From: "Paul E. McKenney" paulmck@kernel.org
[ Upstream commit d31e31365b5b6c0cdfc74d71be87234ced564395 ]
Currently, srcu_get_delay() can be called concurrently, for example, by a CPU that is the first to request a new grace period and the CPU processing the current grace period. Although concurrent access is harmless, it unnecessarily expands the state space. Additionally, all calls to srcu_get_delay() are from slow paths.
This commit therefore protects all calls to srcu_get_delay() with ssp->srcu_sup->lock, which is already held on the invocation from the srcu_funnel_gp_start() function. While in the area, this commit also adds a lockdep_assert_held() to srcu_get_delay() itself.
Reported-by: syzbot+16a19b06125a2963eaee@syzkaller.appspotmail.com Signed-off-by: Paul E. McKenney paulmck@kernel.org Cc: Alexei Starovoitov ast@kernel.org Cc: Andrii Nakryiko andrii@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Kent Overstreet kent.overstreet@linux.dev Cc: bpf@vger.kernel.org Signed-off-by: Boqun Feng boqun.feng@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/rcu/srcutree.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 5e2e534647946..c5419e97bd97b 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -647,6 +647,7 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp) unsigned long jbase = SRCU_INTERVAL; struct srcu_usage *sup = ssp->srcu_sup;
+ lockdep_assert_held(&ACCESS_PRIVATE(ssp->srcu_sup, lock)); if (srcu_gp_is_expedited(ssp)) jbase = 0; if (rcu_seq_state(READ_ONCE(sup->srcu_gp_seq))) { @@ -674,9 +675,13 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp) void cleanup_srcu_struct(struct srcu_struct *ssp) { int cpu; + unsigned long delay; struct srcu_usage *sup = ssp->srcu_sup;
- if (WARN_ON(!srcu_get_delay(ssp))) + spin_lock_irq_rcu_node(ssp->srcu_sup); + delay = srcu_get_delay(ssp); + spin_unlock_irq_rcu_node(ssp->srcu_sup); + if (WARN_ON(!delay)) return; /* Just leak it! */ if (WARN_ON(srcu_readers_active(ssp))) return; /* Just leak it! */ @@ -1102,7 +1107,9 @@ static bool try_check_zero(struct srcu_struct *ssp, int idx, int trycount) { unsigned long curdelay;
+ spin_lock_irq_rcu_node(ssp->srcu_sup); curdelay = !srcu_get_delay(ssp); + spin_unlock_irq_rcu_node(ssp->srcu_sup);
for (;;) { if (srcu_readers_active_idx_check(ssp, idx)) @@ -1849,7 +1856,9 @@ static void process_srcu(struct work_struct *work) ssp = sup->srcu_ssp;
srcu_advance_state(ssp); + spin_lock_irq_rcu_node(ssp->srcu_sup); curdelay = srcu_get_delay(ssp); + spin_unlock_irq_rcu_node(ssp->srcu_sup); if (curdelay) { WRITE_ONCE(sup->reschedule_count, 0); } else {
From: Zhongqiu Han quic_zhonhan@quicinc.com
[ Upstream commit 208baa3ec9043a664d9acfb8174b332e6b17fb69 ]
If malloc returns NULL due to low memory, 'config' pointer can be NULL. Add a check to prevent NULL dereference.
Link: https://lore.kernel.org/r/20250219122715.3892223-1-quic_zhonhan@quicinc.com Signed-off-by: Zhongqiu Han quic_zhonhan@quicinc.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/power/cpupower/bench/parse.c | 4 ++++ 1 file changed, 4 insertions(+)
diff --git a/tools/power/cpupower/bench/parse.c b/tools/power/cpupower/bench/parse.c index 080678d9d74e2..bd67c758b33ac 100644 --- a/tools/power/cpupower/bench/parse.c +++ b/tools/power/cpupower/bench/parse.c @@ -121,6 +121,10 @@ FILE *prepare_output(const char *dirname) struct config *prepare_default_config() { struct config *config = malloc(sizeof(struct config)); + if (!config) { + perror("malloc"); + return NULL; + }
dprintf("loading defaults\n");
From: Dmitry Osipenko dmitry.osipenko@collabora.com
[ Upstream commit 2d81e1bb625238d40a686ed909ff3e1abab7556a ]
Rockchip RK3566/RK3568 GIC600 integration has DDR addressing limited to the first 32bit of physical address space. Rockchip assigned Erratum ID #3568002 for this issue. Add driver quirk for this Rockchip GIC Erratum.
Note, that the 0x0201743b GIC600 ID is not Rockchip-specific and is common for many ARM GICv3 implementations. Hence, there is an extra of_machine_is_compatible() check.
Signed-off-by: Dmitry Osipenko dmitry.osipenko@collabora.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Marc Zyngier maz@kernel.org Link: https://lore.kernel.org/all/20250216221634.364158-2-dmitry.osipenko@collabor... Signed-off-by: Sasha Levin sashal@kernel.org --- Documentation/arch/arm64/silicon-errata.rst | 2 ++ arch/arm64/Kconfig | 9 ++++++++ drivers/irqchip/irq-gic-v3-its.c | 23 ++++++++++++++++++++- 3 files changed, 33 insertions(+), 1 deletion(-)
diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst index b42fea07c5cec..ab87b3499b386 100644 --- a/Documentation/arch/arm64/silicon-errata.rst +++ b/Documentation/arch/arm64/silicon-errata.rst @@ -283,6 +283,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Rockchip | RK3588 | #3588001 | ROCKCHIP_ERRATUM_3588001 | +----------------+-----------------+-----------------+-----------------------------+ +| Rockchip | RK3568 | #3568002 | ROCKCHIP_ERRATUM_3568002 | ++----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ | Fujitsu | A64FX | E#010001 | FUJITSU_ERRATUM_010001 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 100570a048c5e..4531ed216d50c 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1298,6 +1298,15 @@ config NVIDIA_CARMEL_CNP_ERRATUM
If unsure, say Y.
+config ROCKCHIP_ERRATUM_3568002 + bool "Rockchip 3568002: GIC600 can not access physical addresses higher than 4GB" + default y + help + The Rockchip RK3566 and RK3568 GIC600 SoC integrations have AXI + addressing limited to the first 32bit of physical address space. + + If unsure, say Y. + config ROCKCHIP_ERRATUM_3588001 bool "Rockchip 3588001: GIC600 can not support shareability attributes" default y diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 8c3ec5734f1ef..f30ed281882ff 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -205,13 +205,15 @@ static DEFINE_IDA(its_vpeid_ida); #define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base) #define gic_data_rdist_vlpi_base() (gic_data_rdist_rd_base() + SZ_128K)
+static gfp_t gfp_flags_quirk; + static struct page *its_alloc_pages_node(int node, gfp_t gfp, unsigned int order) { struct page *page; int ret = 0;
- page = alloc_pages_node(node, gfp, order); + page = alloc_pages_node(node, gfp | gfp_flags_quirk, order);
if (!page) return NULL; @@ -4887,6 +4889,17 @@ static bool __maybe_unused its_enable_quirk_hip09_162100801(void *data) return true; }
+static bool __maybe_unused its_enable_rk3568002(void *data) +{ + if (!of_machine_is_compatible("rockchip,rk3566") && + !of_machine_is_compatible("rockchip,rk3568")) + return false; + + gfp_flags_quirk |= GFP_DMA32; + + return true; +} + static const struct gic_quirk its_quirks[] = { #ifdef CONFIG_CAVIUM_ERRATUM_22375 { @@ -4954,6 +4967,14 @@ static const struct gic_quirk its_quirks[] = { .property = "dma-noncoherent", .init = its_set_non_coherent, }, +#ifdef CONFIG_ROCKCHIP_ERRATUM_3568002 + { + .desc = "ITS: Rockchip erratum RK3568002", + .iidr = 0x0201743b, + .mask = 0xffffffff, + .init = its_enable_rk3568002, + }, +#endif { } };
From: "Matthew Wilcox (Oracle)" willy@infradead.org
[ Upstream commit c1fcf41cf37f7a3fd3bbf6f0c04aba3ea4258888 ]
The bit pattern of _PAGE_DIRTY set and _PAGE_RW clear is used to mark shadow stacks. This is currently checked for in mk_pte() but not pfn_pte(). If we add the check to pfn_pte(), it catches vfree() calling set_direct_map_invalid_noflush() which calls __change_page_attr() which loads the old protection bits from the PTE, clears the specified bits and uses pfn_pte() to construct the new PTE.
We should, therefore, for kernel mappings, clear the _PAGE_DIRTY bit consistently whenever we clear _PAGE_RW. I opted to do it in the callers in case we want to use __change_page_attr() to create shadow stacks inside the kernel at some point in the future. Arguably, we might also want to clear _PAGE_ACCESSED here.
Note that the 3 functions involved:
__set_pages_np() kernel_map_pages_in_pgd() kernel_unmap_pages_in_pgd()
Only ever manipulate non-swappable kernel mappings, so maintaining the DIRTY:1|RW:0 special pattern for shadow stacks and DIRTY:0 pattern for non-shadow-stack entries can be maintained consistently and doesn't result in the unintended clearing of a live dirty bit that could corrupt (destroy) dirty bit information for user mappings.
Reported-by: kernel test robot oliver.sang@intel.com Signed-off-by: Matthew Wilcox (Oracle) willy@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Acked-by: Linus Torvalds torvalds@linux-foundation.org Link: https://lore.kernel.org/r/174051422675.10177.13226545170101706336.tip-bot2@t... Closes: https://lore.kernel.org/oe-lkp/202502241646.719f4651-lkp@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/mm/pat/set_memory.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 95bc50a8541c6..24c74136acb33 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -2422,7 +2422,7 @@ static int __set_pages_np(struct page *page, int numpages) .pgd = NULL, .numpages = numpages, .mask_set = __pgprot(0), - .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW), + .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY), .flags = CPA_NO_CHECK_ALIAS };
/* @@ -2509,7 +2509,7 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, .pgd = pgd, .numpages = numpages, .mask_set = __pgprot(0), - .mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)), + .mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW|_PAGE_DIRTY)), .flags = CPA_NO_CHECK_ALIAS, };
@@ -2552,7 +2552,7 @@ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address, .pgd = pgd, .numpages = numpages, .mask_set = __pgprot(0), - .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW), + .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY), .flags = CPA_NO_CHECK_ALIAS, };
From: Uros Bizjak ubizjak@gmail.com
[ Upstream commit b6762467a09ba8838c499e4f36561e82fc608ed1 ]
GCC < 14.2 does not correctly propagate address space qualifiers with -fsanitize=bool,enum. Together with address sanitizer then causes that load to be sanitized.
Disable named address spaces for GCC < 14.2 when both, UBSAN_BOOL and KASAN are enabled.
Reported-by: Matt Fleming matt@readmodwrite.com Signed-off-by: Uros Bizjak ubizjak@gmail.com Signed-off-by: Ingo Molnar mingo@kernel.org Link: https://lore.kernel.org/r/20250227140715.2276353-1-ubizjak@gmail.com Closes: https://lore.kernel.org/lkml/20241213190119.3449103-1-matt@readmodwrite.com/ Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/Kconfig | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 757333fe82c76..83ebb7626c283 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2445,18 +2445,20 @@ config CC_HAS_NAMED_AS def_bool $(success,echo 'int __seg_fs fs; int __seg_gs gs;' | $(CC) -x c - -S -o /dev/null) depends on CC_IS_GCC
+# +# -fsanitize=kernel-address (KASAN) and -fsanitize=thread (KCSAN) +# are incompatible with named address spaces with GCC < 13.3 +# (see GCC PR sanitizer/111736 and also PR sanitizer/115172). +# + config CC_HAS_NAMED_AS_FIXED_SANITIZERS - def_bool CC_IS_GCC && GCC_VERSION >= 130300 + def_bool y + depends on !(KASAN || KCSAN) || GCC_VERSION >= 130300 + depends on !(UBSAN_BOOL && KASAN) || GCC_VERSION >= 140200
config USE_X86_SEG_SUPPORT - def_bool y - depends on CC_HAS_NAMED_AS - # - # -fsanitize=kernel-address (KASAN) and -fsanitize=thread - # (KCSAN) are incompatible with named address spaces with - # GCC < 13.3 - see GCC PR sanitizer/111736. - # - depends on !(KASAN || KCSAN) || CC_HAS_NAMED_AS_FIXED_SANITIZERS + def_bool CC_HAS_NAMED_AS + depends on CC_HAS_NAMED_AS_FIXED_SANITIZERS
config CC_HAS_SLS def_bool $(cc-option,-mharden-sls=all)
From: "Xin Li (Intel)" xin@zytor.com
[ Upstream commit ad546940b5991d3e141238cd80a6d1894b767184 ]
The first GDT descriptor is reserved as 'NULL descriptor'. As bits 0 and 1 of a segment selector, i.e., the RPL bits, are NOT used to index GDT, selector values 0~3 all point to the NULL descriptor, thus values 0, 1, 2 and 3 are all valid NULL selector values.
When a NULL selector value is to be loaded into a segment register, reload_segments() sets its RPL bits. Later IRET zeros ES, FS, GS, and DS segment registers if any of them is found to have any nonzero NULL selector value. The two operations offset each other to actually effect a nop.
Besides, zeroing of RPL in NULL selector values is an information leak in pre-FRED systems as userspace can spot any interrupt/exception by loading a nonzero NULL selector, and waiting for it to become zero. But there is nothing software can do to prevent it before FRED.
ERETU, the only legit instruction to return to userspace from kernel under FRED, by design does NOT zero any segment register to avoid this problem behavior.
As such, leave NULL selector values 0~3 unchanged and close the leak.
Do the same on 32-bit kernel as well.
Signed-off-by: Xin Li (Intel) xin@zytor.com Signed-off-by: Ingo Molnar mingo@kernel.org Reviewed-by: Andrew Cooper andrew.cooper3@citrix.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Andy Lutomirski luto@kernel.org Cc: Brian Gerst brgerst@gmail.com Cc: Peter Zijlstra peterz@infradead.org Link: https://lore.kernel.org/r/20241126184529.1607334-1-xin@zytor.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/signal_32.c | 62 +++++++++++++++++++++++++------------ 1 file changed, 43 insertions(+), 19 deletions(-)
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c index ef654530bf5a9..98123ff10506c 100644 --- a/arch/x86/kernel/signal_32.c +++ b/arch/x86/kernel/signal_32.c @@ -33,25 +33,55 @@ #include <asm/smap.h> #include <asm/gsseg.h>
+/* + * The first GDT descriptor is reserved as 'NULL descriptor'. As bits 0 + * and 1 of a segment selector, i.e., the RPL bits, are NOT used to index + * GDT, selector values 0~3 all point to the NULL descriptor, thus values + * 0, 1, 2 and 3 are all valid NULL selector values. + * + * However IRET zeros ES, FS, GS, and DS segment registers if any of them + * is found to have any nonzero NULL selector value, which can be used by + * userspace in pre-FRED systems to spot any interrupt/exception by loading + * a nonzero NULL selector and waiting for it to become zero. Before FRED + * there was nothing software could do to prevent such an information leak. + * + * ERETU, the only legit instruction to return to userspace from kernel + * under FRED, by design does NOT zero any segment register to avoid this + * problem behavior. + * + * As such, leave NULL selector values 0~3 unchanged. + */ +static inline u16 fixup_rpl(u16 sel) +{ + return sel <= 3 ? sel : sel | 3; +} + #ifdef CONFIG_IA32_EMULATION #include <asm/unistd_32_ia32.h>
static inline void reload_segments(struct sigcontext_32 *sc) { - unsigned int cur; + u16 cur;
+ /* + * Reload fs and gs if they have changed in the signal + * handler. This does not handle long fs/gs base changes in + * the handler, but does not clobber them at least in the + * normal case. + */ savesegment(gs, cur); - if ((sc->gs | 0x03) != cur) - load_gs_index(sc->gs | 0x03); + if (fixup_rpl(sc->gs) != cur) + load_gs_index(fixup_rpl(sc->gs)); savesegment(fs, cur); - if ((sc->fs | 0x03) != cur) - loadsegment(fs, sc->fs | 0x03); + if (fixup_rpl(sc->fs) != cur) + loadsegment(fs, fixup_rpl(sc->fs)); + savesegment(ds, cur); - if ((sc->ds | 0x03) != cur) - loadsegment(ds, sc->ds | 0x03); + if (fixup_rpl(sc->ds) != cur) + loadsegment(ds, fixup_rpl(sc->ds)); savesegment(es, cur); - if ((sc->es | 0x03) != cur) - loadsegment(es, sc->es | 0x03); + if (fixup_rpl(sc->es) != cur) + loadsegment(es, fixup_rpl(sc->es)); }
#define sigset32_t compat_sigset_t @@ -105,18 +135,12 @@ static bool ia32_restore_sigcontext(struct pt_regs *regs, regs->orig_ax = -1;
#ifdef CONFIG_IA32_EMULATION - /* - * Reload fs and gs if they have changed in the signal - * handler. This does not handle long fs/gs base changes in - * the handler, but does not clobber them at least in the - * normal case. - */ reload_segments(&sc); #else - loadsegment(gs, sc.gs); - regs->fs = sc.fs; - regs->es = sc.es; - regs->ds = sc.ds; + loadsegment(gs, fixup_rpl(sc.gs)); + regs->fs = fixup_rpl(sc.fs); + regs->es = fixup_rpl(sc.es); + regs->ds = fixup_rpl(sc.ds); #endif
return fpu__restore_sig(compat_ptr(sc.fpstate), 1);
From: Max Grobecker max@grobecker.info
[ Upstream commit a4248ee16f411ac1ea7dfab228a6659b111e3d65 ]
When running in a virtual machine, we might see the original hardware CPU vendor string (i.e. "AuthenticAMD"), but a model and family ID set by the hypervisor. In case we run on AMD hardware and the hypervisor sets a model ID < 0x14, the LAHF cpu feature is eliminated from the the list of CPU capabilities present to circumvent a bug with some BIOSes in conjunction with AMD K8 processors.
Parsing the flags list from /proc/cpuinfo seems to be happening mostly in bash scripts and prebuilt Docker containers, as it does not need to have additionals tools present – even though more reliable ways like using "kcpuid", which calls the CPUID instruction instead of parsing a list, should be preferred. Scripts, that use /proc/cpuinfo to determine if the current CPU is "compliant" with defined microarchitecture levels like x86-64-v2 will falsely claim the CPU is incapable of modern CPU instructions when "lahf_lm" is missing in that flags list.
This can prevent some docker containers from starting or build scripts to create unoptimized binaries.
Admittably, this is more a small inconvenience than a severe bug in the kernel and the shoddy scripts that rely on parsing /proc/cpuinfo should be fixed instead.
This patch adds an additional check to see if we're running inside a virtual machine (X86_FEATURE_HYPERVISOR is present), which, to my understanding, can't be present on a real K8 processor as it was introduced only with the later/other Athlon64 models.
Example output with the "lahf_lm" flag missing in the flags list (should be shown between "hypervisor" and "abm"):
$ cat /proc/cpuinfo processor : 0 vendor_id : AuthenticAMD cpu family : 15 model : 6 model name : Common KVM processor stepping : 1 microcode : 0x1000065 cpu MHz : 2599.998 cache size : 512 KB physical id : 0 siblings : 1 core id : 0 cpu cores : 1 apicid : 0 initial apicid : 0 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 syscall nx rdtscp lm rep_good nopl cpuid extd_apicid tsc_known_freq pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c hypervisor abm 3dnowprefetch vmmcall bmi1 avx2 bmi2 xsaveopt
... while kcpuid shows the feature to be present in the CPU:
# kcpuid -d | grep lahf lahf_lm - LAHF/SAHF available in 64-bit mode
[ mingo: Updated the comment a bit, incorporated Boris's review feedback. ]
Signed-off-by: Max Grobecker max@grobecker.info Signed-off-by: Ingo Molnar mingo@kernel.org Cc: linux-kernel@vger.kernel.org Cc: Borislav Petkov bp@alien8.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/cpu/amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 79d2e17f6582e..425bed00b2e07 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -627,7 +627,7 @@ static void init_amd_k8(struct cpuinfo_x86 *c) * (model = 0x14) and later actually support it. * (AMD Erratum #110, docId: 25759). */ - if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) { + if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM) && !cpu_has(c, X86_FEATURE_HYPERVISOR)) { clear_cpu_cap(c, X86_FEATURE_LAHF_LM); if (!rdmsrl_amd_safe(0xc001100d, &value)) { value &= ~BIT_64(32);
From: Mark Rutland mark.rutland@arm.com
[ Upstream commit dcca27bc1eccb9abc2552aab950b18a9742fb8e7 ]
Currently armpmu_add() tries to handle a newly-allocated counter having a stale associated event, but this should not be possible, and if this were to happen the current mitigation is insufficient and potentially expensive. It would be better to warn if we encounter the impossible case.
Calls to pmu::add() and pmu::del() are serialized by the core perf code, and armpmu_del() clears the relevant slot in pmu_hw_events::events[] before clearing the bit in pmu_hw_events::used_mask such that the counter can be reallocated. Thus when armpmu_add() allocates a counter index from pmu_hw_events::used_mask, it should not be possible to observe a stale even in pmu_hw_events::events[] unless either pmu_hw_events::used_mask or pmu_hw_events::events[] have been corrupted.
If this were to happen, we'd end up with two events with the same event->hw.idx, which would clash with each other during reprogramming, deletion, etc, and produce bogus results. Add a WARN_ON_ONCE() for this case so that we can detect if this ever occurs in practice.
That possiblity aside, there's no need to call arm_pmu::disable(event) for the new event. The PMU reset code initialises the counter in a disabled state, and armpmu_del() will disable the counter before it can be reused. Remove the redundant disable.
Signed-off-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Rob Herring (Arm) robh@kernel.org Reviewed-by: Anshuman Khandual anshuman.khandual@arm.com Tested-by: James Clark james.clark@linaro.org Link: https://lore.kernel.org/r/20250218-arm-brbe-v19-v20-2-4e9922fc2e8e@kernel.or... Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/perf/arm_pmu.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 398cce3d76fc4..2f33e69a8caf2 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -342,12 +342,10 @@ armpmu_add(struct perf_event *event, int flags) if (idx < 0) return idx;
- /* - * If there is an event in the counter we are going to use then make - * sure it is disabled. - */ + /* The newly-allocated counter should be empty */ + WARN_ON_ONCE(hw_events->events[idx]); + event->hw.idx = idx; - armpmu->disable(event); hw_events->events[idx] = event;
hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
From: Yunhui Cui cuiyunhui@bytedance.com
[ Upstream commit 6eb1e8ef586ac4a3dcdc20248f9cb45e4ceb141f ]
Release leaked resources, such as plat_dev and dev_info.
Signed-off-by: Yunhui Cui cuiyunhui@bytedance.com Reviewed-by: Shuai Xue xueshuai@linux.alibaba.com Link: https://lore.kernel.org/r/20250220121716.50324-2-cuiyunhui@bytedance.com Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/perf/dwc_pcie_pmu.c | 33 ++++++++++++++++++++++----------- 1 file changed, 22 insertions(+), 11 deletions(-)
diff --git a/drivers/perf/dwc_pcie_pmu.c b/drivers/perf/dwc_pcie_pmu.c index 9cbea9675e21a..a7e7864e73a8e 100644 --- a/drivers/perf/dwc_pcie_pmu.c +++ b/drivers/perf/dwc_pcie_pmu.c @@ -567,8 +567,10 @@ static int dwc_pcie_register_dev(struct pci_dev *pdev) return PTR_ERR(plat_dev);
dev_info = kzalloc(sizeof(*dev_info), GFP_KERNEL); - if (!dev_info) + if (!dev_info) { + platform_device_unregister(plat_dev); return -ENOMEM; + }
/* Cache platform device to handle pci device hotplug */ dev_info->plat_dev = plat_dev; @@ -724,6 +726,15 @@ static struct platform_driver dwc_pcie_pmu_driver = { .driver = {.name = "dwc_pcie_pmu",}, };
+static void dwc_pcie_cleanup_devices(void) +{ + struct dwc_pcie_dev_info *dev_info, *tmp; + + list_for_each_entry_safe(dev_info, tmp, &dwc_pcie_dev_info_head, dev_node) { + dwc_pcie_unregister_dev(dev_info); + } +} + static int __init dwc_pcie_pmu_init(void) { struct pci_dev *pdev = NULL; @@ -736,7 +747,7 @@ static int __init dwc_pcie_pmu_init(void) ret = dwc_pcie_register_dev(pdev); if (ret) { pci_dev_put(pdev); - return ret; + goto err_cleanup; } }
@@ -745,35 +756,35 @@ static int __init dwc_pcie_pmu_init(void) dwc_pcie_pmu_online_cpu, dwc_pcie_pmu_offline_cpu); if (ret < 0) - return ret; + goto err_cleanup;
dwc_pcie_pmu_hp_state = ret;
ret = platform_driver_register(&dwc_pcie_pmu_driver); if (ret) - goto platform_driver_register_err; + goto err_remove_cpuhp;
ret = bus_register_notifier(&pci_bus_type, &dwc_pcie_pmu_nb); if (ret) - goto platform_driver_register_err; + goto err_unregister_driver; notify = true;
return 0;
-platform_driver_register_err: +err_unregister_driver: + platform_driver_unregister(&dwc_pcie_pmu_driver); +err_remove_cpuhp: cpuhp_remove_multi_state(dwc_pcie_pmu_hp_state); - +err_cleanup: + dwc_pcie_cleanup_devices(); return ret; }
static void __exit dwc_pcie_pmu_exit(void) { - struct dwc_pcie_dev_info *dev_info, *tmp; - if (notify) bus_unregister_notifier(&pci_bus_type, &dwc_pcie_pmu_nb); - list_for_each_entry_safe(dev_info, tmp, &dwc_pcie_dev_info_head, dev_node) - dwc_pcie_unregister_dev(dev_info); + dwc_pcie_cleanup_devices(); platform_driver_unregister(&dwc_pcie_pmu_driver); cpuhp_remove_multi_state(dwc_pcie_pmu_hp_state); }
From: Lizhi Xu lizhi.xu@windriver.com
[ Upstream commit 52323ed1444ea5c2a5f1754ea0a2d9c8c216ccdf ]
syzbot reported a deadlock in lock_system_sleep() (see below).
The write operation to "/sys/module/hibernate/parameters/compressor" conflicts with the registration of ieee80211 device, resulting in a deadlock when attempting to acquire system_transition_mutex under param_lock.
To avoid this deadlock, change hibernate_compressor_param_set() to use mutex_trylock() for attempting to acquire system_transition_mutex and return -EBUSY when it fails.
Task flags need not be saved or adjusted before calling mutex_trylock(&system_transition_mutex) because the caller is not going to end up waiting for this mutex and if it runs concurrently with system suspend in progress, it will be frozen properly when it returns to user space.
syzbot report:
syz-executor895/5833 is trying to acquire lock: ffffffff8e0828c8 (system_transition_mutex){+.+.}-{4:4}, at: lock_system_sleep+0x87/0xa0 kernel/power/main.c:56
but task is already holding lock: ffffffff8e07dc68 (param_lock){+.+.}-{4:4}, at: kernel_param_lock kernel/params.c:607 [inline] ffffffff8e07dc68 (param_lock){+.+.}-{4:4}, at: param_attr_store+0xe6/0x300 kernel/params.c:586
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #3 (param_lock){+.+.}-{4:4}: __mutex_lock_common kernel/locking/mutex.c:585 [inline] __mutex_lock+0x19b/0xb10 kernel/locking/mutex.c:730 ieee80211_rate_control_ops_get net/mac80211/rate.c:220 [inline] rate_control_alloc net/mac80211/rate.c:266 [inline] ieee80211_init_rate_ctrl_alg+0x18d/0x6b0 net/mac80211/rate.c:1015 ieee80211_register_hw+0x20cd/0x4060 net/mac80211/main.c:1531 mac80211_hwsim_new_radio+0x304e/0x54e0 drivers/net/wireless/virtual/mac80211_hwsim.c:5558 init_mac80211_hwsim+0x432/0x8c0 drivers/net/wireless/virtual/mac80211_hwsim.c:6910 do_one_initcall+0x128/0x700 init/main.c:1257 do_initcall_level init/main.c:1319 [inline] do_initcalls init/main.c:1335 [inline] do_basic_setup init/main.c:1354 [inline] kernel_init_freeable+0x5c7/0x900 init/main.c:1568 kernel_init+0x1c/0x2b0 init/main.c:1457 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:148 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244
-> #2 (rtnl_mutex){+.+.}-{4:4}: __mutex_lock_common kernel/locking/mutex.c:585 [inline] __mutex_lock+0x19b/0xb10 kernel/locking/mutex.c:730 wg_pm_notification drivers/net/wireguard/device.c:80 [inline] wg_pm_notification+0x49/0x180 drivers/net/wireguard/device.c:64 notifier_call_chain+0xb7/0x410 kernel/notifier.c:85 notifier_call_chain_robust kernel/notifier.c:120 [inline] blocking_notifier_call_chain_robust kernel/notifier.c:345 [inline] blocking_notifier_call_chain_robust+0xc9/0x170 kernel/notifier.c:333 pm_notifier_call_chain_robust+0x27/0x60 kernel/power/main.c:102 snapshot_open+0x189/0x2b0 kernel/power/user.c:77 misc_open+0x35a/0x420 drivers/char/misc.c:179 chrdev_open+0x237/0x6a0 fs/char_dev.c:414 do_dentry_open+0x735/0x1c40 fs/open.c:956 vfs_open+0x82/0x3f0 fs/open.c:1086 do_open fs/namei.c:3830 [inline] path_openat+0x1e88/0x2d80 fs/namei.c:3989 do_filp_open+0x20c/0x470 fs/namei.c:4016 do_sys_openat2+0x17a/0x1e0 fs/open.c:1428 do_sys_open fs/open.c:1443 [inline] __do_sys_openat fs/open.c:1459 [inline] __se_sys_openat fs/open.c:1454 [inline] __x64_sys_openat+0x175/0x210 fs/open.c:1454 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f
-> #1 ((pm_chain_head).rwsem){++++}-{4:4}: down_read+0x9a/0x330 kernel/locking/rwsem.c:1524 blocking_notifier_call_chain_robust kernel/notifier.c:344 [inline] blocking_notifier_call_chain_robust+0xa9/0x170 kernel/notifier.c:333 pm_notifier_call_chain_robust+0x27/0x60 kernel/power/main.c:102 snapshot_open+0x189/0x2b0 kernel/power/user.c:77 misc_open+0x35a/0x420 drivers/char/misc.c:179 chrdev_open+0x237/0x6a0 fs/char_dev.c:414 do_dentry_open+0x735/0x1c40 fs/open.c:956 vfs_open+0x82/0x3f0 fs/open.c:1086 do_open fs/namei.c:3830 [inline] path_openat+0x1e88/0x2d80 fs/namei.c:3989 do_filp_open+0x20c/0x470 fs/namei.c:4016 do_sys_openat2+0x17a/0x1e0 fs/open.c:1428 do_sys_open fs/open.c:1443 [inline] __do_sys_openat fs/open.c:1459 [inline] __se_sys_openat fs/open.c:1454 [inline] __x64_sys_openat+0x175/0x210 fs/open.c:1454 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f
-> #0 (system_transition_mutex){+.+.}-{4:4}: check_prev_add kernel/locking/lockdep.c:3163 [inline] check_prevs_add kernel/locking/lockdep.c:3282 [inline] validate_chain kernel/locking/lockdep.c:3906 [inline] __lock_acquire+0x249e/0x3c40 kernel/locking/lockdep.c:5228 lock_acquire.part.0+0x11b/0x380 kernel/locking/lockdep.c:5851 __mutex_lock_common kernel/locking/mutex.c:585 [inline] __mutex_lock+0x19b/0xb10 kernel/locking/mutex.c:730 lock_system_sleep+0x87/0xa0 kernel/power/main.c:56 hibernate_compressor_param_set+0x1c/0x210 kernel/power/hibernate.c:1452 param_attr_store+0x18f/0x300 kernel/params.c:588 module_attr_store+0x55/0x80 kernel/params.c:924 sysfs_kf_write+0x117/0x170 fs/sysfs/file.c:139 kernfs_fop_write_iter+0x33d/0x500 fs/kernfs/file.c:334 new_sync_write fs/read_write.c:586 [inline] vfs_write+0x5ae/0x1150 fs/read_write.c:679 ksys_write+0x12b/0x250 fs/read_write.c:731 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f
other info that might help us debug this:
Chain exists of: system_transition_mutex --> rtnl_mutex --> param_lock
Possible unsafe locking scenario:
CPU0 CPU1 ---- ---- lock(param_lock); lock(rtnl_mutex); lock(param_lock); lock(system_transition_mutex);
*** DEADLOCK ***
Reported-by: syzbot+ace60642828c074eb913@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=ace60642828c074eb913 Signed-off-by: Lizhi Xu lizhi.xu@windriver.com Link: https://patch.msgid.link/20250224013139.3994500-1-lizhi.xu@windriver.com [ rjw: New subject matching the code changes, changelog edits ] Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/power/hibernate.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 10a01af63a807..b129ed1d25a8a 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -1446,10 +1446,10 @@ static const char * const comp_alg_enabled[] = { static int hibernate_compressor_param_set(const char *compressor, const struct kernel_param *kp) { - unsigned int sleep_flags; int index, ret;
- sleep_flags = lock_system_sleep(); + if (!mutex_trylock(&system_transition_mutex)) + return -EBUSY;
index = sysfs_match_string(comp_alg_enabled, compressor); if (index >= 0) { @@ -1461,7 +1461,7 @@ static int hibernate_compressor_param_set(const char *compressor, ret = index; }
- unlock_system_sleep(sleep_flags); + mutex_unlock(&system_transition_mutex);
if (ret) pr_debug("Cannot set specified compressor %s\n",
From: "Paul E. McKenney" paulmck@kernel.org
[ Upstream commit 6ea9a1781c70a8be1fcdc49134fc1bf4baba8bca ]
Kernels built with CONFIG_PREEMPT_RT=y can lose significant console output and shutdown time, which hides shutdown-time RCU issues from rcutorture. Therefore, make pr_flush() public and invoke it after then last print in kernel_power_off().
[ paulmck: Apply John Ogness feedback. ] [ paulmck: Appy Sebastian Andrzej Siewior feedback. ] [ paulmck: Apply kernel test robot feedback. ]
Signed-off-by: Paul E. McKenney paulmck@kernel.org Reviewed-by: John Ogness john.ogness@linutronix.de Reviewed-by: Petr Mladek pmladek@suse.com Cc: Steven Rostedt rostedt@goodmis.org Cc: Sergey Senozhatsky senozhatsky@chromium.org Link: https://lore.kernel.org/r/5f743488-dc2a-4f19-bdda-cf50b9314832@paulmck-lapto... Signed-off-by: Boqun Feng boqun.feng@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/printk.h | 6 ++++++ kernel/printk/printk.c | 4 +--- kernel/reboot.c | 1 + 3 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/include/linux/printk.h b/include/linux/printk.h index 4217a9f412b26..5b462029d03c1 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -207,6 +207,7 @@ void printk_legacy_allow_panic_sync(void); extern bool nbcon_device_try_acquire(struct console *con); extern void nbcon_device_release(struct console *con); void nbcon_atomic_flush_unsafe(void); +bool pr_flush(int timeout_ms, bool reset_on_progress); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -315,6 +316,11 @@ static inline void nbcon_atomic_flush_unsafe(void) { }
+static inline bool pr_flush(int timeout_ms, bool reset_on_progress) +{ + return true; +} + #endif
bool this_cpu_in_panic(void); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 07668433644b8..057db78876cd9 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2461,7 +2461,6 @@ asmlinkage __visible int _printk(const char *fmt, ...) } EXPORT_SYMBOL(_printk);
-static bool pr_flush(int timeout_ms, bool reset_on_progress); static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress);
#else /* CONFIG_PRINTK */ @@ -2474,7 +2473,6 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
static u64 syslog_seq;
-static bool pr_flush(int timeout_ms, bool reset_on_progress) { return true; } static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; }
#endif /* CONFIG_PRINTK */ @@ -4466,7 +4464,7 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre * Context: Process context. May sleep while acquiring console lock. * Return: true if all usable printers are caught up. */ -static bool pr_flush(int timeout_ms, bool reset_on_progress) +bool pr_flush(int timeout_ms, bool reset_on_progress) { return __pr_flush(NULL, timeout_ms, reset_on_progress); } diff --git a/kernel/reboot.c b/kernel/reboot.c index a701000bab347..3ba15b2c40662 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -704,6 +704,7 @@ void kernel_power_off(void) migrate_to_reboot_cpu(); syscore_shutdown(); pr_emerg("Power down\n"); + pr_flush(1000, true); kmsg_dump(KMSG_DUMP_SHUTDOWN); machine_power_off(); }
From: Douglas Anderson dianders@chromium.org
[ Upstream commit 401c3333bb2396aa52e4121887a6f6a6e2f040bc ]
Add a definition for the Qualcomm Kryo 300-series Gold cores.
Reviewed-by: Dmitry Baryshkov dmitry.baryshkov@linaro.org Signed-off-by: Douglas Anderson dianders@chromium.org Acked-by: Trilok Soni quic_tsoni@quicinc.com Link: https://lore.kernel.org/r/20241219131107.v3.1.I18e0288742871393228249a768e5d... Signed-off-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+)
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 488f8e7513495..c8058f91a5bd3 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -119,6 +119,7 @@ #define QCOM_CPU_PART_KRYO 0x200 #define QCOM_CPU_PART_KRYO_2XX_GOLD 0x800 #define QCOM_CPU_PART_KRYO_2XX_SILVER 0x801 +#define QCOM_CPU_PART_KRYO_3XX_GOLD 0x802 #define QCOM_CPU_PART_KRYO_3XX_SILVER 0x803 #define QCOM_CPU_PART_KRYO_4XX_GOLD 0x804 #define QCOM_CPU_PART_KRYO_4XX_SILVER 0x805 @@ -195,6 +196,7 @@ #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO) #define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD) #define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER) +#define MIDR_QCOM_KRYO_3XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_GOLD) #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER) #define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD) #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER)
From: Kees Cook kees@kernel.org
[ Upstream commit 1c3dfc7c6b0f551fdca3f7c1f1e4c73be8adb17d ]
When a character array without a terminating NUL character has a static initializer, GCC 15's -Wunterminated-string-initialization will only warn if the array lacks the "nonstring" attribute[1]. Mark the arrays with __nonstring to and correctly identify the char array as "not a C string" and thereby eliminate the warning.
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117178 [1] Cc: Juergen Gross jgross@suse.com Cc: Stefano Stabellini sstabellini@kernel.org Cc: Oleksandr Tyshchenko oleksandr_tyshchenko@epam.com Cc: xen-devel@lists.xenproject.org Signed-off-by: Kees Cook kees@kernel.org Acked-by: Juergen Gross jgross@suse.com Message-ID: 20250310222234.work.473-kees@kernel.org Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/xen/interface/xen-mca.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/xen/interface/xen-mca.h b/include/xen/interface/xen-mca.h index 464aa6b3a5f92..1c9afbe8cc260 100644 --- a/include/xen/interface/xen-mca.h +++ b/include/xen/interface/xen-mca.h @@ -372,7 +372,7 @@ struct xen_mce { #define XEN_MCE_LOG_LEN 32
struct xen_mce_log { - char signature[12]; /* "MACHINECHECK" */ + char signature[12] __nonstring; /* "MACHINECHECK" */ unsigned len; /* = XEN_MCE_LOG_LEN */ unsigned next; unsigned flags;
From: "Kirill A. Shutemov" kirill.shutemov@linux.intel.com
[ Upstream commit f666c92090a41ac5524dade63ff96b3adcf8c2ab ]
The current calculation of the 'next' virtual address in the page table initialization functions in arch/x86/mm/ident_map.c doesn't protect against wrapping to zero.
This is a theoretical issue that cannot happen currently, the problematic case is possible only if the user sets a high enough x86_mapping_info::offset value - which no current code in the upstream kernel does.
( The wrapping to zero only occurs if the top PGD entry is accessed. There are no such users upstream. Only hibernate_64.c uses x86_mapping_info::offset, and it operates on the direct mapping range, which is not the top PGD entry. )
Should such an overflow happen, it can result in page table corruption and a hang.
To future-proof this code, replace the manual 'next' calculation with p?d_addr_end() which handles wrapping correctly.
[ Backporter's note: there's no need to backport this patch. ]
Signed-off-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Signed-off-by: Ingo Molnar mingo@kernel.org Reviewed-by: Kai Huang kai.huang@intel.com Reviewed-by: Tom Lendacky thomas.lendacky@amd.com Cc: Andy Lutomirski luto@kernel.org Cc: Linus Torvalds torvalds@linux-foundation.org Link: https://lore.kernel.org/r/20241016111458.846228-2-kirill.shutemov@linux.inte... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/mm/ident_map.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-)
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index 5ab7bd2f1983c..bd5d101c5c379 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -101,9 +101,7 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, pmd_t *pmd; bool use_gbpage;
- next = (addr & PUD_MASK) + PUD_SIZE; - if (next > end) - next = end; + next = pud_addr_end(addr, end);
/* if this is already a gbpage, this portion is already mapped */ if (pud_leaf(*pud)) @@ -154,10 +152,7 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page, p4d_t *p4d = p4d_page + p4d_index(addr); pud_t *pud;
- next = (addr & P4D_MASK) + P4D_SIZE; - if (next > end) - next = end; - + next = p4d_addr_end(addr, end); if (p4d_present(*p4d)) { pud = pud_offset(p4d, 0); result = ident_pud_init(info, pud, addr, next); @@ -199,10 +194,7 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, pgd_t *pgd = pgd_page + pgd_index(addr); p4d_t *p4d;
- next = (addr & PGDIR_MASK) + PGDIR_SIZE; - if (next > end) - next = end; - + next = pgd_addr_end(addr, end); if (pgd_present(*pgd)) { p4d = p4d_offset(pgd, 0); result = ident_p4d_init(info, p4d, addr, next);
linux-stable-mirror@lists.linaro.org
-
Sasha Levin