Kexec Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Pingfan Liu <piliu@redhat.com>
To: bpf@vger.kernel.org
Cc: Pingfan Liu <piliu@redhat.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	John Fastabend <john.fastabend@gmail.com>,
	Andrii Nakryiko <andrii@kernel.org>,
	Martin KaFai Lau <martin.lau@linux.dev>,
	Eduard Zingerman <eddyz87@gmail.com>, Song Liu <song@kernel.org>,
	Yonghong Song <yonghong.song@linux.dev>,
	Jeremy Linton <jeremy.linton@arm.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>, Ard Biesheuvel <ardb@kernel.org>,
	Simon Horman <horms@kernel.org>,
	Gerd Hoffmann <kraxel@redhat.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Philipp Rudo <prudo@redhat.com>, Viktor Malik <vmalik@redhat.com>,
	Jan Hendrik Farr <kernel@jfarr.cc>, Baoquan He <bhe@redhat.com>,
	Dave Young <dyoung@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	kexec@lists.infradead.org, KP Singh <kpsingh@kernel.org>,
	Stanislav Fomichev <sdf@fomichev.me>, Hao Luo <haoluo@google.com>,
	Jiri Olsa <jolsa@kernel.org>
Subject: [PATCHv3 4/9] bpf: Introduce decompressor kfunc
Date: Thu, 29 May 2025 12:17:39 +0800	[thread overview]
Message-ID: <20250529041744.16458-5-piliu@redhat.com> (raw)
In-Reply-To: <20250529041744.16458-1-piliu@redhat.com>

This commit bridges the gap between bpf-prog and the kernel
decompression routines. At present, only a global memory allocator is
used for the decompression. Later, if needed, the decompress_fn's
prototype can be changed to pass in a task related allocator.

Signed-off-by: Pingfan Liu <piliu@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Song Liu <song@kernel.org>
Cc: Yonghong Song <yonghong.song@linux.dev>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Stanislav Fomichev <sdf@fomichev.me>
Cc: Hao Luo <haoluo@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
To: bpf@vger.kernel.org
---
 kernel/bpf/helpers.c | 111 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 111 insertions(+)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 1f4284e58400b..9748d6101d032 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -23,6 +23,7 @@
 #include <linux/btf_ids.h>
 #include <linux/bpf_mem_alloc.h>
 #include <linux/kasan.h>
+#include <linux/decompress/generic.h>
 
 #include "../../lib/kstrtox.h"
 
@@ -3194,12 +3195,122 @@ __bpf_kfunc void bpf_local_irq_restore(unsigned long *flags__irq_flag)
 	local_irq_restore(*flags__irq_flag);
 }
 
+#define MAX_UNCOMPRESSED_BUF_SIZE	(1 << 28)
+/*
+ * At present, one global allocator for decompression. Later if needed, changing the
+ * prototype of decompress_fn to introduce each task's allocator.
+ */
+static char *output_buf;
+static char *output_cur;
+static DEFINE_MUTEX(output_buf_mutex);
+
+/*
+ * Copy the partial decompressed content in [buf, buf + len) to dst.
+ * If the dst size is beyond the capacity, return -1 to indicate the
+ * decompress method that something is wrong.
+ */
+static long flush(void *buf, unsigned long len)
+{
+
+	if (output_cur - output_buf > MAX_UNCOMPRESSED_BUF_SIZE - len)
+		return -1;
+	memcpy(output_cur, buf, len);
+	output_cur += len;
+	return len;
+}
+
+__bpf_kfunc struct mem_range_result *bpf_decompress(char *image_gz_payload, int image_gz_sz)
+{
+	struct mem_cgroup *memcg, *old_memcg;
+	decompress_fn decompressor;
+	struct mem_range_result *range;
+	const char *name;
+	char *input_buf;
+	int ret;
+
+	memcg = get_mem_cgroup_from_current();
+	old_memcg = set_active_memcg(memcg);
+	range = kmalloc(sizeof(struct mem_range_result), GFP_KERNEL);
+	if (!range) {
+		pr_err("fail to allocate mem_range_result\n");
+		goto error;
+	}
+	kref_init(&range->ref);
+
+	input_buf = __vmalloc(image_gz_sz, GFP_KERNEL | __GFP_ACCOUNT);
+	if (!input_buf) {
+		kfree(range);
+		pr_err("fail to allocate input buffer\n");
+		goto error;
+	}
+
+	ret = copy_from_kernel_nofault(input_buf, image_gz_payload, image_gz_sz);
+	if (ret < 0) {
+		kfree(range);
+		vfree(input_buf);
+		pr_err("Error when copying from 0x%p, size:0x%x\n",
+				image_gz_payload, image_gz_sz);
+		goto error;
+	}
+
+	mutex_lock(&output_buf_mutex);
+	output_buf = __vmalloc(MAX_UNCOMPRESSED_BUF_SIZE, GFP_KERNEL | __GFP_ACCOUNT);
+	if (!output_buf) {
+		mutex_unlock(&output_buf_mutex);
+		kfree(range);
+		vfree(input_buf);
+		pr_err("fail to allocate output buffer\n");
+		goto error;
+	}
+	output_cur = output_buf;
+	decompressor = decompress_method(input_buf, image_gz_sz, &name);
+	if (!decompressor) {
+		kfree(range);
+		vfree(input_buf);
+		vfree(output_buf);
+		mutex_unlock(&output_buf_mutex);
+		pr_err("Can not find decompress method\n");
+		goto error;
+	}
+	ret = decompressor(input_buf, image_gz_sz, NULL, flush,
+				NULL, NULL, NULL);
+
+	vfree(input_buf);
+	/* Update the range map */
+	if (ret == 0) {
+		range->kmalloc = false;
+		range->buf = output_buf;
+		range->buf_sz = MAX_UNCOMPRESSED_BUF_SIZE;
+		range->data_sz = output_cur - output_buf;
+		output_buf = output_cur = NULL;
+		mutex_unlock(&output_buf_mutex);
+		range->status = 0;
+		/* Do not release the reference */
+		range->memcg = memcg;
+		set_active_memcg(old_memcg);
+		return range;
+	}
+
+	/* Decompression fails */
+	vfree(output_buf);
+	output_buf = output_cur = NULL;
+	mutex_unlock(&output_buf_mutex);
+	kfree(range);
+	pr_err("Decompress error\n");
+
+error:
+	set_active_memcg(old_memcg);
+	mem_cgroup_put(memcg);
+	return NULL;
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(generic_btf_ids)
 #ifdef CONFIG_CRASH_DUMP
 BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE)
 #endif
+BTF_ID_FLAGS(func, bpf_decompress, KF_TRUSTED_ARGS | KF_ACQUIRE | KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_mem_range_result_put, KF_RELEASE)
 BTF_ID_FLAGS(func, bpf_copy_to_kernel, KF_TRUSTED_ARGS | KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)
-- 
2.49.0



  parent reply	other threads:[~2025-05-29  4:19 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-05-29  4:17 [PATCHv3 0/9] kexec: Use BPF lskel to enable kexec to load PE format boot image Pingfan Liu
2025-05-29  4:17 ` [PATCHv3 1/9] kexec_file: Make kexec_image_load_default global visible Pingfan Liu
2025-05-29  4:17 ` [PATCHv3 2/9] lib/decompress: Keep decompressor when CONFIG_KEXEC_PE_IMAGE Pingfan Liu
2025-05-29  4:17 ` [PATCHv3 3/9] bpf: Introduce bpf_copy_to_kernel() to buffer the content from bpf-prog Pingfan Liu
2025-05-29 11:48   ` kernel test robot
2025-06-25 18:10   ` Philipp Rudo
2025-05-29  4:17 ` Pingfan Liu [this message]
2025-05-29 12:31   ` [PATCHv3 4/9] bpf: Introduce decompressor kfunc kernel test robot
2025-05-29  4:17 ` [PATCHv3 5/9] kexec: Introduce kexec_pe_image to parse and load PE file Pingfan Liu
2025-06-25 18:09   ` Philipp Rudo
2025-06-30 13:45     ` Pingfan Liu
2025-07-02  9:17       ` Philipp Rudo
2025-07-03  1:17         ` Pingfan Liu
2025-05-29  4:17 ` [PATCHv3 6/9] kexec: Integrate with the introduced bpf kfuncs Pingfan Liu
2025-05-29  4:17 ` [PATCHv3 7/9] kexec: Introduce a bpf-prog lskel to parse PE file Pingfan Liu
2025-05-29  4:17 ` [PATCHv3 8/9] kexec: Integrate bpf light skeleton to load zboot image Pingfan Liu
2025-06-25 18:10   ` Philipp Rudo
2025-06-30 12:40     ` Pingfan Liu
2025-05-29  4:17 ` [PATCHv3 9/9] arm64/kexec: Add PE image format support Pingfan Liu
2025-05-29 15:34   ` kernel test robot

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250529041744.16458-5-piliu@redhat.com \
    --to=piliu@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=andrii@kernel.org \
    --cc=ardb@kernel.org \
    --cc=ast@kernel.org \
    --cc=bhe@redhat.com \
    --cc=bpf@vger.kernel.org \
    --cc=catalin.marinas@arm.com \
    --cc=daniel@iogearbox.net \
    --cc=dyoung@redhat.com \
    --cc=eddyz87@gmail.com \
    --cc=haoluo@google.com \
    --cc=horms@kernel.org \
    --cc=jeremy.linton@arm.com \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kernel@jfarr.cc \
    --cc=kexec@lists.infradead.org \
    --cc=kpsingh@kernel.org \
    --cc=kraxel@redhat.com \
    --cc=martin.lau@linux.dev \
    --cc=prudo@redhat.com \
    --cc=sdf@fomichev.me \
    --cc=song@kernel.org \
    --cc=vkuznets@redhat.com \
    --cc=vmalik@redhat.com \
    --cc=will@kernel.org \
    --cc=yonghong.song@linux.dev \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox