb.sb, ext)->btrees_lost_data |= cpu_to_le64(b);
+ bch2_write_super(c);
+ mutex_unlock(&c->sb_lock);
+ }
+}
+
static bool btree_id_is_alloc(enum btree_id id)
{
switch (id) {
@@ -52,7 +62,7 @@
}
/* for -o reconstruct_alloc: */
-static void do_reconstruct_alloc(struct bch_fs *c)
+static void bch2_reconstruct_alloc(struct bch_fs *c)
{
bch2_journal_log_msg(c, "dropping alloc info");
bch_info(c, "dropping and reconstructing all alloc info");
@@ -87,15 +97,17 @@
c->recovery_passes_explicit |= bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0]));
- struct journal_keys *keys = &c->journal_keys;
- size_t src, dst;
- move_gap(keys, keys->nr);
-
- for (src = 0, dst = 0; src < keys->nr; src++)
- if (!btree_id_is_alloc(keys->data[src].btree_id))
- keys->data[dst++] = keys->data[src];
- keys->nr = keys->gap = dst;
+ bch2_shoot_down_journal_keys(c, BTREE_ID_alloc,
+ 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+ bch2_shoot_down_journal_keys(c, BTREE_ID_backpointers,
+ 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+ bch2_shoot_down_journal_keys(c, BTREE_ID_need_discard,
+ 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+ bch2_shoot_down_journal_keys(c, BTREE_ID_freespace,
+ 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+ bch2_shoot_down_journal_keys(c, BTREE_ID_bucket_gens,
+ 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
}
/*
@@ -186,7 +198,7 @@
return cmp_int(l->journal_seq, r->journal_seq);
}
-static int bch2_journal_replay(struct bch_fs *c)
+int bch2_journal_replay(struct bch_fs *c)
{
struct journal_keys *keys = &c->journal_keys;
DARRAY(struct journal_key *) keys_sorted = { 0 };
@@ -194,6 +206,7 @@
u64 start_seq = c->journal_replay_seq_start;
u64 end_seq = c->journal_replay_seq_start;
struct btree_trans *trans = bch2_trans_get(c);
+ bool immediate_flush = false;
int ret = 0;
if (keys->nr) {
@@ -215,6 +228,13 @@
darray_for_each(*keys, k) {
cond_resched();
+ /*
+ * k->allocated means the key wasn't read in from the journal,
+ * rather it was from early repair code
+ */
+ if (k->allocated)
+ immediate_flush = true;
+
/* Skip fastpath if we're low on space in the journal */
ret = c->journal.watermark ? -1 :
commit_do(trans, NULL, NULL,
@@ -266,7 +286,8 @@
bch2_trans_put(trans);
trans = NULL;
- if (!c->opts.keep_journal)
+ if (!c->opts.retain_recovery_info &&
+ c->recovery_pass_done >= BCH_RECOVERY_PASS_journal_replay)
bch2_journal_keys_put_initial(c);
replay_now_at(j, j->replay_journal_seq_end);
@@ -274,6 +295,12 @@
bch2_journal_set_replay_done(j);
+ /* if we did any repair, flush it immediately */
+ if (immediate_flush) {
+ bch2_journal_flush_all_pins(&c->journal);
+ ret = bch2_journal_meta(&c->journal);
+ }
+
if (keys->nr)
bch2_journal_log_msg(c, "journal replay finished");
err:
@@ -423,10 +450,9 @@
static int read_btree_roots(struct bch_fs *c)
{
- unsigned i;
int ret = 0;
- for (i = 0; i < btree_id_nr_alive(c); i++) {
+ for (unsigned i = 0; i < btree_id_nr_alive(c); i++) {
struct btree_root *r = bch2_btree_id_root(c, i);
if (!r->alive)
@@ -435,186 +461,46 @@
if (btree_id_is_alloc(i) && c->opts.reconstruct_alloc)
continue;
- if (r->error) {
- __fsck_err(c,
- btree_id_is_alloc(i)
- ? FSCK_CAN_IGNORE : 0,
- btree_root_bkey_invalid,
- "invalid btree root %s",
- bch2_btree_id_str(i));
- if (i == BTREE_ID_alloc)
+ if (mustfix_fsck_err_on((ret = r->error),
+ c, btree_root_bkey_invalid,
+ "invalid btree root %s",
+ bch2_btree_id_str(i)) ||
+ mustfix_fsck_err_on((ret = r->error = bch2_btree_root_read(c, i, &r->key, r->level)),
+ c, btree_root_read_error,
+ "error reading btree root %s l=%u: %s",
+ bch2_btree_id_str(i), r->level, bch2_err_str(ret))) {
+ if (btree_id_is_alloc(i)) {
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_allocations);
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_alloc_info);
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_lrus);
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers);
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_alloc_to_lru_refs);
c->sb.compat &= ~(1ULL << BCH_COMPAT_alloc_info);
- }
+ r->error = 0;
+ } else if (!(c->recovery_passes_explicit & BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes))) {
+ bch_info(c, "will run btree node scan");
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes);
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_topology);
+ }
- ret = bch2_btree_root_read(c, i, &r->key, r->level);
- if (ret) {
- fsck_err(c,
- btree_root_read_error,
- "error reading btree root %s",
- bch2_btree_id_str(i));
- if (btree_id_is_alloc(i))
- c->sb.compat &= ~(1ULL << BCH_COMPAT_alloc_info);
ret = 0;
+ bch2_btree_lost_data(c, i);
}
}
- for (i = 0; i < BTREE_ID_NR; i++) {
+ for (unsigned i = 0; i < BTREE_ID_NR; i++) {
struct btree_root *r = bch2_btree_id_root(c, i);
- if (!r->b) {
+ if (!r->b && !r->error) {
r->alive = false;
r->level = 0;
- bch2_btree_root_alloc(c, i);
+ bch2_btree_root_alloc_fake(c, i, 0);
}
}
fsck_err:
return ret;
}
-static int bch2_initialize_subvolumes(struct bch_fs *c)
-{
- struct bkey_i_snapshot_tree root_tree;
- struct bkey_i_snapshot root_snapshot;
- struct bkey_i_subvolume root_volume;
- int ret;
-
- bkey_snapshot_tree_init(&root_tree.k_i);
- root_tree.k.p.offset = 1;
- root_tree.v.master_subvol = cpu_to_le32(1);
- root_tree.v.root_snapshot = cpu_to_le32(U32_MAX);
-
- bkey_snapshot_init(&root_snapshot.k_i);
- root_snapshot.k.p.offset = U32_MAX;
- root_snapshot.v.flags = 0;
- root_snapshot.v.parent = 0;
- root_snapshot.v.subvol = cpu_to_le32(BCACHEFS_ROOT_SUBVOL);
- root_snapshot.v.tree = cpu_to_le32(1);
- SET_BCH_SNAPSHOT_SUBVOL(&root_snapshot.v, true);
-
- bkey_subvolume_init(&root_volume.k_i);
- root_volume.k.p.offset = BCACHEFS_ROOT_SUBVOL;
- root_volume.v.flags = 0;
- root_volume.v.snapshot = cpu_to_le32(U32_MAX);
- root_volume.v.inode = cpu_to_le64(BCACHEFS_ROOT_INO);
-
- ret = bch2_btree_insert(c, BTREE_ID_snapshot_trees, &root_tree.k_i, NULL, 0) ?:
- bch2_btree_insert(c, BTREE_ID_snapshots, &root_snapshot.k_i, NULL, 0) ?:
- bch2_btree_insert(c, BTREE_ID_subvolumes, &root_volume.k_i, NULL, 0);
- bch_err_fn(c, ret);
- return ret;
-}
-
-static int __bch2_fs_upgrade_for_subvolumes(struct btree_trans *trans)
-{
- struct btree_iter iter;
- struct bkey_s_c k;
- struct bch_inode_unpacked inode;
- int ret;
-
- k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes,
- SPOS(0, BCACHEFS_ROOT_INO, U32_MAX), 0);
- ret = bkey_err(k);
- if (ret)
- return ret;
-
- if (!bkey_is_inode(k.k)) {
- bch_err(trans->c, "root inode not found");
- ret = -BCH_ERR_ENOENT_inode;
- goto err;
- }
-
- ret = bch2_inode_unpack(k, &inode);
- BUG_ON(ret);
-
- inode.bi_subvol = BCACHEFS_ROOT_SUBVOL;
-
- ret = bch2_inode_write(trans, &iter, &inode);
-err:
- bch2_trans_iter_exit(trans, &iter);
- return ret;
-}
-
-/* set bi_subvol on root inode */
-noinline_for_stack
-static int bch2_fs_upgrade_for_subvolumes(struct bch_fs *c)
-{
- int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_lazy_rw,
- __bch2_fs_upgrade_for_subvolumes(trans));
- bch_err_fn(c, ret);
- return ret;
-}
-
-const char * const bch2_recovery_passes[] = {
-#define x(_fn, ...) #_fn,
- BCH_RECOVERY_PASSES()
-#undef x
- NULL
-};
-
-static int bch2_check_allocations(struct bch_fs *c)
-{
- return bch2_gc(c, true, c->opts.norecovery);
-}
-
-static int bch2_set_may_go_rw(struct bch_fs *c)
-{
- struct journal_keys *keys = &c->journal_keys;
-
- /*
- * After we go RW, the journal keys buffer can't be modified (except for
- * setting journal_key->overwritten: it will be accessed by multiple
- * threads
- */
- move_gap(keys, keys->nr);
-
- set_bit(BCH_FS_may_go_rw, &c->flags);
-
- if (keys->nr || c->opts.fsck || !c->sb.clean)
- return bch2_fs_read_write_early(c);
- return 0;
-}
-
-struct recovery_pass_fn {
- int (*fn)(struct bch_fs *);
- unsigned when;
-};
-
-static struct recovery_pass_fn recovery_pass_fns[] = {
-#define x(_fn, _id, _when) { .fn = bch2_##_fn, .when = _when },
- BCH_RECOVERY_PASSES()
-#undef x
-};
-
-u64 bch2_recovery_passes_to_stable(u64 v)
-{
- static const u8 map[] = {
-#define x(n, id, ...) [BCH_RECOVERY_PASS_##n] = BCH_RECOVERY_PASS_STABLE_##n,
- BCH_RECOVERY_PASSES()
-#undef x
- };
-
- u64 ret = 0;
- for (unsigned i = 0; i < ARRAY_SIZE(map); i++)
- if (v & BIT_ULL(i))
- ret |= BIT_ULL(map[i]);
- return ret;
-}
-
-u64 bch2_recovery_passes_from_stable(u64 v)
-{
- static const u8 map[] = {
-#define x(n, id, ...) [BCH_RECOVERY_PASS_STABLE_##n] = BCH_RECOVERY_PASS_##n,
- BCH_RECOVERY_PASSES()
-#undef x
- };
-
- u64 ret = 0;
- for (unsigned i = 0; i < ARRAY_SIZE(map); i++)
- if (v & BIT_ULL(i))
- ret |= BIT_ULL(map[i]);
- return ret;
-}
-
static bool check_version_upgrade(struct bch_fs *c)
{
unsigned latest_version = bcachefs_metadata_version_current;
@@ -687,96 +573,6 @@
return false;
}
-u64 bch2_fsck_recovery_passes(void)
-{
- u64 ret = 0;
-
- for (unsigned i = 0; i < ARRAY_SIZE(recovery_pass_fns); i++)
- if (recovery_pass_fns[i].when & PASS_FSCK)
- ret |= BIT_ULL(i);
- return ret;
-}
-
-static bool should_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
-{
- struct recovery_pass_fn *p = recovery_pass_fns + pass;
-
- if (c->opts.norecovery && pass > BCH_RECOVERY_PASS_snapshots_read)
- return false;
- if (c->recovery_passes_explicit & BIT_ULL(pass))
- return true;
- if ((p->when & PASS_FSCK) && c->opts.fsck)
- return true;
- if ((p->when & PASS_UNCLEAN) && !c->sb.clean)
- return true;
- if (p->when & PASS_ALWAYS)
- return true;
- return false;
-}
-
-static int bch2_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
-{
- struct recovery_pass_fn *p = recovery_pass_fns + pass;
- int ret;
-
- if (!(p->when & PASS_SILENT))
- bch2_print(c, KERN_INFO bch2_log_msg(c, "%s..."),
- bch2_recovery_passes[pass]);
- ret = p->fn(c);
- if (ret)
- return ret;
- if (!(p->when & PASS_SILENT))
- bch2_print(c, KERN_CONT " done\n");
-
- return 0;
-}
-
-static int bch2_run_recovery_passes(struct bch_fs *c)
-{
- int ret = 0;
-
- while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns)) {
- if (should_run_recovery_pass(c, c->curr_recovery_pass)) {
- unsigned pass = c->curr_recovery_pass;
-
- ret = bch2_run_recovery_pass(c, c->curr_recovery_pass);
- if (bch2_err_matches(ret, BCH_ERR_restart_recovery) ||
- (ret && c->curr_recovery_pass < pass))
- continue;
- if (ret)
- break;
-
- c->recovery_passes_complete |= BIT_ULL(c->curr_recovery_pass);
- }
- c->curr_recovery_pass++;
- c->recovery_pass_done = max(c->recovery_pass_done, c->curr_recovery_pass);
- }
-
- return ret;
-}
-
-int bch2_run_online_recovery_passes(struct bch_fs *c)
-{
- int ret = 0;
-
- for (unsigned i = 0; i < ARRAY_SIZE(recovery_pass_fns); i++) {
- struct recovery_pass_fn *p = recovery_pass_fns + i;
-
- if (!(p->when & PASS_ONLINE))
- continue;
-
- ret = bch2_run_recovery_pass(c, i);
- if (bch2_err_matches(ret, BCH_ERR_restart_recovery)) {
- i = c->curr_recovery_pass;
- continue;
- }
- if (ret)
- break;
- }
-
- return ret;
-}
-
int bch2_fs_recovery(struct bch_fs *c)
{
struct bch_sb_field_clean *clean = NULL;
@@ -809,24 +605,14 @@
goto err;
}
- if (c->opts.fsck && c->opts.norecovery) {
- bch_err(c, "cannot select both norecovery and fsck");
- ret = -EINVAL;
- goto err;
- }
+ if (c->opts.norecovery)
+ c->opts.recovery_pass_last = BCH_RECOVERY_PASS_journal_replay - 1;
if (!c->opts.nochanges) {
mutex_lock(&c->sb_lock);
+ struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
bool write_sb = false;
- struct bch_sb_field_ext *ext =
- bch2_sb_field_get_minsize(&c->disk_sb, ext, sizeof(*ext) / sizeof(u64));
- if (!ext) {
- ret = -BCH_ERR_ENOSPC_sb;
- mutex_unlock(&c->sb_lock);
- goto err;
- }
-
if (BCH_SB_HAS_TOPOLOGY_ERRORS(c->disk_sb.sb)) {
ext->recovery_passes_required[0] |=
cpu_to_le64(bch2_recovery_passes_to_stable(BIT_ULL(BCH_RECOVERY_PASS_check_topology)));
@@ -885,7 +671,7 @@
goto err;
}
- if (!c->sb.clean || c->opts.fsck || c->opts.keep_journal) {
+ if (!c->sb.clean || c->opts.fsck || c->opts.retain_recovery_info) {
struct genradix_iter iter;
struct journal_replay **i;
@@ -965,7 +751,7 @@
c->journal_replay_seq_end = blacklist_seq - 1;
if (c->opts.reconstruct_alloc)
- do_reconstruct_alloc(c);
+ bch2_reconstruct_alloc(c);
zero_out_btree_mem_ptr(&c->journal_keys);
@@ -1017,6 +803,12 @@
clear_bit(BCH_FS_fsck_running, &c->flags);
+ /* fsync if we fixed errors */
+ if (test_bit(BCH_FS_errors_fixed, &c->flags)) {
+ bch2_journal_flush_all_pins(&c->journal);
+ bch2_journal_meta(&c->journal);
+ }
+
/* If we fixed errors, verify that fs is actually clean now: */
if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG) &&
test_bit(BCH_FS_errors_fixed, &c->flags) &&
@@ -1051,6 +843,7 @@
}
mutex_lock(&c->sb_lock);
+ struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
bool write_sb = false;
if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) != le16_to_cpu(c->disk_sb.sb->version)) {
@@ -1064,15 +857,18 @@
write_sb = true;
}
- if (!test_bit(BCH_FS_error, &c->flags)) {
- struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
- if (ext &&
- (!bch2_is_zero(ext->recovery_passes_required, sizeof(ext->recovery_passes_required)) ||
- !bch2_is_zero(ext->errors_silent, sizeof(ext->errors_silent)))) {
- memset(ext->recovery_passes_required, 0, sizeof(ext->recovery_passes_required));
- memset(ext->errors_silent, 0, sizeof(ext->errors_silent));
- write_sb = true;
- }
+ if (!test_bit(BCH_FS_error, &c->flags) &&
+ !bch2_is_zero(ext->errors_silent, sizeof(ext->errors_silent))) {
+ memset(ext->errors_silent, 0, sizeof(ext->errors_silent));
+ write_sb = true;
+ }
+
+ if (c->opts.fsck &&
+ !test_bit(BCH_FS_error, &c->flags) &&
+ c->recovery_pass_done == BCH_RECOVERY_PASS_NR - 1 &&
+ ext->btrees_lost_data) {
+ ext->btrees_lost_data = 0;
+ write_sb = true;
}
if (c->opts.fsck &&
@@ -1113,9 +909,10 @@
out:
bch2_flush_fsck_errs(c);
- if (!c->opts.keep_journal &&
- test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags))
+ if (!c->opts.retain_recovery_info) {
bch2_journal_keys_put_initial(c);
+ bch2_find_btree_nodes_exit(&c->found_btree_nodes);
+ }
kfree(clean);
if (!ret &&
@@ -1141,6 +938,7 @@
int ret;
bch_notice(c, "initializing new filesystem");
+ set_bit(BCH_FS_new_fs, &c->flags);
mutex_lock(&c->sb_lock);
c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_extents_above_btree_updates_done);
@@ -1155,11 +953,11 @@
}
mutex_unlock(&c->sb_lock);
- c->curr_recovery_pass = ARRAY_SIZE(recovery_pass_fns);
+ c->curr_recovery_pass = BCH_RECOVERY_PASS_NR;
set_bit(BCH_FS_may_go_rw, &c->flags);
for (unsigned i = 0; i < BTREE_ID_NR; i++)
- bch2_btree_root_alloc(c, i);
+ bch2_btree_root_alloc_fake(c, i, 0);
for_each_member_device(c, ca)
bch2_dev_usage_init(ca);
@@ -1230,7 +1028,7 @@
if (ret)
goto err;
- c->recovery_pass_done = ARRAY_SIZE(recovery_pass_fns) - 1;
+ c->recovery_pass_done = BCH_RECOVERY_PASS_NR - 1;
if (enabled_qtypes(c)) {
ret = bch2_fs_quota_read(c);
diff --git a/fs/bcachefs/recovery.h b/fs/bcachefs/recovery.h
index 4e9d247..4bf818d 100644
--- a/fs/bcachefs/recovery.h
+++ b/fs/bcachefs/recovery.h
@@ -2,37 +2,9 @@
#ifndef _BCACHEFS_RECOVERY_H
#define _BCACHEFS_RECOVERY_H
-extern const char * const bch2_recovery_passes[];
+void bch2_btree_lost_data(struct bch_fs *, enum btree_id);
-u64 bch2_recovery_passes_to_stable(u64 v);
-u64 bch2_recovery_passes_from_stable(u64 v);
-
-/*
- * For when we need to rewind recovery passes and run a pass we skipped:
- */
-static inline int bch2_run_explicit_recovery_pass(struct bch_fs *c,
- enum bch_recovery_pass pass)
-{
- if (c->recovery_passes_explicit & BIT_ULL(pass))
- return 0;
-
- bch_info(c, "running explicit recovery pass %s (%u), currently at %s (%u)",
- bch2_recovery_passes[pass], pass,
- bch2_recovery_passes[c->curr_recovery_pass], c->curr_recovery_pass);
-
- c->recovery_passes_explicit |= BIT_ULL(pass);
-
- if (c->curr_recovery_pass >= pass) {
- c->curr_recovery_pass = pass;
- c->recovery_passes_complete &= (1ULL << pass) >> 1;
- return -BCH_ERR_restart_recovery;
- } else {
- return 0;
- }
-}
-
-int bch2_run_online_recovery_passes(struct bch_fs *);
-u64 bch2_fsck_recovery_passes(void);
+int bch2_journal_replay(struct bch_fs *);
int bch2_fs_recovery(struct bch_fs *);
int bch2_fs_initialize(struct bch_fs *);
diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c
new file mode 100644
index 0000000..cb50146
--- /dev/null
+++ b/fs/bcachefs/recovery_passes.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "bcachefs.h"
+#include "alloc_background.h"
+#include "backpointers.h"
+#include "btree_gc.h"
+#include "btree_node_scan.h"
+#include "ec.h"
+#include "fsck.h"
+#include "inode.h"
+#include "journal.h"
+#include "lru.h"
+#include "logged_ops.h"
+#include "rebalance.h"
+#include "recovery.h"
+#include "recovery_passes.h"
+#include "snapshot.h"
+#include "subvolume.h"
+#include "super.h"
+#include "super-io.h"
+
+const char * const bch2_recovery_passes[] = {
+#define x(_fn, ...) #_fn,
+ BCH_RECOVERY_PASSES()
+#undef x
+ NULL
+};
+
+static int bch2_check_allocations(struct bch_fs *c)
+{
+ return bch2_gc(c, true, false);
+}
+
+static int bch2_set_may_go_rw(struct bch_fs *c)
+{
+ struct journal_keys *keys = &c->journal_keys;
+
+ /*
+ * After we go RW, the journal keys buffer can't be modified (except for
+ * setting journal_key->overwritten: it will be accessed by multiple
+ * threads
+ */
+ move_gap(keys, keys->nr);
+
+ set_bit(BCH_FS_may_go_rw, &c->flags);
+
+ if (keys->nr || c->opts.fsck || !c->sb.clean)
+ return bch2_fs_read_write_early(c);
+ return 0;
+}
+
+struct recovery_pass_fn {
+ int (*fn)(struct bch_fs *);
+ unsigned when;
+};
+
+static struct recovery_pass_fn recovery_pass_fns[] = {
+#define x(_fn, _id, _when) { .fn = bch2_##_fn, .when = _when },
+ BCH_RECOVERY_PASSES()
+#undef x
+};
+
+static const u8 passes_to_stable_map[] = {
+#define x(n, id, ...) [BCH_RECOVERY_PASS_##n] = BCH_RECOVERY_PASS_STABLE_##n,
+ BCH_RECOVERY_PASSES()
+#undef x
+};
+
+static enum bch_recovery_pass_stable bch2_recovery_pass_to_stable(enum bch_recovery_pass pass)
+{
+ return passes_to_stable_map[pass];
+}
+
+u64 bch2_recovery_passes_to_stable(u64 v)
+{
+ u64 ret = 0;
+ for (unsigned i = 0; i < ARRAY_SIZE(passes_to_stable_map); i++)
+ if (v & BIT_ULL(i))
+ ret |= BIT_ULL(passes_to_stable_map[i]);
+ return ret;
+}
+
+u64 bch2_recovery_passes_from_stable(u64 v)
+{
+ static const u8 map[] = {
+#define x(n, id, ...) [BCH_RECOVERY_PASS_STABLE_##n] = BCH_RECOVERY_PASS_##n,
+ BCH_RECOVERY_PASSES()
+#undef x
+ };
+
+ u64 ret = 0;
+ for (unsigned i = 0; i < ARRAY_SIZE(map); i++)
+ if (v & BIT_ULL(i))
+ ret |= BIT_ULL(map[i]);
+ return ret;
+}
+
+/*
+ * For when we need to rewind recovery passes and run a pass we skipped:
+ */
+int bch2_run_explicit_recovery_pass(struct bch_fs *c,
+ enum bch_recovery_pass pass)
+{
+ if (c->recovery_passes_explicit & BIT_ULL(pass))
+ return 0;
+
+ bch_info(c, "running explicit recovery pass %s (%u), currently at %s (%u)",
+ bch2_recovery_passes[pass], pass,
+ bch2_recovery_passes[c->curr_recovery_pass], c->curr_recovery_pass);
+
+ c->recovery_passes_explicit |= BIT_ULL(pass);
+
+ if (c->curr_recovery_pass >= pass) {
+ c->curr_recovery_pass = pass;
+ c->recovery_passes_complete &= (1ULL << pass) >> 1;
+ return -BCH_ERR_restart_recovery;
+ } else {
+ return 0;
+ }
+}
+
+int bch2_run_explicit_recovery_pass_persistent(struct bch_fs *c,
+ enum bch_recovery_pass pass)
+{
+ enum bch_recovery_pass_stable s = bch2_recovery_pass_to_stable(pass);
+
+ mutex_lock(&c->sb_lock);
+ struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
+
+ if (!test_bit_le64(s, ext->recovery_passes_required)) {
+ __set_bit_le64(s, ext->recovery_passes_required);
+ bch2_write_super(c);
+ }
+ mutex_unlock(&c->sb_lock);
+
+ return bch2_run_explicit_recovery_pass(c, pass);
+}
+
+static void bch2_clear_recovery_pass_required(struct bch_fs *c,
+ enum bch_recovery_pass pass)
+{
+ enum bch_recovery_pass_stable s = bch2_recovery_pass_to_stable(pass);
+
+ mutex_lock(&c->sb_lock);
+ struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
+
+ if (test_bit_le64(s, ext->recovery_passes_required)) {
+ __clear_bit_le64(s, ext->recovery_passes_required);
+ bch2_write_super(c);
+ }
+ mutex_unlock(&c->sb_lock);
+}
+
+u64 bch2_fsck_recovery_passes(void)
+{
+ u64 ret = 0;
+
+ for (unsigned i = 0; i < ARRAY_SIZE(recovery_pass_fns); i++)
+ if (recovery_pass_fns[i].when & PASS_FSCK)
+ ret |= BIT_ULL(i);
+ return ret;
+}
+
+static bool should_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
+{
+ struct recovery_pass_fn *p = recovery_pass_fns + pass;
+
+ if (c->recovery_passes_explicit & BIT_ULL(pass))
+ return true;
+ if ((p->when & PASS_FSCK) && c->opts.fsck)
+ return true;
+ if ((p->when & PASS_UNCLEAN) && !c->sb.clean)
+ return true;
+ if (p->when & PASS_ALWAYS)
+ return true;
+ return false;
+}
+
+static int bch2_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
+{
+ struct recovery_pass_fn *p = recovery_pass_fns + pass;
+ int ret;
+
+ if (!(p->when & PASS_SILENT))
+ bch2_print(c, KERN_INFO bch2_log_msg(c, "%s..."),
+ bch2_recovery_passes[pass]);
+ ret = p->fn(c);
+ if (ret)
+ return ret;
+ if (!(p->when & PASS_SILENT))
+ bch2_print(c, KERN_CONT " done\n");
+
+ return 0;
+}
+
+int bch2_run_online_recovery_passes(struct bch_fs *c)
+{
+ int ret = 0;
+
+ for (unsigned i = 0; i < ARRAY_SIZE(recovery_pass_fns); i++) {
+ struct recovery_pass_fn *p = recovery_pass_fns + i;
+
+ if (!(p->when & PASS_ONLINE))
+ continue;
+
+ ret = bch2_run_recovery_pass(c, i);
+ if (bch2_err_matches(ret, BCH_ERR_restart_recovery)) {
+ i = c->curr_recovery_pass;
+ continue;
+ }
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+int bch2_run_recovery_passes(struct bch_fs *c)
+{
+ int ret = 0;
+
+ while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns)) {
+ if (c->opts.recovery_pass_last &&
+ c->curr_recovery_pass > c->opts.recovery_pass_last)
+ break;
+
+ if (should_run_recovery_pass(c, c->curr_recovery_pass)) {
+ unsigned pass = c->curr_recovery_pass;
+
+ ret = bch2_run_recovery_pass(c, c->curr_recovery_pass);
+ if (bch2_err_matches(ret, BCH_ERR_restart_recovery) ||
+ (ret && c->curr_recovery_pass < pass))
+ continue;
+ if (ret)
+ break;
+
+ c->recovery_passes_complete |= BIT_ULL(c->curr_recovery_pass);
+ }
+
+ c->recovery_pass_done = max(c->recovery_pass_done, c->curr_recovery_pass);
+
+ if (!test_bit(BCH_FS_error, &c->flags))
+ bch2_clear_recovery_pass_required(c, c->curr_recovery_pass);
+
+ c->curr_recovery_pass++;
+ }
+
+ return ret;
+}
diff --git a/fs/bcachefs/recovery_passes.h b/fs/bcachefs/recovery_passes.h
new file mode 100644
index 0000000..99b464e
--- /dev/null
+++ b/fs/bcachefs/recovery_passes.h
@@ -0,0 +1,17 @@
+#ifndef _BCACHEFS_RECOVERY_PASSES_H
+#define _BCACHEFS_RECOVERY_PASSES_H
+
+extern const char * const bch2_recovery_passes[];
+
+u64 bch2_recovery_passes_to_stable(u64 v);
+u64 bch2_recovery_passes_from_stable(u64 v);
+
+u64 bch2_fsck_recovery_passes(void);
+
+int bch2_run_explicit_recovery_pass(struct bch_fs *, enum bch_recovery_pass);
+int bch2_run_explicit_recovery_pass_persistent(struct bch_fs *, enum bch_recovery_pass);
+
+int bch2_run_online_recovery_passes(struct bch_fs *);
+int bch2_run_recovery_passes(struct bch_fs *);
+
+#endif /* _BCACHEFS_RECOVERY_PASSES_H */
diff --git a/fs/bcachefs/recovery_types.h b/fs/bcachefs/recovery_passes_types.h
similarity index 91%
rename from fs/bcachefs/recovery_types.h
rename to fs/bcachefs/recovery_passes_types.h
index 4959e95..773aea9 100644
--- a/fs/bcachefs/recovery_types.h
+++ b/fs/bcachefs/recovery_passes_types.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _BCACHEFS_RECOVERY_TYPES_H
-#define _BCACHEFS_RECOVERY_TYPES_H
+#ifndef _BCACHEFS_RECOVERY_PASSES_TYPES_H
+#define _BCACHEFS_RECOVERY_PASSES_TYPES_H
#define PASS_SILENT BIT(0)
#define PASS_FSCK BIT(1)
@@ -13,6 +13,7 @@
* must never change:
*/
#define BCH_RECOVERY_PASSES() \
+ x(scan_for_btree_nodes, 37, 0) \
x(check_topology, 4, 0) \
x(alloc_read, 0, PASS_ALWAYS) \
x(stripes_read, 1, PASS_ALWAYS) \
@@ -31,13 +32,13 @@
x(check_alloc_to_lru_refs, 15, PASS_ONLINE|PASS_FSCK) \
x(fs_freespace_init, 16, PASS_ALWAYS|PASS_SILENT) \
x(bucket_gens_init, 17, 0) \
+ x(reconstruct_snapshots, 38, 0) \
x(check_snapshot_trees, 18, PASS_ONLINE|PASS_FSCK) \
x(check_snapshots, 19, PASS_ONLINE|PASS_FSCK) \
x(check_subvols, 20, PASS_ONLINE|PASS_FSCK) \
x(check_subvol_children, 35, PASS_ONLINE|PASS_FSCK) \
x(delete_dead_snapshots, 21, PASS_ONLINE|PASS_FSCK) \
x(fs_upgrade_for_subvolumes, 22, 0) \
- x(resume_logged_ops, 23, PASS_ALWAYS) \
x(check_inodes, 24, PASS_FSCK) \
x(check_extents, 25, PASS_FSCK) \
x(check_indirect_extents, 26, PASS_FSCK) \
@@ -47,6 +48,7 @@
x(check_subvolume_structure, 36, PASS_ONLINE|PASS_FSCK) \
x(check_directory_structure, 30, PASS_ONLINE|PASS_FSCK) \
x(check_nlinks, 31, PASS_FSCK) \
+ x(resume_logged_ops, 23, PASS_ALWAYS) \
x(delete_dead_inodes, 32, PASS_FSCK|PASS_UNCLEAN) \
x(fix_reflink_p, 33, 0) \
x(set_fs_needs_rebalance, 34, 0) \
@@ -56,6 +58,7 @@
#define x(n, id, when) BCH_RECOVERY_PASS_##n,
BCH_RECOVERY_PASSES()
#undef x
+ BCH_RECOVERY_PASS_NR
};
/* But we also need stable identifiers that can be used in the superblock */
@@ -65,4 +68,4 @@
#undef x
};
-#endif /* _BCACHEFS_RECOVERY_TYPES_H */
+#endif /* _BCACHEFS_RECOVERY_PASSES_TYPES_H */
diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c
index c47c66c..ff78647 100644
--- a/fs/bcachefs/reflink.c
+++ b/fs/bcachefs/reflink.c
@@ -185,8 +185,7 @@
} else {
bkey_error_init(update);
update->k.p = p.k->p;
- update->k.p.offset = next_idx;
- update->k.size = next_idx - *idx;
+ update->k.size = p.k->size;
set_bkey_val_u64s(&update->k, 0);
}
diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c
index cc2672c..678b9c2 100644
--- a/fs/bcachefs/replicas.c
+++ b/fs/bcachefs/replicas.c
@@ -6,12 +6,15 @@
#include "replicas.h"
#include "super-io.h"
+#include <linux/sort.h>
+
static int bch2_cpu_replicas_to_sb_replicas(struct bch_fs *,
struct bch_replicas_cpu *);
/* Some (buggy!) compilers don't allow memcmp to be passed as a pointer */
-static int bch2_memcmp(const void *l, const void *r, size_t size)
+static int bch2_memcmp(const void *l, const void *r, const void *priv)
{
+ size_t size = (size_t) priv;
return memcmp(l, r, size);
}
@@ -39,7 +42,8 @@
static void bch2_cpu_replicas_sort(struct bch_replicas_cpu *r)
{
- eytzinger0_sort(r->entries, r->nr, r->entry_size, bch2_memcmp, NULL);
+ eytzinger0_sort_r(r->entries, r->nr, r->entry_size,
+ bch2_memcmp, NULL, (void *)(size_t)r->entry_size);
}
static void bch2_replicas_entry_v0_to_text(struct printbuf *out,
@@ -228,7 +232,7 @@
verify_replicas_entry(search);
-#define entry_cmp(_l, _r, size) memcmp(_l, _r, entry_size)
+#define entry_cmp(_l, _r) memcmp(_l, _r, entry_size)
idx = eytzinger0_find(r->entries, r->nr, r->entry_size,
entry_cmp, search);
#undef entry_cmp
@@ -824,10 +828,11 @@
{
unsigned i;
- sort_cmp_size(cpu_r->entries,
- cpu_r->nr,
- cpu_r->entry_size,
- bch2_memcmp, NULL);
+ sort_r(cpu_r->entries,
+ cpu_r->nr,
+ cpu_r->entry_size,
+ bch2_memcmp, NULL,
+ (void *)(size_t)cpu_r->entry_size);
for (i = 0; i < cpu_r->nr; i++) {
struct bch_replicas_entry_v1 *e =
diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c
index e4396cb..d6f8117 100644
--- a/fs/bcachefs/sb-downgrade.c
+++ b/fs/bcachefs/sb-downgrade.c
@@ -7,7 +7,7 @@
#include "bcachefs.h"
#include "darray.h"
-#include "recovery.h"
+#include "recovery_passes.h"
#include "sb-downgrade.h"
#include "sb-errors.h"
#include "super-io.h"
diff --git a/fs/bcachefs/sb-errors_types.h b/fs/bcachefs/sb-errors_types.h
index 5178bf5..d7d6091 100644
--- a/fs/bcachefs/sb-errors_types.h
+++ b/fs/bcachefs/sb-errors_types.h
@@ -265,7 +265,12 @@
x(subvol_children_bad, 257) \
x(subvol_loop, 258) \
x(subvol_unreachable, 259) \
- x(btree_node_bkey_bad_u64s, 260)
+ x(btree_node_bkey_bad_u64s, 260) \
+ x(btree_node_topology_empty_interior_node, 261) \
+ x(btree_ptr_v2_min_key_bad, 262) \
+ x(btree_root_unreadable_and_scan_found_nothing, 263) \
+ x(snapshot_node_missing, 264) \
+ x(dup_backpointer_to_bad_csum_extent, 265)
enum bch_sb_error_id {
#define x(t, n) BCH_FSCK_ERR_##t = n,
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index 39debe8..0e806f0 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -8,6 +8,7 @@
#include "errcode.h"
#include "error.h"
#include "fs.h"
+#include "recovery_passes.h"
#include "snapshot.h"
#include <linux/random.h>
@@ -93,8 +94,10 @@
static bool __bch2_snapshot_is_ancestor_early(struct snapshot_table *t, u32 id, u32 ancestor)
{
- while (id && id < ancestor)
- id = __snapshot_t(t, id)->parent;
+ while (id && id < ancestor) {
+ const struct snapshot_t *s = __snapshot_t(t, id);
+ id = s ? s->parent : 0;
+ }
return id == ancestor;
}
@@ -110,6 +113,8 @@
static inline u32 get_ancestor_below(struct snapshot_table *t, u32 id, u32 ancestor)
{
const struct snapshot_t *s = __snapshot_t(t, id);
+ if (!s)
+ return 0;
if (s->skip[2] <= ancestor)
return s->skip[2];
@@ -127,7 +132,7 @@
rcu_read_lock();
struct snapshot_table *t = rcu_dereference(c->snapshots);
- if (unlikely(c->recovery_pass_done <= BCH_RECOVERY_PASS_check_snapshots)) {
+ if (unlikely(c->recovery_pass_done < BCH_RECOVERY_PASS_check_snapshots)) {
ret = __bch2_snapshot_is_ancestor_early(t, id, ancestor);
goto out;
}
@@ -151,36 +156,39 @@
static noinline struct snapshot_t *__snapshot_t_mut(struct bch_fs *c, u32 id)
{
size_t idx = U32_MAX - id;
- size_t new_size;
struct snapshot_table *new, *old;
- new_size = max(16UL, roundup_pow_of_two(idx + 1));
+ size_t new_bytes = kmalloc_size_roundup(struct_size(new, s, idx + 1));
+ size_t new_size = (new_bytes - sizeof(*new)) / sizeof(new->s[0]);
- new = kvzalloc(struct_size(new, s, new_size), GFP_KERNEL);
+ new = kvzalloc(new_bytes, GFP_KERNEL);
if (!new)
return NULL;
+ new->nr = new_size;
+
old = rcu_dereference_protected(c->snapshots, true);
if (old)
- memcpy(new->s,
- rcu_dereference_protected(c->snapshots, true)->s,
- sizeof(new->s[0]) * c->snapshot_table_size);
+ memcpy(new->s, old->s, sizeof(old->s[0]) * old->nr);
rcu_assign_pointer(c->snapshots, new);
- c->snapshot_table_size = new_size;
- kvfree_rcu_mightsleep(old);
+ kvfree_rcu(old, rcu);
- return &rcu_dereference_protected(c->snapshots, true)->s[idx];
+ return &rcu_dereference_protected(c->snapshots,
+ lockdep_is_held(&c->snapshot_table_lock))->s[idx];
}
static inline struct snapshot_t *snapshot_t_mut(struct bch_fs *c, u32 id)
{
size_t idx = U32_MAX - id;
+ struct snapshot_table *table =
+ rcu_dereference_protected(c->snapshots,
+ lockdep_is_held(&c->snapshot_table_lock));
lockdep_assert_held(&c->snapshot_table_lock);
- if (likely(idx < c->snapshot_table_size))
- return &rcu_dereference_protected(c->snapshots, true)->s[idx];
+ if (likely(table && idx < table->nr))
+ return &table->s[idx];
return __snapshot_t_mut(c, id);
}
@@ -567,6 +575,13 @@
u32 subvol_id;
ret = bch2_snapshot_tree_master_subvol(trans, root_id, &subvol_id);
+ bch_err_fn(c, ret);
+
+ if (bch2_err_matches(ret, ENOENT)) { /* nothing to be done here */
+ ret = 0;
+ goto err;
+ }
+
if (ret)
goto err;
@@ -724,7 +739,6 @@
u32 parent_id = bch2_snapshot_parent_early(c, k.k->p.offset);
u32 real_depth;
struct printbuf buf = PRINTBUF;
- bool should_have_subvol;
u32 i, id;
int ret = 0;
@@ -770,7 +784,7 @@
}
}
- should_have_subvol = BCH_SNAPSHOT_SUBVOL(&s) &&
+ bool should_have_subvol = BCH_SNAPSHOT_SUBVOL(&s) &&
!BCH_SNAPSHOT_DELETED(&s);
if (should_have_subvol) {
@@ -872,6 +886,154 @@
return ret;
}
+static int check_snapshot_exists(struct btree_trans *trans, u32 id)
+{
+ struct bch_fs *c = trans->c;
+
+ if (bch2_snapshot_equiv(c, id))
+ return 0;
+
+ u32 tree_id;
+ int ret = bch2_snapshot_tree_create(trans, id, 0, &tree_id);
+ if (ret)
+ return ret;
+
+ struct bkey_i_snapshot *snapshot = bch2_trans_kmalloc(trans, sizeof(*snapshot));
+ ret = PTR_ERR_OR_ZERO(snapshot);
+ if (ret)
+ return ret;
+
+ bkey_snapshot_init(&snapshot->k_i);
+ snapshot->k.p = POS(0, id);
+ snapshot->v.tree = cpu_to_le32(tree_id);
+ snapshot->v.btime.lo = cpu_to_le64(bch2_current_time(c));
+
+ return bch2_btree_insert_trans(trans, BTREE_ID_snapshots, &snapshot->k_i, 0) ?:
+ bch2_mark_snapshot(trans, BTREE_ID_snapshots, 0,
+ bkey_s_c_null, bkey_i_to_s(&snapshot->k_i), 0) ?:
+ bch2_snapshot_set_equiv(trans, bkey_i_to_s_c(&snapshot->k_i));
+}
+
+/* Figure out which snapshot nodes belong in the same tree: */
+struct snapshot_tree_reconstruct {
+ enum btree_id btree;
+ struct bpos cur_pos;
+ snapshot_id_list cur_ids;
+ DARRAY(snapshot_id_list) trees;
+};
+
+static void snapshot_tree_reconstruct_exit(struct snapshot_tree_reconstruct *r)
+{
+ darray_for_each(r->trees, i)
+ darray_exit(i);
+ darray_exit(&r->trees);
+ darray_exit(&r->cur_ids);
+}
+
+static inline bool same_snapshot(struct snapshot_tree_reconstruct *r, struct bpos pos)
+{
+ return r->btree == BTREE_ID_inodes
+ ? r->cur_pos.offset == pos.offset
+ : r->cur_pos.inode == pos.inode;
+}
+
+static inline bool snapshot_id_lists_have_common(snapshot_id_list *l, snapshot_id_list *r)
+{
+ darray_for_each(*l, i)
+ if (snapshot_list_has_id(r, *i))
+ return true;
+ return false;
+}
+
+static void snapshot_id_list_to_text(struct printbuf *out, snapshot_id_list *s)
+{
+ bool first = true;
+ darray_for_each(*s, i) {
+ if (!first)
+ prt_char(out, ' ');
+ first = false;
+ prt_printf(out, "%u", *i);
+ }
+}
+
+static int snapshot_tree_reconstruct_next(struct bch_fs *c, struct snapshot_tree_reconstruct *r)
+{
+ if (r->cur_ids.nr) {
+ darray_for_each(r->trees, i)
+ if (snapshot_id_lists_have_common(i, &r->cur_ids)) {
+ int ret = snapshot_list_merge(c, i, &r->cur_ids);
+ if (ret)
+ return ret;
+ goto out;
+ }
+ darray_push(&r->trees, r->cur_ids);
+ darray_init(&r->cur_ids);
+ }
+out:
+ r->cur_ids.nr = 0;
+ return 0;
+}
+
+static int get_snapshot_trees(struct bch_fs *c, struct snapshot_tree_reconstruct *r, struct bpos pos)
+{
+ if (!same_snapshot(r, pos))
+ snapshot_tree_reconstruct_next(c, r);
+ r->cur_pos = pos;
+ return snapshot_list_add_nodup(c, &r->cur_ids, pos.snapshot);
+}
+
+int bch2_reconstruct_snapshots(struct bch_fs *c)
+{
+ struct btree_trans *trans = bch2_trans_get(c);
+ struct printbuf buf = PRINTBUF;
+ struct snapshot_tree_reconstruct r = {};
+ int ret = 0;
+
+ for (unsigned btree = 0; btree < BTREE_ID_NR; btree++) {
+ if (btree_type_has_snapshots(btree)) {
+ r.btree = btree;
+
+ ret = for_each_btree_key(trans, iter, btree, POS_MIN,
+ BTREE_ITER_ALL_SNAPSHOTS|BTREE_ITER_PREFETCH, k, ({
+ get_snapshot_trees(c, &r, k.k->p);
+ }));
+ if (ret)
+ goto err;
+
+ snapshot_tree_reconstruct_next(c, &r);
+ }
+ }
+
+ darray_for_each(r.trees, t) {
+ printbuf_reset(&buf);
+ snapshot_id_list_to_text(&buf, t);
+
+ darray_for_each(*t, id) {
+ if (fsck_err_on(!bch2_snapshot_equiv(c, *id),
+ c, snapshot_node_missing,
+ "snapshot node %u from tree %s missing", *id, buf.buf)) {
+ if (t->nr > 1) {
+ bch_err(c, "cannot reconstruct snapshot trees with multiple nodes");
+ ret = -BCH_ERR_fsck_repair_unimplemented;
+ goto err;
+ }
+
+ ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
+ check_snapshot_exists(trans, *id));
+ if (ret)
+ goto err;
+ }
+ }
+ }
+fsck_err:
+err:
+ bch2_trans_put(trans);
+ snapshot_tree_reconstruct_exit(&r);
+ printbuf_exit(&buf);
+ bch_err_fn(c, ret);
+ return ret;
+}
+
/*
* Mark a snapshot as deleted, for future cleanup:
*/
@@ -1682,6 +1844,20 @@
POS_MIN, 0, k,
(set_is_ancestor_bitmap(c, k.k->p.offset), 0)));
bch_err_fn(c, ret);
+
+ /*
+ * It's important that we check if we need to reconstruct snapshots
+ * before going RW, so we mark that pass as required in the superblock -
+ * otherwise, we could end up deleting keys with missing snapshot nodes
+ * instead
+ */
+ BUG_ON(!test_bit(BCH_FS_new_fs, &c->flags) &&
+ test_bit(BCH_FS_may_go_rw, &c->flags));
+
+ if (bch2_err_matches(ret, EIO) ||
+ (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_snapshots)))
+ ret = bch2_run_explicit_recovery_pass_persistent(c, BCH_RECOVERY_PASS_reconstruct_snapshots);
+
return ret;
}
diff --git a/fs/bcachefs/snapshot.h b/fs/bcachefs/snapshot.h
index 7c66ffc..b7d2fed 100644
--- a/fs/bcachefs/snapshot.h
+++ b/fs/bcachefs/snapshot.h
@@ -33,7 +33,11 @@
static inline struct snapshot_t *__snapshot_t(struct snapshot_table *t, u32 id)
{
- return &t->s[U32_MAX - id];
+ u32 idx = U32_MAX - id;
+
+ return likely(t && idx < t->nr)
+ ? &t->s[idx]
+ : NULL;
}
static inline const struct snapshot_t *snapshot_t(struct bch_fs *c, u32 id)
@@ -44,7 +48,8 @@
static inline u32 bch2_snapshot_tree(struct bch_fs *c, u32 id)
{
rcu_read_lock();
- id = snapshot_t(c, id)->tree;
+ const struct snapshot_t *s = snapshot_t(c, id);
+ id = s ? s->tree : 0;
rcu_read_unlock();
return id;
@@ -52,7 +57,8 @@
static inline u32 __bch2_snapshot_parent_early(struct bch_fs *c, u32 id)
{
- return snapshot_t(c, id)->parent;
+ const struct snapshot_t *s = snapshot_t(c, id);
+ return s ? s->parent : 0;
}
static inline u32 bch2_snapshot_parent_early(struct bch_fs *c, u32 id)
@@ -66,19 +72,19 @@
static inline u32 __bch2_snapshot_parent(struct bch_fs *c, u32 id)
{
-#ifdef CONFIG_BCACHEFS_DEBUG
- u32 parent = snapshot_t(c, id)->parent;
+ const struct snapshot_t *s = snapshot_t(c, id);
+ if (!s)
+ return 0;
- if (parent &&
- snapshot_t(c, id)->depth != snapshot_t(c, parent)->depth + 1)
+ u32 parent = s->parent;
+ if (IS_ENABLED(CONFIG_BCACHEFS_DEBU) &&
+ parent &&
+ s->depth != snapshot_t(c, parent)->depth + 1)
panic("id %u depth=%u parent %u depth=%u\n",
id, snapshot_t(c, id)->depth,
parent, snapshot_t(c, parent)->depth);
return parent;
-#else
- return snapshot_t(c, id)->parent;
-#endif
}
static inline u32 bch2_snapshot_parent(struct bch_fs *c, u32 id)
@@ -116,7 +122,8 @@
static inline u32 __bch2_snapshot_equiv(struct bch_fs *c, u32 id)
{
- return snapshot_t(c, id)->equiv;
+ const struct snapshot_t *s = snaps